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 .
Claim Objections
1. Claims 5, 12, and 18 are objected to because of the following informalities:
Claim 5, 12, 18: in lines 3 and 14 of claim 5, “the set of widget” should instead be “the set of widgets”; similar correction should be made for claims 12 and 18. Additionally, in line 6 of claim 5, “and wherein the indicator additional data” should instead be “and wherein the indicator for additional data”; similar correction should be made for claims 12 and 18.
Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
2. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claims 1, 8, and 15, “A computer-implemented method”, “A system, and “A non-transitory computer-readable medium” are recited, which are each directed to one of the four statutory categories of invention (process, machine, article of manufacture; Step 1: YES). However, the claims limitations, under their broadest reasonable interpretation, recite mental processes which fall into the category of abstract idea (Step 2A Prong 1: YES).
The following limitations, under their broadest reasonable interpretation, recite mental processes:
receiving, by a dashboard service engine using at least one processor, the natural language command …, wherein the natural language command comprises a request of generating the dashboard for an outcome: a person receives a command from a user
retrieving, …, dashboard information associated with the outcome, wherein the dashboard information comprises a previous dashboard associated with the outcome: a person searches and reads information about a dashboard associated with a particular outcome (e.g. layouts)
obtaining, …, user information associated with the user device, wherein the user information comprises a previous user preference of generating the previous dashboard: a person searches and reads information about user preferences (e.g. preference about layouts)
determining, …, one or more available tools for generating a set of widgets associated with the dashboard: a person looks at available tools and selects tools which are relevant for a particular set of widgets.
generating…using the one or more determined tools…and a prompt, the set of widgets associated with the dashboard, wherein the prompt is associated with the dashboard information and the user information: a person writes down widget information based on using the tools and based on user and dashboard information
Claims 1, 8, and 15 do not recite any additional elements which integrate the judicial exception into a practical application (Step 2A Prong 2: NO). The additional limitations are “A system…comprising: one or more memories; at least one processor each coupled to at least one of the memories and configured to perform operations comprising” (claim 8), “A non-transitory computer-readable medium…” (claim 15), “receiving, by a dashboard service engine using at least one processor”, “retrieving, from a knowledge database by the dashboard service engine”, “obtaining, from a user context database by the dashboard service engine”, “determining, at a tool database by the dashboard service engine”, “generating, by the dashboard service engine using…a large language model (LLM)”, and “generating, by the dashboard service engine, the dashboard using the set of widgets”. These limitations are recited at a high level of generality and amount to mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claims as a whole, mere instructions to implement the judicial exception using a generic computer do not integrate the judicial exception into a practical application as they do not impose any meaningful limits on practicing the abstract idea. Therefore, claims 1, 8, and 15 are directed to abstract ideas.
Claims 1, 8, and 15 do not contain additional elements which amount to significantly more than the judicial exception (Step 2B: NO). As discussed above, the only additional limitations are mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claims as a whole, mere instructions to implement the judicial exception using a generic computer do not amount to significantly more than the judicial exception as they do not provide an inventive concept. Therefore, claims 1, 8, and 15 are not patent eligible.
Regarding claims 2-7, 9-14, and 16-20, “The computer-implemented method”, “The system, and “The non-transitory computer-readable medium” are recited, which are each directed to one of the four statutory categories of invention (process, machine, article of manufacture; Step 1: YES). However, the claims limitations, under their broadest reasonable interpretation, recite further mental processes which fall into the category of abstract idea (Step 2A Prong 1: YES).
The following limitations, under their broadest reasonable interpretation, recite mental processes:
Claims 2, 9, and 16:
obtaining,… a user feedback, wherein the user feedback comprises a correction or an update of the set of widgets; and refining, by the dashboard service engine, the set of widgets based on combining the user feedback into the set of widgets: a person listens to user feedback about a widget (e.g. correct a particular aspect of the widget), and a person uses the feedback to correct the widget
Claims 2, 9, and 16 contain the addition limitation “from the user device by the dashboard service engine,”, which amounts to mere instructions to implement the judicial exception using a generic computer.
