DETAILED ACTION
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 . Claims 1-26 have been reviewed and are under consideration by this office action.
Notice to Applicant
The following is a Final Office action. Applicant, on 03/23/2026, amended claims and previously withdrew claims 27-28. Claims 1-26 are pending in this application and have been rejected below.
Response to Amendment
Applicant’s amendments are received and acknowledged.
Response to Arguments - 35 USC § 101
Applicant’s arguments with respect to the 35 USC 101 rejections have been fully considered, but they are not persuasive.
Applicant contends that the inclusion of real-time provides a concept not capable of being performed in the human mind.
Examiner finds the argument unpersuasive. Real-time implies the use of a general purpose computing device and as such is determined to be performing the steps would be no more than mere instructions to apply the exception using a generic computer component. See MPEP 2106.05(f).
The 101 rejection is updated and maintained below.
Response to Arguments - 35 USC § 103
Applicant’s arguments with respect to the 35 USC 103 rejections have been fully considered, but they are moot in view of the new line of 103 rejections seen below.
The 103 rejection is updated and maintained.
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 1-26 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Step One - First, pursuant to step 1 in the January 2019 Guidance on 84 Fed. Reg. 53, the claim(s) is/are directed to statutory categories.
Step 2A, Prong One – The claims are found to recite limitations that set forth the abstract idea(s), namely in independent claims recite a series of steps for the abstract idea recited below.
Regarding independent claims, (additional elements bolded)
Regarding Claim(s) 1. A method comprising: obtaining asset data associated with an asset, wherein the asset data includes time series data associated with resources consumed by the asset and output by the asset to serve as a target variable to baseline;
predicting, by a machine learning model based on the time series asset data, a target resource baseline value associated with the asset based upon the asset’s operating conditions;
detecting actual resource values associated with the asset based on one or more sensor values; and (Examiner notes the sensors are not positively recited, but merely recites sensor values)
determining a recommendation in real time (implies the use of a general purpose computer) based on a difference between the target resource baseline value and the actual resource values for the target variable.
Regarding Claim(s) 15, A method comprising: determining a cohort of assets;
obtaining asset data associated with a particular asset of the cohort of assets, wherein the asset data includes time series data associated with resources consumed by the asset and output by the asset;
predicting, for each asset of the cohort of assets, a respective target resource baseline value, wherein each of the respective target resource baseline values is predicted by a different machine learning model in real time (implies the use of a general purpose computer) based on the asset data associated with the particular asset of the cohort of assets;
aggregating the respective predicted target resource baseline values; and
determining a difference between the target resource baseline value of the particular asset and the aggregated respective predicted target resource baseline values.
Regarding Claim(s) 22, A method comprising: identifying asset data associated with an asset based on a query, wherein the asset data includes time series data associated with resources consumed by the asset and output by the asset;
predicting, by a machine learning model based on the time series asset data, a target resource baseline value associated with the asset;
detecting actual resource values associated with the asset based on one or more sensor values; (Examiner notes the sensors are not positively recited, but merely recites sensor values)
determining a difference between the target resource baseline value and the detected actual resource values; and
generating a recommendation, by the machine learning models in real time (implies the use of a general purpose computer) based on the difference, a natural language recommendation associated with the asset.
Regarding Claim(s) 25, A method comprising: obtaining facility data associated with a facility, wherein the facility data includes time series data associated with resources consumed by the facility or output by the facility to serve as a target variable to baseline;
predicting, by a machine learning model based on the time series facility data, a target resource baseline value associated with the facility based upon the facility’s operating conditions;
detecting actual resource values associated with the facility based on one or more sensor values; and (Examiner notes the sensors are not positively recited, but merely recites sensor values)
determining a recommendation in real time (implies the use of a general purpose computer) based on a difference between the target resource baseline value and the actual resource values for the target variable.
As drafted, this is, under its broadest reasonable interpretation, within the Abstract idea groupings of “Mental processes—concepts performed in the human mind” (observation, evaluation, judgment, opinion) as the claims are directed towards obtaining asset data, predicting a target resource baseline, detecting actual resource values, and determining a recommendation all of which are concepts capable of being performed in the human mind (i.e. via pen and paper).
Further the claims are directed towards the abstract idea grouping of “Certain methods of organizing human activity” — commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations) and/or managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions) as the claims are directed towards managing and mitigating resource consumption (See Specification, [22]).
Step 2A, Prong Two - This judicial exception is not integrated into a practical application. The independent claims utilize at least an a machine learning model (recited at a high level of generality) and real-time (implies use of a general purpose computer). The additional elements are performing the steps would be no more than mere instructions to apply the exception using a generic computer component. See MPEP 2106.05(f) and/or amounts to no more than generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h).
Step 2B - The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements are just “apply it” on a computer. (See MPEP 2106.05(f) – Mere Instructions to Apply an Exception – “Thus, for example, claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea eligible.” Alice Corp., 134 S. Ct. at 235) and/or amounts to no more than generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h).
Regarding Claim(s) 2-14, 16-21, 24, and 26, the claim further narrows the abstract idea or recite additional elements previously rejected in the independent claims. Examiner notes claims 17, 24, and 26 recite a trained machine learning model but does not recite the actual training step. The machine learning models are addressed similarly to those of the independent claims.
Regarding Claim(s) 23, the claim further recite the additional element(s) of an omni-modal model (recited at a high level of generality) This element(s) is performing the steps would be no more than mere instructions to apply the exception using a generic computer component. See MPEP 2106.05(f) and/or amounts to no more than generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h) in Steps 2A-Prong 2 and 2B.
Accordingly, the claim fails to recite any improvements to another technology or technical field, improvements to the functioning of the computer itself, use of a particular machine, effecting a transformation or reduction of a particular article to a different state or thing, adding unconventional steps that confine the claim to a particular useful application, and/or meaningful limitations beyond generally linking the use of an abstract idea to a particular environment. See 84 Fed. Reg. 55. Viewed individually or as a whole, these additional claim element(s) do not provide meaningful limitation(s) to transform the abstract idea into a patent eligible application of the abstract idea such that the claim(s) amounts to significantly more than the abstract idea itself.
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:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-5, 7, 9-11, 13-15, 17-22, and 25 is/are rejected under 35 U.S.C. 103 as being unpatentable over Davis et al. (US 20230148149 A1) in view of Koch et al. (US 20110137574 A1), and Ingram et al. (US 20220114616 A1).
Regarding Claim(s) 1, Davis teaches: A method comprising: obtaining asset data associated with an asset, wherein the asset data includes time series data associated with resources consumed by the asset… by the asset to serve as a target variable to baseline; (Davis, [07]; A method executable by a building management system includes generating a graphical user interface showing a bar graph comprising a plurality of bars representing resource consumption values for a plurality of time periods and a line overlaid on the bar graph and representing a baseline or target resource consumption. The method also includes comparing the resource consumption values to the baseline or target resource consumption, adding a first icon aligned with a first bar of the plurality of bars in response to determining that a first resource consumption value represented by the first bar is within a threshold of the baseline or target resource consumption and less than the baseline or target resource consumption, and adding a second icon aligned with the first bar in response to determining that the first resource consumption value exceeds the baseline, the second icon different than the first icon and Davis, [35]; The present application in part addresses technical challenges in surfacing resource consumption data to users in a manner that provides meaningful insights and enables operational changes to reduce consumption to at or below baseline values or consumption targets. Because of the complexity of a typical BMS system, such data is often difficult to find, presented in only diverse places or interfaces (e.g., separate interfaces for different equipment, different types of equipment, different resources, etc.) and thus not practically available to or collectable by human users and Davis, [44]; Building management platform 102 can process and transform collected data to generate timeseries data and entity data. Several features of building management platform 102 are describes in more detail below and Davis, [95]; the tracking devices 624 can be sensors or meters capable of monitoring the utilization of one or more resources (e.g., water, energy, gas, steam, electricity, and the like) by one or more building subsystems 528 or one or more location(s)).
