DETAILED ACTION
This action is in response to the application filed on December 30th, 2024. Claims 1-20 are pending and have been examined.
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
Claims 5, 6, and 19 objected to because of the following informalities:
Claim 5 and claim 6 each read “generating the necessary API code through Tool Manager and executing API call through the bot builder” but should read “generating the necessary API code through the Tool Manager and executing an API call through the bot builder”.
Claim 19 reads “wherein creating an individualized user document that contains comprehensive information about the user, including personal details such as birth dates, transaction histories, and post session conversation flow, customer preferences, behavioral patterns;”, which is an incomplete phrase with multiple grammatical errors, which should be amended to fix the errors and make a complete phrase.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 7, 15, 18, and 19 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claims 7 and 19, the phrase "such as" renders the claim indefinite because it is unclear whether the limitations following the phrase are part of the claimed invention. See MPEP § 2173.05(d).
Claim 15 recites the limitation "the Tool Use JSON format" in line 1. There is insufficient antecedent basis for this limitation in the claim.
The term “accurate” in claim 18 is a relative term which renders the claim indefinite. The term “accurate” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. As such, it is unclear as to what degree of accuracy a response must be to be considered accurate.
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 2 rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. Claim 2 recites a limitation that is nearly identical to a limitation of claim 1, and as such does not further limit the subject matter of claim 1. Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
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.
Claim(s) 1-12 and 14-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bell et al. (US Pat. Pub. No. 2024/0404687 A1 hereinafter Bell), in view of Matsuoka et al. (US Pat. Pub. No. 2023/0069133 A1 hereinafter Matsuoka) and McIntyre et al. (US Pat. Pub. No. 2025/0111167 A1 hereinafter McIntyre).
Regarding claim 1, Bell discloses a computer-implemented method for dynamically routing and processing user queries in a bot-builder system, the computer-implemented method comprising: receiving a user query at a bot-builder service (Bell, [0171]: "FIG. 9D illustrate an example process for patient querying in accordance with some embodiments."); routing the user query to a Document Retrieval Module (Bell, [0172]: "The system 970 also obtains query embeddings from user queries and identifies similar embeddings in the vector database to output text chunks that are relevant to the user queries."); retrieving document embeddings from a first vector store through the Document Retrieval Module (Bell, [0172]: "In accordance with some embodiments, the system 970 (e.g., a first agent module) is configured to extract text from the documents 972 (e.g., using various text recognition and extraction techniques).... In some embodiments, the model 982 is a document classification model (e.g., configured to identify chunks with relevant information and discard chunks without relevant information). The extracted text is chunked and stored as embeddings in a vector database (e.g., using processes described above with respect to FIGS. 9A-9C)."); processing the user query by an Al model to generate query embeddings (Bell, [0172]: "The system 970 also obtains query embeddings from user queries and identifies similar embeddings in the vector database to output text chunks that are relevant to the user queries."); performing a similarity search using the query embeddings against the document embeddings in the first vector store to retrieve the most relevant document chunks (Bell, [0149]: "In some embodiments, the query embedding is compared to embeddings in a vector database 6240 (e.g., to determine and provide a vector similarity 804) and results are sent to the backend component as context with the query vector and/or a different agent module 6102 in accordance with the logic 6112 of the node architecture."; [0155]: "FIG. 9A shows a process of generating embeddings from documents (e.g., PDF documents 902). In some embodiments, the documents are obtained from a medical database (e.g., clinical trial protocol documents from a clinical trial database), which may be a live collection of medical data (e.g., including a means for obtaining real-time updates to the data source). In some embodiments, embeddings are also generated from metadata corresponding to the documents and stored in a vector database 904."; [0156]: "FIG. 9A also shows a process of generating a question embedding and using a cosine similarity with vectors in a vector database 6240 to identify relevant chunks of the documents."); combining the retrieved personal information, document chunks, and tools with the user query and chat history to form a comprehensive input (Bell, [0175]: "In the example of FIG. 9D, the outputs of the systems 970, 974, and 976 are provided to a model 984 (e.g., a large language model configured to understand user queries) along with information from the user queries."); processing the comprehensive input by the Al model to determine an appropriate response pathway; generating a response based on the comprehensive input, delivering the final response to the user (Bell, [0175]: "In some embodiments, the model 984 is configured to provide an output that incorporates information from each of the systems 970, 974, and 976 (e.g., a summary of the information from the other systems). In some embodiments, the model 984 is configured to provide a natural language output for a user."). However, Bell fails to expressly recite routing the user query to a Personal Info Retrieval Module and a Tool Manager; retrieving personal information from a Personal Info Store through the Personal Info Retrieval Module, wherein the Personal Info Retrieval Module updates the Personal Info Store in real time by invoking external services via API calls; retrieving tool embeddings from a second vector store through the Tool Manager; and performing a similarity search using the query embeddings against the tool embeddings in the second vector store to retrieve the most relevant tools.
