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 § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-6, 8-13, 15-20 rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more.
Claim 1 recites an abstract idea, namely receiving information in the form of a natural language request, identifying a scenario based on the request, generating further information based on the request and identified scenario, evaluating whether the identified scenario is accepted or rejected, and, when accepted, using the identified scenario to formulate information for generating a response. These limitations describe observation, evaluation, judgement, and the formulation of information based upon the results of the evaluation, which fall within the mental process grouping.
The claim additionally recites one or more hardware processors, memory, and first, second, and third large language models that are used to perform the foregoing analysis and information generation.
These additional elements do not integrate the judicial exception into a practical application. The hardware processors, memory, and LLMs are used as tools for carrying out the recited information analysis, evaluation, and generation. The claim does not recite a particular improvement to the operation or architecture of the hardware processors, memory, and LLMs themselves, such as improved model architecture, training technique, inference technique, or any other improvement to computer functionality.
Instead, the claim applies the abstract analysis through computer components and LLMs at a high level of generality. Merely implementing an abstract idea using a computer as a tool does not integrate the exception into a practical application. The additional elements, considered individually and in combination, do not amount to significantly more than the judicial exception.
The processors and memory execute and store instructions associated with the recited information analysis process. Likewise, the recited LLMs are invoked to receive prompts, generate outputs, and pass information through the claimed workflow. The claim does not recite a technological implementation or improvement to these components that provides an inventive concept independent of the abstract information analysis process.
Accordingly, the additional elements merely implement the judicial exception using computer and machine learning components and do not transform the abstract idea into patent eligible subject matter.
With respect to claim 2, it recites retrieving information for use in the foregoing analysis and does not meaningfully limit the judicial exception or improve the functioning of computer or database. Accordingly, the additional limitation does not integrate the exception into a practical application or amount to significantly more.
With respect to claim 3, it recites a user interface receiving a natural language request. A user interface merely provides a mechanism for retrieving the information upon which the abstract process operates. Accordingly, the additional limitation does not integrate the exception into a practical application or amount to significantly more.
With respect to claim 4, it recites generating another prompt upon rejection of the scenario identifier based on the natural language request and output from the second LLM. This limitation merely continues the information evaluation and generation process after a determination and does not recite an improvement to computer or LLM functionality.
With respect to claim 5, it recites accessing conversation memory with the user. This limitation merely retrieves stored information for the claimed analysis. The use of memory to store and receive information does not limit the exception or amount to significantly more.
With respect to claim 6, it recites determining whether the user has a role allowed to execute a scenario. This amounts to evaluation of authorization information and making a determination based thereon. Accordingly, the additional limitation does not improve computer functionality and does not integrate the exception into a practical application or amount to significantly more.
Claims 8-13 and claims 15-20 contain similar limitations to claims 1-6 and are rejected for the same reasons.
With respect to claim 7, the additional limitations recite breaking the natural language request into a plurality of sub-tasks, generating separate prompts based on the respective sub tasks and using a scenario identifier alongside prompt generation. Taken as a whole, these limitations require coordinated computer-based processing and interaction among multiple LLMs alongside multiple sub tasks simultaneously and are not practically performed in the human mind. Accordingly, claim 7 is not considered to recite the mental process exception and is not rejected under 35 U.S.C. 101.
Claim 14 contains similar limitations to claim 7, in the form of a non-transitory computer-readable medium. Thus, it is not rejected under 35 U.S.C. 101 for the same reasons.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 102(a)(1) and 35 U.S.C. 102(a)(2) a as being anticipated by Bell et al. (US 20240404687).