predicting, based on the time series asset data, a target resource baseline value associated with the asset based upon the asset’s operating conditions; (Davis, [102]; The baseline calculator 610 is configured to cooperate with the resource consumption calculator 608 and the database 603. The baseline calculator 610 performs one or more arithmetic operations on historical consumption values for each resource to determine dynamic baseline (shown in subsequent figures). In an embodiment, each resource and location may have a different dynamic baseline that may depend on their respective historical resource consumption values. For example, dynamic baseline for electricity, as a resource, may be calculated separately for building 10 and separately for one or more floors. In some other embodiments, the baseline calculator 610 may be configured to determine dynamic baseline for each building subsystems 528 considering their historical resource consumption values. For an example, dynamic baseline for electricity as resource may be separately calculated for an AHU).
detecting actual resource values associated with the asset based on one or more sensor values; and (Davis, [98]; one tracking device may be responsible for keeping track of electricity consumption and another tracking device may be responsible for keeping track of water consumption. In this case, the tracking device 624 may cooperate with multiple sensors that are configured to provide resource consumption data of varied locations (e.g., multiple sensors configured to determine water consumption data may communicate with the tracking device responsible for keeping track of water consumption). Therefore, in some embodiments, the tracking devices are processor enabled tracking devices capable of processing resource consumption data, wherein the processed resource consumption data is provided to the resource consumption calculator 608).
determining a recommendation in real-time based on a difference between the target resource baseline value and the actual resource values for the target variable. (Davis, [111]; In one embodiment, the data comparator 612 may be configured to compare resource consumption value with dynamic and/or static baseline in real time as well as for historical resource consumption values and Davis, [139]; Still referring to FIGS. 11 and 12, the user can select resource(s) 1106 using check box 1104 for which resource(s) in static baseline or dynamic baseline they want to compare the actual resource consumption. In case the user wishes to not compare consumption against dynamic baseline 906, then user can uncheck all resources 1106 via check boxes 1104 and Davis, [150]; The interfaces described above may also include selectable options to alter operation of building equipment so as to increase or decrease resource consumption. For example, a user may be able to select an option to implement a resource savings control strategy (e.g., relaxing temperature constraints, turning off certain equipment, changing temperature setpoints, changing other settings), etc.).
While Davis teaches a obtaining asset data in a time series of resources consumed, Davis does not appear to explicitly teach resources output. However, Davis in view of the analogous art of Koch (i.e. resource management) does teach obtaining… resource output (and further input) (Koch, [37]; The organization will typically want to reduce emissions from the baseline level and will set an emission target level for each accounting period (e.g., year), as shown in step 26. In order to be able to compare the current or future estimated emission level (with or without reduction strategies) to this target level, this target level needs to be visualized alongside the current and future estimated emission levels. The same applies for the cap level that might have been set externally for this organization. Setting a cap level is optional. An ideal outcome for this organization is that the target and/or cap level slightly exceed the current and future estimated emission levels at any given point in time. Instead of using emissions as the units of measurements, the units of measurement may instead by the organization's resource input or output other than emissions).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis teaches a obtaining asset data in a time series of resources consumed with the teachings of Koch including obtaining resource output in order to determine emissions with respect to either the input or output (Koch, [29]; Each input resource and/or output, assuming a certain usage efficiency, is applied to an appropriate algorithm to determine its corresponding CO2e emission quantity or other unit of measurement. Many of the algorithms 18 correlating resources, outputs, or activities to an equivalent CO2e emission are based on publicly known standards).
While Davis teaches acquiring asset data, predicting baselines, and determining recommendations, Davis does not appear to explicitly teach the use of a machine learning model. However, Davis in view of the analogous art of Ingram (i.e. business recommendations) does teach the entirety of the limitation: (Ingram, [98]; the artificial intelligence system 604 may leverage the machine learned models (e.g., prediction models and/or classification models) to make predictions regarding media asset outcomes with respect to media asset genome data, demographic data, interaction data, digital personas, digital villages, financial data, health data, traffic data, identity management data, customer data, digital anthropology data, and the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514. For example, the client algorithms 502 may implement classifiers, clustering, pattern recognition, reinforcement learning, attribution, natural language processing and natural language understanding, segmentation, prediction, particle swarm optimization, recommender super learning, and the like. In embodiments, each of the client algorithms 502 trains a local version of a model, where each local version is initially parameterized in the same manner…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
Regarding Claim(s) 2, Davis/Koch/Ingram teaches: The method of claim 1, wherein the target resource baseline value corresponds to any of an expected resource consumption of the asset and an optimal resource consumption of the asset. (Davis, [08]; the method includes obtaining one or more values defining the baseline or target resource consumption from a user. In some embodiments, the method includes determining the baseline or target resource consumption based on historical resource consumption values and Davis, [80]; Demand response layer 514 can be configured to determine (e.g., optimize) resource usage (e.g., electricity use, natural gas use, water use, etc.) and/or the monetary cost of such resource usage to satisfy the demand of building 10. The resource usage determination can be based on time-of-use prices, curtailment signals, energy availability, or other data received from utility providers, distributed energy generation systems 524, energy storage 527 (e.g., hot TES 342, cold TES 344, etc.), or from other sources).
Regarding Claim(s) 3, Davis/Koch/Ingram teaches: The method of claim 1, wherein the target resource baseline value corresponds to any of an expected resource output of the asset and an optimal resource output of the asset. (Davis, [08]; the method includes obtaining one or more values defining the baseline or target resource consumption from a user. In some embodiments, the method includes determining the baseline or target resource consumption based on historical resource consumption values and Davis, [80]; Demand response layer 514 can be configured to determine (e.g., optimize) resource usage (e.g., electricity use, natural gas use, water use, etc.) and/or the monetary cost of such resource usage to satisfy the demand of building 10. The resource usage determination can be based on time-of-use prices, curtailment signals, energy availability, or other data received from utility providers, distributed energy generation systems 524, energy storage 527 (e.g., hot TES 342, cold TES 344, etc.), or from other sources).
Regarding Claim(s) 4, Davis/Koch/Ingram teaches: The method of claim 1, wherein the actual resource values include real-time time series values associated with the resources consumed… by the asset, and the target resource values comprise time series values. (Davis, [111]; resource consumption values. Additionally, the user may provide static baseline for one or more building subsystem(s). In one embodiment, the data comparator 612 may be configured to compare resource consumption value with dynamic and/or static baseline in real time as well as for historical resource consumption values. It is to be noted that while comparing historical resource consumption values, the data comparator 612 may retrieve historical consumption values and dynamic baseline as per timestamp information associated with the historical value).
While Davis teaches acquiring asset data, predicting baselines, and determining recommendations, Davis does not appear to explicitly teach the use of a machine learning model. However, Davis in view of the analogous art of Ingram (i.e. business recommendations) does teach the entirety of the limitation: (Ingram, [98]; the artificial intelligence system 604 may leverage the machine learned models (e.g., prediction models and/or classification models) to make predictions regarding media asset outcomes with respect to media asset genome data, demographic data, interaction data, digital personas, digital villages, financial data, health data, traffic data, identity management data, customer data, digital anthropology data, and the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514. For example, the client algorithms 502 may implement classifiers, clustering, pattern recognition, reinforcement learning, attribution, natural language processing and natural language understanding, segmentation, prediction, particle swarm optimization, recommender super learning, and the like. In embodiments, each of the client algorithms 502 trains a local version of a model, where each local version is initially parameterized in the same manner…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
Regarding Claim(s) 5, Davis/Koch/Ingram teaches: The method of claim 1, wherein the resources comprise any of greenhouse gas emissions, electricity consumption or generation, combusted fuels, water, waste, and compressed air, derived resources, and other metrics informing operational or sustainability performance. (Davis, [125]; a graphical representation that provides electricity consumption analysis, in form of graphical representation, for building 1 wherein electricity is selected by the user via resource selector 702 and building 1 is selected via entity selector 701. Similarly, widget 804 provides steam consumption analysis, in form of graphical representation, for building 1 wherein steam is selected by the user via resource selector 702 and building 1 is selected via entity selector 701 and Davis, [145]; The sustainability metrics may include any of a variety of metrics that quantify the performance of a building, campus, or organization with respect to energy sustainability or environmental sustainability. Some examples of sustainability metrics include carbon dioxide (CO2) related metrics (i.e., carbon equivalents) such as carbon emissions, carbon footprint, carbon credits, carbon offsets, and the like. Other examples of sustainability metrics include greenhouse gas emissions (e.g., methane, nitrous oxide, fluorinated gases, etc.), water usage, water pollution, waste generation, ecological footprint, resource consumption, or any other metric that can be used to quantify sustainable building operations. In some embodiments, sustainability metrics can be expressed on a per unit basis such as carbon per number of widgets produced, carbon per volume of product produced, carbon per meals served, carbon per patients treated, carbon per experiments run, carbon per sales revenue, carbon per items shipped, carbon per emails sent, carbon per unit of data processed, carbon per occupant, carbon per occupied room, carbon per normalized utilization value, etc. In some embodiments, sustainability metrics can be generated on an enterprise-wide basis).
