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 Rejections - 35 USC § 103
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.
Claims 1-7 and 9-25 are rejected under 35 U.S.C. 103 as being unpatentable over Saligrama Shreeram et al. (US 2025/0110979), hereinafter Saligrama Shreeram in view of Bell et al. (US 2024/0406166), hereinafter Bell.
As for claim 1 Saligrama Shreeram teaches a system interposed between a user and a natural language generative application service (chatbot) (paragraphs [0026]-[0027] and [0031] describe a natural language generative application service supports requests from a user to find information and execute follow-up actions), the system comprising:
a processor and a computer readable medium operably coupled thereto (paragraph [0108] describes processors coupled to a system memory via an I/O interface), the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform operations which comprise (paragraphs [0111] and [0115] describe the system memory stores program instructions which implement desired functions, in real time (paragraph [0028] describes a natural language generative application service (NLS) offers an intuitive user interface to create and deploy an enterprise-grade application to users in minutes without requiring generative machine learning domain expertise):
with a conversational interface, receiving a user input (paragraph [0027] describes the natural language generative application service allows users to ask complex questions; Fig. 8, S 810; paragraph [0099] describes a natural language request may be received via an interface of a generative machine learning service );
with a broker agent (Fig. 1, data retrieval management), based on the user input and a conversation history, passing the user input to at least one assistant agent (paragraph [0020] and [0101] describe the generative machine learning service implements data retrieval management invokes select data retrievers, for example, requests may be dispatched to the selected data retrievers to access results similar to or relevant to the natural language task; paragraphs [0085] and [0088]-[0089] describe a natural language request for a natural language task is received, task orchestration workflow implements conversation history in order to perform decontextualization. If conversation history is obtained, the conversation history is provided to a generative language model (LLM) to rewrite the instruction, keyword or question based on the conversation history. The rewrite prompt causes the generative machine learning model to return a rewritten form of the natural language request to perform the task. The data retrieval selects the appropriate data retrievers), wherein the at least one assistant agent comprises an action agent or a data agent (paragraph [0021] describes selected data retrievers);
if the at least one assistant agent comprises a data agent:
fetching data from at least one database (paragraphs [0040]-[0041] and [0063] describe NLS supports various features to ingest, index and/or retrieve relevant data from associated data repositories for a generative application. The NLS uses a retriever to find relevant data for a request from the associated data repositories); and
based on the user input and the fetched data, generating a reply (paragraph [0041] describes the NLS finds relevant data then feeds portions from the top relevant data to a generative machine learning model to get a synthesized response);
with the broker agent, in real time, based on the user input and the reply:
formulating a chatbot prompt (paragraphs [0089]-[0090] describe once relevant data passages are obtained, they are provided to a prompt generation. The prompt generation implements a rules-based prompt generator which according to a classification type, may generate a prompt with the request);
passing the chatbot prompt to the chatbot (paragraph [0103] describes the prompt may be submitted to the generative machine learning model to perform the natural language task. The response may be generated based, at least in part, on a result of the prompt received from the generative machine learning model);
receiving an answer from the chatbot (paragraphs [0091]-[0092] describe a result of a generative language model may then be evaluated for completion); and
with the conversational interface, presenting the answer to the user.
Saligrama Shreeram fails to teach
a chatbot;
if the at least one assistant agent comprises an action agent:
determining an action consistent with the user input; and
executing the action;
receiving an answer from the chatbot; and
with the conversational interface, presenting the answer to the user.