Claims 3 and 10:
Claims 3 and 10 contain the additional limitation “wherein the user feedback is obtained based on using a user interface configured to real-time monitor the dashboard using a second natural language command” which amounts to mere instructions to implement the judicial exception using a generic computer.
Claims 4, 11, and 17:
…configured to set up an action, in a third natural language command, for refining the set of widgets, wherein the action occurs based on a metric associated with the action meeting a condition: a person performs an action to update a widget (e.g. update particular data displayed) based on a metric meeting a condition (e.g., a particular amount of time has passed)
Claims 4, 11, and 17 contain the additional limitation “wherein the dashboard comprises an actionable dashboard”, which amounts to mere instructions to implement the judicial exception using a generic computer.
Claims 5, 12, and 18:
receiving, …, a user question associated with the set of widget;determining, …, a user intent from the user question, wherein the user intent comprises an indicator for additional data or an indicator for troubleshooting, and wherein the indicator additional data or the indicator for troubleshooting is associated with the set of widgets; in response to determining the user intent: retrieving, …, the additional data associated with the user intent; performing, …, the troubleshooting associated with the user intent; and thereby, obtaining a troubleshooting result; and generating, …, a response to the user question associated with the set of widget: a person can read a user question, determine an intent, and either provide the user with additional information or troubleshoot their problems
Claims 5, 12, and 18 contain the additional limitations “by a dashboard widget service engine from the user device…by a backend service…from a database by a structured data agent…by a troubleshooting agent…by the dashboard widget service engine for the user device”, which amounts to mere instructions to implement the judicial exception using a generic computer.
Claims 6, 13, and 19:
generating, …, a set of widget recipes associated with the set of widgets, wherein a widget recipe of the set of widget recipes comprises an executable instruction for reproducing a widget of the set of widgets using the natural language command; and storing, …, the set of widget recipes associated with the set of widgets: a person writes down instructions for reproducing a widget and stores in on a piece of paper
Claims 6, 13, and 19 contain the additional limitation “at the dashboard service engine…into a recipe database by the dashboard service engine”, which amounts to mere instructions to implement the judicial exception using a generic computer.
Claims 7, 14, and 20:
receiving, …, a notification of an availability of new data associated with the set of widgets; retrieving, …, a set of widget recipes; executing, …, the set of widget recipes, and thereby obtaining the new data associated with the set of widgets; and refining, …, the set of widgets based on combining the new data into the set of widgets: a person receives notice of new data, looks at the widget recipes, and uses the widget recipes to update the widgets with the new data
Claims 7, 14, and 20 contain the additional limitation “from the user device by the dashboard service engine…from a recipe database by the dashboard service engine…by the dashboard service engine…by the dashboard service engine”, which amounts to mere instructions to implement the judicial exception using a generic computer.
Claims 2-7, 9-14, and 16-20 do not recite any additional elements which integrate the judicial exception into a practical application (Step 2A Prong 2: NO). As discussed above, the only additional limitations are mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claims as a whole, mere instructions to implement the judicial exception using a generic computer do not integrate the judicial exception into a practical application as they do not impose any meaningful limits on practicing the abstract idea. Therefore, claims 2-7, 9-14, and 16-20 are directed to abstract ideas.
Claims 2-7, 9-14, and 16-20 do not contain additional elements which amount to significantly more than the judicial exception (Step 2B: NO). As discussed above, the only additional limitations are mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claims as a whole, mere instructions to implement the judicial exception using a generic computer do not amount to significantly more than the judicial exception as they do not provide an inventive concept. Therefore, claims 2-7, 9-14, and 16-20 are not patent eligible.
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 (i.e., changing from AIA to pre-AIA ) 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.
3. Claims 1-3, 6, 8-10, 13, 15-16, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Crabtree et al. (US 2025/0355645 A1, hereinafter Crabtree) in view of Castillo & Azmoon (US 2025/0028759 A1, hereinafter Castillo).