Regarding Claim(s) 7, Davis/Koch/Ingram teaches: The method of claim 1, further comprising detecting degradation of the asset based on the difference between the target resource baseline value and the detected actual resource values over a period. (Davis, [35]; Teachings herein enable building managers (e.g., users of a BMS) to manage resource consumption, for example electricity consumption, water consumption, natural gas consumption, etc. Resource consumption contributes to environmental degradation, climate change, aggravated drought conditions and water shortages, etc. The present application in part addresses technical challenges in surfacing resource consumption data to users in a manner that provides meaningful insights and enables operational changes to reduce consumption to at or below baseline values or consumption targets and Davis, [90]; The data generated by building subsystems 528 can include measured or calculated values that exhibit statistical characteristics and provide information about how the corresponding system or process (e.g., a temperature control process, a flow control process, etc.) is performing in terms of error from its setpoint. These processes can be examined by FDD layer 516 to expose when the system begins to degrade in performance and alert a user to repair the fault before it becomes more severe).
Regarding Claim(s) 9, Davis/Koch/Ingram teaches: The method of claim 1, further comprising: determining, based on the difference between the predicted resource baseline value and the detected actual resource values, a potential resource reduction or increase associated with the asset and the resource. (Davis, [107]; the user is enabled to provide a first threshold and a second threshold for each resource, preferably, via user interface 626. The data comparator 612 is configured to generate a first flag when resource consumption value is less than dynamic and/or static baseline by the first threshold. Generation of first flag represents that the resource consumption value for the particular resource is approaching dynamic and/or static baseline. Further, the data comparator 612 is configured to generate a second flag once the resource consumption value exceeds dynamic and/or static baseline by the second threshold).
Regarding Claim(s) 10, Davis/Koch/Ingram teaches: The method of claim 4, further comprising: tracking a reduction or increase of the detected resource consumption or output over a period of time against the potential resource reduction or increase associated with the asset and the resources; and (Davis, [107]; the user is enabled to provide a first threshold and a second threshold for each resource, preferably, via user interface 626. The data comparator 612 is configured to generate a first flag when resource consumption value is less than dynamic and/or static baseline by the first threshold. Generation of first flag represents that the resource consumption value for the particular resource is approaching dynamic and/or static baseline. Further, the data comparator 612 is configured to generate a second flag once the resource consumption value exceeds dynamic and/or static baseline by the second threshold and Davis, [128]; when a user selects or hovers over one of these months, the widget 900 may provide additional information. That is, when the user selects March, the widget 900 pop-ups a text box 914 that provides additional information. The additional information indicates that the total resource consumption in the month of March was above static baseline by second threshold (e.g., fifteen percent).
determining one or more corrective actions based on the tracking. (Davis, [07]; adding a first icon aligned with a first bar of the plurality of bars in response to determining that a first resource consumption value represented by the first bar is within a threshold of the baseline or target resource consumption and less than the baseline or target resource consumption, and adding a second icon aligned with the first bar in response to determining that the first resource consumption value exceeds the baseline, the second icon different than the first icon and Davis, [15]; the operations also include providing the graphical user interface with a user-selectable option to adjust an operation of building equipment based on presence or absence of the first icon or the second icon and adjusting the operation of the building equipment in response to selection of the user-selectable option and the demand response policy definitions can specify which equipment can be turned on or off in response to particular demand inputs, how long a system or piece of equipment should be turned off, what setpoints can be changed, what the allowable set point adjustment range is, how long to hold a high demand setpoint before returning to a normally scheduled setpoint, how close to approach capacity limits, which equipment modes to utilize, the energy transfer rates (e.g., the maximum rate, an alarm rate, other rate boundary information, etc.) into and out of energy storage devices (e.g., thermal storage tanks, battery banks, etc.), and when to dispatch on-site generation of energy (e.g., via fuel cells, a motor generator set, etc. and Davis, [150]; The interfaces described above may also include selectable options to alter operation of building equipment so as to increase or decrease resource consumption. For example, a user may be able to select an option to implement a resource savings control strategy (e.g., relaxing temperature constraints, turning off certain equipment, changing temperature setpoints, changing other settings), etc.).
Regarding Claim(s) 11, Davis/Koch/Ingram teaches: The method of claim 1, wherein the predicted target resource baseline value comprises time series data values predicted over a period of time. (Davis, [12]; The operations include generating a graphical user interface showing a bar graph comprising a plurality of bars representing resource consumption values for a plurality of time periods and a line overlaid on the bar graph and representing a baseline or target resource consumption. The operations also include comparing the resource consumption values to the baseline or target resource consumption, adding a first icon aligned with a first bar of the plurality of bars in response to determining that a first resource consumption value represented by the first bar is within a threshold of the baseline or target resource consumption and less than the baseline or target resource consumption).
Regarding Claim(s) 13, Davis/Koch/Ingram teaches The method of claim 1, wherein the asset comprises an asset of multiple assets, and further comprising: obtaining other asset data associated with the multiple assets, wherein the other asset data includes other time series data associated with resources consumed by the other assets of the multiple assets… by the other assets to serve as other target variables to baseline; (Davis, [07]; A method executable by a building management system includes generating a graphical user interface showing a bar graph comprising a plurality of bars representing resource consumption values for a plurality of time periods and a line overlaid on the bar graph and representing a baseline or target resource consumption. The method also includes comparing the resource consumption values to the baseline or target resource consumption, adding a first icon aligned with a first bar of the plurality of bars in response to determining that a first resource consumption value represented by the first bar is within a threshold of the baseline or target resource consumption and less than the baseline or target resource consumption, and adding a second icon aligned with the first bar in response to determining that the first resource consumption value exceeds the baseline, the second icon different than the first icon and Davis, [35]; The present application in part addresses technical challenges in surfacing resource consumption data to users in a manner that provides meaningful insights and enables operational changes to reduce consumption to at or below baseline values or consumption targets. Because of the complexity of a typical BMS system, such data is often difficult to find, presented in only diverse places or interfaces (e.g., separate interfaces for different equipment, different types of equipment, different resources, etc.) and thus not practically available to or collectable by human users and Davis, [44]; Building management platform 102 can process and transform collected data to generate timeseries data and entity data. Several features of building management platform 102 are describes in more detail below and Davis, [95]; the tracking devices 624 can be sensors or meters capable of monitoring the utilization of one or more resources (e.g., water, energy, gas, steam, electricity, and the like) by one or more building subsystems 528 or one or more location(s) and Davis, [105]; In some embodiments, the user may define different static baselines for different resources and/or locations. In some other embodiments, the user may define a single static baseline for all locations or resources and Davis, [116]; the custom field creator 616 is shown to include an entity selector 701, a resource selector 702, a baseline selector 704, and a baseline customizer 706. Resource selector 702 is configured to allow a user to select one or more resources for analysis, i.e., the user may select a particular resource that he/she wishes to compare with at least one of static baseline and dynamic baseline).
predicting other target resource baseline values for each of the other assets of the multiple based upon the other asset’s operating conditions; (Davis, [102]; The baseline calculator 610 is configured to cooperate with the resource consumption calculator 608 and the database 603. The baseline calculator 610 performs one or more arithmetic operations on historical consumption values for each resource to determine dynamic baseline (shown in subsequent figures). In an embodiment, each resource and location may have a different dynamic baseline that may depend on their respective historical resource consumption values. For example, dynamic baseline for electricity, as a resource, may be calculated separately for building 10 and separately for one or more floors. In some other embodiments, the baseline calculator 610 may be configured to determine dynamic baseline for each building subsystems 528 considering their historical resource consumption values. For an example, dynamic baseline for electricity as resource may be separately calculated for an AHU).