Matsuoka teaches routing the user query to a Personal Info Retrieval Module (Matsuoka, [0041]: "the task facilitation service 102 may automatically surface relevant portions of the member profile when creating or performing a task on behalf of the member 118."); and retrieving personal information from a Personal Info Store through the Personal Info Retrieval Module, wherein the Personal Info Retrieval Module updates the Personal Info Store in real time by invoking external services via API calls (Matsuoka, [0041]: "the task facilitation service 102 may automatically surface relevant portions of the member profile when creating or performing a task on behalf of the member 118."; [0247]: "In some examples, as the representatives 804 perform or otherwise coordinate performance of tasks on behalf of a member 812, the task-facilitation service 802 updates a profile of the member 812 and/or a computational model of the profile of the member 812 in real-time.").
Bell and Matsuoka are analogous arts because they each belong to the same field of user dialogue systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the AI routing agent of Bell to incorporate the teachings of Matsuoka to retrieve and update personal information of a user. This allows the system to adapt its responses based on past interactions and information it can access about the user (Matsuoka, [0254]). Doing so ensures the system responds intelligently in response to a user’s queries, needs, and goals. However, Bell, in view of Matsuoka, fails to expressly recite routing the user query to a Tool Manager; retrieving tool embeddings from a second vector store through the Tool Manager; and performing a similarity search using the query embeddings against the tool embeddings in the second vector store to retrieve the most relevant tools.
McIntyre teaches routing the user query to a Tool Manager (McIntyre, [0054]: "Embodiments of the semantic search engine 224 perform a search to find related candidate LM skills within a semantic vector space to the task, for example, through the use of word embedding and vector representations of the task and query."); retrieving tool embeddings from a second vector store through the Tool Manager (McIntyre, [0054]: "Embodiments of the semantic search engine 224 perform a search to find related candidate LM skills within a semantic vector space to the task, for example, through the use of word embedding and vector representations of the task and query."); and performing a similarity search using the query embeddings against the tool embeddings in the second vector store to retrieve the most relevant tools (McIntyre, [0054]: "To find related results, embodiments of the semantic search engine 224 calculate the semantic similarity between the vector representation of the query associated with the task and the vector representations of LM skills in the corpus.").
Bell, Matsuoka, and McIntyre are analogous arts because they each belong to the same field of user dialogue systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the AI routing agent of Bell, as modified by the user interaction system of Matsuoka, to incorporate the teachings of McIntyre to generate high-dimensional embeddings to enable the system to search for tools. This allows the system to comprehend the intent of a user’s query and better understand and match it to relevant text (McIntyre, [0027]). As such, the system is able to provide more accurate and contextually relevant results.
Regarding claim 2, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Matsuoka further teaches wherein the Personal Info Retrieval Module updates a Personal Info Store in real time by invoking external services via API calls (Matsuoka, [0247]: "In some examples, as the representatives 804 perform or otherwise coordinate performance of tasks on behalf of a member 812, the task-facilitation service 802 updates a profile of the member 812 and/or a computational model of the profile of the member 812 in real-time."). The same motivation for claim 1 applies equally to claim 2.
Regarding claim 3, the rejection of claim 2 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. McIntyre further teaches wherein the document embeddings are generated by transforming textual data into high-dimensional vectors (McIntyre, [0054]: "For example, each word in a corpus (collection of text) is represented as a high-dimensional vector in a semantic vector space."). The same motivation for claim 1 applies equally to claim 3.
Regarding claim 4, the rejection of claim 3 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. McIntyre further teaches wherein the tool embeddings are generated by transforming tool descriptions, metadata, or usage examples into high-dimensional vectors (McIntyre, [0054]: "In one embodiment, documents, such as articles associated with LM skills, web pages associated with LM skills, or queries associated with LM skills, are also transformed into vectors by aggregating or averaging the word embeddings of the words within them, generating a vector representation of the document's semantic meaning."). The same motivation for claim 1 applies equally to claim 4.