Regarding claim 1, Crabtree discloses A computer-implemented method for generating a dashboard using a natural language command (Abstract), comprising: receiving, by a dashboard service engine using at least one processor (Fig. 12, 21; para. 0047 “FIG. 12 illustrates an exemplary computing environment on which an embodiment described herein may be implemented, in full or in part.”), the natural language command from a user device (user inputs via chatbot interaction in system 200: para. 0057 “FIG. 2 is a block diagram illustrating an exemplary aspect of dynamic application experience generation platform, a design management system 200…”; para. 0058 “At the design portal, a user (e.g., website/application owner/designer) can interact with design library 204 to browse and view various design elements. This may be performed manually via a wizard 201 or via interrogation using, for example, chatbot 202 prompts.”), wherein the natural language command comprises a request of generating the dashboard for an outcome (para. 0041 “According to an aspect of an embodiment, an owner/designer can select from a set of prospective categories or sites they like. For example, the set of categories/sites/templates/elements may be implemented as a visual workboard for design elements which allows users to browse and select design elements that appeal to them or their website/application use case. This could be tagged for things like “design”, “color”, “layout”, “function”, “imagery”, “workflow”, etc. This may be performed manually (e.g., via a wizard) or via interrogation (i.e., chatbot prompts) to get sufficient user clarity through a series of interactions. The clarity of the user specification may be scored or otherwise analyzed to determine if there is sufficient clarity for generative AI prompt generation/engineering and feedback loop purposes. According to an aspect, a clarity score may be determined based on how clear and specific the user specification is.”); retrieving from a knowledge database by the dashboard service engine, dashboard information associated with the outcome, wherein the dashboard information comprises a previous dashboard associated with the outcome (search performed for stored previous/in-progress dashboards: para. 0124-0125 “A search may be performed within a specific category 404-416 of design elements/templates. [0125] A shown, workboard 400 may display various templates and design elements 405-416. Additionally, workboard 400 can display a designer's previous or in-progress designs 404 allowing the designer to use previous designs as a starting point for new or updated content”; para. 0044 “In some implementations, an AI system may be used to catalogue and suggest historical templatized interfaces and concepts that are part of an ongoing “generative content” catalogue which may be stored in design catalogue database 136.”; para. 0058 “For example, wizard or chatbot may obtain from the user a type of website/application they want to create and a set of templates associated with the type may be retrieved from design catalogue database 136 and displayed to the user via design library 204.”; see Fig. 1, 136); obtaining, from a user context database by the dashboard service engine (preference database: para. 0060 “The responses to wizard/chatbot, the design elements and/or templates selected by the user, the users interaction with the workboard (e.g., search queries, mouse clicks, hover time, etc.), and any available user preferences (e.g., retrieved from a preference database or submitted directly by the user) may be included in a user specification…”), user information associated with the user device, wherein the user information comprises a previous user preference of generating the previous dashboard (para. 0060 “The responses to wizard/chatbot, the design elements and/or templates selected by the user, the users interaction with the workboard (e.g., search queries, mouse clicks, hover time, etc.), and any available user preferences (e.g., retrieved from a preference database or submitted directly by the user) may be included in a user specification…”; para. 0057 “In some implementations, a user can submit a user preference configuration document which may be a file or set of files that explicitly defines the preferences, settings, and customization options for a particular user or user segment. This document allows designers to tailor the generated UX/UI content to specific needs, interests, and behaviors of different users. A user preference configuration document may comprise the following types of information: user profile data, content preferences, layout and design preferences, interaction preferences, personalization settings, accessibility settings, device and platform preferences, and/or data privacy and security settings.”); … generating, by the dashboard service engine using… a large language model (LLM) (para. 0062 “Agent selector 301 may be configured to parse the user specification and select one or more appropriate generative AI systems (also referred to herein as