detecting other actual resource values associated with the other assets based on one or more other sensor values; and (Davis, [98]; one tracking device may be responsible for keeping track of electricity consumption and another tracking device may be responsible for keeping track of water consumption. In this case, the tracking device 624 may cooperate with multiple sensors that are configured to provide resource consumption data of varied locations (e.g., multiple sensors configured to determine water consumption data may communicate with the tracking device responsible for keeping track of water consumption). Therefore, in some embodiments, the tracking devices are processor enabled tracking devices capable of processing resource consumption data, wherein the processed resource consumption data is provided to the resource consumption calculator 608).
determining another recommendation based on differences between the other target resource baseline values of the other assets and the other actual resource values. (Davis, [139]; Still referring to FIGS. 11 and 12, the user can select resource(s) 1106 using check box 1104 for which resource(s) in static baseline or dynamic baseline they want to compare the actual resource consumption. In case the user wishes to not compare consumption against dynamic baseline 906, then user can uncheck all resources 1106 via check boxes 1104 and Davis, [150]; The interfaces described above may also include selectable options to alter operation of building equipment so as to increase or decrease resource consumption. For example, a user may be able to select an option to implement a resource savings control strategy (e.g., relaxing temperature constraints, turning off certain equipment, changing temperature setpoints, changing other settings), etc. Building equipment may operate differently in response to selection of such an option, for example due to different control settings selected by the processing circuit 602 or other circuitry of BMS 600 in response to user input. The teachings herein thereby result in physical changes in equipment operation driven by the features of the various interfaces, processes, systems, etc. disclosed herein).
While Davis teaches acquiring asset data, predicting baselines, and determining recommendations, Davis does not appear to explicitly teach the use of a machine learning model. However, Davis in view of the analogous art of Ingram (i.e. business recommendations) does teach the entirety of the limitation: (Ingram, [98]; the artificial intelligence system 604 may leverage the machine learned models (e.g., prediction models and/or classification models) to make predictions regarding media asset outcomes with respect to media asset genome data, demographic data, interaction data, digital personas, digital villages, financial data, health data, traffic data, identity management data, customer data, digital anthropology data, and the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514. For example, the client algorithms 502 may implement classifiers, clustering, pattern recognition, reinforcement learning, attribution, natural language processing and natural language understanding, segmentation, prediction, particle swarm optimization, recommender super learning, and the like. In embodiments, each of the client algorithms 502 trains a local version of a model, where each local version is initially parameterized in the same manner…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
Regarding Claim(s) 14, Davis/Koch/Ingram teaches: The method of claim 1, further comprising: providing the recommendation to the asset, thereby causing an adjustment to the asset. (Davis, [139]; Still referring to FIGS. 11 and 12, the user can select resource(s) 1106 using check box 1104 for which resource(s) in static baseline or dynamic baseline they want to compare the actual resource consumption. In case the user wishes to not compare consumption against dynamic baseline 906, then user can uncheck all resources 1106 via check boxes 1104 and Davis, [150]; The interfaces described above may also include selectable options to alter operation of building equipment so as to increase or decrease resource consumption. For example, a user may be able to select an option to implement a resource savings control strategy (e.g., relaxing temperature constraints, turning off certain equipment, changing temperature setpoints, changing other settings), etc.).
Regarding Claim(s) 15, Davis/Koch/Ingram teaches: A method comprising: determining a cohort of assets; obtaining asset data associated with a particular asset of the cohort of assets, wherein the asset data includes time series data associated with resources consumed by the asset… by the asset; (Davis, [07]; A method executable by a building management system includes generating a graphical user interface showing a bar graph comprising a plurality of bars representing resource consumption values for a plurality of time periods and a line overlaid on the bar graph and representing a baseline or target resource consumption. The method also includes comparing the resource consumption values to the baseline or target resource consumption, adding a first icon aligned with a first bar of the plurality of bars in response to determining that a first resource consumption value represented by the first bar is within a threshold of the baseline or target resource consumption and less than the baseline or target resource consumption, and adding a second icon aligned with the first bar in response to determining that the first resource consumption value exceeds the baseline, the second icon different than the first icon and Davis, [35]; The present application in part addresses technical challenges in surfacing resource consumption data to users in a manner that provides meaningful insights and enables operational changes to reduce consumption to at or below baseline values or consumption targets. Because of the complexity of a typical BMS system, such data is often difficult to find, presented in only diverse places or interfaces (e.g., separate interfaces for different equipment, different types of equipment, different resources, etc.) and thus not practically available to or collectable by human users and Davis, [44]; Building management platform 102 can process and transform collected data to generate timeseries data and entity data. Several features of building management platform 102 are describes in more detail below and Davis, [95]; the tracking devices 624 can be sensors or meters capable of monitoring the utilization of one or more resources (e.g., water, energy, gas, steam, electricity, and the like) by one or more building subsystems 528 or one or more location(s) and Davis, [105]; In some embodiments, the user may define different static baselines for different resources and/or locations. In some other embodiments, the user may define a single static baseline for all locations or resources and Davis, [116]; the custom field creator 616 is shown to include an entity selector 701, a resource selector 702, a baseline selector 704, and a baseline customizer 706. Resource selector 702 is configured to allow a user to select one or more resources for analysis, i.e., the user may select a particular resource that he/she wishes to compare with at least one of static baseline and dynamic baseline).
predicting, for each asset of the cohort of assets, a respective target resource baseline value, wherein each of the respective target resource baseline values is predicted by a different… in real time based on the asset data associated with the particular asset of the cohort of assets; (Davis, [102]; The baseline calculator 610 is configured to cooperate with the resource consumption calculator 608 and the database 603. The baseline calculator 610 performs one or more arithmetic operations on historical consumption values for each resource to determine dynamic baseline (shown in subsequent figures). In an embodiment, each resource and location may have a different dynamic baseline that may depend on their respective historical resource consumption values. For example, dynamic baseline for electricity, as a resource, may be calculated separately for building 10 and separately for one or more floors. In some other embodiments, the baseline calculator 610 may be configured to determine dynamic baseline for each building subsystems 528 considering their historical resource consumption values. For an example, dynamic baseline for electricity as resource may be separately calculated for an AHU and Davis, [105]; In some embodiments, the user may define different static baselines for different resources and/or locations. In some other embodiments, the user may define a single static baseline for all locations or resources and Davis, [111]; In one embodiment, the data comparator 612 may be configured to compare resource consumption value with dynamic and/or static baseline in real time as well as for historical resource consumption values and Davis, [116]; the custom field creator 616 is shown to include an entity selector 701, a resource selector 702, a baseline selector 704, and a baseline customizer 706. Resource selector 702 is configured to allow a user to select one or more resources for analysis, i.e., the user may select a particular resource that he/she wishes to compare with at least one of static baseline and dynamic baseline).
aggregating the respective predicted target resource baseline values; and (Davis, [112]; the baseline calculator 610, the data comparator 612, and the database 603. The data representor 614 is capable of utilizing resource consumption values, associated dynamic and/or static baselines, and information stored within the database 603 to selectively generate and provide graphical representation for resource consumption analysis via user interface 626 and Davis, [148]; the processing circuit 602 compares the resource consumption value with one or more baselines. The baseline includes a static baseline and a dynamic baseline. In some embodiments, the resource consumption value is compared with only static baseline. In some other embodiments, the resource consumption value is compared with only dynamic baseline. In some yet another embodiment, the resource consumption value is compared with both static baseline and dynamic baseline..
determining a difference between the target resource baseline value of the particular asset and the aggregated respective predicted target resource baseline values. (Davis, [139]; Still referring to FIGS. 11 and 12, the user can select resource(s) 1106 using check box 1104 for which resource(s) in static baseline or dynamic baseline they want to compare the actual resource consumption. In case the user wishes to not compare consumption against dynamic baseline 906, then user can uncheck all resources 1106 via check boxes 1104).