Bell discloses
a chatbot (paragraphs [0111]-[0112] describes a system determining that a prompt provided by the user include natural language description of a cohort which is derived by parsing the prompt. An agent module provides an LLM-driven chatbot);
if the at least one assistant agent comprises an action agent (paragraph [0054] describes a platform for generating, deploying, and using task-specific orchestrations (e.g., task-specific agents) that include task-specific machine-learning models for specific tasks and/or within specific domains; paragraph [0122] describes an agent module:
determining an action consistent with the user input (paragraphs [0083]-[0086] describe one or more agent modules are configured to engage with a user in an integrated, conversational manner using natural language dialog. A plurality of agent modules, each respective agent module is associated with defined domain or a task-specific capability. An agent module is configured for a first specific task of generating a summary report. Each agent module is configured to assist end users to either resolve a question and/or problem or to fulfill a specific request); and
executing the action (paragraphs [0084]-[0085] describe a first agent module is configured for a first specific task of generating a summary report of a patient’s medical records, a second agent module is configured for a second specific task of guiding a patient through a care plan, etc.,);
receiving an answer from the chatbot (paragraphs [0110]-[0111] describe a user agent includes an agent portion in which a user poses prompts and view information returned and generated by an agent module. The agent module provides an LLM-driven chatbot); and
with the conversational interface, presenting the answer to the user (paragraph [0110] describes the user interface includes an agent portion in which the user poses prompts to an agent module and views information returned generated by the agent module).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for implementing a chatbot. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to receive a user text prompt and provide results to the user. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to simplify documentation navigation and discovery (Bell: paragraph [0111]).
As for claim 2, the combined system of Saligrama Shreeram and Bell the system comprising the chatbot (Saligrama Shreeram: paragraphs [0072] and [0090] and [0102] describe a created generative application supports for both hosted and non-hosted applications, interactions to chat/converse using application-associated data repositories and a service hosted generative machine learning model. The generative machine learning service performs a natural language task for a generative natural language application; Bell: paragraph [0111] describes an LLM-driven chatbot).
As for claim 3, the combined system of Saligrama Shreeram and Bell teaches wherein the chatbot comprises a first large language model (LLM) chatbot or machine learning (ML) chatbot (Bell: paragraph [0111] describes a LLM-driven chatbot).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for implementing a chatbot. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to receive a user text prompt and provide results to the user. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to simplify documentation navigation and discovery (Bell: paragraph [0111]).
As for claim 4, the combined system of Saligrama Shreeram and Bell teaches wherein the action agent, data agent, or broker agent comprises or communicates with a second LLM or ML chatbot (Saligrama Shreeram: paragraph [0061] describes the natural language generative application service implements a natural language task orchestration (i.e. agent); Bell: paragraph [0057] describes an agent receives a user query, generates a structured API call, uses the generated API call to query a remote server to retrieve a relevant result; paragraph [0075] describes an agent library includes a plurality of agent modules).
As for claim 5, wherein the second LLM or ML chatbot and the first LLM or ML chatbot are the same (Saligrama Shreeram: paragraph [0014] describes the natural language generative machine learning models, such as large language models (LLMs), are one type of generative machine learning model that refer to machine learning techniques applied to model language, which may include natural language and machine-readable language. For generative machine learning models that model language, the generative machine learning models take language prompts and generate corresponding programming language predictions. Note: the natural language generative machine learning models are of the same type).
As for claim 6, the combined system of Saligrama Shreeram and Bell teaches wherein the action agent is selected from a plurality of action agents by the broker agent based on the user input (paragraphs [0020]-[0021] describe data retrievers are selected which access various data repositories to obtain relevant data and provide that data to a prompt generation. The prompt generation then generates a prompt based on the obtained data. The prompt is provided to a generative machine learning model trained to perform the requested natural language task); or wherein the data agent is selected from a plurality of data agents by the broker agent based on the user input (Saligrama Shreeram: paragraphs [0020]-[0021] and [0099]-[0100] describe a natural language request is received via an interface of a generative machine learning service to perform a natural language task, one or data retrievers is selected by the generative natural language application).
As for claim 7, the combined system of Saligrama Shreeram and Bell teaches wherein the conversational interface is part of a business intelligence software application (Bell: paragraph [0109] describes a user interface with a prompt user interface for interacting with a general-purpose language module and/or one or more task specific orchestrations, a user enters a text prompt and the agent module provides a response in accordance with a correspondence node architecture associated with the agent module), wherein the at least one database comprises data related to a business (Bell: paragraph [0101] describes medical databases for storing medical data), and wherein the user input is related to the data or the business (Bell: paragraph [0109] describes a user’s text prompt related to patient’s diagnosed).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for implementing a chatbot. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to receive a user text prompt and provide results to the user. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to simplify documentation navigation and discovery (Bell: paragraph [0111]).