agents) to generate the UX/UI content described by the user specification. The selection of the one or more agents may be based on various factors including, but not limited to, the user defined requirements (e.g., target audience, design goals, functionality, platform/device, etc.), generative AI (gen AI) system compatibility (e.g., using an LLM to generate text, diffusion models to generate images or sound, etc.), model performance (e.g., factors such as the quality of designs, the range of design options, and the ability to customize to meet the user's needs), model integration (e.g., models which can easily be integrated into existing workflows and tools), cost and licensing, and user/expert feedback (e.g., gathered feedback from stakeholders and iterate on design).”), and a prompt (para. 0065 “The one or more selected agents 303a, 303b, and 303n may be fed as inputs the engineered prompt to generate UX/UI content based on the user specification”), the set of widgets associated with the dashboard (para. 0065 “The one or more selected agents 303a, 303b, and 303n may be fed as inputs the engineered prompt to generate UX/UI content based on the user specification”; para. 0133 “As a last step 605, the generative AI system outputs generated UX/UI content or workflow based on the prompt. UX/UI content refers to the textual and visual elements that make up the user interface and user experience of a digital product, such as a website, mobile app, or software application. This content includes text, images, videos, buttons, icons, menus, forms, and other interactive elements that users engage with to interact with the product…”), wherein the prompt is associated with the dashboard information and the user information (user specification for generating prompt includes user information (preferences): para. 0060 “The responses to wizard/chatbot, the design elements and/or templates selected by the user, the users interaction with the workboard (e.g., search queries, mouse clicks, hover time, etc.), and any available user preferences (e.g., retrieved from a preference database or submitted directly by the user) may be included in a user specification.”; user specification for generating prompt includes dashboard information: para. 0129 “If possible, the user specification can include examples 504 of the desired output to give to the generative AI systems a clear reference point. For example, a user selected template or design elements from the catalogue of templates/design elements can be used as an example for the generative AI systems.”); and generating, by the dashboard service engine, the dashboard using the set of widgets (para. 0065 “The one or more selected agents 303a, 303b, and 303n may be fed as inputs the engineered prompt to generate UX/UI content based on the user specification”; para. 0133 “As a last step 605, the generative AI system outputs generated UX/UI content or workflow based on the prompt. UX/UI content refers to the textual and visual elements that make up the user interface and user experience of a digital product, such as a website, mobile app, or software application. This content includes text, images, videos, buttons, icons, menus, forms, and other interactive elements that users engage with to interact with the product…”).
Crabtree does not specifically disclose determining, at a tool database by the dashboard service engine, one or more available tools for generating a set of widgets associated with the dashboard; [generating, by the dashboard service engine] using the determined one or more available tools…[the set of widgets associated with the dashboard].
Castillo teaches determining, at a tool database by the dashboard service engine, one or more available tools for generating a set of widgets associated with the dashboard (para. 0178 “In some embodiments, the operations of context mediator 604 may be governed by a finite set of pre-defined skills. These skills may include techniques for interacting with databases, third-party tools, different types of users, and for different types of applications. Thus, the operations of context mediator 604 may involve, for requests and LLM responses, first determining the appropriate skill to invoke based on context, and then invoking that skill.”; skills stored in 604: para. 0180 “The skills may be specific software modules or capabilities built into context mediator 604 that are configured to determine the intent of a request, based on the request, application information 606A, user information 606B, and/or other information 606C.”); [generating, by the dashboard service engine] using the determined one or more available tools…[the set of widgets associated with the dashboard] (para. 0181 “Once the skill is identified, it can be used to assist with various types of user interaction. As needed, the skill may generate skill-specific LLM prompts and transmit these prompts to LLM service 608.”; para. 0190 “As an example, skill 704A may relate to generating charts in the form of user interface components by way of LLM prompts…”).
