Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
Status of the Application
The following is a Final Office Action.
In response to Examiner's communication of 5/15/2025, Applicant responded on 8/21/2025. Amended claims 1-5, 9- 11, and 20. Cancelled 12-19. Added. Claims 21-27.
Claims 1-11, 20-27 are pending in this application and have been examined.
Response to Amendment
Applicant's amendments to claims 1-5, 9- 11, and 20 are not sufficient to overcome the 35 USC 101 rejections set forth in the previous action.
Applicant's amendments to claims 1-5, 9- 11, and 20 are not sufficient to overcome the prior art rejections set forth in the previous action.
Response to Arguments – 35 USC § 101
Applicant’s arguments with respect to the rejections have been fully considered, but they are not persuasive.
Applicant submits, “…the claim includes the components or steps of the invention that provide the improvement described in the specification. The claim itself does not need to explicitly recite the improvement described in the specification (e.g., "thereby increasing the bandwidth of the channel").…The recent USPTO Examples on Al-Implemented Inventions apply the same paradigm set forth in MPEP 2106.04(d)(1)…EXAMPLE 47 - Claim 3…USPTO EXAMPLE 48 - Claim 2…EXAMPLE 48- Claim 3… The claimed invention is integrated into a practical application…1, 11, and 20 integrate several technical improvements. Amongst other things, these claims integrate a technical improvement in predictive modeling technologies by configuring a machine-learning model to more accurately predict real- time demand metrics for specific geographic channels based on the conditions within the channels. As described throughout Applicant's disclosure, this predictive modeling technique collects real-time channel events across multiple channels corresponding to geographic regions, derives a set of geographic-specific channel features for one or more target channels identified by a request, and feeds the assembled set of channel features to a machine learning network that can be trained to predict demand metrics corresponding to the one or more target channels. This predictive modeling technique provides a technical solution that enables an analytics system to more accurately model and predict the demand in a given channel at a particular point in time, and visualize real- time, location-specific demand analytics across target channels. Additionally, claims 1, 11, and 20 also integrate a technical improvement in UI functionality and human-computer interactions by generating and presenting dynamic visualizations that integrate the demand predictions generated by the machine-learning network. An analytics display can include an interactive visualization that enables an end- user to navigate between macro-level and micro-level channels corresponding to geographic regions and, in doing so, the demand predictions generated by the machine- learning network can be incorporated into the interactive visualizations to indicate the current demand in the channels presented via the visualization. Additionally, this analytics display and/or corresponding interactive visualization can be continuously updated as the system detects changes in the real-time demand conditions in one or more target channels (e.g., as the changes are detected in the real- time channel event input signals, which, in turn, cause changes in the channel features input to the machine-learning network and demand predictions generated by the machine-learning network)…The claimed invention incorporates a technological improvement comprising an ordered sequence of processing steps to generate the demand metric using a predictive machine-learning model…This ordered sequence of steps, when viewed as a whole, amounts to a technical improvement that integrates the claimed invention in a practical application….” The Examiner respectfully disagrees.
While Applicant’s amendments further prosecution, however unlike EXAMPLE 47 - Claim 3, EXAMPLE 48 - Claim 2, EXAMPLE 48- Claim 3, the present claims, as claimed, are directed to, …to more accurately predict real- time demand metrics for specific geographic channels based on the conditions within the channels …., which is a problem directed to a mental process (i.e. human managing and predicting human demand with pen and paper), organizing human activities (i.e. human managing and predicting human demand, fundamental economic principles), as established in Step 2A Prong 1. This problem does not specifically arise in the realm of computer technology, but rather, this problem existed and was addressed long before the advent of computers. Thus, the claims do not recite a technical improvement to a technical problem or necessarily roots in computing technologies. The alleged solutions and improvements in Applicant’s remarks are solutions and improvements directed to solving and improving abstract ideas, which are still abstract ideas. Additionally, pursuant to the broadest reasonable interpretation, as an ordered combination, each of the additional elements are computing elements, such as interactive visualization, machine learning network, which are recited at high level of generality implementing the abstract idea, and thus, are no more than applying the abstract idea with generic computer components. Further, these additional elements generally link the abstract idea to a technical environment, namely the environment of a computer, performing extra solution activities. Therefore, as a whole, the additional elements do not integrate the abstract ideas into a practical application in Step 2A Prong 2 or amount to significantly more under Step 2B. Even novel and newly discovered judicial exceptions are still exceptions, despite their novelty. July 2015 Update, p. 3; see SAP America Inc. v. Investpic, LLC, No. 2017-2081, slip op. at 2 (Fed Cir. May 15, 2018).
[T]he courts have indicated may not be sufficient to show an improvement in computer-functionality: Instructions to display two sets of information on a computer display in a non-interfering manner, without any limitations specifying how to achieve the desired result, Interval Licensing LLC v. AOL, Inc., 896 F.3d 1335, 1344-45, 127 USPQ2d 1553, 1559-60 (Fed. Cir. 2018);
Similarly, “claiming the improved speed or efficiency inherent with applying the abstract idea on a computer” does not integrate a judicial exception into a practical application or provide an inventive concept. Intellectual Ventures I LLC v. Capital One Bank (USA), 792 F.3d 1363, 1367, 115 USPQ2d 1636, 1639 (Fed. Cir. 2015).
Simply reciting specific limitations that narrow the abstract idea does not make an abstract idea non-abstract. 79 Fed. Reg. 74631; buySAFE Inc. v. Google, Inc., 765 F.3d 1350, 1355 (2014); see SAP America at p. 12. As discussed in SAP America, no matter how much of an advance the claims recite, when “the advance lies entirely in the realm of abstract ideas, with no plausibly alleged innovation in the non-abstract application realm,” “[a]n advance of that nature is ineligible for patenting.” Id. at p. 3.
Response to Arguments – Prior Art
Applicant’s arguments with respect to the rejections have been fully considered, but they are not persuasive. However, Applicant’s remarks are moot in light of new grounds of rejection necessitated by Applicant’s amendments.
Claim Objections
Claim 27 is objected due to the following informalities.
Claim 27 recite “the machine-learning”, it is not clear if this element refers to “machine-learning network” in Claim 1. Appropriate correction required.
Claim Rejections – 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-11, 20-27 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim 1 (similarly 11, 20) recites, “A … to execute functions comprising:
providing access … to a demand analytics platform that is configured to monitor real-time demand conditions in a plurality of channels that correspond to geographic regions and provide an analytics dashboard configured to display real-time demand predictions corresponding to the plurality of channels;
receiving, by the demand analytics platform, real-time channel events pertaining to each of the plurality of channels …, wherein each channel is associated with location definition data that defines a geographic boundary corresponding to the channel and the real-time channel events include attributes reflecting real-time demand conditions for one or more verticals in the plurality of channels;
receiving, via the analytics dashboard, a request designating at least one channel of the plurality of channels from a …;
generating channel analysis data pertaining to the at least one channel based, at least in part, on the real-time channel events corresponding to the at least one channel designated by the request, wherein generating the channel analysis data includes executing a … to generate one or more real-time demand predictions corresponding to the at least one channel identified by the request such that (i) the… receives an input comprising a set of channel features derived, at least in part, from the real-time channel events, the set of channel features modeling the real-time demand conditions for the at least one channel; and (ii) the … outputs the one or more real-time demand predictions to predict a current demand corresponding to the at least one channel; and
generating, by the analytics dashboard, an analytics display for presentation on the … that includes the channel analysis data and the one or more real-time demand predictions pertaining to the at least one channel, wherein:
the analytics display includes … display geographic regions corresponding to the plurality of channels, the … between macro-level channels and micro-level channels;
the … is updated to display a geographic area corresponding to the at least one channel designated by the request and incorporate the one or more real-time demand predictions indicating the current demand corresponding to the at least one channel; and
as the end-user navigates between or among the macro-level channels and the micro-level channels using the …, ... to display a real-time demand prediction for each channel that is presented via the ….”
Analyzing under Step 2A, Prong 1:
The limitations regarding, …providing access … to a demand analytics platform that is configured to monitor real-time demand conditions in a plurality of channels that correspond to geographic regions and provide an analytics dashboard configured to display real-time demand predictions corresponding to the plurality of channels; receiving, by the demand analytics platform, real-time channel events pertaining to each of the plurality of channels …, wherein each channel is associated with location definition data that defines a geographic boundary corresponding to the channel and the real-time channel events include attributes reflecting real-time demand conditions for one or more verticals in the plurality of channels; receiving, via the analytics dashboard, a request designating at least one channel of the plurality of channels from a …; generating channel analysis data pertaining to the at least one channel based, at least in part, on the real-time channel events corresponding to the at least one channel designated by the request, wherein generating the channel analysis data includes executing a … to generate one or more real-time demand predictions corresponding to the at least one channel identified by the request such that (i) the… receives an input comprising a set of channel features derived, at least in part, from the real-time channel events, the set of channel features modeling the real-time demand conditions for the at least one channel; and (ii) the … outputs the one or more real-time demand predictions to predict a current demand corresponding to the at least one channel; and generating, by the analytics dashboard, an analytics display for presentation on the … that includes the channel analysis data and the one or more real-time demand predictions pertaining to the at least one channel, wherein: the analytics display includes … display geographic regions corresponding to the plurality of channels, the … between macro-level channels and micro-level channels; the … is updated to display a geographic area corresponding to the at least one channel designated by the request and incorporate the one or more real-time demand predictions indicating the current demand corresponding to the at least one channel; and as the end-user navigates between or among the macro-level channels and the micro-level channels using the …, ... to display a real-time demand prediction for each channel that is presented via the…, under the broadest reasonable interpretation, can include a human using their mind and using pen and paper to, …providing access … to a demand analytics platform that is configured to monitor real-time demand conditions in a plurality of channels that correspond to geographic regions and provide an analytics dashboard configured to display real-time demand predictions corresponding to the plurality of channels; receiving, by the demand analytics platform, real-time channel events pertaining to each of the plurality of channels …, wherein each channel is associated with location definition data that defines a geographic boundary corresponding to the channel and the real-time channel events include attributes reflecting real-time demand conditions for one or more verticals in the plurality of channels; receiving, via the analytics dashboard, a request designating at least one channel of the plurality of channels from a …; generating channel analysis data pertaining to the at least one channel based, at least in part, on the real-time channel events corresponding to the at least one channel designated by the request, wherein generating the channel analysis data includes executing a … to generate one or more real-time demand predictions corresponding to the at least one channel identified by the request such that (i) the… receives an input comprising a set of channel features derived, at least in part, from the real-time channel events, the set of channel features modeling the real-time demand conditions for the at least one channel; and (ii) the … outputs the one or more real-time demand predictions to predict a current demand corresponding to the at least one channel; and generating, by the analytics dashboard, an analytics display for presentation on the … that includes the channel analysis data and the one or more real-time demand predictions pertaining to the at least one channel, wherein: the analytics display includes … display geographic regions corresponding to the plurality of channels, the … between macro-level channels and micro-level channels; the … is updated to display a geographic area corresponding to the at least one channel designated by the request and incorporate the one or more real-time demand predictions indicating the current demand corresponding to the at least one channel; and as the end-user navigates between or among the macro-level channels and the micro-level channels using the …, ... to display a real-time demand prediction for each channel that is presented via the.…; therefore, the claims are directed to a mental process.
Further, the limitations regarding, ……providing access … to a demand analytics platform that is configured to monitor real-time demand conditions in a plurality of channels that correspond to geographic regions and provide an analytics dashboard configured to display real-time demand predictions corresponding to the plurality of channels; receiving, by the demand analytics platform, real-time channel events pertaining to each of the plurality of channels …, wherein each channel is associated with location definition data that defines a geographic boundary corresponding to the channel and the real-time channel events include attributes reflecting real-time demand conditions for one or more verticals in the plurality of channels; receiving, via the analytics dashboard, a request designating at least one channel of the plurality of channels from a …; generating channel analysis data pertaining to the at least one channel based, at least in part, on the real-time channel events corresponding to the at least one channel designated by the request, wherein generating the channel analysis data includes executing a … to generate one or more real-time demand predictions corresponding to the at least one channel identified by the request such that (i) the… receives an input comprising a set of channel features derived, at least in part, from the real-time channel events, the set of channel features modeling the real-time demand conditions for the at least one channel; and (ii) the … outputs the one or more real-time demand predictions to predict a current demand corresponding to the at least one channel; and generating, by the analytics dashboard, an analytics display for presentation on the … that includes the channel analysis data and the one or more real-time demand predictions pertaining to the at least one channel, wherein: the analytics display includes … display geographic regions corresponding to the plurality of channels, the … between macro-level channels and micro-level channels; the … is updated to display a geographic area corresponding to the at least one channel designated by the request and incorporate the one or more real-time demand predictions indicating the current demand corresponding to the at least one channel; and as the end-user navigates between or among the macro-level channels and the micro-level channels using the …, ... to display a real-time demand prediction for each channel that is presented via the.…, under the broadest reasonable interpretation, is human managing and predicting human demand, which is fundamental economic principles or practices, therefore, the claims are directed to organizing human activities.
Accordingly, the claims are directed to a mental process, organizing human activities, and thus, the claims are directed to an abstract idea under the first prong of Step 2A.
Analyzing under Step 2A, Prong 2:
This judicial exception is not integrated into a practical application under the second prong of Step 2A.