As for claim 9, the combined system of Saligrama Shreeram and Bell teaches wherein the at least one database comprises a customer success, customer service, flow data, objectives, key results, roadmap, project portfolio, work plan (Saligrama Shreeram: paragraph [0032] describes data repositories for a generative application supports data retrievers), or resource allocation database.
As for claim 10, the combined system of Saligrama Shreeram and Bell teaches wherein the data comprises at least one of a document (Bell: paragraph [0122] describes an agent module is associated with a first domain for generating a summary report of a patient’s medical records), application data, a knowledge graph, a tabular data frame, or a relational database (Bell: paragraph [0123] describe an agent type is a database-interfacing agent module associated with one or more data source nodes).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for implementing a chatbot. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to receive a user text prompt and provide results to the user. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to simplify documentation navigation and discovery (Bell: paragraph [0111]).
As for claim 11, the combined system of Saligrama Shreeram and Bell teaches wherein the at least one assistant agent comprises a plurality of data agents (Bell: paragraph [0124] describes a custom-chain agent module (e.g., a super-agent module) comprising a sequence of nodes), and wherein formulating the chatbot prompt includes combining and summarizing replies from the plurality of data agents (Bell: paragraph [0124] describes a node of the custom-chain agent module obtains data from different databases in which the data is obtained in a variety of different formats and structures. The agent module evaluates and obtains an optimal set of parameters for inputting data to a model. The obtained data is restructured into a homogenous dataset).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for implementing a custom-chain agent module. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to restructure data obtained in a variety of different formats and structures. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to dissect complex evaluations and logics into a reasoning path through the plurality of interconnected nodes which makes arriving at an accurate and precise response computationally less burdensome (Bell: paragraph [0124]).
As for claim 12, the combined system of Saligrama Shreeram and Bell teaches wherein the operations further comprise, with the broker agent:
summarizing the answer (Saligrama Shreeram: paragraph [0034] describes the natural language generative application presents references and other summary information from the sources which were used to generate the response for the end user; Bell: paragraph [0184] describes a natural language search agent that allows for open-ended questions answering and summarization with multi-step conversation support); and
with the conversational interface, presenting the summarized answer to the user (Saligrama Shreeram: paragraph [0034] describes the natural language generative application service presents other summary information which were used to generate the response for the end user; Bell: paragraphs [0279]-[0280] describe the computing system provides a summarized and/or reformatted response to the user).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for providing a summary answer to users. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to assist and response to a user’s request. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to personalize an output to a particular user.
As for claim 13, Saligrama Shreeram teaches a computer-implemented method for interposing between a user and a natural language generative application service (chatbot) (paragraphs [0026]-[0027] and [0031] describe a natural language generative application service supports requests from a user to find information and execute follow-up actions; paragraph [0097] describes methods to implement distributed orchestration of natural language tasks using a generative machine learning model), the method comprising, in real time:
with a conversational interface, receiving a user input ((paragraph [0027] describes the natural language generative application service allows users to ask complex questions; Fig. 8, S 810; paragraph [0099] describes a natural language request may be received via an interface of a generative machine learning service);
with a broker agent, based on the user input and a conversation history, passing the user input to at least one assistant agent (Fig. 1, data retrieval management), based on the user input and a conversation history, passing the user input to at least one assistant agent (paragraph [0020] and [0101] describe the generative machine learning service implements data retrieval management invokes select data retrievers, for example, requests may be dispatched to the selected data retrievers to access results similar to or relevant to the natural language task; paragraphs [0085] and [0088]-[0089] describe a natural language request for a natural language task is received, task orchestration workflow implements conversation history in order to perform decontextualization. If conversation history is obtained, the conversation history is provided to a generative language model (LLM) to rewrite the instruction, keyword or question based on the conversation history. The rewrite prompt causes the generative machine learning model to return a rewritten form of the natural language request to perform the task. The data retrieval selects the appropriate data retrievers), wherein the at least one assistant agent comprises an action agent or a data agent (paragraph [0021] describes selected data retrievers);
if the at least one assistant agent comprises a data agent:
fetching data from at least one database (paragraphs [0040]-[0041] and [0063] describe NLS supports various features to ingest, index and/or retrieve relevant data from associated data repositories for a generative application. The NLS uses a retriever to find relevant data for a request from the associated data repositories); and
based on the user input and the fetched data, generating a reply (paragraph [0041] describes the NLS finds relevant data then feeds portions from the top relevant data to a generative machine learning model to get a synthesized response);
with the broker agent, in real time, based on the user input and the reply:
formulating a chatbot prompt (paragraphs [0089]-[0090] describe once relevant data passages are obtained, they are provided to a prompt generation. The prompt generation implements a rules-based prompt generator which according to a classification type, may generate a prompt with the request);
passing the chatbot prompt to the chatbot (paragraph [0103] describes the prompt may be submitted to the generative machine learning model to perform the natural language task. The response may be generated based, at least in part, on a result of the prompt received from the generative machine learning model);
receiving an answer from the chatbot (paragraphs [0091]-[0092] describe a result of a generative language model may then be evaluated for completion); and
with the conversational interface, presenting the answer to the user.