Crabtree and Castillo are considered to be analogous to the claimed invention as
they both are in the same field of natural language processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Crabtree to incorporate the teachings of Castillo in order to determine at a tool database by the dashboard service engine, one or more available tools for generating a set of widgets associated with the dashboard, and to generate the set of widgets using the determined available tools. Doing so would be beneficial, as these tools/skills would aid the LLM in generating the user interface components, such as by generating chart, application specific querying/interactions, necessary API calls, etc. (Castillo, para. 0180, para. 0190)
Regarding claim 2, Crabtree in view of Castillo discloses obtaining, from the user device, by the dashboard service engine, a user feedback (Crabtree, para. 0136 “As a last step 706 the platform 100 collects a plurality of feedback to evaluate the generative AI systems output. Feedback may be collected from application users. Feedback may be collected from experts such as UX/UI designers or experts related to the category of application/website (e.g., a fitness application may utilize fitness experts such as personal trainers and coaches to provide feedback on generated fitness application content). Feedback may be collected from user behavior and/or interactions with the generated content.”), wherein the user feedback comprises a correction or an update of the set of widgets (para. 0136 “The collected feedback information may be used to improve prompt engineering functionality. For example, if the generated output does not quite capture the idea the designer had in mind when making the user specification, then feedback may be used to improve or iterate on the prompts to better capture the designer's intent or vision.”); and refining, by the dashboard service engine, the set of widgets based on combining the user feedback into the set of widgets (Fig. 7, feedback loop from 706 back to steps 703-705, leading to improved output UX/UI content at step 705; para. 0136 “The collected feedback information may be used to improve prompt engineering functionality. For example, if the generated output does not quite capture the idea the designer had in mind when making the user specification, then feedback may be used to improve or iterate on the prompts to better capture the designer's intent or vision.”; para. 0133 “As a last step 605, the generative AI system outputs generated UX/UI content or workflow based on the prompt. UX/UI content refers to the textual and visual elements that make up the user interface and user experience of a digital product, such as a website, mobile app, or software application. This content includes text, images, videos, buttons, icons, menus, forms, and other interactive elements that users engage with to interact with the product…”).
Regarding claim 3, Crabtree in view of Castillo discloses wherein the user feedback is obtained based on using a user interface configured to real-time monitor the dashboard using a second natural language command (Crabtree, para. 0143 “FIG. 10 is a flow diagram illustrating an exemplary method for providing dynamic UX/UI modification in real-time based on a user request, according to an embodiment. According to the embodiment, the process begins at step 1001 when an application user interacts with a chatbot to make an design element request or a request for information. At step 1002 the application user's preferences may be retrieved from a user profile which may be stored in a preference database. At step 1003, an AI agent (i.e., generative AI model) uses the user request data to dynamically modify or navigate the application in a way that is tailored to the user's needs and preferences.”).
Regarding claim 6, Crabtree in view of Castillo discloses generating, at the dashboard service engine, a set of widget recipes associated with the set of widgets, wherein a widget recipe of the set of widget recipes comprises an executable instruction for reproducing a widget of the set of widgets using the natural language command (Crabtree, para. 0070 “In an embodiment, dynamic application experience generation platform 100 may utilize a domain-specific language (DSL) to enable designers to define cross-platform experiences at a high level of abstraction. The DSL provides a structured, purposeful syntax for specifying experiential elements, content elements, design elements, cross-platform targeting, AI integration, and analytics and optimization.”; para. 0086 “Design elements in the DSL provide primitives for common UI components and design patterns, such as layouts, navigation, input controls, and information architecture. Designers can also specify branding, visual style, and accessibility requirements. For example, a designer could define a consistent header layout with a logo, navigation menu, and search bar. The DSL syntax for this might look like: [0087] design: [0088] header: [0089] layout: horizontal [0090] components: [0091] logo: image [0092] navigation: menu [0093] search: input [0094] branding: [0095] color: #001F3F [0096] font_family: Helvetica”); and storing, into a recipe database by the dashboard service engine, the set of widget recipes associated with the set of widgets (para. 0043 “The databases for storing design elements and templates 136 may also include a repository for storing domain-specific language (DSL) code. This repository could contain reusable DSL code snippets, templates, and libraries that designers can leverage when defining new experiences. The repository could also include version control and collaboration features, allowing multiple designers to work on the same DSL code and track changes over time.”).
Regarding claim 8, claim 8 is a system claim with limitations similar to those recited in method claim 1, and is thus rejected under similar rationale.
Additionally, Crabtree disclose A system for generating a dashboard using a natural language command (Fig. 12), comprising: one or more memories (Fig. 12, 30); at least one processor each coupled to at least one of the memories (Fig. 12, 20, connected via bus 11) and configured to perform operations comprising (para. 0007).
Regarding claim 9, claim 9 is rejected for analogous reasons to claim 2.
Regarding claim 10, claim 10 is rejected for analogous reasons to claim 3.
Regarding claim 13, claim 13 is rejected for analogous reasons to claim 6.
Regarding claim 15, claim 15 is a non-transitory computer readable medium claim with limitations similar to those recited in method claim 1, and thus is rejected under similar rationale.