In particular, the claims recite the additional elements beyond the recited abstract idea identified under Step 2A, Prong 1, such as:
Claim 1, 11, 20: system comprising: one or more processors; and one or more non-transitory computer-readable storage devices storing computing instructions configured to run on the one or more processors and cause the one or more processors, execution of computing instructions configured to run at one or more processing devices and configured to be stored on non-transitory computer- readable media, A computer program product, the computer program product comprising a non- transitory computer-readable medium including instructions for causing a computing device, over a network, analytics platform, computing device over the network, computing device, machine-learning network, an interactive visualization that is configured to, interactive visualization integrating one or more selectable navigation options that permit an end-user to navigate, one or more selectable navigation options, interactive visualization is dynamically updated to display
Claim 3, 4: interactive
Claim 9: a OCSVM (One-class support vector machine) classification model; a SVDD (Support Vector Data Description) classification model
Claim 10: application programming interface (API), client systems
, and pursuant to the broadest reasonable interpretation, as an ordered combination, each of the additional elements are computing elements recited at high level of generality implementing the abstract idea, and thus, are no more than applying the abstract idea with generic computer components. Further, these additional elements generally link the abstract idea to a technical environment, namely the environment of a computer.
Additionally, with respect to, “receiving…”, “…receives an input…” “to generate and display…”, “generating…”, “….to display real-time…”, “…outputs the one or more real-time demand predictions…”, “…updated to display…”, “…to display a real-time demand prediction…”, these elements do not add a meaningful limitations to integrate the abstract idea into a practical application because they are extra-solution activity, pre and post solution activity - i.e. data gathering – “receiving…”, “…receives an input…”, data output – “to generate and display…”, “generating…”, “….to display real-time…”, “…outputs the one or more real-time demand predictions…”, “…updated to display…”, “…to display a real-time demand prediction…”.
Analyzing under Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under Step 2B.
As noted above, the aforementioned additional elements beyond the recited abstract idea are not sufficient to amount to significantly more than the recited abstract idea because, as an order combination, the additional elements are no more than mere instructions to implement the idea using generic computer components (i.e. apply it).
Additionally, as an order combination, the additional elements append the recited abstract idea to well-understood, routine, and conventional activities in the field as individually evinced by the applicant’s own disclosure, as required by the Berkheimer Memo, in at least:
[0049] All the components illustrated in FIG. 1A, including the one or more computing devices 110, one or more servers 120, one or more external data sources 130, and one or more client systems 140, and geolocation analytics platform 150 can be configured to communicate directly with each other and/or over the network 105 via wired or wireless communication links, or a combination of the two. Each of the computing devices 110, servers 120, external data sources 130, client systems 140, and geolocation analytics platform 150 can include one or more communication devices, one or more computer storage devices 101, and one or more processing devices 102 (FIG. 1B) that are capable of executing computer program instructions.
[0050] The one or more computer storage devices 101 may include (i) non-volatile memory, such as, for example, read only memory (ROM) and/or (ii) volatile memory, such as, for example, random access memory (RAM). The non-volatile memory may be removable and/or non-removable non-volatile memory. Meanwhile, RAM may include dynamic RAM (DRAM), static RAM (SRAM), etc. Further, ROM may include mask-programmed ROM, programmable ROM (PROM), one-time programmable ROM (OTP), erasable programmable read-only memory (EPROM), electrically erasable programmable ROM (EEPROM) (e.g., electrically alterable ROM (EAROM) and/or flash memory), etc. In certain embodiments, the one or more computing storage devices 101 may be physical, non-transitory mediums. The one or more computer storage devices 101 can store, inter alia, instructions associated with implementing the functionalities of the geolocation analytics platform 150 described herein.
[0051] The one or more processing devices 102 may include one or more central processing units (CPUs), one or more microprocessors, one or more microcontrollers, one or more controllers, one or more complex instruction set computing (CISC) microprocessors, one or more reduced instruction set computing (RISC) microprocessors, one or more very long instruction word (VLIW) microprocessors, one or more graphics processor units (GPU), one or more digital signal processors, one or more application specific integrated circuits (ASICs), and/or any other type of processor or processing circuit capable of performing desired functions. The one or more processing devices 102 can be configured to execute any computer program instructions that are stored or included on the one or more computer storage devices 101 including, but not limited to, instructions associated with implementing the functionalities of the geolocation analytics platform 150 described throughout this disclosure.
[0052] Each of the one or more communication devices can include wired and wireless communication devices and/or interfaces that enable communications using wired and/or wireless communication techniques. Wired and/or wireless communication can be implemented using any one or combination of wired and/or wireless communication network topologies (e.g., ring, line, tree, bus, mesh, star, daisy chain, hybrid, etc.) and/or protocols (e.g., personal area network (PAN) protocol(s), local area network (LAN) protocol(s), wide area network (WAN) protocol(s), cellular network protocol(s), powerline network protocol(s), etc.). Exemplary PAN protocol(s) can comprise Bluetooth, Zigbee, Wireless Universal Serial Bus (USB), Z-Wave, etc. Exemplary LAN and/or WAN protocol(s) can comprise Institute of Electrical and Electronic Engineers (IEEE) 802.3 (also known as Ethernet), IEEE 802.11 (also known as WiFi), etc. Exemplary wireless cellular network protocol(s) can comprise Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Evolution-Data Optimized (EV-DO), Enhanced Data Rates for GSM Evolution (EDGE), Universal Mobile Telecommunications System (UMTS), Digital Enhanced Cordless Telecommunications (DECT), Digital AMPS (IS-136/Time Division Multiple Access (TDMA)), Integrated Digital Enhanced Network (iDEN), Evolved High-Speed Packet Access (HSPA+), Long-Term Evolution (LTE), WiMAX, etc. The specific communication software and/or hardware can depend on the network topologies and/or protocols implemented. In certain embodiments, exemplary communication hardware can comprise wired communication hardware including, but not limited to, one or more data buses, one or more universal serial buses (USBs), one or more networking cables (e.g., one or more coaxial cables, optical fiber cables, twisted pair cables, and/or other cables). Further exemplary communication hardware can comprise wireless communication hardware including, for example, one or more radio transceivers, one or more infrared transceivers, etc. Additional exemplary communication hardware can comprise one or more networking components (e.g., modulator-demodulator components, gateway components, etc.). In certain embodiments, the one or more communication devices can include one or more transceiver devices, each of which includes a transmitter and a receiver for communicating wirelessly. The one or more communication devices also can include one or more wired ports (e.g., Ethernet ports, USB ports, auxiliary ports, etc.) and related cables and wires (e.g., Ethernet cables, USB cables, auxiliary wires, etc.).
[0053] In certain embodiments, the one or more communication devices additionally, or alternatively, can include one or more modem devices, one or more router devices, one or more access points, and/or one or more mobile hot spots. For example, modem devices may enable some or all of the computing devices 110, servers 120, external data sources 130, client systems 140, and/or geolocation analytics platform 150 to be connected to the Internet and/or other networks. The modem devices can permit bi-directional communication between the Internet (and/or other networks) and the computing devices 110, servers 120, external data sources 130, client systems 140, and/or geolocation analytics platform 150. In certain embodiments, one or more router devices and/or access points may enable the computing devices 110, servers 120, external data sources 130, client systems 140, and/or geolocation analytics platform 150 to be connected to a LAN and/or other networks. In certain embodiments, one or more mobile hot spots may be configured to establish a LAN (e.g., a Wi-Fi network) that is linked to another network (e.g., a cellular network). The mobile hot spot may enable the computing devices 110, servers 120, external data sources 130, client systems 140, and/or geolocation analytics platform 150 to access the Internet and/or other networks.
[0054] In certain embodiments, the computing devices 110 may represent desktop computers, laptop computers, mobile devices (e.g., smart phones, personal digital assistants, tablet devices, vehicular computing devices, wearable devices, or any other device that is mobile in nature), and/or other types of devices. The one or more servers 120 may generally represent any type of computing device, including any of the aforementioned computing devices 110. The one or more servers 120 also can comprise one or more mainframe computing devices and/or one or more virtual servers that are executed in a cloud-computing environment. In some embodiments, the one or more servers 120 can be configured to execute web servers and can communicate with the computing devices 110, external data sources 130, client systems 140, and/or other devices over the network 105 (e.g., over the Internet).
[0055] In certain embodiments, the geolocation analytics platform 150 can be implemented as a software-as-a-service (SaaS) platform, and may host one or more applications (e.g., one or more web-based applications) that are made available to users of the computing devices 110 over the network 105. For example, the geolocation analytics platform 150 may offer separate accounts to users (e.g., which may correspond to individuals, merchants, companies, businesses, and/or other entities). In certain embodiments, in response to a user creating an account, the geolocation analytics platform 150 may create a separate instance of one or more applications offered by the platform and the separate instance may be associated with the account. Users may access their accounts to view various types of channel analysis data, configure notification settings, interface client systems 140 with the geolocation analytics platform 150, and perform other functions described herein.
[0060] Each of the client systems 140 may include one or more computing devices 110 that enable the client systems 140 to access the geolocation analytics platform 150 over the network 105. In some cases, one or more of the client systems 140 may include sophisticated technological infrastructures, such as those that include enterprise systems, servers 120, virtual private networks (VPNs), intranets, etc. The computing devices 110, servers 120, and/or other devices associated with each client system 140 can store and execute various applications (e.g., such as ride hailing applications, lodging booking applications, dining reservation applications, pricing applications, inventory management applications, etc.). The client systems 140 and associated applications can leverage the data provided by the geolocation analytics platform 150 in various ways.
[0101] The geolocation analytics platform 150 also can include an analytics dashboard 165 that displays and/or provides access to the channel analysis data 180 in a variety of formats, and permits users to interact with the channel analysis data 180 in variety of ways. Generally speaking, the analytics dashboard 165 can be configured to generate various graphical user interfaces (GUIs) that provide access to, and display, any of the channel analysis data 180, channel events 175, and other data collected or processed by the geolocation analytics platform 150 to users operating computing devices 110. As explained in further detail below, the analytics dashboard 165 can be configured to display the aforementioned data and/or other data to users through a variety of display options (such as display options 260 in FIG. 2). The analytics dashboard 165 also can provide users with various configuration options, such as those facilitate transmission of notifications and/or interfacing with client systems 140.
[0121] The analytics dashboard 165 also includes a configuration display 250. The configuration display 250 can include one or more interactive graphical user interfaces that permits user to configure settings for executing deployment functions 190. For example, the configuration display 250 can include a client system interface display 252 that enables a user to interface or connect one or more client systems 140 with the geolocation analytics platform 150. The client system interface display 252 can include graphical user interfaces that establishes communications between the one or more client systems and the geolocation analytics platform 150 via an application programming interface (API) provided by the geolocation analytics platform 150. After a client system 140 is interfaced with the geolocation analytics platform 150, the client system 140 can receive and utilize the channel analysis data 180 (and any other information) generated by the geolocation analytics platform 150.
[0126] While the interfaces, displays, and interactive features described below demonstrate examples of how the channel analysis data 180 can be presented and displayed by the analytics dashboard 165, it should be understood that various modifications can be made. Amongst other things, any data or visualizations illustrated for one interface can be combined with, or incorporated into any other interface described in this disclosure. Additionally, certain features or options illustrated in the interfaces can be modified or omitted in certain cases. Additionally, while certain displays (e.g., channel display 212, merchant display 214, demand display 216) may be described as being separate components in some cases, it should be recognized that this distinction may be made for purposes of clarity and that a single display can be configured to generate any or all of the mentioned displays.
[0181] It should be recognized that any features and/or functionalities described for an embodiment in this application can be incorporated into any other embodiment mentioned in this disclosure. Moreover, the embodiments described in this disclosure can be combined in various ways. Additionally, while the description herein may describe certain embodiments, features, or components as being implemented in software or hardware, it should be recognized that any embodiment, feature, or component that is described in the present application may be implemented in hardware, software, or a combination of the two.
[0182] While various novel features of the invention have been shown, described, and pointed out as applied to particular embodiments thereof, it should be understood that various omissions and substitutions, and changes in the form and details of the systems and methods described and illustrated, may be made by those skilled in the art without departing from the spirit of the invention. Amongst other things, the steps in the methods may be carried out in different orders in many cases where such may be appropriate. Those skilled in the art will recognize, based on the above disclosure and an understanding of the teachings of the invention, that the particular hardware and devices that are part of the system described herein, and the general functionality provided by and incorporated therein, may vary in different embodiments of the invention. Accordingly, the description of system components are for illustrative purposes to facilitate a full and complete understanding and appreciation of the various aspects and functionality of particular embodiments of the invention as realized in system and method embodiments thereof. Those skilled in the art will appreciate that the invention can be practiced in other than the described embodiments, which are presented for purposes of illustration and not limitation. Variations, modifications, and other implementations of what is described herein may occur to those of ordinary skill in the art without departing from the spirit and scope of the present invention and its claims.
Furthermore, as an ordered combination, these elements amount to generic computer components receiving or transmitting data over a network, performing repetitive calculations, electronic record keeping, and storing and retrieving information in memory, which, as held by the courts, are well-understood, routine, and conventional. See MPEP 2106.05(d).
Moreover, the remaining elements of dependent claims do not transform the recited abstract idea into a patent eligible invention because these remaining elements merely recite further abstract limitations that provide nothing more than simply a narrowing of the abstract idea recited in the independent claims.
Looking at these limitations as an ordered combination adds nothing additional that is sufficient to amount to significantly more than the recited abstract idea because they simply provide instructions to use a generic arrangement of generic computer components to “apply” the recited abstract idea, perform insignificant extra-solution activity, and generally link the abstract idea to a technical environment. Thus, the elements of the claims, considered both individually and as an ordered combination, are not sufficient to ensure that the claim as a whole amounts to significantly more than the abstract idea itself. Since there are no limitations in these claims that transform the exception into a patent eligible application such that these claims amount to significantly more than the exception itself, claims 1-11, 20-27 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Claim Rejections – 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
Determining the scope and contents of the prior art.