Regarding claim 5, the rejection of claim 4 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Bell further discloses wherein the response is either formulated using existing knowledge and personal information or involves invoking an external tool; if an external tool is required, generating the necessary API code through Tool Manager and executing API call through the bot builder; integrating the results from the external tool back into the system for further processing by the Al model; delivering the final response to the user (Bell, [0057]: "As another example, after deployment, an agent may receive a user query (e.g., requesting information about clinical trials), generate a structured application programming interface (API) call, use the generated API call to query a remote server to retrieve a relevant result, and reformat the relevant information to return to the user.").
Regarding claim 6, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Bell further discloses wherein the response is either formulated using existing knowledge and personal information or involves invoking an external tool; if an external tool is required, generating the necessary API code through Tool Manager and executing API call through the bot builder; integrating the results from the external tool back into the system for further processing by the Al model (Bell, [0057]: "As another example, after deployment, an agent may receive a user query (e.g., requesting information about clinical trials), generate a structured application programming interface (API) call, use the generated API call to query a remote server to retrieve a relevant result, and reformat the relevant information to return to the user.").
Regarding claim 7, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Bell further discloses wherein the Personal Info Retrieval Module retrieves personal data from external services selected from the group consisting of external services such as CRM platforms and HR systems (Bell, [0241]: "In some embodiments, the node 6108-1 retrieves, via the communication network, a plurality of restricted data, such as a plurality of personal health information or personally identifiable information associated with a patient from one or more electronic health records.").
Regarding claim 8, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Bell further discloses wherein the document embeddings are generated by dividing original text documents into smaller chunks before transforming them into high- dimensional vectors (Bell, [0172]: "In accordance with some embodiments, the system 970 (e.g., a first agent module) is configured to extract text from the documents 972 (e.g., using various text recognition and extraction techniques).... In some embodiments, the model 982 is a document classification model (e.g., configured to identify chunks with relevant information and discard chunks without relevant information). The extracted text is chunked and stored as embeddings in a vector database (e.g., using processes described above with respect to FIGS. 9A-9C).").
Regarding claim 9, the rejection of claim 4 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. McIntyre further teaches wherein the tool embeddings are generated by transforming tool descriptions, metadata, or usage examples into high-dimensional vectors that align with the same vector space as document embeddings (McIntyre, [0054]: "In one embodiment, documents, such as articles associated with LM skills, web pages associated with LM skills, or queries associated with LM skills, are also transformed into vectors by aggregating or averaging the word embeddings of the words within them, generating a vector representation of the document's semantic meaning."). The same motivation for claim 1 applies equally to claim 9.
Regarding claim 10, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Bell further discloses wherein the similarity search performed using the query embeddings against the document embeddings retrieves the top-K most relevant document chunks (Bell, [0164]: "In some embodiments, the identified portion (e.g., snippet) must satisfy a relevance threshold. For instance, in some embodiments, a set of candidate portions are identified and ranked in terms of relevance to the medical condition relative to each other and the top X number of candidate portions are selected for retrieval. In some embodiments, the ranking is limited to portions obtained from a single document within a medical record.").
Regarding claim 11, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. McIntyre further teaches wherein the similarity search performed using the query embeddings against the tool embeddings retrieves the top-N most relevant tools (McIntyre, [0054]: "In some embodiments, the semantic search engine 224 utilizes a relevance threshold to filter out LM skills that are not sufficiently similar to the task, ensuring that those LM skills that satisfy the relevance threshold are surfaced as candidate LM skills."). The same motivation for claim 1 applies equally to claim 11.
Regarding claim 12, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Matsuoka further teaches updating the Personal Info Store directly by external services when there is a change or update in personal information (Matsuoka, [0247]: "In some examples, as the representatives 804 perform or otherwise coordinate performance of tasks on behalf of a member 812, the task-facilitation service 802 updates a profile of the member 812 and/or a computational model of the profile of the member 812 in real-time."). The same motivation for claim 1 applies equally to claim 12.