Additionally, Crabtree discloses A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one processor, cause the at least one processor to perform operations comprising (para. 0010).
Regarding claim 16, claim 16 is rejected for analogous reasons to claim 2.
Regarding claim 19, claim 19 is rejected for analogous reasons to claim 6.
4. Claims 4, 7, 11, 14, 17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Crabtree in view of Castillo, and further in view of Johnson & Redpath (US 2012/0023200 A1, hereinafter Johnson).
Regarding claim 4, Crabtree in view of Castillo discloses wherein the dashboard comprises an actionable dashboard configured to set up an action, in a third natural language command, for refining the set of widgets… (Crabtree, para. 0136 “As a last step 706 the platform 100 collects a plurality of feedback to evaluate the generative AI systems output. Feedback may be collected from application users. Feedback may be collected from experts such as UX/UI designers or experts related to the category of application/website (e.g., a fitness application may utilize fitness experts such as personal trainers and coaches to provide feedback on generated fitness application content). Feedback may be collected from user behavior and/or interactions with the generated content.”; para. 0136 “The collected feedback information may be used to improve prompt engineering functionality. For example, if the generated output does not quite capture the idea the designer had in mind when making the user specification, then feedback may be used to improve or iterate on the prompts to better capture the designer's intent or vision.”; Fig. 7, feedback loop from 706 back to steps 703-705, leading to improved output UX/UI content at step 705; para. 0136).
Crabtree in view of Castillo does not specifically disclose wherein the action occurs based on a metric associated with the action meeting a condition.
Johnson teaches refining of a set of widgets based on an action, wherein the action occurs based on a metric associated with the action meeting a condition (updating of widgets based on timer meeting a threshold amount of time: para. 0064 “At block 408, the aggregated widget request processing module 214 determines that an aggregated data update event has occurred in association with the data query identified by the data identifier "DATA_1." For purposes of the present example, it is the registration of the widget_1 302 with a periodic interval of 5 minutes that triggers the aggregated data update event at block 408… In response to the aggregated data update event, the aggregated widget request processing module 214 initiates a query based upon the data query identified by the identifier "DATA_1," such as an AJAX query, to the server_1 106 to retrieve the requested data (line 4). In response to receiving the query, the server_1 106 responds with the data identified within the query (line 5).”; para. 0065 “At block 410, the aggregated widget request processing module 214 determines a distribution for the received data. …Within the present example, the aggregated widget request processing module 214 will identify that the widget_1 302 and the widget_2 304 are both registered to retrieve updates for the data identified by the data identifier "DATA_1." …”).
Crabtree, Castillo, and Johnson are considered to be analogous to the claimed invention as Crabtree and Castillo are in the same field of natural language processing and Johnson is in the same field of generating widgets. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Crabtree in view of Castillo to incorporate the teachings of Johnson in order to specifically refine the set of widgets based on an action, the action based on a metric associated with the action meeting a condition. Doing so would be beneficial, as this would ensure that visible widgets are provided with the most up-to-date information/data, while also reducing internal complexity of the widgets (Johnson, para. 0030).
Regarding claim 7, Crabtree in view of Castillo discloses retrieving, from a recipe database by the dashboard service engine, a set of widget recipes (para. 0043 “The databases for storing design elements and templates 136 may also include a repository for storing domain-specific language (DSL) code. This repository could contain reusable DSL code snippets, templates, and libraries that designers can leverage when defining new experiences. The repository could also include version control and collaboration features, allowing multiple designers to work on the same DSL code and track changes over time.”); executing, by the dashboard service engine, the set of widget recipes, … (para. 0132 “In an embodiment, the user specification may be defined using a domain-specific language (DSL) that allows designers to specify experiential elements, content elements, design elements, cross-platform targeting, AI integration, and analytics & optimization at a high level of abstraction. The DSL code is then parsed and interpreted by the design management system to generate the appropriate user specification data structure.”); and refining, by the dashboard service engine, the set of widgets…(Fig. 7, feedback loop from 706 back to steps 703-705, leading to improved output UX/UI content at step 705; para. 0136 “The collected feedback information may be used to improve prompt engineering functionality. For example, if the generated output does not quite capture the idea the designer had in mind when making the user specification, then feedback may be used to improve or iterate on the prompts to better capture the designer's intent or vision.”).