Ascertaining the differences between the prior art and the claims at issue.
Resolving the level of ordinary skill in the pertinent art.
Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-8, 10-11, 20-27 is/are rejected under 35 U.S.C. 103 as being unpatentable by US Patent Publication to US20220075515A1 to Floren et al., (hereinafter referred to as “Floren”) in view of US Patent Publication to US20170098181A1 to Herman et al., (hereinafter referred to as “Herman”)
As per Claim 1, Floren teaches: (Currently Amended) A system comprising: one or more processors; and one or more non-transitory computer-readable storage devices storing computing instructions configured to run on the one or more processors and cause the one or more processors to execute functions comprising: ([0280])
providing access over a network to a demand analytics platform that is configured to monitor real-time demand conditions in a plurality of channels that correspond to geographic regions and provide an analytics dashboard configured to display real-time demand predictions corresponding to the plurality of channels; (in at least [0008] the user interfaces described herein are more efficient as compared to previous user interfaces in which data is not dynamically updated and compactly and efficiently presented to the user in response to interactive inputs. In some embodiments, the data is updated and presented to the user in real-time [0039] Visualizing the interaction of the data models is often useful in understanding the rea-world system. For example, properly visualizing simulations of the data models over time can be useful in understanding how the real-world system may perform, specifically at a particular point in time, over a period of time, or in real-time. [0082] The model simulator 118 may obtain, generate, and/or simulate one or more models based on the one or more real-world systems 102 and/or the error detection data stored in the real-world system data store 106. The one or more models may be stored in the simulated system data store 122. The error detection data from the real-world system data store 106 may include when the real-world subsystem 112, logical computations, and/or physical sensor error may have occurred over a period of time (e.g., historical sensor error data, live sensor data, real-time sensor data, etc.) and may store this time-series data in the time-series data store 121. The model simulator 118 may transmit the various models and/or data from the time-series data store 121 and/or the simulated system data store 122 to the object simulator 120 to generate objects (e.g., virtual items or products, virtual sensors, virtual measuring devices, etc.) and/or to the subsystem simulator 119 to generate subsystems (e.g., virtual subsystems that may further include the set of virtual logical computations, virtual sensors, virtual measuring devices, etc.). If no real-world subsystem, logical computations, and/or physical sensor error has occurred, the one or more model relationships, subsystems and/or objects may closely mirror the actual real-world subsystem, logical computations, and/or physical sensors. The model simulator 118 may compare actual real-world subsystem 112, logical computations, and/or physical sensor data with simulated data of the one or more simulated models (e.g., data from the generated virtual logical computations, virtual sensors, virtual measuring devices, virtual subsystems, etc.). [0166] FIGS. 8A-8O illustrate various example implementations, features, and advantages associated with graph-based GUIs of the system, according to one or more embodiments. The graph-based GUIs of the system can, for example, enable exploring entities, events, and connections in a complex enterprise system; monitoring the current or historical state of any part of such a system; setting up visual warnings or actionable alerts to target risks and opportunities; and/or simulating scenarios to find the local decisions for the best global outcomes. [0168] The example user interface 800 provides a view of a simulated technical system representing a real-world system. The view may include various technical systems, subsystems, objects, and the like. Although not shown in the user interface, the system can associate various data, including time-based data, and models with the systems, subsystems, and objects, such that simulations can be run. The user interface, based on simulations, can provide a view of how the real-world system has performed in the past, is performing, and can be expected to perform in the future. As an example, by simulating movements of materials and goods, the system may determine a current inventory of goods, a bottleneck in production, an expected lack of supply or inventory to meet demand [0191] FIG. 9A, an example user interface 900 includes an interactive map section 902 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 904 and 905. As described above, the nodes may be colored or highlighted based on related statuses, and/or the like. Relationships among the objects are represented by edges, such as edge 907, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items. [0197] User interface portion 921 shows that a first model 930 has been added to the simulation. Via button 931, the user may add one or more time-based data sets, properties, measures, and/or parameters to the model. Such items may include inputs and output of the model. User interface portion 922 shows that multiple inputs and outputs have been added to the model, and that the user may now optionally run the simulation by selecting the “run simulation” button 937. Details of actions taken by the system when a simulation is executed are provided elsewhere in the present disclosure. The user may edit one or more values in the input rows of the model (e.g., item 940) to modify the parameters of the simulation before it is run. Results of the simulation are shown as the values in the model outputs in the simulation column of the table. As discussed above, the user may run multiple simulations with the same set of inputs and outputs by adding another column to the table, modifying one or more of the input values, and again running the simulation. [0308] the one or more object properties may be numerical, physical, geometrical, inferred, real, simulated, or virtual. Further the object properties may comprise of logical computations related to order volume (i.e. demand), sales amounts (i.e. demand), sales quantity during a time period (e.g., a day, a week, a year, etc.), population density, patient volume, or other object properties relevant to the pertaining model.)
Examiner notes: the claimed real-time demand conditions under the broadest reasonable interpretation is “simulated” when processed by the claimed processor, which is taught by Floren simulating real-world events and product demand using simulation objects on the computer, since Floren discloses in [0308] the one or more object properties may be numerical, physical, geometrical, inferred, real, simulated, or virtual.
receiving, by the demand analytics platform, real-time channel events pertaining to each of the plurality of channels over the network, wherein each channel is associated with location definition data that defines a geographic boundary corresponding to the channel and the real-time channel events include attributes reflecting real-time demand conditions for one or more verticals in the plurality of channels; (in at least [0083] the interactive user interface may be configured to allow a user to view or edit, in at least one of the displayed panels, unusual (e.g., abnormal) or periodic events that have occurred and/or that may occur in the future during operation of the logical computations, sensors, and/or measuring devices 114 and/or real-world subsystems 112. Such events may also apply to the simulated virtual objects (e.g., virtual items or products, virtual measuring devices, and/or virtual subsystems). For example, in the case of a supply chain, the object properties may include a time that an item or product was shipped from one location to another location, a time that an item or product arrived at a particular location, etc. In the case of an oil well, events may include sand entering a well during the drilling process, a structural vibration in a component or a piece of equipment of the oil well, a failure of a component or a piece of equipment of the oil well, maintenance being performed on a component or equipment of the oil well, deferral of a component or equipment of the oil well, and/or the like. In the case of a manufacturing site, events may include machinery malfunction, a structural vibration in a part of the machinery, changes in manufacturing conditions (e.g., temperature, efficiency, output, etc.), and/or the like. In the case of a vehicle, events may include a component malfunction, a change in a weather condition (e.g., humidity, wind speed, temperature, etc.), a weather phenomenon (e.g., icing, a lightning strike, a large wave, a tornado, etc.), deviations from an expected travel route (e.g., a change from an expected route determined by a navigation system, a change from the flight plan, etc.), a change in fuel efficiency, and/or the like. In the case of a fracking site, events may include the movement of fluids across various depths, changes in the rock layer, equipment failure, and/or the like. In the case of an environmental monitoring and/or researching site, events may include seismic activity (e.g., as caused by tectonic plates, volcanoes, etc.), ice breakage, lava flow, weather phenomena, and/or the like. In the case of a mine, events may include rock movements, rock burst bumps (e.g., seismic jolts within the mine), blasts, micro-seismic events (e.g., events associated with impending ground control problems like roof collapses or other structural failures), equipment failure, and/or the like. In the case of other types of logical computations, sensors, and/or measuring devices 114 and/or real-world subsystems 112, events can include misalignment of parts on a manufacturing machine, trees falling, landslides, mudslides, avalanches, and/or the like. Although several specific cases are mentioned as example events that have occurred and/or that may occur during operation, this is merely illustrative and not meant to be limiting. For example, maintenance, deferral, weather, equipment failure, delivery delays, re-routing of items or products, order cancellation, etc. are other events that may occur in other cases. [0167] FIG. 8A, an example user interface 800 includes an interactive graph section 802 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 804 and 806. For ease of description, the information shown in the GUIs of the present disclosure is generally referred to as objects, but as noted various systems and subsystems may similarly be represented. As described throughout the present disclosure, the systems, subsystems, and objects may represent various things, such as people, locations, facilities, and the like. Relationships among the various systems, subsystems, and objects are represented by edges, such as edge 808, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items. In the example user interface 800, a supply chain is represented, including node representing parts and goods suppliers, manufacturing plants, distributors, consumers (e.g., hospitals), and the like (i.e. channels). The graph section 802 is interactive, and a user may adjust the view of the objects via zooming in and out, or moving nodes around. The system may also automatically adjust the positioning of the nodes to provide an organized view and/or alignment of related objects. Additionally, the system allows the user to interact with (e.g., view, edit, move, add, delete, etc.) model specific subsystems, objects, object properties, error detection data, and/or events of the system. For example, the user may add additional related objects/nodes to the graph section 802 in various ways, including by searching the system for objects related to already displayed objects/nodes. FIG. 8C illustrates a toolbar by which the user may select to add objects to the graph via button 818. [0168] The example user interface 800 provides a view of a simulated technical system representing a real-world system. The view may include various technical systems, subsystems, objects, and the like. Although not shown in the user interface, the system can associate various data, including time-based data, and models with the systems, subsystems, and objects, such that simulations can be run. The user interface, based on simulations, can provide a view of how the real-world system has performed in the past, is performing, and can be expected to perform in the future. As an example, by simulating movements of materials and goods (i.e. verticals), the system may determine a current inventory of goods (i.e. verticals), a bottleneck in production, an expected lack of supply or inventory to meet demand [0192] Dots or nodules may be represented on the edges to indicate movement events, or quantities of items (i.e. verticals) moved from one location to another. The nodules can be time-based, meaning that they can accurately represent the points in time that items move from one location to another, based on the point in time selected by the user via time slider 909. Thus, the nodules may be determined based on time-based data associated with the related objects. As the user adjusts the date/time, the time-based data associated with the objects and/or links, and movement of data and/or items among the objects, can be displayed. Optionally the movements can be displayed in an animated fashion as the user slides the slider across the shown time span. Similar animated dots or nodules may be displayed along edges of the graph-based GUIs of the present disclosure to indicate movements of data/goods/etc. from one object to another.)
receiving, via the analytics dashboard, a request designating at least one channel of the plurality of channels from a computing device over the network; (in at least [0094] data object 154 is a container for information representing things in the world. For example, data object 154 can represent an entity such as a person or user, a place, a group, an organization, a resource, a data asset, a request, a purpose, a link, or other noun. Data object 154 can represent an event that happens at a point in time or for a duration. Data object 154 can represent a document or other unstructured data source such as an e-mail message, a news report, or a written paper or article. Each data object 154 is associated with a unique identifier that uniquely identifies the data object within the access management system. [0167] FIG. 8A, an example user interface 800 includes an interactive graph section 802 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 804 and 806. For ease of description, the information shown in the GUIs of the present disclosure is generally referred to as objects, but as noted various systems and subsystems may similarly be represented. As described throughout the present disclosure, the systems, subsystems, and objects may represent various things, such as people, locations, facilities, and the like. Relationships among the various systems, subsystems, and objects are represented by edges, such as edge 808, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items. In the example user interface 800, a supply chain is represented, including node representing parts and goods suppliers, manufacturing plants, distributors, consumers (e.g., hospitals), and the like. The graph section 802 is interactive, and a user may adjust the view of the objects via zooming in and out, or moving nodes around. The system may also automatically adjust the positioning of the nodes to provide an organized view and/or alignment of related objects. Additionally, the system allows the user to interact with (e.g., view, edit, move, add, delete, etc.) model specific subsystems, objects, object properties, error detection data, and/or events of the system. For example, the user may add additional related objects/nodes to the graph section 802 in various ways, including by searching the system for objects related to already displayed objects/nodes. FIG. 8C illustrates a toolbar by which the user may select to add objects to the graph via button 818. [0168] The example user interface 800 provides a view of a simulated technical system representing a real-world system. The view may include various technical systems, subsystems, objects, and the like. Although not shown in the user interface, the system can associate various data, including time-based data, and models with the systems, subsystems, and objects, such that simulations can be run. The user interface, based on simulations, can provide a view of how the real-world system has performed in the past, is performing, and can be expected to perform in the future. As an example, by simulating movements of materials and goods, the system may determine a current inventory of goods, a bottleneck in production, an expected lack of supply or inventory to meet demand [0171] The user interface 800 may include an information panel 810 comprising various properties and other information associated with a selected object (e.g., selected object 804). Via the information panel 810, a user may also, for example, view time-based data associated with objects. [0191] FIG. 9A, an example user interface 900 includes an interactive map section 902 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 904 and 905. As described above, the nodes may be colored or highlighted based on related statuses, and/or the like. Relationships among the objects are represented by edges, such as edge 907, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items.)