Regarding claim 14, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. McIntyre further teaches wherein the Tool Manager transmits API documentation of external services to an AI model, which converts the specifications into a Tool Use format (McIntyre, [0061]: "In some embodiments, the API call generator 228 generates an API call 250 against the target LM skill to retrieve data from databases, websites, or external services. For example, the API call generator 228 sends requests to specific API endpoints associated with the target LM skill to retrieve information in a structured format (for example, JavaScript Object Notation [JSON] or Extensible Markup Language [XML]) that would be responsive to the initial request. In this example, the API call 250 generated by the API call generator 228 causes the intermediate LM skill layer 210 or the LLM to receive the information in the structured format."). The same motivation for claim 1 applies equally to claim 14.
Regarding claim 15, the rejection of claim 9 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. McIntyre further teaches embedding the Tool Use JSON format into the vector store to enable seamless and efficient function handling (McIntyre, [0062]: "In some embodiments, the API call generator 228 can integrate the LM skill into a workflow associated with the user to automate operations for the user. For example, an LM skill associated with a social media platform can use APIs to schedule posts, gather analytics, and interact with social media platforms on behalf of users based on the API call 250. In this manner, the API call can extend the functionality afforded by the LLM 240 by integrating APIs of the LM skills with the LLM 240.").
Bell, Matsuoka, and McIntyre are analogous arts because they each belong to the same field of user dialogue systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the AI routing agent of Bell, as modified by the user interaction system of Matsuoka, to incorporate the teachings of McIntyre to embed the tool use JSON format into the vector store. Embedding the tool into the vector store effectively extends the functionality of the system (McIntyre, [0062]), allowing the system to automate operations for the user, and thus improving the user’s experience.
Regarding claim 16, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Bell further discloses wherein the AI model generates the client code required to call the selected tool or API, enabling seamless integration and execution (Bell, [0057]: "As another example, after deployment, an agent may receive a user query (e.g., requesting information about clinical trials), generate a structured application programming interface (API) call, use the generated API call to query a remote server to retrieve a relevant result, and reformat the relevant information to return to the user.").
Regarding claim 17, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Matsuoka further teaches dynamically updating the embeddings in the vector store in real time to ensure that responses reflect the most current data (Matsuoka, [0247]: "In some examples, as the representatives 804 perform or otherwise coordinate performance of tasks on behalf of a member 812, the task-facilitation service 802 updates a profile of the member 812 and/or a computational model of the profile of the member 812 in real-time."). The same motivation for claim 1 applies equally to claim 17.
Regarding claim 18, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Bell further discloses wherein the AI model integrates retrieved data, tools, and user context to deliver accurate, personalized responses (Bell, [0054]: "The platform may include a plurality of individual task-specific orchestrations that may operation independently or in combination to return accurate and relevant information (e.g., identifying target cohorts, clinical trial information, and/or members of target populations).").
Regarding claim 19, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Bell further discloses leveraging historical interaction records extracted via post session flow and additional CRM data to generate more personalized and context-aware responses (Bell, [0120]: "In some embodiments, the language model agent modules provide/store context information such as conversation history, user preferences, subject details, and the like."). However, Bell fails to expressly recite wherein creating an individualized user document that contains comprehensive information about the user, including personal details such as birth dates, transaction histories, and post session conversation flow, customer preferences, behavioral patterns ; ensuring that user information is updated in real-time and accurately synchronized across systems; prompting a review process at the end of a session or interaction, therefore identifying any changes or additions to the user's personal information; identifying updates or modifications by analyzing the session data and comparing it with existing user profiles; and integrating the changes into the user's JSON profile during the post-session process.