While Davis teaches acquiring asset data, predicting baselines, and determining recommendations, Davis does not appear to explicitly teach the use of a machine learning model. However, Davis in view of the analogous art of Ingram (i.e. business recommendations) does teach the entirety of the limitation: (Ingram, [98]; the artificial intelligence system 604 may leverage the machine learned models (e.g., prediction models and/or classification models) to make predictions regarding media asset outcomes with respect to media asset genome data, demographic data, interaction data, digital personas, digital villages, financial data, health data, traffic data, identity management data, customer data, digital anthropology data, and the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514. For example, the client algorithms 502 may implement classifiers, clustering, pattern recognition, reinforcement learning, attribution, natural language processing and natural language understanding, segmentation, prediction, particle swarm optimization, recommender super learning, and the like. In embodiments, each of the client algorithms 502 trains a local version of a model, where each local version is initially parameterized in the same manner…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
While Davis teaches acquiring asset data, predicting baselines, and determining recommendations, Davis does not appear to explicitly teach the use of a machine learning model nor a different machine learning model. However, Davis in view of the analogous art of Ingram (i.e. business recommendations) does teach the entirety of the limitation: (Ingram, [98]; the artificial intelligence system 604 may leverage the machine learned models (e.g., prediction models and/or classification models) to make predictions regarding media asset outcomes with respect to media asset genome data, demographic data, interaction data, digital personas, digital villages, financial data, health data, traffic data, identity management data, customer data, digital anthropology data, and the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514. For example, the client algorithms 502 may implement classifiers, clustering, pattern recognition, reinforcement learning, attribution, natural language processing and natural language understanding, segmentation, prediction, particle swarm optimization, recommender super learning, and the like. In embodiments, each of the client algorithms 502 trains a local version of a model, where each local version is initially parameterized in the same manner…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
Regarding Claim(s) 17, Davis/Koch/Ingram teaches: The method of claim 15, wherein each of the different machine learning models comprises a respective machine learning model trained for a different asset of the cohort of assets. (Ingram, [51]; In the case of images and/or video, the media asset processing system 3C02 may leverage one or more classification models that are trained to classify one or more elements of an image, video, or other visual media asset. In embodiments, the classification models (e.g., image classification models or video classification models) may be trained using labeled images or videos, wherein the labels may indicate respective classifications of the image or video (e.g., beach image, mountain image, action video, and the like) as a whole, or classifications of a subject of the image (e.g., model is female, model is wearing a swimsuit, model is surfing, model is doing yoga, etc.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
Regarding Claim(s) 18, Davis/Koch/Ingram teaches: The method of claim 15, wherein the respective predicted target resource baseline values correspond to any of an expected resource consumption or expected resource output of the assets of the cohort of assets. (Davis, [08]; the method includes obtaining one or more values defining the baseline or target resource consumption from a user. In some embodiments, the method includes determining the baseline or target resource consumption based on historical resource consumption values and Davis, [80]; Demand response layer 514 can be configured to determine (e.g., optimize) resource usage (e.g., electricity use, natural gas use, water use, etc.) and/or the monetary cost of such resource usage to satisfy the demand of building 10. The resource usage determination can be based on time-of-use prices, curtailment signals, energy availability, or other data received from utility providers, distributed energy generation systems 524, energy storage 527 (e.g., hot TES 342, cold TES 344, etc.), or from other sources).
Regarding Claim(s) 19, Davis/Koch/Ingram teaches: The method of claim 15, further comprising performing one or more corrective actions based on the difference between the target resource baseline value of the particular asset and the aggregated respective predicted target resource baseline values. (Davis, [07]; adding a first icon aligned with a first bar of the plurality of bars in response to determining that a first resource consumption value represented by the first bar is within a threshold of the baseline or target resource consumption and less than the baseline or target resource consumption, and adding a second icon aligned with the first bar in response to determining that the first resource consumption value exceeds the baseline, the second icon different than the first icon and Davis, [15]; the operations also include providing the graphical user interface with a user-selectable option to adjust an operation of building equipment based on presence or absence of the first icon or the second icon and adjusting the operation of the building equipment in response to selection of the user-selectable option and the demand response policy definitions can specify which equipment can be turned on or off in response to particular demand inputs, how long a system or piece of equipment should be turned off, what setpoints can be changed, what the allowable set point adjustment range is, how long to hold a high demand setpoint before returning to a normally scheduled setpoint, how close to approach capacity limits, which equipment modes to utilize, the energy transfer rates (e.g., the maximum rate, an alarm rate, other rate boundary information, etc.) into and out of energy storage devices (e.g., thermal storage tanks, battery banks, etc.), and when to dispatch on-site generation of energy (e.g., via fuel cells, a motor generator set, etc. and Davis, [150]; The interfaces described above may also include selectable options to alter operation of building equipment so as to increase or decrease resource consumption. For example, a user may be able to select an option to implement a resource savings control strategy (e.g., relaxing temperature constraints, turning off certain equipment, changing temperature setpoints, changing other settings), etc.).
Regarding Claim(s) 20, Davis/Koch/Ingram teaches: The method of claim 15, wherein the asset data includes real-time time series data associated with the resources consumed… by the cohort of assets. (Davis, [95]; the tracking devices 624 can be sensors or meters capable of monitoring the utilization of one or more resources (e.g., water, energy, gas, steam, electricity, and the like) by one or more building subsystems 528 or one or more location(s) and Davis, [111]; In one embodiment, the data comparator 612 may be configured to compare resource consumption value with dynamic and/or static baseline in real time as well as for historical resource consumption values. It is to be noted that while comparing historical resource consumption values, the data comparator 612 may retrieve historical consumption values and dynamic baseline as per timestamp information associated with the historical value. In one embodiment, a custom field creator 616 may allow the user to select one or more building subsystem(s) for analysis).
While Davis teaches acquiring asset data, predicting baselines, and determining recommendations, Davis does not appear to explicitly teach the use of a machine learning model. However, Davis in view of the analogous art of Ingram (i.e. business recommendations) does teach the entirety of the limitation: (Ingram, [98]; the artificial intelligence system 604 may leverage the machine learned models (e.g., prediction models and/or classification models) to make predictions regarding media asset outcomes with respect to media asset genome data, demographic data, interaction data, digital personas, digital villages, financial data, health data, traffic data, identity management data, customer data, digital anthropology data, and the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514. For example, the client algorithms 502 may implement classifiers, clustering, pattern recognition, reinforcement learning, attribution, natural language processing and natural language understanding, segmentation, prediction, particle swarm optimization, recommender super learning, and the like. In embodiments, each of the client algorithms 502 trains a local version of a model, where each local version is initially parameterized in the same manner…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
Regarding Claim(s) 21, Davis/Koch/Ingram teaches: The method of claim 15, wherein the cohort of assets is determined based one or more similar attributes of the assets. (Davis, [35]; Because of the complexity of a typical BMS system, such data is often difficult to find, presented in only diverse places or interfaces (e.g., separate interfaces for different equipment, different types of equipment, different resources, etc.) and thus not practically available to or collectable by human users. The present disclosure thus provides technical advantages in providing meaningful insights into resource consumption and enabling actions to reduce consumption to acceptable values, for example at or below baselines or targets). Examiner notes the assets all share the same attribute of being used by the same organization.