generating channel analysis data pertaining to the at least one channel based, at least in part, on the real-time channel events corresponding to the at least one channel designated by the request, wherein generating the channel analysis data includes executing a machine-learning network to generate one or more real-time demand predictions corresponding to the at least one channel identified by the request such that (i) the machine-learning network receives an input … a set of channel features derived, at least in part, from the real-time channel event, the set of channel features modeling the real-time demand conditions for the at least one channel; and (ii) the machine-learning network outputs the one or more real-time demand predictions to predict a current demand corresponding to the at least one channel; and (in at least [0144] in FIGS. 6 and 7. For example, the artificial intelligence training system 402 can train an artificial intelligence system using the parameter input and output nodes of the plurality of models, where the artificial intelligence system may be a neural network like an RNN. At (19), the artificial intelligence training system 402 may predict nodal relationships between parameter output and input nodes based on the classifications made by the artificial intelligence training system 402. The artificial intelligence training system 402 can then transmit the predicted nodal relationship data to the model connector 404 at (20). [0151] new parameter output and input nodes may be simulated by the model simulator 118 during operation (620) if new models are generated and/or simulated from the obtained plurality of models. The new parameter output and input nodes may further include new subsystems and/or objects generated by the subsystem simulator 119 and/or object simulator 120. Thus, the artificial intelligence training system 402 can additionally train the artificial intelligence system to further predict new potential nodal relationships. For example, a new wastewater facility model may be simulated that may include a new virtual treatment comminutor sensor, where the new virtual treatment comminutor sensor may be generated by the object simulator 120 after the initial linking has occurred. Thus, there may be a new parameter output or input node for the new wastewater facility model that may then be used by the artificial intelligence training system 402 to further predict new potential nodal relationships. [0168] The example user interface 800 provides a view of a simulated technical system representing a real-world system. The view may include various technical systems, subsystems, objects, and the like. Although not shown in the user interface, the system can associate various data, including time-based data, and models with the systems, subsystems, and objects, such that simulations can be run. The user interface, based on simulations, can provide a view of how the real-world system has performed in the past, is performing, and can be expected to perform in the future. As an example, by simulating movements of materials and goods, the system may determine a current inventory of goods, a bottleneck in production, an expected lack of supply or inventory to meet demand [0171] The user interface 800 may include an information panel 810 comprising various properties and other information associated with a selected object (e.g., selected object 804). Via the information panel 810, a user may also, for example, view time-based data associated with objects. [0175] Based on the time selected (e.g., via the time slider 816), objects in the graph section 802 may be colored and/or highlighted based on a status of those objects, where the status may be determined based on time-based data, models, and/or simulations. For example, a color of node 804 may be green at one point in time, indicating a sufficient supply of goods, but it may be red at another time indicating a lack of inventory. Such statuses may be predictive based on other objects and their associated models. For example, if a supplier is modeled as having a reduced supply in the future, the manufacturer may model a reduced output, and a supplier may model a shortage of inventory, assuming a modeled constant or increasing demand for goods. In some embodiments the colors that represent an object and/or subsystem may change based on the time-series data specific times within the time-series. Thus, the styling of items shown in the user interface 800 may depend on the time-series data, models, simulations, and/or the ontology upon which the modeled system is based. [0185] FIG. 8L, an example user interface portion 870 is shown which may comprise a portion of, or an update to, user interface 800. The user interface portion 870 illustrates additional system functionality related to alerting, in which alerts 871 associated with a selected object are displayed in an event panel of the GUI. In various implementations, the GUI can include a panel that displays any alerts associated with any objects in the graph. In either case these alerts can then be opened in other applications for more details or workflows, as described herein. Alerts may be generated when models indicate an undesirable status, such as an insufficient inventory)
generating, by the analytics dashboard, an analytics display for presentation on the computing device that includes the channel analysis data and the one or more real-time demand predictions pertaining to the at least one channel, wherein: ([0166][0190])
the analytics display includes an interactive visualization that is configured to display geographic regions corresponding to the plurality of channels, the interactive visualization integrating one or more selectable navigation options that permit an end-user to navigate between macro-level channels and micro-level channels; (in at least [0167] FIG. 8A, an example user interface 800 includes an interactive graph section 802 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 804 and 806. For ease of description, the information shown in the GUIs of the present disclosure is generally referred to as objects, but as noted various systems and subsystems may similarly be represented. As described throughout the present disclosure, the systems, subsystems, and objects may represent various things, such as people, locations, facilities, and the like. Relationships among the various systems, subsystems, and objects are represented by edges, such as edge 808, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items. In the example user interface 800, a supply chain is represented, including node representing parts and goods suppliers, manufacturing plants, distributors, consumers (e.g., hospitals), and the like. The graph section 802 is interactive, and a user may adjust the view of the objects via zooming in and out, or moving nodes around. [0190] FIGS. 9A-9H illustrate various example implementations, features, and advantages associated with map-based GUIs of the system, according to one or more embodiments. The map -based GUIs of the system can allow a user to, e.g., generate visualizations of properties, links, and/or time-based data associated with objects; interact with properties associated with one or more objects; interact with a histogram of objects; interact with time-based data associated with objects; and/or the like. In various implementations, the map-based GUIs may be 2-dimensional or 3-dimensional, and interactive such that the user may move around the map, zoom in and out, change the angle of view, and the like. As mentioned above, the functionality of the map-based GUIs can be similar to the graph-based GUI. However, in addition the map-based GUIs can include a geographical map, and indicate geographical locations of objects representing objects on the map as nodes or indicators, such as icons. [0191] Referring to FIG. 9A, an example user interface 900 includes an interactive map section 902 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 904 and 905. As described above, the nodes may be colored or highlighted based on related statuses, and/or the like. Relationships among the objects are represented by edges, such as edge 907, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items.)
the interactive visualization is updated to display a geographic area corresponding to the at least one channel designated by the request and incorporate the one or more real-time demand predictions indicating the current demand corresponding to the at least one channel; and (in at least [0201] FIGS. 9G-9H, example user interface portions 950-951 are shown which may comprise portions of, or updates to, user interface 900. The user interface portions 950-951 illustrate system functionality related to optimizations, e.g., via a remediation panel 952. For example, the user may access optimizations/remediations via a “remediation” button on the upper right side of the GUI. As shown in user interface portion 950, the user may select to optimize for a particular simulation (e.g., via button 954), or based on current data via “generate suggestions” button 956. User interface portion 951 shows that the user has selected button 956, in response to which the system has generated a list of suggested optimizations/remediations 958. The system generates the list of suggested optimizations/remediations by running a number of scenarios and simulations, targeting to remove or reduce the severity of any alerts (e.g., any object statuses that are undesirable), as described elsewhere herein. Examples of remediations may include, for example, ordering more supplies, moving inventory, rushing existing orders, and/or the like. Via buttons 959 the user may select one or more of the suggested remediation actions, in response to which the system may automatically take action to make the suggested changes. Further examples of suggestions/recommendation for remediations and related functionality are described below in reference to various GUIs/applications/use cases. [0233] The panel 1306 can include various information, examples of which are shown in the example user interface 1300. For example, the panel 1306 may indicate an alert type, a component/object associated with the alert, a number of days covered by the alert, etc. In the example of a supply chain-related alert, the alert may indicate, for example, inventories and demand over time (e.g., as indicated in chart 1308), and/or breakdowns of orders and demand (e.g., as indicated in table 1310). As discussed herein, the simulations of the system can be predictive, thus an alert may be based on an expected demand not being met by orders placed and expected shipment times, for example. In other words, the shortage may be predicted by the system based on a current model of shipments, inventory, demand)
as the end-user navigates between or among the macro-level channels and the micro-level channels using the one or more selectable navigation options, the interactive visualization is dynamically updated to display a real-time demand prediction for each channel that is presented via the interactive visualization. (in at least [0048] Workflow modules (“applications”) can provide various advantages, for example: the system can provide benefits to operational users as the system can provide customized views for the users' specific contexts which may be accessible from objects in the system, where available. This can make it simpler to switch between a “zoomed out” view of the system, and a zoomed-in view for a specific functional workflow. [0079] The user interface generator 117 may be configured to generate user interface code or data that, when executed, results in additional features being depicted in the rendered and/or displayed interactive user interface. For example, the interactive user interface may allow the user to scroll on any of the displayed panels and/or change a zoom level of the displayed panels to view information at different depths and/or times. [0167] FIG. 8A, an example user interface 800 includes an interactive graph section 802 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 804 and 806. For ease of description, the information shown in the GUIs of the present disclosure is generally referred to as objects, but as noted various systems and subsystems may similarly be represented. As described throughout the present disclosure, the systems, subsystems, and objects may represent various things, such as people, locations, facilities, and the like. Relationships among the various systems, subsystems, and objects are represented by edges, such as edge 808, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items. In the example user interface 800, a supply chain is represented, including node representing parts and goods suppliers, manufacturing plants, distributors, consumers (e.g., hospitals), and the like. The graph section 802 is interactive, and a user may adjust the view of the objects via zooming in and out, or moving nodes around. )
Although implied, Floren does not expressly disclose the following limitations, which however, are taught by Herman,
the machine-learning network receives an input comprising … channel events, … machine-learning network outputs the one or more real-time demand predictions to predict a current demand corresponding to the at least one channel… (in at least [0028] adaptations of expectation-maximization clustering algorithms, assignment algorithms, Monte Carlo simulation of likely outcomes, and queueing-based algorithms to allow command staff to interactively schedule patrols in real-time. The patrol schedules and objective function values may be optimized using, for example, the incident event data, a predicted-demand model, street map(s), traffic model(s), and crime rates for the relevant city. [0053] In step 120, the predicted-demand model may also be generated using feature-aided machine learning. From a historic incident database, data may be extracted for each incident s∈D, including the auxiliary data. The k features may be defined xi:=φi(s) for s∈D, i=l, . . . ,k that provide mappings of the raw data into a feature space that is believed to provide meaningful correlations with the observed incident rates. Choices for θi include the original data itself (e.g., location, time of day, day of the week, month of the year, type of event, etc.), categorizations (e.g., weekday, weekend, holiday), and measured quantities (e.g., snow depth in inches or temperature in degrees Fahrenheit). Ultimately, any combination of features that can possibly be correlated to incident rates may be included (e.g., hours after a professional sports team loss, school vacation days, phase of the moon, pay day for a major employer, stock indices, etc.). In this way, a feature vector x=φ(s) may be obtained for each s∈D. Also, by averaging over an appropriate time interval, an observed incident rate, λ, associated with each feature vector x, may be computed. [0058] The learning algorithm may capture and use trends, such as the number of incidents in an area steadily increasing as the local population increases (e.g., due to urbanization), to inform the predicted incident rates for individual regions. In certain embodiments, Gaussian process regression may be used to incorporate predictive models for trends in known quantities (e.g., population growth, population density, home values, income levels, etc.) to learn the effect of hidden variables. Gaussian process regression may be used to detect the influence of an underlying driver that affects the rate of incidents city-wide but may not be listed as one of the feature variables. Gaussian process regression may be used to analyze the trend behind the influence of the underlying driver. Gaussian process regression may be used to analyze the underlying driver's effect on forecasted rates of future events (i.e., incidents). Gaussian process regression is a unified non-parametric machine-learning framework that may require few assumptions on the data. A Gaussian prior probability distribution (“prior”) over the space of all functions may be provided, and the data used to determine the function that provides the most likely model. Thus, the combination of the prior and the data leads to the posterior distribution over functions from which the predictions and the uncertainty in these predictions may be drawn. [0068] the predicted-demand model generated in step 120 may be particular to a certain geographic area. The geographic area may be, for example, a sector that police officers will patrol. Such a sector may be divided into smaller geographic sections, or “regions.” In some embodiments, every point within a sector may be contained by some region. In some embodiments, the model may desire to restrict one or more patrol officers to a particular region. In some cases, it is desirable to restrict a given patrol unit to only one region at a time. In some embodiments the geographic area may be, for example, larger than the sector that police officers will patrol (e.g., the entire country). In some embodiments, the geographic area may be smaller than the sector that police officers will patrol (e.g., one region within a patrol sector). [0082] predictions of demand rates for police assistance in geographic areas may be displayed to users on an expected-demand map, such as exemplary expected-demand map 210, as illustrated in FIG. 2A. The map may have different colors or shadings, such as shading 220 on expected-demand map 210, to indicate the predicted demand rate at a given geographic point. Another exemplary expected-demand map is illustrated in FIG. 2B as expected-demand map 230. In expected-demand map 230, a larger geographic region 240, rather than a point, is shaded in a manner that indicates the predicted demand rate (e.g., with darker shading indicating a higher predicted demand rate). [0092] The selection and optimality of patrol schedule σ may be guided by various additional data. Updates to a database of incidents, D, that may contain data comprising records may be provided regularly (e.g., daily, hourly, or real-time) from a database or memory with data (e.g., CAD data). Each incident s∈D may be marked with pertinent information such as time, location, incident type, incident priority, number of responding officers, and/or duration of the incident. Incidents are also cross-referenced with auxiliary data such as city zoning type, weather data (temperature, precipitation, snow depth, wind speeds, etc.), census data (population demographics, density, income levels, etc. for the incident location), traffic conditions, special event data, etc. A goal may be to use machine-learning techniques to correlate the auxiliary data with incident rates and use those correlations to provide accurate forecasts of future demand for law enforcement services. [0135] the system may receive updated historic demand event data and/or correlative data and generate a new predicted demand model. The new model may then be used to update the schedules in step 160.)
At the time the invention was filed, it would have been obvious for one of ordinary skill in the art to have modified the teachings of Floren, as taught by Herman above, with a reasonable expectation of success if arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make this modification to the teachings of Floren with the motivation of, …apply big-data machine-learning techniques to predict rates of calls for service in various geographic regions of a sector and then to make those predictions actionable to command staff by providing optimized assignments of officers to patrol routes within a region or sector. Feature-aided machine learning may be used to more accurately predict crime and incident rates by time, type, and location. To further improve the accuracy of the demand model, the historic demand event data may be correlated with other data relating to past events, such as the date, time of day, day of the week, month of the year, weather, zoning, demographics, traffic, public events, and the occurrence of holidays.…the historic demand event data may be correlated with multiple types of correlative data to further improve the reliability of the demand model…properly identify the influence of hidden variables on the observed variables and extrapolation of that effect forward in time may be investigated to improve incident forecasts by more accurately capturing the effect of trends in the hidden variables.., as recited in Herman.