Regarding claim 1, Bell discloses:
A system for recommending data assets, the system comprising:
one or more hardware processors (The method 1300 is performed at a computing system (e.g., a client device, server system, and/or service platform) having one or more processors [0182]); and
a memory that stores instructions (memory 218, and one or more communication buses 217 for interconnecting these components [0067]) that, when executed by the one or more hardware processors, cause the one or more hardware processors to perform operations comprising (the client device 102 includes a processor or other control circuitry) [0067]):
generating, based on a natural language request, a first prompt for a first large language model (LLM) (the agent-builder application is able to create a message to pass to the machine-learning model that, in conjunction with the prompt provided by the user [0214]);
receiving, from the first LLM and in response to the first prompt, a scenario identifier (allows the composite orchestration to determine which agent is the appropriate agent to answer a particular query [0214] (ii) in response to the request, identifying a first agent type from a set of agent types based on one or more requirements for performing the specific task [0230]);
generating, based on context of the natural language request (Another example agent type is a custom-chain agent module (e.g., a super agent module) that takes an input prompt, analyzes the prompt (e.g., parsing the prompt into one or commands and/or a plurality of tokens), and transmits information from the parsed prompt (e.g., commands and/or tokens) to a model 228 or other component [0124]) and the scenario identifier, (the computing system selects (2604), by a machine-learning model trained to select from among a plurality of task-specific machine-learning models each trained to assist with one of a plurality of clinical tasks, a respective task-specific machine-learning model from among the plurality of task-specific machine-learning models based on the prompt [0292]) a second prompt for a second LLM (the system deploys a task-specific agent model associated with a task-specific machine-learning model that specializes in understanding context associated with the particular domain, such as by training within the particular domain using knowledge database 404 [0233] For example, an output from the large-language model represented by the block 1834C in FIG. 18D can be provided as an input to another large-language model for performing a different task [0323]);
receiving, from the second LLM and in response to the second prompt, (each respective agent module 6102 is associated with a defined domain of information and/or a task-specific capability, which allows for retrieving a particular agent module 6102 based on information determined from a prompt provided by a user and/or based on a selection of the agent module 6102 by the user [0084]) acceptance or rejection of the scenario identifier (In some embodiments, validating the agent module comprises determining whether the agent module is capable of performing the specific task [506] defines a conditional logic 6112 for performing the specific task of the task-specific machine-learning mode [0237]);
in response to a determination that the scenario identifier is accepted, (validating the agent module comprises determining whether the agent module is capable of performing the specific task [506]) generating a third prompt for a third LLM based on the scenario identifier (In some embodiments, the agent includes two or more models, each of the two or more models configured to operate on a different type of data. For example, an output from the large-language model represented by the block 1834C in FIG. 18D can be provided as an input to another large-language model for performing a different task [0323]); and
providing the third prompt to the third LLM (the first node is associated with a first domain-specific machine-learning model in the plurality of task-specific machine-learning models, each task-specific machine-learning model in the plurality of task-specific machine-learning model [0296]) to generate a response to the natural language request (first node in a plurality of interconnected nodes, thereby generating the response different from prompt and responsive to the prompt from the use [0296]);
Regarding claim 2, Bell discloses:
The system of claim 1, wherein the operations further comprise:
accessing, from a database and based on the scenario identifier, text to include in the third prompt (In an embodiment, a prompt for the agent module 6102 includes retrieved patient context, inclusion/exclusion criteria, and a question to determine if the patient satisfies the criteria [0151]);
Regarding claim 3, Bell discloses:
The system of claim 1, wherein the operations further comprise:
receiving, via a user interface, the natural language request (The hub component may be used in conjunction with the AI-enabled clinical assistant to allow physicians to interact using conversational language including natural language inputs, follow-up questions, and remarks [0060]);
Regarding claim 4, Bell discloses:
The system of claim 1, wherein the operation further comprise:
in response to a determination that the scenario identifier is rejected, (a recursive agent module (e.g., configured to recursively perform an action or function until a condition is met) [0317]) generating a fourth prompt for the first LLM based on the natural language request and output from the second LLM (e.g., the block representing the agent router of the representation 1900 in FIG. 19A indicates a connection between the agent router orchestration and the LLM messages builder orchestration) [0323]);
Regarding claim 5, Bell discloses:
The system of claim 1, wherein the operations further comprise:
accessing, by the first LLM, a conversation memory of communications with a user that provided the natural language request (In some embodiments, the agent module 6102 sends the context, query, and optionally chat history to a node 6108 associated model 228 component (e.g., a large language model [0149]);
Regarding claim 6, Bell discloses:
The system of claim 1, wherein the operations further comprise:
determining, by the first LLM, (In some embodiments, the data module 240 (e.g., document index) shown in FIG. 6 includes one or more of: [0130]) whether a user that provided the natural language request has a role that is allowed to execute a scenario identified by the scenario identifier (a data classifier (e.g., public, internal, or secret), and/or a visibility setting (e.g., private, public, or restricted by role) [0130]);