Saligrama Shreeram fails to teach
a chatbot;
if the at least one assistant agent comprises an action agent:
determining an action consistent with the user input; and
executing the action;
receiving an answer from the chatbot; and
with the conversational interface, presenting the answer to the user.
Bell discloses
a chatbot (paragraphs [0111]-[0112] describes a system determining that a prompt provided by the user include natural language description of a cohort which is derived by parsing the prompt. An agent module provides an LLM-driven chatbot);
if the at least one assistant agent comprises an action agent (paragraph [0054] describes a platform for generating, deploying, and using task-specific orchestrations (e.g., task-specific agents) that include task-specific machine-learning models for specific tasks and/or within specific domains; paragraph [0122] describes an agent module:
determining an action consistent with the user input (paragraphs [0083]-[0086] describe one or more agent modules are configured to engage with a user in an integrated, conversational manner using natural language dialog. A plurality of agent modules, each respective agent module is associated with defined domain or a task-specific capability. An agent module is configured for a first specific task of generating a summary report. Each agent module is configured to assist end users to either resolve a question and/or problem or to fulfill a specific request); and
executing the action (paragraphs [0084]-[0085] describe a first agent module is configured for a first specific task of generating a summary report of a patient’s medical records, a second agent module is configured for a second specific task of guiding a patient through a care plan, etc.,);
receiving an answer from the chatbot (paragraphs [0110]-[0111] describe a user agent includes an agent portion in which a user poses prompts and view information returned and generated by an agent module. The agent module provides an LLM-driven chatbot); and
with the conversational interface, presenting the answer to the user (paragraph [0110] describes the user interface includes an agent portion in which the user poses prompts to an agent module and views information returned generated by the agent module).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for implementing a chatbot. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to receive a user text prompt and provide results to the user. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to simplify documentation navigation and discovery (Bell: paragraph [0111]).
As for claim 14, the combined system of Saligrama Shreeram and Bell teaches wherein the chatbot comprises a first large language model (LLM) chatbot or machine learning (ML) chatbot (Bell: paragraph [0111] describes a LLM-driven chatbot).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for implementing a chatbot. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to receive a user text prompt and provide results to the user. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to simplify documentation navigation and discovery (Bell: paragraph [0111]).
As for claim 15, the combined system of Saligrama Shreeram and Bell teaches wherein the action agent, data agent, or broker agent comprises or communicates with a second LLM or ML chatbot (Saligrama Shreeram: paragraph [0041] describes the natural language generative application service combines generative machine learning models (i.e. LLMs – paragraph [0032]) with application-specific data retrieval to provide question answering functionality; paragraph [0061] describes the natural language generative application service implements a natural language task orchestration (i.e. agent); Bell: paragraph [0057] describes an agent receives a user query, generates a structured API call, uses the generated API call to query a remote server to retrieve a relevant result; paragraph [0075] describes an agent library includes a plurality of agent modules).
As for claim 16, the combined system of Saligrama Shreeram and Bell teaches wherein the second LLM or ML chatbot and the first LLM or ML chatbot are the same (Saligrama Shreeram: paragraph [0014] describes the natural language generative machine learning models, such as large language models (LLMs), are one type of generative machine learning model that refer to machine learning techniques applied to model language, which may include natural language and machine-readable language. For generative machine learning models that model language, the generative machine learning models take language prompts and generate corresponding programming language predictions. Note: the natural language generative machine learning models are of the same type).