As per Claim 2, Floren teaches: (Currently Amended) The system of claim 1, wherein the analytics display visualizes:
the one or more real-time demand predictions that predict the current demand for the at least one channel designated by the request; and (in at least [0008] the user interfaces described herein are more efficient as compared to previous user interfaces in which data is not dynamically updated and compactly and efficiently presented to the user in response to interactive inputs. In some embodiments, the data is updated and presented to the user in real-time [0039] Visualizing the interaction of the data models is often useful in understanding the rea-world system. For example, properly visualizing simulations of the data models over time can be useful in understanding how the real-world system may perform, specifically at a particular point in time, over a period of time, or in real-time. [0168] The user interface, based on simulations, can provide a view of how the real-world system has performed in the past, is performing, and can be expected to perform in the future. As an example, by simulating movements of materials and goods, the system may determine a current inventory of goods, a bottleneck in production, an expected lack of supply or inventory to meet demand [0175] Based on the time selected (e.g., via the time slider 816), objects in the graph section 802 may be colored and/or highlighted based on a status of those objects, where the status may be determined based on time-based data, models, and/or simulations. For example, a color of node 804 may be green at one point in time, indicating a sufficient supply of goods, but it may be red at another time indicating a lack of inventory. Such statuses may be predictive based on other objects and their associated models. For example, if a supplier is modeled as having a reduced supply in the future, the manufacturer may model a reduced output, and a supplier may model a shortage of inventory, assuming a modeled constant or increasing demand for goods.)
at least one additional demand prediction that indicates or predicts a future demand for the at least one channel in a future time period. (in at least [0008] the user interfaces described herein are more efficient as compared to previous user interfaces in which data is not dynamically updated and compactly and efficiently presented to the user in response to interactive inputs. In some embodiments, the data is updated and presented to the user in real-time [0039] Visualizing the interaction of the data models is often useful in understanding the rea-world system. For example, properly visualizing simulations of the data models over time can be useful in understanding how the real-world system may perform, specifically at a particular point in time, over a period of time, or in real-time. [0168] The user interface, based on simulations, can provide a view of how the real-world system has performed in the past, is performing, and can be expected to perform in the future. As an example, by simulating movements of materials and goods, the system may determine a current inventory of goods, a bottleneck in production, an expected lack of supply or inventory to meet demand [0175] Based on the time selected (e.g., via the time slider 816), objects in the graph section 802 may be colored and/or highlighted based on a status of those objects, where the status may be determined based on time-based data, models, and/or simulations. For example, a color of node 804 may be green at one point in time, indicating a sufficient supply of goods, but it may be red at another time indicating a lack of inventory. Such statuses may be predictive based on other objects and their associated models. For example, if a supplier is modeled as having a reduced supply in the future, the manufacturer may model a reduced output, and a supplier may model a shortage of inventory, assuming a modeled constant or increasing demand for goods.)
As per Claim 3, Floren teaches: (Currently Amended) The system of claim 1, wherein:
the interactive visualization presented on the analytics display comprises an interactive map that includes an overlay visualizing the geographic boundary for the at least one channel and annotating the interactive map with one or more demand indicators identifying or predicting the current demand in the at least one channel; and (in at least [0008] the user interfaces described herein are more efficient as compared to previous user interfaces in which data is not dynamically updated and compactly and efficiently presented to the user in response to interactive inputs. In some embodiments, the data is updated and presented to the user in real-time [0039] Visualizing the interaction of the data models is often useful in understanding the rea-world system. For example, properly visualizing simulations of the data models over time can be useful in understanding how the real-world system may perform, specifically at a particular point in time, over a period of time, or in real-time. [0168] The example user interface 800 provides a view of a simulated technical system representing a real-world system. The view may include various technical systems, subsystems, objects, and the like. Although not shown in the user interface, the system can associate various data, including time-based data, and models with the systems, subsystems, and objects, such that simulations can be run. The user interface, based on simulations, can provide a view of how the real-world system has performed in the past, is performing, and can be expected to perform in the future. As an example, by simulating movements of materials and goods, the system may determine a current inventory of goods, a bottleneck in production, an expected lack of supply or inventory to meet demand [0175] Based on the time selected (e.g., via the time slider 816), objects in the graph section 802 may be colored and/or highlighted based on a status of those objects, where the status may be determined based on time-based data, models, and/or simulations. For example, a color of node 804 may be green at one point in time, indicating a sufficient supply of goods, but it may be red at another time indicating a lack of inventory. Such statuses may be predictive based on other objects and their associated models. For example, if a supplier is modeled as having a reduced supply in the future, the manufacturer may model a reduced output, and a supplier may model a shortage of inventory, assuming a modeled constant or increasing demand for goods. [0190] FIGS. 9A-9H illustrate various example implementations, features, and advantages associated with map-based GUIs of the system, according to one or more embodiments. The map -based GUIs of the system can allow a user to, e.g., generate visualizations of properties, links, and/or time-based data associated with objects; interact with properties associated with one or more objects; interact with a histogram of objects; interact with time-based data associated with objects; and/or the like. In various implementations, the map-based GUIs may be 2-dimensional or 3-dimensional, and interactive such that the user may move around the map, zoom in and out, change the angle of view, and the like. As mentioned above, the functionality of the map-based GUIs can be similar to the graph-based GUI. However, in addition the map-based GUIs can include a geographical map, and indicate geographical locations of objects representing objects on the map as nodes or indicators, such as icons. [0191] FIG. 9A, an example user interface 900 includes an interactive map section 902 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 904 and 905. As described above, the nodes may be colored or highlighted based on related statuses, and/or the like. Relationships among the objects are represented by edges, such as edge 907, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items.)
the analytics dashboard generates the analytics display, at least in part, using the real-time channel events corresponding to the at least one channel. (in at least [0008] the user interfaces described herein are more efficient as compared to previous user interfaces in which data is not dynamically updated and compactly and efficiently presented to the user in response to interactive inputs. In some embodiments, the data is updated and presented to the user in real-time [0039] Visualizing the interaction of the data models is often useful in understanding the rea-world system. For example, properly visualizing simulations of the data models over time can be useful in understanding how the real-world system may perform, specifically at a particular point in time, over a period of time, or in real-time. [0191] FIG. 9A, an example user interface 900 includes an interactive map section 902 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 904 and 905. As described above, the nodes may be colored or highlighted based on related statuses, and/or the like. Relationships among the objects are represented by edges, such as edge 907, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items. [0204] to FIG. 10A, an example user interface 1000 includes both an interactive map-based section 1002, and an interactive alert-based section 1004. As noted above, various different GUIs of the present system can have similar functionality, and can be combined in various ways. For example, an alert-based section could also similarly be combined with a graph-based section. [0175] Based on the time selected (e.g., via the time slider 816), objects in the graph section 802 may be colored and/or highlighted based on a status of those objects, where the status may be determined based on time-based data, models, and/or simulations. For example, a color of node 804 may be green at one point in time, indicating a sufficient supply of goods, but it may be red at another time indicating a lack of inventory. Such statuses may be predictive based on other objects and their associated models. For example, if a supplier is modeled as having a reduced supply in the future, the manufacturer may model a reduced output, and a supplier may model a shortage of inventory, assuming a modeled constant or increasing demand for goods. [0205] The alert-based section 1004 of the user interface 1000 may include a listing of alerts associated with the objects shown in the map-based section 1002, and/or any selected objects. The list may be filterable, and as shown may include various details regarding the listed alerts. In the example user interface 1000, one alert is shown, and the associated object on the map is shown in red. The user may select the alert, in response to which the system updates the GUI to show details associated with the selected alert, as shown in the example user interface 1010 of FIG. 10B.)
As per Claim 4, Floren teaches: (Currently Amended) The system of claim 3, wherein:
the interactive map includes options that enable the one or more verticals included in the at least one channel to be selected; and (in at least [0167] FIG. 8A, an example user interface 800 includes an interactive graph section 802 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 804 (i.e. channel) and 806 (i.e. verticals). For ease of description, the information shown in the GUIs of the present disclosure is generally referred to as objects [0171] The user interface 800 may include an information panel 810 comprising various properties and other information associated with a selected object (e.g., selected object 804). Via the information panel 810, a user may also, for example, view time-based data associated with objects. [0193] Changes in the various displayed objects may be indicated, for example, by changes in color (similar to the indications provided in the graph-based GUIs described above). For example, if one or more alerts are or become associated with a displayed object, the object may change from, e.g., green to red. Thus, the user may slide the time slider, viewing movements of items, and may observe then certain object/locations in the map turn red. The user may then select the object, and may view the alerts associated with the object (e.g., which may indicate the reasons that the object changed color). The user may optionally view the alerts via a panel-based GUI, as further described below. Alerts/coloring of objects may be based on one or more predictive models of the system that model/predict, e.g., flows of goods, supplies, orders, delays, inventory, and the like. Thus, the system may predict, e.g., likely shortages in certain supplies, and/or the like (and may indicate the same in the map-based GUI). [0194] the map-based GUI may include and show time series data 911, which may include a sliding indicator as the user moves the time slider, similar to the time series data shown in the graph-based GUI described above. Thus, the map-based GUI may simultaneously show animated movements of items among objects/locations as the user interacts with the time-based slider, and movement of an indicator along the time series chart. [0195] to FIG. 9B, an example user interface portion 915 is shown which may comprise a portion of, or an update to, user interface 900. In various implementations, the map-based GUI may enable the user to select one or more objects, and then view a popup menu 917, select to view the objects in another application/GUI of the system. In the example shown in the example GUI below, the user may select to view the objects in the “explore objects” application and/or the “alert inbox” application.)
in response to receiving a selection of a vertical, the overlay is updated to display one or more demand indicators identifying or predicting the current demand in the selected vertical for the at least one channel. (in at least [0008] the user interfaces described herein are more efficient as compared to previous user interfaces in which data is not dynamically updated and compactly and efficiently presented to the user in response to interactive inputs. In some embodiments, the data is updated and presented to the user in real-time [0039] Visualizing the interaction of the data models is often useful in understanding the rea-world system. For example, properly visualizing simulations of the data models over time can be useful in understanding how the real-world system may perform, specifically at a particular point in time, over a period of time, or in real-time. [0171] The user interface 800 may include an information panel 810 comprising various properties and other information associated with a selected object (e.g., selected object 804). Via the information panel 810, a user may also, for example, view time-based data associated with objects. [0168] The example user interface 800 provides a view of a simulated technical system representing a real-world system. The view may include various technical systems, subsystems, objects, and the like. Although not shown in the user interface, the system can associate various data, including time-based data, and models with the systems, subsystems, and objects, such that simulations can be run. The user interface, based on simulations, can provide a view of how the real-world system has performed in the past, is performing, and can be expected to perform in the future. As an example, by simulating movements of materials and goods, the system may determine a current inventory of goods, a bottleneck in production, an expected lack of supply or inventory to meet demand [0175] Based on the time selected (e.g., via the time slider 816), objects in the graph section 802 may be colored and/or highlighted based on a status of those objects, where the status may be determined based on time-based data, models, and/or simulations. For example, a color of node 804 may be green at one point in time, indicating a sufficient supply of goods, but it may be red at another time indicating a lack of inventory. Such statuses may be predictive based on other objects and their associated models. For example, if a supplier is modeled as having a reduced supply in the future, the manufacturer may model a reduced output, and a supplier may model a shortage of inventory, assuming a modeled constant or increasing demand for goods. [0183] In response, in user interface portion 861, which can comprise an overlaid GUI portion, or a separate GUI portion, the user can fill in details of the subgraph just like a regular graph, can name the subgraph, and can then link the subgraph back to the parent graph. User interface portion 862 (of FIG. 8J) illustrates that, back in the parent graph, the user can link the created subgraph to the parent graph (e.g., the user can add a ‘Region’ to link to the subgraph on click). [0193] Changes in the various displayed objects may be indicated, for example, by changes in color (similar to the indications provided in the graph-based GUIs described above). For example, if one or more alerts are or become associated with a displayed object, the object may change from, e.g., green to red. Thus, the user may slide the time slider, viewing movements of items, and may observe then certain object/locations in the map turn red. The user may then select the object, and may view the alerts associated with the object (e.g., which may indicate the reasons that the object changed color). The user may optionally view the alerts via a panel-based GUI, as further described below. Alerts/coloring of objects may be based on one or more predictive models of the system that model/predict, e.g., flows of goods, supplies, orders, delays, inventory, and the like. Thus, the system may predict, e.g., likely shortages in certain supplies, and/or the like (and may indicate the same in the map-based GUI). [0194] the map-based GUI may include and show time series data 911, which may include a sliding indicator as the user moves the time slider, similar to the time series data shown in the graph-based GUI described above. Thus, the map-based GUI may simultaneously show animated movements of items among objects/locations as the user interacts with the time-based slider, and movement of an indicator along the time series chart. [0195] to FIG. 9B, an example user interface portion 915 is shown which may comprise a portion of, or an update to, user interface 900. In various implementations, the map-based GUI may enable the user to select one or more objects, and then view a popup menu 917, select to view the objects in another application/GUI of the system. In the example shown in the example GUI below, the user may select to view the objects in the “explore objects” application and/or the “alert inbox” application.)