Crabtree in view of Castillo does not specifically disclose receiving, from the user device by the dashboard service engine, a notification of an availability of new data associated with the set of widgets…; …thereby obtaining the new data associated with the set of widgets; and [refining…the set of widgets] based on combining the new data into the set of widgets.
Johnson teaches receiving, from the user device by the dashboard service engine, a notification of an availability of new data associated with the set of widgets… (para. 0088 “Further, the determination of whether an aggregated data update event has occurred may further include comparing an aggregated data update event processing schedule with a timer, such as a timer associated with the timer/clock module 216, and determining that a match between one of the plurality of aggregated data update events and the timer has occurred.”); …thereby obtaining the new data associated with the set of widgets (para. 0064 “At block 408, the aggregated widget request processing module 214 determines that an aggregated data update event has occurred in association with the data query identified by the data identifier "DATA_1." For purposes of the present example, it is the registration of the widget_1 302 with a periodic interval of 5 minutes that triggers the aggregated data update event at block 408… In response to the aggregated data update event, the aggregated widget request processing module 214 initiates a query based upon the data query identified by the identifier "DATA_1," such as an AJAX query, to the server_1 106 to retrieve the requested data (line 4). In response to receiving the query, the server_1 106 responds with the data identified within the query (line 5).”; para. 0065 “At block 410, the aggregated widget request processing module 214 determines a distribution for the received data. …Within the present example, the aggregated widget request processing module 214 will identify that the widget_1 302 and the widget_2 304 are both registered to retrieve updates for the data identified by the data identifier "DATA_1." …”); and [refining…the set of widgets] based on combining the new data into the set of widgets (para. 0065 “… As such, the aggregated widget request processing module 214 distributes the data associated with the data identifier "DATA_1" to each of the widget_1 302 and the widget_2 304 (line 6 and line 7, respectively).”).
Crabtree, Castillo, and Johnson are considered to be analogous to the claimed invention as Crabtree and Castillo are in the same field of natural language processing and Johnson is in the same field of generating widgets. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Crabtree in view of Castillo to incorporate the teachings of Johnson in order to specifically receive a notification of an availability of new data associated with a set of widgets, to obtain the new data associated with the set of widgets, and to refine the set of widgets based on combining the new data into the set of widgets. Doing so would be beneficial, as this would ensure that visible widgets are provided with the most up-to-date information/data, while also reducing internal complexity of the widgets (Johnson, para. 0030).
Regarding claim 11, claim 11 is rejected for analogous reasons to claim 4.
Regarding claim 14, claim 14 is rejected for analogous reasons to claim 7.
Regarding claim 17, claim 17 is rejected for analogous reasons to claim 4.
Regarding claim 20, claim 20 is rejected for analogous reasons to claim 7.
5. Claims 5, 12, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Crabtree in view of Castillo, and further in view of Alemeida et al. (US 2022/0036424 A1, hereinafter Almeida).
Regarding claim 5, Crabtree in view of Castillo does not specifically disclose receiving, by a dashboard widget service engine from the user device, a user question associated with the set of widget;determining, by a backend service, a user intent from the user question, wherein the user intent comprises an indicator for additional data or an indicator for troubleshooting, and wherein the indicator additional data or the indicator for troubleshooting is associated with the set of widgets;in response to determining the user intent:retrieving, from a database by a structured data agent, the additional data associated with the user intent;performing, by a troubleshooting agent, the troubleshooting associated with the user intent; and thereby, obtaining a troubleshooting result; andgenerating, by the dashboard widget service engine for the user device, a response to the user question associated with the set of widget.