As for claim 17, the combined system of Saligrama Shreeram and Bell teaches wherein the action agent is selected from a plurality of action agents by the broker agent based on the user input (Saligrama Shreeram: paragraphs [0020]-[0021] describe data retrievers are selected which access various data repositories to obtain relevant data and provide that data to a prompt generation. The prompt generation then generates a prompt based on the obtained data. The prompt is provided to a generative machine learning model trained to perform the requested natural language task); or wherein the data agent is selected from a plurality of data agents by the broker agent based on the user input (Saligrama Shreeram: paragraphs [0020]-[0021] and [0099]-[0100] describe a natural language request is received via an interface of a generative machine learning service to perform a natural language task, one or data retrievers is selected by the generative natural language application).
As for claim 18, the combined system of Saligrama Shreeram and Bell teaches wherein the at least one assistant agent comprises a plurality of data agents (Bell: paragraph [0124] describes a custom-chain agent module (e.g., a super-agent module) comprising a sequence of nodes), and wherein formulating the chatbot prompt includes combining and summarizing replies from the plurality of data agents (Bell: paragraph [0124] describes a node of the custom-chain agent module obtains data from different databases in which the data is obtained in a variety of different formats and structures. The agent module evaluates and obtains an optimal set of parameters for inputting data to a model. The obtained data is restructured into a homogenous dataset).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for implementing a custom-chain agent module. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to restructure data obtained in a variety of different formats and structures. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to dissect complex evaluations and logics into a reasoning path through the plurality of interconnected nodes which makes arriving at an accurate and precise response computationally less burdensome (Bell: paragraph [0124]).
As for claim 19, the combined system of Saligrama Shreeram and Bell teaches the method comprising, with the broker agent:
summarizing the answer (Saligrama Shreeram: paragraph [0034] describes the natural language generative application presents references and other summary information from the sources which were used to generate the response for the end user; Bell: paragraph [0184] describes a natural language search agent that allows for open-ended questions answering and summarization with multi-step conversation support); and
with the conversational interface, presenting the summarized answer to the user (Saligrama Shreeram: paragraph [0034] describes the natural language generative application service presents other summary information which were used to generate the response for the end user; Bell: paragraphs [0279]-[0280] describe the computing system provides a summarized and/or reformatted response to the user).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for providing a summary answer to users. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to assist and response to a user’s request. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to personalize an output to a particular user.
As for claim 20, the claim lists all elements of claim 13, but in a non-transitory computer-readable storage medium storing instructions, which when executed by at least one processor of a computer system (Saligrama Shreeram: paragraphs [0110]-[0111] describe system memory store program instructions that are executed by a GPU), causes the computer system to carry out the method of claim 13. Therefore, the supporting rationale of the rejection to claim 13 applies equally as well to claim 20.
As for claim 21, the claim lists all elements of claim 13, but in a computer system comprising: one or more processors (Saligrama Shreeram; paragraph [0109] describes processors) and a storage medium storing instructions (Saligrama Shreeram: paragraph [0111] describes system memory stores program instructions accessible by the processor ), which when executed by at least one processor, cause the system to implement the method of claim 13 (Saligrama Shreeram: paragraph [0115] describes the program instructions implement the various methods and techniques). The supporting rationale of the rejection to claim 13 applies equally as well to claim 21.
As for claim 22, the combined system of Saligrama Shreeram and Bell teaches wherein the conversational interface is part of a business intelligence software application (Bell: paragraph [0109] describes a user interface with a prompt user interface for interacting with a general-purpose language module and/or one or more task specific orchestrations, a user enters a text prompt and the agent module provides a response in accordance with a correspondence node architecture associated with the agent module), wherein the at least one database comprises data related to a business (Bell: paragraph [0101] describes medical databases for storing medical data), and wherein the user input is related to the data or the business (Bell: paragraph [0109] describes a user’s text prompt related to patient’s diagnosed).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for implementing a chatbot. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to receive a user text prompt and provide results to the user. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to simplify documentation navigation and discovery (Bell: paragraph [0111]).