Regarding Claim(s) 22, Davis/Koch/Ingram teaches: A method comprising: identifying asset data associated with an asset based on a query, wherein the asset data includes time series data associated with a resources consumed by the asset… by the asset; (Davis, [104]; For an instance, if user input indicates selection of electricity as a resource and building 10 as location then the baseline calculator 610 cooperates with the database 603 to extract historical resource (electricity) consumption values for building 10 from the database 603. Subsequently, the baseline calculator 610 may determine dynamic baseline by calculating average of historical resource (electricity) consumption values for the historical time period and Davis, [95]; the tracking devices 624 can be sensors or meters capable of monitoring the utilization of one or more resources (e.g., water, energy, gas, steam, electricity, and the like) by one or more building subsystems 528 or one or more location).
predicting, by… based on the time series asset data, a target resource baseline value associated with the asset; (Davis, [102]; The baseline calculator 610 is configured to cooperate with the resource consumption calculator 608 and the database 603. The baseline calculator 610 performs one or more arithmetic operations on historical consumption values for each resource to determine dynamic baseline (shown in subsequent figures). In an embodiment, each resource and location may have a different dynamic baseline that may depend on their respective historical resource consumption values. For example, dynamic baseline for electricity, as a resource, may be calculated separately for building 10 and separately for one or more floors. In some other embodiments, the baseline calculator 610 may be configured to determine dynamic baseline for each building subsystems 528 considering their historical resource consumption values. For an example, dynamic baseline for electricity as resource may be separately calculated for an AHU).
detecting actual resource values associated with the asset based on one or more sensor values; (Davis, [98]; one tracking device may be responsible for keeping track of electricity consumption and another tracking device may be responsible for keeping track of water consumption. In this case, the tracking device 624 may cooperate with multiple sensors that are configured to provide resource consumption data of varied locations (e.g., multiple sensors configured to determine water consumption data may communicate with the tracking device responsible for keeping track of water consumption). Therefore, in some embodiments, the tracking devices are processor enabled tracking devices capable of processing resource consumption data, wherein the processed resource consumption data is provided to the resource consumption calculator 608).
determining a difference between the target resource baseline value and the detected actual resource values; and generating a recommendation,… based on the difference, a natural language response associated with the asset. (Davis, [111]; In one embodiment, the data comparator 612 may be configured to compare resource consumption value with dynamic and/or static baseline in real time as well as for historical resource consumption values and Davis, [139]; Still referring to FIGS. 11 and 12, the user can select resource(s) 1106 using check box 1104 for which resource(s) in static baseline or dynamic baseline they want to compare the actual resource consumption. In case the user wishes to not compare consumption against dynamic baseline 906, then user can uncheck all resources 1106 via check boxes 1104 and Davis, [150]; The interfaces described above may also include selectable options to alter operation of building equipment so as to increase or decrease resource consumption. For example, a user may be able to select an option to implement a resource savings control strategy (e.g., relaxing temperature constraints, turning off certain equipment, changing temperature setpoints, changing other settings), etc.).
While Davis teaches acquiring asset data, predicting baselines, and determining recommendations, Davis does not appear to explicitly teach the use of a machine learning model. However, Davis in view of the analogous art of Ingram (i.e. business recommendations) does teach the entirety of the limitation: (Ingram, [98]; the artificial intelligence system 604 may leverage the machine learned models (e.g., prediction models and/or classification models) to make predictions regarding media asset outcomes with respect to media asset genome data, demographic data, interaction data, digital personas, digital villages, financial data, health data, traffic data, identity management data, customer data, digital anthropology data, and the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514. For example, the client algorithms 502 may implement classifiers, clustering, pattern recognition, reinforcement learning, attribution, natural language processing and natural language understanding, segmentation, prediction, particle swarm optimization, recommender super learning, and the like. In embodiments, each of the client algorithms 502 trains a local version of a model, where each local version is initially parameterized in the same manner…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
While Davis teaches acquiring asset data, predicting baselines, and determining recommendations, Davis does not appear to explicitly teach the use of a machine learning model or natural language. However, Davis in view of the analogous art of Ingram (i.e. business recommendations) does teach the entirety of the limitation: (Ingram, [83]; For example, the client algorithms 502 may implement classifiers, clustering, pattern recognition, reinforcement learning, attribution, natural language processing and natural language understanding, segmentation, prediction, particle swarm optimization, recommender super learning, and the like and Ingram, [98]; the artificial intelligence system 604 may leverage the machine learned models (e.g., prediction models and/or classification models) to make predictions regarding media asset outcomes with respect to media asset genome data, demographic data, interaction data, digital personas, digital villages, financial data, health data, traffic data, identity management data, customer data, digital anthropology data, and the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models and natural language in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514. For example, the client algorithms 502 may implement classifiers, clustering, pattern recognition, reinforcement learning, attribution, natural language processing and natural language understanding, segmentation, prediction, particle swarm optimization, recommender super learning, and the like. In embodiments, each of the client algorithms 502 trains a local version of a model, where each local version is initially parameterized in the same manner…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
Regarding Claim(s) 25, Davis/Koch/Ingram teaches: A method comprising: obtaining facility data associated with a facility, wherein the facility data includes time series data associated with a resources consumed by the facility… by the facility to serve as a target variable to baseline; (Davis, [02]; The present disclosure relates more particularly to systems and methods for tracking usage of commodities associated with a facility and Davis, [06]; systems and methods to improve resource/commodity consumption that is associated with sustainability goals of buildings is desirable. Wide-scale deployment of such solutions can have positive effects on the environment while also reducing operational costs for building owners and Davis, [07]; A method executable by a building management system includes generating a graphical user interface showing a bar graph comprising a plurality of bars representing resource consumption values for a plurality of time periods and a line overlaid on the bar graph and representing a baseline or target resource consumption. The method also includes comparing the resource consumption values to the baseline or target resource consumption, adding a first icon aligned with a first bar of the plurality of bars in response to determining that a first resource consumption value represented by the first bar is within a threshold of the baseline or target resource consumption and less than the baseline or target resource consumption, and adding a second icon aligned with the first bar in response to determining that the first resource consumption value exceeds the baseline, the second icon different than the first icon and Davis, [35]; The present application in part addresses technical challenges in surfacing resource consumption data to users in a manner that provides meaningful insights and enables operational changes to reduce consumption to at or below baseline values or consumption targets. Because of the complexity of a typical BMS system, such data is often difficult to find, presented in only diverse places or interfaces (e.g., separate interfaces for different equipment, different types of equipment, different resources, etc.) and thus not practically available to or collectable by human users and Davis, [44]; Building management platform 102 can process and transform collected data to generate timeseries data and entity data. Several features of building management platform 102 are describes in more detail below and Davis, [95]; the tracking devices 624 can be sensors or meters capable of monitoring the utilization of one or more resources (e.g., water, energy, gas, steam, electricity, and the like) by one or more building subsystems 528 or one or more location(s)).
predicting… based on the time series facility data, a target resource baseline value associated with the facility based upon the facility’s operating conditions; (Davis, [102]; The baseline calculator 610 is configured to cooperate with the resource consumption calculator 608 and the database 603. The baseline calculator 610 performs one or more arithmetic operations on historical consumption values for each resource to determine dynamic baseline (shown in subsequent figures). In an embodiment, each resource and location may have a different dynamic baseline that may depend on their respective historical resource consumption values. For example, dynamic baseline for electricity, as a resource, may be calculated separately for building 10 and separately for one or more floors. In some other embodiments, the baseline calculator 610 may be configured to determine dynamic baseline for each building subsystems 528 considering their historical resource consumption values. For an example, dynamic baseline for electricity as resource may be separately calculated for an AHU).
detecting actual resource values associated with the facility based on one or more sensor values; and (Davis, [98]; one tracking device may be responsible for keeping track of electricity consumption and another tracking device may be responsible for keeping track of water consumption. In this case, the tracking device 624 may cooperate with multiple sensors that are configured to provide resource consumption data of varied locations (e.g., multiple sensors configured to determine water consumption data may communicate with the tracking device responsible for keeping track of water consumption). Therefore, in some embodiments, the tracking devices are processor enabled tracking devices capable of processing resource consumption data, wherein the processed resource consumption data is provided to the resource consumption calculator 608).
determining a recommendation in real time based on a difference between the target resource baseline value and the actual resource values for the target variable. (Davis, [111]; In one embodiment, the data comparator 612 may be configured to compare resource consumption value with dynamic and/or static baseline in real time as well as for historical resource consumption values and Davis, [139]; Still referring to FIGS. 11 and 12, the user can select resource(s) 1106 using check box 1104 for which resource(s) in static baseline or dynamic baseline they want to compare the actual resource consumption. In case the user wishes to not compare consumption against dynamic baseline 906, then user can uncheck all resources 1106 via check boxes 1104 and Davis, [150]; The interfaces described above may also include selectable options to alter operation of building equipment so as to increase or decrease resource consumption. For example, a user may be able to select an option to implement a resource savings control strategy (e.g., relaxing temperature constraints, turning off certain equipment, changing temperature setpoints, changing other settings), etc.).