Regarding claim 7, Bell discloses:
The system of claim 1, wherein the operations further comprise:
breaking the natural language request into a plurality of sub-tasks including a first sub-task and a second sub-task (In some embodiments, the digital assistant includes a frontend agent module (e.g., including a language model) configured to identify commands and/or tokens in user queries [0179] the prompt is parsed, such as by applying the prompt to an input node 6108 of a node architecture 6106, in order to generate the plurality of tokens [0234]) wherein the first prompt is based on the first sub task (the digital assistant includes a routing agent module configured to route subsets of the commands and/or tokens to appropriate agent modules [0179] one or more commands represented by various subsets of tokens, which can be provided to various nodes 6108 of one or more agent modules 6102 [0234] The examiner interprets a plurality of commands/tokens as the claimed first sub-task and second sub-task. The respective commands/tokens are provided to appropriate agent modules through the prompts/input which generated the commands/tokens);
generating a fourth prompt for the first LLM based on the second sub-task (In some embodiments, parsing the prompt into the plurality of tokens allows for structuring the prompt into a form that is optimized for input for a particular agent module 6102, model 228, and/or node 6108. Advantageously, the plurality of tokens provides for delineations of the prompt into one or more commands represented by various subsets of tokens, which can be provided to various nodes 6108 of one or more agent modules 6102 [0234] In some embodiments, an agent module 6102-1 is configured for a first specific task of generating a summary report of a patient's medical records, a second agent module 6102-2 is configured for a second specific-task of guiding a patient through a care plan [0084]);
receiving, from the first LLM and in response to the fourth prompt, a second scenario identifier (In some embodiments, determining that the prompt requests assistance with a clinical task further comprises parsing the prompt into one or more commands, thereby forming an intent of the prompt for requesting assistance with a clinical task [0292]); and
generating a fifth prompt for the third LLM (the agent-builder application is able to create a message to pass to the machine-learning model that, in conjunction with the prompt provided by the user [0214]) based on the second scenario identifier (allows the composite orchestration to determine which agent is the appropriate agent to answer a particular query (e.g., a query determined based on an identified intent of a user prompt) [0234] For example, the categorization agent module determines an intent/domain for an input and the routing agent module routes the input to a downstream component in accordance with the determined intent/domain [0120]);
wherein the response to the natural language request is further generated by providing the fifth prompt to the third LLM (In some embodiments, an agent module 6102-1 is configured for a first specific task of generating a summary report of a patient's medical records, a second agent module 6102-2 is configured for a second specific-task of guiding a patient through a care plan, a third agent module 6102-3 is configured for a third specific-task of creating patient care guidelines based on a patient's health profile, a fourth agent module 6102-4 is configured for a fourth specific-task of identifying patients requiring follow-up at a hospital, a fifth agent module 6102-5 is configured for a fifth specific-task of identifying changes in a standard of care for a disease setting, a sixth agent module 6102-6 is configured for a sixth specific-task of evaluating unstructured data associated with a patient to identify a cohort of similar patients, a seventh agent module 6102-7 is configured for a seventh specific-task of phenotyping a subject, or a combination thereof. However, the present disclosure is not limited thereto [0084] The examiner notes this as an example of compound prompting, providing a plurality of prompts/sub-tasks to a plurality of agents done in response to the natural language request);
Claim 8 contains similar limitations to claim 1 and is therefore rejected for the same reasons. Additionally, Bell discloses:
A non-transitory computer-readable medium that stores instructions (some embodiments include a non-transitory computer-readable storage medium storing one or more sets of instructions for execution [0513]);
Claim 9 contains similar limitations to claim 2 and is therefore rejected for the same
reasons.
Claim 10 contains similar limitations to claim 3 and is therefore rejected for the same
reasons.
Claim 11 contains similar limitations to claim 4 and is therefore rejected for the same
reasons.
Claim 12 contains similar limitations to claim 5 and is therefore rejected for the same
reasons.
Claim 13 contains similar limitations to claim 6 and is therefore rejected for the same
reasons.
Claim 14 contains similar limitations to claim 7 and is therefore rejected for the same
reasons.
Claim 15 contains similar limitations to claim 1 and is therefore rejected for the same reasons. Additionally, Bell discloses:
A method comprising: generating, by one or more hardware processors (the one or more sets of instructions including instructions for performing one or more of the methods described herein [0512]);
Claim 16 contains similar limitations to claim 2 and is therefore rejected for the same
reasons.
Claim 17 contains similar limitations to claim 3 and is therefore rejected for the same
reasons.
Claim 18 contains similar limitations to claim 4 and is therefore rejected for the same
reasons.
Claim 19 contains similar limitations to claim 5 and is therefore rejected for the same
reasons.
Claim 20 contains similar limitations to claim 6 and is therefore rejected for the same
reasons.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Kyle Espinas whose telephone number is (571)270-0596. The examiner can normally be reached Monday Friday, 8 a.m. 5 p.m. ET..
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, Andrew Flanders can be reached at (571) 272-7516. 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.
/Kylenino Espinas/
Patent Examiner
Art Unit 2655
8/27/2026
/ANDREW C FLANDERS/Supervisory Patent Examiner, Art Unit 2655
Prosecution Insights