As for claim 23, the combined system of Saligrama Shreeram and Bell teaches wherein the data agent comprises a help bot (Bell: paragraph [0109] describes if a first prompt includes a plurality of graphical data of chest x-rays from a single human, the agent module provides the plurality of graphical data to a first filter of a node associated with screen chest x-ray modalities for a first biomarker; Saligrama Shreeram: paragraphs [0091]-[0092] describe a result of generative language model is evaluated for completion. An additional machine learning model trained to detect profane or other in appropriate content may be invoked on the result to ensure that the result is not invalid for inappropriate content), a flow metric bot, an objectives agent, a key results agent, or a roadmap agent.
As for claim 24, the combined system of Saligrama Shreeram and Bell teaches wherein the at least one database comprises a customer success, customer service, flow data, objectives, key results, roadmap, project portfolio, work plan (Saligrama Shreeram: paragraph [0032] describes data repositories for a generative application supports data retrievers), or resource allocation database.
As for claim 25, the combined system of Saligrama Shreeram and Bell teaches wherein the data comprises at least one of a document, application data, a knowledge graph, a tabular data frame, or a relational database (Bell: paragraph [0122] describes an agent module is associated with a first domain for generating a summary report of a patient’s medical records), application data, a knowledge graph, a tabular data frame, or a relational database (Bell: paragraph [0123] describe an agent type is a database-interfacing agent module associated with one or more data source nodes).
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Bell for implementing a chatbot. The teachings of Bell, when implemented in the Saligrama Shreeram system, will allow one of ordinary skill in the art to receive a user text prompt and provide results to the user. One of ordinary skill in the art would be motivated to utilize the teachings of Bell in the Saligrama Shreeram system in order to simplify documentation navigation and discovery (Bell: paragraph [0111]).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Saligrama Shreeram (US 2025/0110979) in view of Bell (US 2024/0406166) further in view of Dhillon et al. (US 2024/0385885), hereinafter Dhillon.
As for claim 8, the combined system of Saligrama Shreeram and Bell teaches wherein the data agent comprises a help bot (Bell: paragraph [0109] describes if a first prompt includes a plurality of graphical data of chest x-rays from a single human, the agent module provides the plurality of graphical data to a first filter of a node associated with screen chest x-ray modalities for a first biomarker; Saligrama Shreeram: paragraphs [0091]-[0092] describe a result of generative language model is evaluated for completion. An additional machine learning model trained to detect profane or other in appropriate content may be invoked on the result to ensure that the result is not invalid for inappropriate content), a flow metric bot, an objectives agent, a key results agent, or a roadmap agent.
The combined system of Saligrama Shreeram and Bell fails to teach a data agent comprises a flow metric bot, an objectives agent, a key results agent, or a roadmap agent.
Dhillon discloses
a data agent comprises a flow metric bot (Fig. 8A; paragraph [0197] describes interactive GUIs including graph-based visualizations of processes. A plurality of metrics, calculated based on data objects associated with the various states, are determined and displayed with an associated node), an objectives agent (paragraphs [0048]-[0050] describe a system for object-based process management and visualization), a key results agent (paragraph [0099] describes the LLM service receives a query and transmits results based on the query to a user interface of the system), or a roadmap agent.
One of ordinary skill in the art before the effective filing date of the claimed invention would have recognized the ability to utilize the teachings of Dhillon for providing large language models. The teachings of Dhillon, when implemented in the Saligrama Shreeram and Bell system, will allow one of ordinary skill in the art to provide a representation of a process. One of ordinary skill in the art would be motivated to utilize the teachings of Dhillon in the Saligrama Shreeram and Bell system in order to generate an automation for at least a portion of a process managed by a system.
Conclusions
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Kearns (US 2025/0094470) teaches method for intent-based action recommendations and/or fulfillment in a messaging platform
Cunningham et al. (US 2024/0394285) teach chatbot
Zhong et al. (US 2024/0126795) teach conversational document question answering.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to L. T N. whose telephone number is (571)272-1013. The examiner can normally be reached M & Th 5:30 am - 2:30 pm 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, TONIA DOLLINGER can be reached at 571-272-4170. 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.
/L. T. N/
Examiner, Art Unit 2459
/TONIA L DOLLINGER/Supervisory Patent Examiner, Art Unit 2459
Prosecution Insights