While Davis teaches acquiring asset data, predicting baselines, and determining recommendations, Davis does not appear to explicitly teach the use of a machine learning model. However, Davis in view of the analogous art of Ingram (i.e. business recommendations) does teach the entirety of the limitation: (Ingram, [98]; the artificial intelligence system 604 may leverage the machine learned models (e.g., prediction models and/or classification models) to make predictions regarding media asset outcomes with respect to media asset genome data, demographic data, interaction data, digital personas, digital villages, financial data, health data, traffic data, identity management data, customer data, digital anthropology data, and the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514. For example, the client algorithms 502 may implement classifiers, clustering, pattern recognition, reinforcement learning, attribution, natural language processing and natural language understanding, segmentation, prediction, particle swarm optimization, recommender super learning, and the like. In embodiments, each of the client algorithms 502 trains a local version of a model, where each local version is initially parameterized in the same manner…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
While Davis teaches acquiring asset data, predicting baselines, and determining recommendations, Davis does not appear to explicitly teach the use of a machine learning model. However, Davis in view of the analogous art of Ingram (i.e. business recommendations) does teach the entirety of the limitation: (Ingram, [98]; the artificial intelligence system 604 may leverage the machine learned models (e.g., prediction models and/or classification models) to make predictions regarding media asset outcomes with respect to media asset genome data, demographic data, interaction data, digital personas, digital villages, financial data, health data, traffic data, identity management data, customer data, digital anthropology data, and the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514. For example, the client algorithms 502 may implement classifiers, clustering, pattern recognition, reinforcement learning, attribution, natural language processing and natural language understanding, segmentation, prediction, particle swarm optimization, recommender super learning, and the like. In embodiments, each of the client algorithms 502 trains a local version of a model, where each local version is initially parameterized in the same manner…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
Claim(s) 6 and 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Davis et al. (US 20230148149 A1) in view of Koch et al. (US 20110137574 A1), Ingram et al. (US 20220114616 A1) and Santoso et al. (US 20240288839 A1).
Regarding Claim(s) 6, While Davis/Koch/Ingram teaches adjustment to assets and predictions, neither appears to explicitly teach the use of simulations. However ,Davis/Koch/Ingram in view of the analogous art of Santoso (i.e. resource allocation) does teach: The method of claim 1, further comprising: simulating an adjustment to the asset; (Santoso, [21]; simulate one or more operations of the asset using the second target value of the one or more second operational parameters; and provide, via a user interface, one or more recommended actions in response to a result associated with simulating the one or more operations).
predicting an outcome of the simulation using one or more additional machine learning models; and (Santoso, [21]; simulate one or more operations of the asset using the second target value of the one or more second operational parameters; and provide, via a user interface, one or more recommended actions in response to a result associated with simulating the one or more operations).
generating one or more instructions to adjust the asset based on a comparison of the predicted outcome and a threshold value. (Santoso, [04]; simulating one or more operations of the asset using the second target value of the one or more second operational parameters; and providing, via a user interface, one or more recommended actions in response to a result associated with simulating the one or more operations).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis/Koch/Ingram including adjustment to assets and predictions with the teachings of Santoso including simulations in order to capture operational variation in modeling (Santoso, [115]; Aspects of the present disclosure may support building and/or training a data model(s) 142 using machine learning techniques that are able to capture operational variations contained in the dataset without human intervention. For example, Aspects of the present disclosure support building a data model(s) 142 using process data associated with operational variations (e.g., normal, faulty) associated with devices 122 and the system 100. In some cases, the operational variations may be identified based on information provided by domain experts (e.g., experienced operators of the system).
Regarding Claim(s) 8, Davis/Koch/Ingram teaches: determining, based on a comparison of the… resource value and the predicted target resource value, a corrective action; and (Davis, [139]; Still referring to FIGS. 11 and 12, the user can select resource(s) 1106 using check box 1104 for which resource(s) in static baseline or dynamic baseline they want to compare the actual resource consumption. In case the user wishes to not compare consumption against dynamic baseline 906, then user can uncheck all resources 1106 via check boxes 1104 and Davis, [150]; The interfaces described above may also include selectable options to alter operation of building equipment so as to increase or decrease resource consumption. For example, a user may be able to select an option to implement a resource savings control strategy (e.g., relaxing temperature constraints, turning off certain equipment, changing temperature setpoints, changing other settings), etc. Building equipment may operate differently in response to selection of such an option, for example due to different control settings selected by the processing circuit 602 or other circuitry of BMS 600 in response to user input. The teachings herein thereby result in physical changes in equipment operation driven by the features of the various interfaces, processes, systems, etc. disclosed herein).
causing an adjustment to the asset based on the corrective action. (Davis, [150]; The interfaces described above may also include selectable options to alter operation of building equipment so as to increase or decrease resource consumption. For example, a user may be able to select an option to implement a resource savings control strategy (e.g., relaxing temperature constraints, turning off certain equipment, changing temperature setpoints, changing other settings), etc. Building equipment may operate differently in response to selection of such an option, for example due to different control settings selected by the processing circuit 602 or other circuitry of BMS 600 in response to user input. The teachings herein thereby result in physical changes in equipment operation driven by the features of the various interfaces, processes, systems, etc. disclosed herein).
While Davis/Koch/Ingram teach comparing resource values to a baseline, neither appears to explicitly teach the use of a future resource value. However, Davis/Koch/Ingram/Santoso does teach: The method of claim 1, further comprising: predicting, based on one or more additional machine learning models and the detected actual resource values, a future resource value associated with the asset; (Santoso, [195]; In some examples, the target prediction and recommendation module 397 may provide predictions of the simulated asset status/asset operations and recommendations associated with the target asset/selected asset. In an example, the target prediction and recommendation module 397 may provide the predictions associated with the target asset/selected asset via the user interface 391 or another graphical user interface).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis/Koch/Ingram including comparing resource values to a baseline, with the teachings of Santoso including future resource values in order to assist in predictions and recommendations (Santoso, [195]; In some examples, the target prediction and recommendation module 397 may provide predictions of the simulated asset status/asset operations and recommendations associated with the target asset/selected asset. In an example, the target prediction and recommendation module 397 may provide the predictions associated with the target asset/selected asset via the user interface 391 or another graphical user interface).
Claim(s) 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Davis et al. (US 20230148149 A1) in view of Koch et al. (US 20110137574 A1),Ingram et al. (US 20220114616 A1) and Smaargard et al. (US 20240430361 A1).
Regarding Claim(s) 12, While Davis/Koch/Ingram teaches determining baselines for target resources but neither appear to teach masking data. However, Davis/Koch/Ingram in view of the analogous art of Smaargard (i.e. business modeling) does teach: The method of claim 1, further comprising: masking a portion of the asset data, wherein the target resource baseline value is predicted based on the asset data excluding the masked portion of the asset data. (Smaargard, [27]; In certain examples, it may be beneficial to mask, meaning remove certain words, phrases, topics, actions, and/or phrases to improve the training data and ultimately the compliance model's ability to recognize triggering phrases).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis/Koch/Ingram including determining baselines for target resources with the teachings of Smaargard including masking and removing data from analysis in order to improve model training and recognize relevant data. (Smaargard, [27]; In certain examples, it may be beneficial to mask, meaning remove certain words, phrases, topics, actions, and/or phrases to improve the training data and ultimately the compliance model's ability to recognize triggering phrases).
Claim(s) 16, 24, and 26 is/are rejected under 35 U.S.C. 103 as being unpatentable over Davis et al. (US 20230148149 A1) in view of Koch et al. (US 20110137574 A1), Ingram et al. (US 20220114616 A1) and Copperthite et al. (US 20240201639 A1).