Matsuoka further teaches wherein creating an individualized user document that contains comprehensive information about the user, including personal details such as birth dates, transaction histories, and post session conversation flow, customer preferences, behavioral patterns (Matsuoka, [0038]: "In some examples, the data associated with the member 118 may be used by the task-facilitation service 102 to create a member profile corresponding to the member 118… For example, through the survey or questionnaire, the task facilitation service 102 may prompt the member 118 to provide additional information about friends or family members (and/or other contacts of the member 118), important dates (e.g., birthdays, etc.), dietary restrictions, and the like. Based on the responses provided by the member 118, the task facilitation service 102 may update the member profile corresponding to the member 118."); ensuring that user information is updated in real-time and accurately synchronized across systems (Matsuoka, [0247]: "In some examples, as the representatives 804 perform or otherwise coordinate performance of tasks on behalf of a member 812, the task-facilitation service 802 updates a profile of the member 812 and/or a computational model of the profile of the member 812 in real-time."); prompting a review process at the end of a session or interaction, therefore identifying any changes or additions to the user's personal information (Matsuoka, [0254]: "task-facilitation service systems and/or sub-systems 808 can update the profile of the member 812 and/or a computational model of the profile of the member 812 continuously, dynamically, automatically, and/or in real-time. For example, task-facilitation service systems and/or sub-systems 808 can update the profile of the member 812 and/or a computational model of the profile of the member 812 using the machine learning sub-system 806 as described herein. Accordingly, task-facilitation service systems and/or sub-systems 808 can update the profile of the member 812 and/or a computational model of the profile of the member 812 to provide up-to-date information about the member based on the member's automatic interaction with the task-facilitation service 802, based on the member's interaction with the representative 804, and/or based on tasks performed on behalf of the member 812 over time. This information may also be updated continuously, automatically, dynamically, and/or in real-time as tasks and/or proposals are created, proposed, and performed for the member 812."); identifying updates or modifications by analyzing the session data and comparing it with existing user profiles (Matsuoka, [0138]: "If the representative 106 makes any changes to the information within an automatically populated data field (based on the representative's personal knowledge of the member 118, etc.), the task creation sub-system 302 may use these changes to automatically update the member profile to incorporate these changes."); and integrating the changes into the user's JSON profile during the post-session process (Matsuoka, [0254]: "This information may also be updated continuously, automatically, dynamically, and/or in real-time as tasks and/or proposals are created, proposed, and performed for the member 812."). The same motivation for claim 1 applies equally to claim 19.
Regarding claim 20, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. Bell further discloses wherein the bot-builder service manages API calls and the entire orchestration process from receiving and interpreting user queries to delivering contextually accurate and personalized responses (Bell, [0054]: "The present disclosure describes, among other things, a platform for generating, deploying, and using task-specific orchestrations (e.g., task-specific agents) that include task-specific machine-learning models (e.g., language models, transformer models, and other types of models) for specific tasks and/or within specific domains. The platform may include a plurality of individual task-specific orchestrations that may operation independently or in combination to return accurate and relevant information (e.g., identifying target cohorts, clinical trial information, and/or members of target populations). In some embodiments, each task-specific orchestration (or agent) may include one or more machine-learning models, such as a language model trained and/or fine-tuned on a particular domain. The platform may also include one or more composite orchestrations (e.g., composite agents) that give instructions to, and combine results from, a plurality of task-specific orchestrations configured for different tasks.").
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bell, in view of Matsuoka and McIntyre, as applied to claims 1-12 and 14-20 above, and further in view of Zhu et al. (US Pat. Pub. No. 2026/0154314 A1 hereinafter Zhu).
Regarding claim 13, the rejection of claim 1 is incorporated. Bell, in view of Matsuoka and McIntyre, discloses all of the elements of the claimed invention as stated above. However, Bell, in view of Matsuoka and McIntyre, fails to expressly recite wherein the AI model processes the comprehensive input to determine whether the response can be generated using existing knowledge and personal information or requires invoking an external tool.
Zhu teaches wherein the AI model processes the comprehensive input to determine whether the response can be generated using existing knowledge and personal information or requires invoking an external tool (Zhu, [0066]: "Subsequently, an operation 618 determines if there are any additional skills needed. If so, an operation 620 receives documents with post-LM skills.").
Bell, Matsuoka, McIntyre, and Zhu are analogous arts because they each belong to the same field of user dialogue systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the AI routing agent of Bell, as modified by the user interaction system of Matsuoka and language model skill system of McIntyre, to incorporate the teachings of Zhu to determine if a response can be responded to with existing knowledge or if an external tool is required. This lets the system extend its functionality if different skills are needed to respond to a user’s query (Zhu, [0066]). This increases the amount of queries the system can respond to, but still allows it to use existing knowledge if possible.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Saligrama et al. (US Pat. Pub. No. 2025/0110979 A1) discloses a system for distributed orchestration of natural language tasks.
Vishnoi et al. (US Pat. Pub. No. 2020/0342850 A1) discloses a system for chatbot routing.
Jessen, Carl Reed discloses a virtual agent for the retrieval and analysis of information.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TYLER J BECKER whose telephone number is (703)756-1271. The examiner can normally be reached M-Th, 7:15am-5:45pm PT.
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, Daniel Washburn can be reached at (571) 272-5551. 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.
/TYLER BECKER/ Examiner, Art Unit 2657
/SAMUEL G NEWAY/ Primary Examiner, Art Unit 2657
Prosecution Insights