As per Claim 5, Floren teaches: (Currently Amended) The system of claim 1, wherein:
the analytics dashboard includes, or communicates with, the machine learning network that is configured to generate the one or more real-time demand predictions pertaining to the at least one channel; (in at least [0135] the artificial intelligence training system 402 may execute and/or train a recurrent neural network (“RNN”). The RNN may be a type of artificial neural network where connections are formed between nodes (e.g., parameter input nodes and parameter output nodes), constructing a digraph (e.g., a graph that is made up of a set of vertices connected by edges) in which the edges of the digraph may have an associated direction, along a time series. The RNN may chain a plurality of black box and/or known models by recurrently linking related parameter input nodes and parameter output nodes. Accordingly, the RNN may improve the functionality of the system optimization server 104 itself as the RNN may allow the system optimization server 104 to optimize the chaining of the plurality of black box and/or known models, and thereby produce more accurate model relationships, classifications, rankings, and health evaluations. [0168] The user interface, based on simulations, can provide a view of how the real-world system has performed in the past, is performing, and can be expected to perform in the future. As an example, by simulating movements of materials and goods, the system may determine a current inventory of goods, a bottleneck in production, an expected lack of supply or inventory to meet demand,)
the machine learning network utilizes an anomaly detection model or time series forecasting model to generate the one or more real-time demand predictions for the at least one channel; and (in at least [0069] The time-series data store 121 may store and provide to the network 110, physical system data store 106 and/or to the other various data stores and executable code modules within the system optimization server 104, various data items related to objects, subsystems, and/or measured or generated over a period of a time and/or at a specific point in time. For example, such data items may include a shelf life of an object, a schedule of a subsystem, historical information of a model, and/or other like data items. [0080] the interactive user interface may be configured to allow a user to view or edit error detection data (e.g., information associated with the detection of a malfunction or miscalibration of measuring devices 114 and/or real-world subsystems 112 depicted in at least one of the displayed panels). For example, the interactive user interface can display a message indicating that a fault is detected when such an error is detected by the logical computations, sensors, and/or measuring devices 114 and/or real-world subsystems 112 depicted in at least one of the displayed panels. [0082] The model simulator 118 may obtain, generate, and/or simulate one or more models based on the one or more real-world systems 102 and/or the error detection data stored in the real-world system data store 106. The one or more models may be stored in the simulated system data store 122. The error detection data from the real-world system data store 106 may include when the real-world subsystem 112, logical computations, and/or physical sensor error may have occurred over a period of time (e.g., historical sensor error data, live sensor data, real-time sensor data, etc.) and may store this time-series data in the time-series data store 121. The model simulator 118 may transmit the various models and/or data from the time-series data store 121 and/or the simulated system data store 122 to the object simulator 120 to generate objects (e.g., virtual items or products, virtual sensors, virtual measuring devices, etc.) and/or to the subsystem simulator 119 to generate subsystems (e.g., virtual subsystems that may further include the set of virtual logical computations, virtual sensors, virtual measuring devices, etc.). If no real-world subsystem, logical computations, and/or physical sensor error has occurred, the one or more model relationships, subsystems and/or objects may closely mirror the actual real-world subsystem, logical computations, and/or physical sensors. The model simulator 118 may compare actual real-world subsystem 112, logical computations, and/or physical sensor data with simulated data of the one or more simulated models (e.g., data from the generated virtual logical computations, virtual sensors, virtual measuring devices, virtual subsystems, etc.). If the difference between the two datasets is greater than a threshold value, then the model simulator 118 may determine that a virtual subsystem and/or virtual sensor error has occurred. The system optimization server 104 (e.g., the model simulator 118) may use the difference between the two datasets to determine the health of a subsystem (e.g., virtual subsystem), object (e.g., virtual item or product, virtual sensor, etc.), and/or object property (e.g., measurement of the virtual sensor), and display the health on at least one of the displayed panels. The system optimization server 104 (e.g., the model simulator 118) may determine that a smaller difference may result in a healthier subsystem, object, and/or object property, and therefore indicate a healthier model given that these components make up the model. [0135] The RNN may be a type of artificial neural network where connections are formed between nodes (e.g., parameter input nodes and parameter output nodes), constructing a digraph (e.g., a graph that is made up of a set of vertices connected by edges) in which the edges of the digraph may have an associated direction, along a time series. [0083] interactive user interface may be configured to allow a user to view or edit, in at least one of the displayed panels, unusual (e.g., abnormal) or periodic events that have occurred and/or that may occur in the future during operation of the logical computations, sensors, and/or measuring devices 114 and/or real-world subsystems 112. Such events may also apply to the simulated virtual objects (e.g., virtual items or products, virtual measuring devices, and/or virtual subsystems). For example, in the case of a supply chain, the object properties may include a time that an item or product was shipped from one location to another location, a time that an item or product arrived at a particular location, etc. [0233] a user selection of an alert in the listing of alerts 1304, the system determines and shows information associated with the selected alert in the panel 1306. The panel 1306 can include various information, examples of which are shown in the example user interface 1300. For example, the panel 1306 may indicate an alert type, a component/object associated with the alert, a number of days covered by the alert, etc. In the example of a supply chain-related alert, the alert may indicate, for example, inventories and demand over time (e.g., as indicated in chart 1308), and/or breakdowns of orders and demand (e.g., as indicated in table 1310). As discussed herein, the simulations of the system can be predictive, thus an alert may be based on an expected demand not being met by orders placed and expected shipment times, for example. In other words, the shortage may be predicted by the system based on a current model of shipments, inventory, demand)
the one or more real-time demand predictions generated by the anomaly detection model or the time series forecasting model of the machine learning network are utilized to generate the analytics display. (in at least [0069] The time-series data store 121 may store and provide to the network 110, physical system data store 106 and/or to the other various data stores and executable code modules within the system optimization server 104, various data items related to objects, subsystems, and/or measured or generated over a period of a time and/or at a specific point in time. For example, such data items may include a shelf life of an object, a schedule of a subsystem, historical information of a model, and/or other like data items. [0083] interactive user interface may be configured to allow a user to view or edit, in at least one of the displayed panels, unusual (e.g., abnormal) or periodic events that have occurred and/or that may occur in the future during operation of the logical computations, sensors, and/or measuring devices 114 and/or real-world subsystems 112. Such events may also apply to the simulated virtual objects (e.g., virtual items or products, virtual measuring devices, and/or virtual subsystems). For example, in the case of a supply chain, the object properties may include a time that an item or product was shipped from one location to another location, a time that an item or product arrived at a particular location, etc. [0233] In response to a user selection of an alert in the listing of alerts 1304, the system determines and shows information associated with the selected alert in the panel 1306. The panel 1306 can include various information, examples of which are shown in the example user interface 1300. For example, the panel 1306 may indicate an alert type, a component/object associated with the alert, a number of days covered by the alert, etc. In the example of a supply chain-related alert, the alert may indicate, for example, inventories and demand over time (e.g., as indicated in chart 1308), and/or breakdowns of orders and demand (e.g., as indicated in table 1310). As discussed herein, the simulations of the system can be predictive, thus an alert may be based on an expected demand not being met by orders placed and expected shipment times, for example. In other words, the shortage may be predicted by the system based on a current model of shipments, inventory, demand,)
As per Claim 6, Floren teaches: (Original) The system of claim 1,
wherein the analytics display generated by the analytics dashboard visualizes population density metrics for the at least one channel designated by the request. (in at least [0041] GUIs may further comprise at least one of information, trend, simulation, mapping, schematic, time, equipment, and toolbar panels. Various panels may display the objects, object properties, inputs, and outputs of the simulated models. [0308] the one or more object properties may be numerical, physical, geometrical, inferred, real, simulated, or virtual. Further the object properties may comprise of logical computations related to order volume, sales amounts, sales quantity during a time period (e.g., a day, a week, a year, etc.), population density, patient volume, or other object properties relevant to the pertaining model. )
As per Claim 7, Floren teaches: (Original) The system of claim 1,
wherein the analytics display generated by the analytics dashboard visualizes movement tracking metrics for the at least one channel designated by the request. (in at least [0062] the real-world subsystems 112 may be a physical or technical subsystem, such as a gas pumping subsystem, a gas separation subsystem, and a gas compression subsystem that make up a gas pipeline physical system. As another example, the real-world subsystems 112 may be a movement detection subsystem [0168] The user interface, based on simulations, can provide a view of how the real-world system has performed in the past, is performing, and can be expected to perform in the future. As an example, by simulating movements of materials and goods, the system may determine a current inventory of goods, a bottleneck in production, an expected lack of supply or inventory to meet demand, and/or the like.)
As per Claim 8, Floren teaches: (Original) The system of claim 1,
wherein the analytics display generated by the analytics dashboard visualizes vertical density metrics for the at least one channel designated by the request. (in at least [0171] The user interface 800 may include an information panel 810 comprising various properties and other information associated with a selected object (e.g., selected object 804). Via the information panel 810, a user may also, for example, view time-based data associated with objects. [0204] FIG. 10A, an example user interface 1000 includes both an interactive map-based section 1002, and an interactive alert-based section 1004. As noted above, various different GUIs of the present system can have similar functionality, and can be combined in various ways. For example, an alert-based section could also similarly be combined with a graph-based section. [0205] The alert-based section 1004 of the user interface 1000 may include a listing of alerts associated with the objects shown in the map-based section 1002, and/or any selected objects. The list may be filterable, and as shown may include various details regarding the listed alerts. In the example user interface 1000, one alert is shown, and the associated object on the map is shown in red. The user may select the alert, in response to which the system updates the GUI to show details associated with the selected alert, as shown in the example user interface 1010 of FIG. 10B. [0259] Models may be mapped to the ontology to create a system-wide simulation engine that powers what-if analyses. Users at every level of the organization, from strategic to operational, can understand the potential outcomes and side effects of a decision as they are making it. For example, in the supply chain example, production and pricing models leverage data from raw materials and plant capacity, and determines production volume and customer demand estimates based on price changes. This type of model is often used by a supply chain manager to decide how much of particular refined products to make from raw materials. This model may be chained to a seasonal demand model to dynamically optimize the product catalogue for increased revenue. [0308] the one or more object properties may be numerical, physical, geometrical, inferred, real, simulated, or virtual. Further the object properties may comprise of logical computations related to order volume, sales amounts, sales quantity during a time period (e.g., a day, a week, a year, etc.), population density, patient volume, or other object properties relevant to the pertaining model.)
As per Claim 10, Floren teaches: (Currently Amended) The system of claim 1, wherein:
an application programming interface (API) enables the channel analysis data generated by the analytics dashboard to be accessed by one or more client systems; and in at least [0313] Various third-parties operate electronic services systems which in some instances, these systems may allow access through APIs. Typically, each API requires its own set of information about a data object, such as name, age, and height for a data object representing a person. Advantageously, embodiments of the present disclosure may collect information related to a data object, form API requests in the format and containing the information required by the API of each third-party (“third-party format”), collect responses from the API of each third-party, translate the different results back into a uniform format that facilitates comparison, storage and/or processing (“common format”), and show the results to the user. For example, different third-parties may require different types of information, and in different format; for example, third-party A may require a data object's name and age properties, whereas third-party B may require an a data object's age and height properties but not name. )
the channel analysis data accessed via the API is utilized by the one or more client systems to execute one or more demand adjustment functions. (in at least [0106] The one or more applications 174 can include applications that enable users to view datasets, interact with datasets, filter data sets, and/or configure dataset transformation processes or builds. The one or more services 175 can include services that can trigger the data transformation builds and API services for receiving and transmitting data. The one or more initial datasets 176 can be automatically retrieved from external sources and/or can be manually imported by a user. The one or more initial datasets 176 can be in many different formats such as a tabular data format (SQL, delimited, or a spreadsheet data format), a data log format (such as network logs), or time series data (such as sensor data). [0313] collect information related to a data object, form API requests in the format and containing the information required by the API of each third-party (“third-party format”), collect responses from the API of each third-party, translate the different results back into a uniform format that facilitates comparison, storage and/or processing (“common format”), and show the results to the user. For example, different third-parties may require different types of information, and in different format; for example, third-party A may require a data object's name and age properties, whereas third-party B may require an a data object's age and height properties but not name.)