Almeida teaches receiving, by a dashboard widget service engine from the user device, a user question associated with the set of widget (para. 0058 “A communication channel receives the communication from the user at step 522. This communication is converted to data format via a NLP at step 502…”; e.g., Fig. 13, 1314); determining, by a backend service, a user intent from the user question, wherein the user intent comprises an indicator for additional data or an indicator for troubleshooting (first option taught: para. 0058 “At step 502, the NLP also deduces the intent and entities of the conversation. All of this information is sent to a fulfillment API, which communicates the data associated with the intent and entities to a knowledge engine at step 504. The knowledge engine then retrieves information that fulfills the intent at step 506.”; see Fig. 15, “System Server 1502” and “NLP 1522”; Fig. 13, 1314 contains user request for additional data (in this case, more information about viewing data in dashboards)), and wherein the indicator additional data or the indicator for troubleshooting is associated with the set of widgets (Fig. 13, 1314 contains user request for additional data (in this case, more information about viewing data in dashboards); user has choice of learning more about widgets: para. 0078-0079 “Here, the user is given the choice of learning more about widgets or viewing data in dashboards. [0079] At 1314, the user indicates that s/he makes a choice, based on the choices offered at 1312. The user chooses to learn more about viewing data on dashboards.”); in response to determining the user intent: retrieving, from a database by a structured data agent, the additional data associated with the user intent (para. 0058 “All of this information is sent to a fulfillment API, which communicates the data associated with the intent and entities to a knowledge engine at step 504. The knowledge engine then retrieves information that fulfills the intent at step 506. The knowledge engine sends the retrieved information back to the fulfillment API at step 508, which converts the information (i.e. response) into conversational form at step 510.”; para. 0048 “The query engine 206 interprets the intent (provided by the fulfillment API 108 in FIG. 1) and queries the knowledge base 204 for information. The query engine 206 structures that information in a way that the fulfillment API 108 can send back to the communication channel 104.”; ); performing, by a troubleshooting agent, the troubleshooting associated with the user intent (since the claim language only necessitates that either the user intent be an indicator for additional information OR an indicator for troubleshooting, this limitation is not required to be taught by Almeida); and thereby, obtaining a troubleshooting result (since the claim language only necessitates that either the user intent be an indicator for additional information OR an indicator for troubleshooting, this limitation is not required to be taught by Almeida); and generating, by the dashboard widget service engine for the user device, a response to the user question associated with the set of widget (para. 0058 “The response is conveyed to the NLP at step 512, which is then conveyed to the user via the communication channel at step 514.”; para. 0078-0079 “Here, the user is given the choice of learning more about widgets or viewing data in dashboards. [0079] At 1314, the user indicates that s/he makes a choice, based on the choices offered at 1312. The user chooses to learn more about viewing data on dashboards. At 1316, the virtual agent provides detailed guidance on viewing data in a dashboard, including an image of a tree map widget and source worksheet (particular to the product).”).
Crabtree, Castillo, and Almeida are considered to be analogous to the claimed invention as they are all in the same field of natural language processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Crabtree in view of Castillo to incorporate the teachings of Almeida in order to specifically receive a user question associated with the set of widget, determine, by a backend service, a user intent from the user question comprising an indicator for additional data, wherein the indicator is associated with the set of widgets, and in response to determining the user intent, retrieving, from a database by a structured data agent, the additional data associated with the user intent, and to generate a response to the user question associated with the set of widget. Doing so would be beneficial, as this would enable user to better understand aspects of the widgets without having to wade through documentation (Almeida, para. 0001), improving user experience.
Regarding claim 12, claim 12 is rejected for analogous reasons to claim 5.
Regarding claim 18, claim 18 is rejected for analogous reasons to claim 5.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Inala et al. (US 2025/0190230 A1): receiving user request to alter data, dynamically synthesizing widgets to alter data, presenting widget in a dashboard (Fig. 10), use of widget templates (para. 0025)
Yu et al. (US 11,138,518 B1): generating custom UI including internally customized widgets based on user intent (Fig. 6)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CODY DOUGLAS HUTCHESON whose telephone number is (703)756-1601. The examiner can normally be reached M-F 8:00AM-5:00PM EST.
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, Pierre-Louis Desir can be reached at (571)-272-7799. 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.
/CODY DOUGLAS HUTCHESON/Examiner, Art Unit 2659
/PIERRE LOUIS DESIR/Supervisory Patent Examiner, Art Unit 2659
Prosecution Insights