Regarding Claim(s) 16, While Davis/Koch/Ingram teach target baselines for resources neither appears to teach a minimum/maximum value. However, Davis/Koch/Ingram in view of the analogous art of Copperthite (i.e. resource allocation) does teach: The method of claim 15, wherein the aggregated respective predicted target resource baseline values comprise a minimum value or a maximum value of the respective target resource baseline values over a period of time. (Copperthite, [167]; The term “operating environment” may refer to electronically managed data representing any physical characteristic related to an asset and/or a plurality of assets. In some embodiments, the operating environment may refer to the resources available in and around the asset, such as power capabilities, fuel sources, maximum flow of fuel, types and sizes of infrastructure equipment and other parameters related to the operation of a particular asset).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis/Koch/Ingram including target baselines for resources with the teachings of Copperthite including in order to have an exact maximum of resource parameters for modeling purposes (Copperthite, [167]; The term “operating environment” may refer to electronically managed data representing any physical characteristic related to an asset and/or a plurality of assets. In some embodiments, the operating environment may refer to the resources available in and around the asset, such as power capabilities, fuel sources, maximum flow of fuel, types and sizes of infrastructure equipment and other parameters related to the operation of a particular asset).
Regarding Claim(s) 24, Davis/Koch/Ingram teaches: The method of claim 22, wherein the machine learning model is trained on production data associated with the asset, and (Ingram, [111]; The intelligence system 110 may include a computer vision system 608 for providing computer vision services, whereby the vision services may, for example, classify uploaded images and/or videos into one or more categories and/or extract objects, faces, and text from images or videos. In embodiments, the computer vision system 608 may receive a media asset, such as a video or an image, and may extract a set of media asset features of the media asset and may classify one or more aspects of the media asset. For instance, the computer vision system 608 may classify the type of scene depicted (e.g., beach front, in-studio, mountains, etc.), the subjects and/or objects depicted (e.g., models, landscapes, gym equipment, etc.), clothing types worn by models (e.g., winter clothing, beach clothing, revealing clothing, etc.), and/or other aspects of the media asset. In embodiments, the computer vision system 608 may leverage one or more machine-learned image classification models that are trained to classify images (or time-sequences images, such as a video) and/or aspects of the images (or time-sequences of video). In embodiments, the computer vision system 608 may output classifications to another system, such as the intelligence system 604, the machine-learning system 602, the analytics system 610, the recommendation system 606, or the like). Examiner interprets the asset type such as image/video/etc. as production data as it indicates how the asset was produced.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
While Davis/Koch/Ingram teach models and training neither appears to explicitly teach a model-driven architecture. However, Davis/Koch/Ingram in view of the analogous art of Copperthite (i.e. resource allocation) does teach: wherein the production data is structured by a model driven architecture. (Copperthite, [268]; The IoT platform 1125 is a model-driven architecture. Thus, in certain embodiments, the extensible object model 1250 communicates with each layer 1205-1230 to contextualize site data of the enterprise 1160a-1160n using an extensible object model (or “asset model”) and knowledge graphs 251 where the equipment (e.g., edge devices 1161a-1161n) and processes of the enterprise 1160a-1160n are modeled).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis/Koch/Ingram including models and training with the teachings of Copperthite including model-driven architecture in order to contextualize data. (Copperthite, [268]; The IoT platform 1125 is a model-driven architecture. Thus, in certain embodiments, the extensible object model 1250 communicates with each layer 1205-1230 to contextualize site data of the enterprise 1160a-1160n using an extensible object model (or “asset model”) and knowledge graphs 251 where the equipment (e.g., edge devices 1161a-1161n) and processes of the enterprise 1160a-1160n are modeled).
Regarding Claim(s) 26, Davis/Koch/Ingram teaches:. The method of claim 25, wherein the machine learning model is trained on the facility data, and (Ingram, [80]; an organization may have different data centers in different parts of a country, whereby the data stored in each data center corresponds to a different geographic location. In this scenario, each respective data center may be a respective host 500 that stores the data corresponding to its respective geographic region. In embodiments, distributing the client algorithms 502 to the different data hosts 500 allows the digital anthropology system 108 to distribute the training of the client algorithm across different data sets, with potentially different owners of the disparate data sets and Ingram, [104]; competitors for a product or service being advertised in a media asset based on competitor-related data (e.g., retail locations, products available, pricing, and the like). According to some embodiments, the artificial intelligence system 604 may leverage these models to determine merchandise or services to make available at a retail location that may be based at least in part on data related to competitors (e.g., retail location distance from a competitor retail location, products available at competitor retail location, or the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis including acquiring asset data, predicting baselines, and determining recommendations. with the teachings of Ingram including machine learning models in order to generate more accurate results (Ingram, [83]; In embodiments, the client algorithms 502 may implement one or more machine learning and/or artificial intelligence processes and may leverage one or more machine learned models to provide a result requested by the master algorithm 514…. The client algorithm 502 may then execute on the training data set to parameterize the local version of the model. In some of these embodiments, the client algorithm 502 may also receive a validation set, whereby the validation set is used by the client algorithm 502 to validate/error check the accuracy of the local model during or after training).
While Davis/Koch/Ingram teach models and training neither appears to explicitly teach a model-driven architecture. However, Davis/Koch/Ingram in view of the analogous art of Copperthite (i.e. resource allocation) does teach: wherein the production data is structured by a model driven architecture. (Copperthite, [268]; The IoT platform 1125 is a model-driven architecture. Thus, in certain embodiments, the extensible object model 1250 communicates with each layer 1205-1230 to contextualize site data of the enterprise 1160a-1160n using an extensible object model (or “asset model”) and knowledge graphs 251 where the equipment (e.g., edge devices 1161a-1161n) and processes of the enterprise 1160a-1160n are modeled).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis/Koch/Ingram including models and training with the teachings of Copperthite including model-driven architecture in order to contextualize data. (Copperthite, [268]; The IoT platform 1125 is a model-driven architecture. Thus, in certain embodiments, the extensible object model 1250 communicates with each layer 1205-1230 to contextualize site data of the enterprise 1160a-1160n using an extensible object model (or “asset model”) and knowledge graphs 251 where the equipment (e.g., edge devices 1161a-1161n) and processes of the enterprise 1160a-1160n are modeled).
Claim(s) 23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Davis et al. (US 20230148149 A1) in view of Koch et al. (US 20110137574 A1), Ingram et al. (US 20220114616 A1) and Zhang et al. (CN115618270B).
Regarding Claim(s) 23, While Davis/Koch/Ingram teach generating recommendation neither appears to teach: The method of claim 22, further comprising, wherein the recommendation is generated as a natural language response to the query by one or more omni-modal models. However, Davis/Koch/Ingram in view of the analogous art of Zhang (i.e. data modeling): (Zhang, [pg. 1, pg. 3]; The intent recognition model generates and executes a series of behaviors and strategies by determining the intent corresponding to the user input to achieve interaction with the user. But in real life, we often need to use multiple modal information (such as natural language, video and audio signals, etc.) and Zhang, [pg. 4, para. 4]; In this embodiment, a three-modal pre-training model (Omni-Perception pre-Trainer, OPT) is used to encode the data to be recognized to obtain a representation sequence of each modality data, and the encoded features are used as node features.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the disclosed invention to have combined the teachings of Davis/Koch/Ingram teach generating recommendation with the teachings of Zhang including omni-model models in order to obtain a representation of modal data including word segmentation processing, encoding words to obtain first encoding data, etc. (Zhang, [pg. 4, para. 5]; data to be recognized is encoded to obtain the representation sequence of each modal data, including: performing word segmentation processing on the text data to obtain multiple words, encoding the words to obtain the first encoding information; performing image feature processing on the image data extracting to obtain a plurality of image regions, encoding the image regions to obtain the second encoding information; performing audio feature extraction on the audio data to obtain a plurality of audio segments, encoding the audio segments to obtain the third encoding information; encoding the first information, the second coded information and the third coded information are used as the input of the three-modal pre-training model to obtain the text sequence, picture sequence and audio sequence respectively corresponding to the text data, picture data and audio data).
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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JEREMY L GUNN whose telephone number is (571)270-1728. The examiner can normally be reached Monday - Friday 6:30-4:30.
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, Jerry O'Connor can be reached on (571) 272-6787. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JEREMY L GUNN/ Examiner, Art Unit 3624