As per Claim 21, Floren teaches: (New) The system of claim 1,
wherein the one or more demand predictions are continuously updated by the analytics dashboard in response to detecting changes in the real-time demand conditions based on the real-time channel events received by the demand analytics platform over time. (in at least [0047] This means that operational users can easily explore what-if scenarios, simulate effects across the enterprise, and run optimizations to find global optimal leveraging models in the platform. It also means that analytical users can receive continuous feedback on the accuracy of their models based on real-world operational usage which leads to significantly accelerated learning and improvement. [0077] The interactive user interface rendered and/or displayed as a result of the user interface code generated by the user interface generator 117 may include a viewing mode and/or an editing mode. In the viewing mode, the user may view the displayed information, schematic, trend, simulation, time, equipment, toolbar, and/or mapping panels. In the editing mode, the user may edit the displayed information, schematic, trend, simulation, time, equipment, toolbar, and/or mapping panels. These panels and modes lay the framework for how a user can properly visualize and analyze the models at a particular point in time or over a period of time. [0078] the trend panel in the viewing mode may display the trends for one or more technical object properties (e.g., temperature, pressure, flow rate, order volume, sales amounts, sales quantity during a time period (e.g., a day, a week, a year, etc.), patient volume, etc.) of a technical object (e.g., a pump, a product or item, a factory, a customer, a hospital, etc.) for a given period of time (e.g., Monday to Wednesday). In the editing mode, the trend panel may allow the user to edit one or more object properties of an object at a specific time instant (e.g., Monday at noon) or for a period of time (e.g., Monday to Wednesday). The user can further minimize or maximize any panel to optimally achieve the user's display preferences for the system. The user can also markup the system using annotations, change graph line widths to represent different object properties, change the colors or highlighting of various objects or object properties to represent the state (e.g., open, closed, running above specification, running below specification, etc.) of the corresponding object [0173] The user interface 800 may further include a time-visualization panel 814, which allows a user to view the trends, simulations, mappings, and/or the like, and which may depict the results of the simulation of one or more models by the model simulator 118, the optimization component 116, and/or the like. For example, the time-visualization panel 814 may display an interactive line graph, simulation table, mapping chart, and/or the like that corresponds to the model specific technical subsystems, technical objects, technical object properties, error detection data, and/or events of the modeled technical system, as illustrated in the example user interface 800. [0221] the models may be chained by linking predicted related parameter input and output nodes and may be continuously re-chained by re-linking related parameter input and output nodes based on the predicted parameter node relationships established by each execution of the artificial intelligence system. Additional details regarding the operations performed in blocks 1126, 1128 and 1130 are further detailed in the present disclosure, e.g., in reference to FIGS. 5-7)
As per Claim 22, Floren teaches: (New) The system of claim 1,
wherein the machine-learning network is configured to generate both a real-time demand prediction and a future demand prediction based on channel events obtained in a historical time window or a real-time time window. (in at least [0008] the user interfaces described herein are more efficient as compared to previous user interfaces in which data is not dynamically updated and compactly and efficiently presented to the user in response to interactive inputs. In some embodiments, the data is updated and presented to the user in real-time [0039] Visualizing the interaction of the data models is often useful in understanding the rea-world system. For example, properly visualizing simulations of the data models over time can be useful in understanding how the real-world system may perform, specifically at a particular point in time, over a period of time, or in real-time. [0137] The artificial intelligence training system 402 may use the error detection data as training examples. The artificial intelligence training system 402 may establish a set of learned relationship data that mathematically describes the physical relationships between the inputs and outputs of one or more logical computations, physical sensors, and/or measuring devices 114 and/or one or more technical real-world subsystems 112 that comprise the one or more technical real-world systems 102. The learned relationship data may be stored in the neural network data store 406. The model simulator 118 may transmit the various models and/or data from the time-series data store 121, neural network data store 406, and/or the simulated system data store 122 to the object simulator 120 to generate objects, and/or to the subsystem simulator 119 to generate subsystems [0143] the model simulator 118 may simulate the plurality of models to obtain parameter output and input nodes based on the model specific generated subsystems and objects. For example, a parameter output node of the first water treatment model may be an output water level of the virtual water level sensor object, and a parameter input node of the second water treatment model may be an input water composition of the virtual pH level sensor object. Furthermore, the parameter output and input nodes may include error detection data, learned relationship data, etc. (e.g., the output water level of the virtual water level sensor object may include historical data parameters, max output water level parameters, minimum water level parameters, connection parameters etc. of the water level sensor object). At (14), the model simulator 118A simulates the first model to obtain parameter output and input nodes. At (15), the model simulator 118B simulates the second model to obtain parameter output and input nodes. The model simulator 118A can then transmit the first model parameter output and input nodes to the artificial intelligence training system 402 at (16), and the model simulator 118B can transmit the second model parameter output and input nodes to the artificial intelligence training system 402 at (17). [0173] The user interface 800 may further include a time-visualization panel 814, which allows a user to view the trends, simulations, mappings, and/or the like, and which may depict the results of the simulation of one or more models by the model simulator 118, the optimization component 116, and/or the like. For example, the time-visualization panel 814 may display an interactive line graph, simulation table, mapping chart, and/or the like that corresponds to the model specific technical subsystems, technical objects, technical object properties, error detection data, and/or events of the modeled technical system, as illustrated in the example user interface 800. In some embodiments, the time-visualization panel 814 may be a singular time-series visualization panel that display the results of the simulation of one or more models by the model simulator 118, the optimization component 116, and/or the like. The user may add additional time-series to, or remove time-series from, the visualization panel 814. [0174] The user interface 800 may further include a time slider 816 that may include a time axis and which may be used to select a particular point in time, or scrub over a time span (e.g., seconds, minutes, hours, days, weeks, years, etc.). In various implementations the time slider 816 may include a user input element for selecting a specific point in time via inputs other than a slider. The time span represented by the time slider 816 may include both past and future times. User interactions with the time slider 816 may result in updates to information displayed in various other portions of the user interface 800. For example, time-based data and/or outputs of models associated with the various objects may be used to determine status of the various objects, which statuses may be depicted in the graph section 802 and/or information panel 810. Similarly, the time-visualization panel 814 may be a line graph composed of time-series data (e.g., historical measuring device data, live measuring device data, derived values, simulation results, etc.) stored in the time-series data store 121. Accordingly, as the user moves or slides the time slider 816 bi-directionally, the time indicator in the visualization panel 814 may move similarly to indicate a relevant portion or point in the time-series data shown in the visualization panel 814. In various implementations, the user can use the slider to scrub to various points in time, and the graph is updated in real-time as the user scrubs. The changes over time can be shown in an animated way. Optionally the user can press a play button to animatedly show changes over time. Similarly, an indicator in the time-series data chart indicates the currently selected date/time and associated time-series data values. [0175] Based on the time selected (e.g., via the time slider 816), objects in the graph section 802 may be colored and/or highlighted based on a status of those objects, where the status may be determined based on time-based data, models, and/or simulations. For example, a color of node 804 may be green at one point in time, indicating a sufficient supply of goods, but it may be red at another time indicating a lack of inventory. Such statuses may be predictive based on other objects and their associated models. For example, if a supplier is modeled as having a reduced supply in the future, the manufacturer may model a reduced output, and a supplier may model a shortage of inventory, assuming a modeled constant or increasing demand for goods. In some embodiments the colors that represent an object and/or subsystem may change based on the time-series data specific times within the time-series. Thus, the styling of items shown in the user interface 800 may depend on the time-series data, models, simulations, and/or the ontology upon which the modeled system is based.)
As per Claim 23, Floren teaches: (New) The system of claim 1,
wherein the demand analytics platform stores one or more threshold values corresponding to the one or more real-time demand predictions, and the one or more threshold values are utilized to trigger an automatic transmission of an alert or notification in response to determining that the one or more threshold values have been satisfied or exceeded. (in at least [0184] FIG. 8K, an example user interface portion 865 is shown which may comprise a portion of, or an update to, user interface 800. The user interface portion 865 illustrates system functionality related to alerting, and coloring or highlighting nodes based on status and/or other data related to the nodes and associated objects (e.g., based on time-based data, models, and/or simulations). For example, as mentioned above, node coloring or highlighting may be green at one point in time, indicating a sufficient supply of goods, but it may be red at another time indicating a lack of inventory. Such statuses may be predictive based on other objects and their associated models. Via a node configuration panel 866, the user can configure nodes in the graph to show up in a certain color depending on their status. The configuration can be based on, for example, a value of a property, or a comparison of a property to another property or a threshold. In various implementations, graph nodes may be colored based on any property of the objects, and coloring may be based on a gradient. [0185] to FIG. 8L, an example user interface portion 870 is shown which may comprise a portion of, or an update to, user interface 800. The user interface portion 870 illustrates additional system functionality related to alerting, in which alerts 871 associated with a selected object are displayed in an event panel of the GUI. In various implementations, the GUI can include a panel that displays any alerts associated with any objects in the graph. In either case these alerts can then be opened in other applications for more details or workflows, as described herein. Alerts may be generated when models indicate an undesirable status, such as an insufficient inventory)
As per Claim 24, Floren teaches: (New). The system of claim 1,
wherein the interactive visualization includes a graphical overlay that incorporates multiple visual cues, including a population density indicator, a vertical density indicator, at least one demand prediction indicator, and a movement tracking indicator. (in at least [0041] graphical user interfaces (“GUIs”) may be generated that can include, for example, graph-based GUIs, map-based GUIs, and panel-based GUIs, among others. The GUIs may include one or more panels to display data including technical data objects (also referred to herein as “objects”) (e.g., pumps, compressors, valves, machinery, welding stations, vats, containers, products or items, organizations, countries, counties, factories, customers, hospitals, etc.), technical object properties (e.g., flow rate, suction temperature, volume, capacity, order volume, sales amounts, sales quantity during a time period (e.g., a day, a week, a year, etc.), population density, patient volume, etc.), [0167] the systems, subsystems, and objects may represent various things, such as people, locations, facilities, and the like. Relationships among the various systems, subsystems, and objects are represented by edges, such as edge 808, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items. In the example user interface 800, a supply chain is represented, including node representing parts and goods suppliers, manufacturing plants, distributors, consumers (e.g., hospitals), and the like. The graph section 802 is interactive, and a user may adjust the view of the objects via zooming in and out, or moving nodes around. [0168] The user interface, based on simulations, can provide a view of how the real-world system has performed in the past, is performing, and can be expected to perform in the future. As an example, by simulating movements of materials and goods, the system may determine a current inventory of goods, a bottleneck in production, an expected lack of supply or inventory to meet demand, and/or the like [0171] The user interface 800 may include an information panel 810 comprising various properties and other information associated with a selected object (e.g., selected object 804). Via the information panel 810, a user may also, for example, view time-based data associated with objects. [0259] in the supply chain example, production and pricing models leverage data from raw materials and plant capacity, and determines production volume (i.e. vertical density) and customer demand estimates based on price changes. This type of model is often used by a supply chain manager to decide how much of particular refined products to make from raw materials. This model may be chained to a seasonal demand model to dynamically optimize the product catalogue for increased revenue. [0192] Dots or nodules may be represented on the edges to indicate movement events, or quantities of items moved from one location to another. The nodules can be time-based, meaning that they can accurately represent the points in time that items move from one location to another, based on the point in time selected by the user via time slider 909. Thus, the nodules may be determined based on time-based data associated with the related objects. As the user adjusts the date/time, the time-based data associated with the objects and/or links, and movement of data and/or items among the objects, can be displayed. Optionally the movements can be displayed in an animated fashion as the user slides the slider across the shown time span. Similar animated dots or nodules may be displayed along edges of the graph-based GUIs of the present disclosure to indicate movements of data/goods/etc. from one object to another. [0308] the one or more object properties may be numerical, physical, geometrical, inferred, real, simulated, or virtual. Further the object properties may comprise of logical computations related to order volume, sales amounts, sales quantity during a time period (e.g., a day, a week, a year, etc.), population density, patient volume (i.e. vertical density), or other object properties relevant to the pertaining model. Alternatively or in addition, the technical object properties may comprise of measurements related to temperature, pressure, flow rate, capacity, time, length, mass, electric current, amount of substance, luminous intensity, plane angle, solid angle, frequency, energy, power, charge, voltage, capacitance, resistance, conductance, flux, inductance, radioactivity, dose, catalytic activity, area, volume, speed, acceleration, density, or other object properties relevant to the pertaining model.)
As per Claim 25, Floren teaches: (New) The system of claim 1,
wherein the one or more real-time demand predictions are transmitted via an application programming interface to one or more client systems for rendering or operational execution. (in at least [0106] The system can transform data and record the data transformations. The one or more applications 174 can include applications that enable users to view datasets, interact with datasets, filter data sets, and/or configure dataset transformation processes or builds. The one or more services 175 can include services that can trigger the data transformation builds and API services for receiving and transmitting data. [0313] Various third-parties operate electronic services systems which in some instances, these systems may allow access through APIs. Typically, each API requires its own set of information about a data object, such as name, age, and height for a data object representing a person. Advantageously, embodiments of the present disclosure may collect information related to a data object, form API requests in the format and containing the information required by the API of each third-party (“third-party format”), collect responses from the API of each third-party, translate the different results back into a uniform format that facilitates comparison, storage and/or processing (“common format”), and show the results to the user. For example, different third-parties may require different types of information, and in different format; for example, third-party A may require a data object's name and age properties, whereas third-party B may require an a data object's age and height properties but not name)
As per Claim 26, Floren teaches: (New) The system of claim 1,
wherein a user interface presented to the end-user permits the end-user to define a forecast window and an operational vertical, and the analytics dashboard renders a corresponding graphical overlay associated with the interactive visualization based on the forecast window and the operational vertical. (in at least [0173] The user interface 800 may further include a time-visualization panel 814, which allows a user to view the trends, simulations, mappings, and/or the like, and which may depict the results of the simulation of one or more models by the model simulator 118, the optimization component 116, and/or the like. For example, the time-visualization panel 814 may display an interactive line graph, simulation table, mapping chart, and/or the like that corresponds to the model specific technical subsystems, technical objects, technical object properties, error detection data, and/or events of the modeled technical system, as illustrated in the example user interface 800. In some embodiments, the time-visualization panel 814 may be a singular time-series visualization panel that display the results of the simulation of one or more models by the model simulator 118, the optimization component 116, and/or the like. The user may add additional time-series to, or remove time-series from, the visualization panel 814. [0174] The user interface 800 may further include a time slider 816 that may include a time axis and which may be used to select a particular point in time, or scrub over a time span (e.g., seconds, minutes, hours, days, weeks, years, etc.). In various implementations the time slider 816 may include a user input element for selecting a specific point in time via inputs other than a slider. The time span represented by the time slider 816 may include both past and future times. User interactions with the time slider 816 may result in updates to information displayed in various other portions of the user interface 800. For example, time-based data and/or outputs of models associated with the various objects may be used to determine status of the various objects, which statuses may be depicted in the graph section 802 and/or information panel 810. Similarly, the time-visualization panel 814 may be a line graph composed of time-series data (e.g., historical measuring device data, live measuring device data, derived values, simulation results, etc.) stored in the time-series data store 121. Accordingly, as the user moves or slides the time slider 816 bi-directionally, the time indicator in the visualization panel 814 may move similarly to indicate a relevant portion or point in the time-series data shown in the visualization panel 814. In various implementations, the user can use the slider to scrub to various points in time, and the graph is updated in real-time as the user scrubs. The changes over time can be shown in an animated way. Optionally the user can press a play button to animatedly show changes over time. Similarly, an indicator in the time-series data chart indicates the currently selected date/time and associated time-series data values. [0175] Based on the time selected (e.g., via the time slider 816), objects in the graph section 802 may be colored and/or highlighted based on a status of those objects, where the status may be determined based on time-based data, models, and/or simulations. For example, a color of node 804 may be green at one point in time, indicating a sufficient supply of goods, but it may be red at another time indicating a lack of inventory. Such statuses may be predictive based on other objects and their associated models. For example, if a supplier is modeled as having a reduced supply in the future, the manufacturer may model a reduced output, and a supplier may model a shortage of inventory, assuming a modeled constant or increasing demand for goods. In some embodiments the colors that represent an object and/or subsystem may change based on the time-series data specific times within the time-series. Thus, the styling of items shown in the user interface 800 may depend on the time-series data, models, simulations, and/or the ontology upon which the modeled system is based. [0193] Alerts/coloring of objects may be based on one or more predictive models of the system that model/predict, e.g., flows of goods, supplies, orders, delays, inventory, and the like. Thus, the system may predict, e.g., likely shortages in certain supplies (i.e. operational vertical), and/or the like (and may indicate the same in the map-based GUI).)
As per Claim 27, Floren teaches: (New) The system of claim 1,
wherein a graphical overlay associated with the interactive visualization displays a predictive summary indicator for each geographic region, the predictive summary indicator for each geographic region being generated, at least in part, on an aggregation of predictive outputs generated by the machine-learning for sub-channels corresponding to a corresponding geographic region. (in at least [0011] the system may present aggregate quantities, such as totals, counts, and averages. The system may also utilize the information to interpolate or extrapolate (e.g. forecast) future developments. [0134] The artificial intelligence training system 402 may execute one or more artificial intelligence algorithms to perform analysis on data items, such as parameter output nodes, parameter input nodes, and models. In some embodiments, the artificial intelligence training system 402 may execute artificial intelligence algorithms that may use machine learning such that the artificial intelligence training system 402 may iteratively learn from the data items (e.g., parameter output nodes, parameter input nodes, black box models (e.g., models in which the algorithm(s) function(s), propert(ies), value(s), etc. that are used to produce an output given an input may be unknown or inaccessible) and/or known models (e.g., models in which the algorithm(s) function(s), propert(ies), value(s), etc. that are used to produce an output given an input may be known, obtained, derived, or are otherwise accessible)) without being explicitly programmed. [0137] The artificial intelligence training system 402 may use the error detection data as training examples. The artificial intelligence training system 402 may establish a set of learned relationship data that mathematically describes the physical relationships between the inputs and outputs of one or more logical computations, physical sensors, and/or measuring devices 114 and/or one or more technical real-world subsystems 112 that comprise the one or more technical real-world systems 102. The learned relationship data may be stored in the neural network data store 406. The model simulator 118 may transmit the various models and/or data from the time-series data store 121, neural network data store 406, and/or the simulated system data store 122 to the object simulator 120 to generate objects, and/or to the subsystem simulator 119 to generate subsystems [0167] FIG. 8A, an example user interface 800 includes an interactive graph section 802 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 804 and 806. For ease of description, the information shown in the GUIs of the present disclosure is generally referred to as objects, but as noted various systems and subsystems may similarly be represented. As described throughout the present disclosure, the systems, subsystems, and objects may represent various things, such as people, locations, facilities, and the like. Relationships among the various systems, subsystems, and objects are represented by edges, such as edge 808, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items. In the example user interface 800, a supply chain is represented, including node representing parts and goods suppliers, manufacturing plants, distributors, consumers (e.g., hospitals), and the like. The graph section 802 is interactive, and a user may adjust the view of the objects via zooming in and out, or moving nodes around. The system may also automatically adjust the positioning of the nodes to provide an organized view and/or alignment of related objects. Additionally, the system allows the user to interact with (e.g., view, edit, move, add, delete, etc.) model specific subsystems, objects, object properties, error detection data, and/or events of the system. For example, the user may add additional related objects/nodes to the graph section 802 in various ways, including by searching the system for objects related to already displayed objects/nodes. FIG. 8C illustrates a toolbar by which the user may select to add objects to the graph via button 818. [0190] FIGS. 9A-9H illustrate various example implementations, features, and advantages associated with map-based GUIs of the system, according to one or more embodiments. The map -based GUIs of the system can allow a user to, e.g., generate visualizations of properties, links, and/or time-based data associated with objects; interact with properties associated with one or more objects; interact with a histogram of objects; interact with time-based data associated with objects; and/or the like. In various implementations, the map-based GUIs may be 2-dimensional or 3-dimensional, and interactive such that the user may move around the map, zoom in and out, change the angle of view, and the like. As mentioned above, the functionality of the map-based GUIs can be similar to the graph-based GUI. However, in addition the map-based GUIs can include a geographical map, and indicate geographical locations of objects representing objects on the map as nodes or indicators, such as icons. [0191] FIG. 9A, an example user interface 900 includes an interactive map section 902 in which various systems, subsystems, and data objects can be represented by nodes or indicators, such as icons 904 and 905. As described above, the nodes may be colored or highlighted based on related statuses, and/or the like. Relationships among the objects are represented by edges, such as edge 907, which may optionally be directional (or bi-directional) to indicate, e.g., flows of information or items. [0204] FIGS. 10A-10B illustrate various example implementations, features, and advantages associated with alert-based GUIs of the system, according to one or more embodiments. Referring to FIG. 10A, an example user interface 1000 includes both an interactive map-based section 1002, and an interactive alert-based section 1004. As noted above, various different GUIs of the present system can have similar functionality, and can be combined in various ways. For example, an alert-based section could also similarly be combined with a graph-based section. [0209] FIGS. 11A-11B provide additional description of example systems and methods for running simulations and/or chaining models together, such that the models may be used in simulating values of parameters at various nodes of a graph, such as a supply chain graph. [0221] the models may be chained by linking predicted related parameter input and output nodes and may be continuously re-chained by re-linking related parameter input and output nodes based on the predicted parameter node relationships established by each execution of the artificial intelligence system. Additional details regarding the operations performed in blocks 1126, 1128 and 1130 are further detailed in the present disclosure, e.g., in reference to FIGS. 5-7. [0233] a user selection of an alert in the listing of alerts 1304, the system determines and shows information associated with the selected alert in the panel 1306. The panel 1306 can include various information, examples of which are shown in the example user interface 1300. For example, the panel 1306 may indicate an alert type, a component/object associated with the alert, a number of days covered by the alert, etc. In the example of a supply chain-related alert, the alert may indicate, for example, inventories and demand over time (e.g., as indicated in chart 1308), and/or breakdowns of orders and demand (e.g., as indicated in table 1310). As discussed herein, the simulations of the system can be predictive, thus an alert may be based on an expected demand not being met by orders placed and expected shipment times, for example. In other words, the shortage may be predicted by the system based on a current model of shipments, inventory, demand, and the like.)
As per Claim 11 for a method (see at least Floren [0038]), respectively, substantially recite the subject matter of Claim 1 and are rejected based on the same reasoning and rationale.
As per Claim 20 for a computer program product (see at least Floren [0084]), respectively, substantially recite the subject matter of Claim 1 and are rejected based on the same reasoning and rationale.
Claims 9 is/are rejected under 35 U.S.C. 103 as being unpatentable by US Patent Publication to US20220075515A1 to Floren et al., (hereinafter referred to as “Floren”) in view of US Patent Publication to US20170098181A1 to Herman et al., (hereinafter referred to as “Herman”) in view of US Patent Publication to US20180316571A1 to Andrade et al., (hereinafter referred to as “Andrade”)
As per Claim 9, Floren teaches: (Currently Amended) The system of claim 5,
wherein the anomaly detection model includes a classification model that is pre-trained using a supervised training procedure to generate the one or more real-time demand predictions and the classification model generates the one or more real-time demand predictions using one or more of the following: (in at least [0073] models may be based on and/or trained based on historical data (e.g., historical cost data, historical quality data (e.g., number of warranty claims for materials from various suppliers), historical sustainability data, and the like). [0174] The user interface 800 may further include a time slider 816 that may include a time axis and which may be used to select a particular point in time, or scrub over a time span (e.g., seconds, minutes, hours, days, weeks, years, etc.). In various implementations the time slider 816 may include a user input element for selecting a specific point in time via inputs other than a slider. The time span represented by the time slider 816 may include both past and future times. User interactions with the time slider 816 may result in updates to information displayed in various other portions of the user interface 800. For example, time-based data and/or outputs of models associated with the various objects may be used to determine status of the various objects, which statuses may be depicted in the graph section 802 and/or information panel 810. Similarly, the time-visualization panel 814 may be a line graph composed of time-series data (e.g., historical measuring device data, live measuring device data, derived values, simulation results, etc.) stored in the time-series data store 121. Accordingly, as the user moves or slides the time slider 816 bi-directionally, the time indicator in the visualization panel 814 may move similarly to indicate a relevant portion or point in the time-series data shown in the visualization panel 814. In various implementations, the user can use the slider to scrub to various points in time, and the graph is updated in real-time as the user scrubs. The changes over time can be shown in an animated way. Optionally the user can press a play button to animatedly show changes over time. Similarly, an indicator in the time-series data chart indicates the currently selected date/time and associated time-series data values. [0175] Based on the time selected (e.g., via the time slider 816), objects in the graph section 802 may be colored and/or highlighted based on a status of those objects, where the status may be determined based on time-based data, models, and/or simulations. For example, a color of node 804 may be green at one point in time, indicating a sufficient supply of goods, but it may be red at another time indicating a lack of inventory. Such statuses may be predictive based on other objects and their associated models. For example, if a supplier is modeled as having a reduced supply in the future, the manufacturer may model a reduced output, and a supplier may model a shortage of inventory, assuming a modeled constant or increasing demand for goods. In some embodiments the colors that represent an object and/or subsystem may change based on the time-series data specific times within the time-series. Thus, the styling of items shown in the user interface 800 may depend on the time-series data, models, simulations, and/or the ontology upon which the modeled system is based. [0219] At block 1126, an artificial intelligence system (e.g., artificial intelligence training system 402 illustrated in FIG. 4) may be trained using the parameter input and output nodes as training examples. For example, the artificial intelligence system can be an RNN. [0221] the models may be chained by linking predicted related parameter input and output nodes and may be continuously re-chained by re-linking related parameter input and output nodes based on the predicted parameter node relationships established by each execution of the artificial intelligence system. Additional details regarding the operations performed in blocks 1126, 1128 and 1130 are further detailed in the present disclosure, e.g., in reference to FIGS. 5-7. [0233] The panel 1306 can include various information, examples of which are shown in the example user interface 1300. For example, the panel 1306 may indicate an alert type, a component/object associated with the alert, a number of days covered by the alert, etc. In the example of a supply chain-related alert, the alert may indicate, for example, inventories and demand over time (e.g., as indicated in chart 1308), and/or breakdowns of orders and demand (e.g., as indicated in table 1310). As discussed herein, the simulations of the system can be predictive, thus an alert may be based on an expected demand not being met by orders placed and expected shipment times, for example. In other words, the shortage may be predicted by the system based on a current model of shipments, inventory, demand)
…
Although implied, Floren in view of Herman does not expressly disclose the following limitations, which however, are taught by Andrade,
a Naive Bayes classification model; a OCSVM (One-class support vector machine) classification model; a SVDD (Support Vector Data Description) classification model; or a one-class K-means classification model. (in at least [0097] The age and gender modeling algorithm can use predictive modeling process to learn complex patterns in mobile device usage. For classification modeling of gender, the algorithm may implement a support vector machine (SVM) learning model. The algorithm may implement a decision tree to classify gender and age bands. [0098] a number of machine learning models can be used to determine age and gender of a group of mobile users. Examples include decision tress, random forest, gradient boosting machine, and extreme gradient boosting (XGBoost). The Gradient Boosting Machine (GBM) model was used as (y˜f1x+f2x+ . . . +fnx=i=1nfi(x)). GBM allows efficient building of an ensemble of decision trees that can boost model performance. A combination of feature engineering with features were used including, but not limited to bytes in, bytes out, average session time, noise removal, association rules and feature selection using to identify variables for prediction. [0196] Another algorithm that can be used to determine and generate consumer insight information may include a Bayesian location planning algorithm Such an algorithm can be implemented by the location planning engine 128. [0197] The algorithm may include implementing steps to refactor a location planning insight. The implementation described below may provide reporting in the form of a heat map and/or a table. The heat map may be location based and derived from actual map locations in addition to user location information. An example heat map is shown in FIG. 22. The table may be divided by postal code and each row may represent a particular postal code. An example table is shown in FIG. 13A. [0198] the term “biased information” may pertain to information presented up until a current time in a location planning engine 128. The term “non-biased” information may take into account a size of a selected public population within a total population of a particular area.)
At the time the invention was filed, it would have been obvious for one of ordinary skill in the art to have modified the teachings of Floren in view of Herman, as taught by Andrade above, with a reasonable expectation of success if arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make this modification to the teachings of Floren in view of Herman with the motivation of, ... increasing with usage and maximum accuracy…optimizing performance and accuracy of results…the combined model above can be improved upon by removing particular noise in the data as well as tuning categorization of the data… The algorithms can be used to measure and improve marketer/retailer websites, mobile apps, advertising, and marketing effectiveness…An efficient way to find such subsets of data may be to apply particular combinations of rules to find frequent item sets and discover interesting relationships that can be used to determine features of the data…measure efficacy of business within a particular company…, as recited in Andrade.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PO HAN MAX LEE whose telephone number is (571)272-3821. The examiner can normally be reached on Mon-Thurs 8:00 am - 7:00 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Rutao Wu can be reached on (571) 272-6045. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/PO HAN LEE/Examiner, Art Unit 3623 /RUTAO WU/Supervisory Patent Examiner, Art Unit 3623