DETAILED ACTION
Claims 1-20 are pending in this application.
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, 8 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Pat. No. 12,670,899 B1 issued to Qiu et al. in view of U.S. Pub. No. 2025/0190501 A1 to Konakanchi et al. and further in view of U.S. Pub. No. 2024/0202452 A1 to Schillace et al.
As to claim 1, Qiu teaches a system comprising:
a memory storing program code (Storage 1208); and
one or more processing units to execute the program code to (Processors 1204) cause the system to:
receive a natural language query of a data source (User Input Data 227/query a storage (e.g., a database, repository, knowledge base, etc.) ) (“…In some embodiments, the LLM orchestrator component 230 may generate prompt data representing a prompt for input to the language models. As shown in FIG. 2, the system component(s) 220 receive user input data 227, which may be provided to the LLM orchestrator component 230. In some instances, the user input data 227 may correspond to various data types, such as text (e.g., a text or tokenized representation of a user input), audio, image, video, etc. For example, the user input data may include input text (or tokenized) data when the user input is a typed natural language user input. For further example, prior to the LLM orchestrator component 230 receiving the user input data 227, another component (e.g., an automatic speech recognition (ASR) component 850) of the system 100 may receive audio data representing the user input. The ASR component 850 may perform ASR processing on the audio data to determine ASR data corresponding to the user input, which may correspond to a transcript of the user input. As described below, with respect to FIG. 8, the ASR component 850 may determine ASR data that includes an ASR N-best list including multiple ASR hypotheses and corresponding confidence scores representing what the user may have said. The ASR hypotheses may include text data, token data, ASR confidence score, etc. as representing the input utterance. The confidence score of each ASR hypothesis may indicate the ASR component's 850 level of confidence that the corresponding hypothesis represents what the user said. The ASR component 850 may also determine token scores corresponding to each token/word of the ASR hypothesis, where the token score indicates the ASR component's 850 level of confidence that the respective token/word was spoken by the user. The token scores may be identified as an entity score when the corresponding token relates to an entity. In some instances, the user input data 227 may include a top scoring ASR hypothesis of the ASR data. As an even further example, in some embodiments, the user input may correspond to an actuation of a physical button, data representing selection of a button displayed on a graphical user interface (GUI), image data of a gesture user input, combination of different types of user inputs (e.g., gesture and button actuation), etc. In such embodiments, the system 100 may include one or more components configured to process such user inputs to generate the text or tokenized representation of the user input (e.g., the user input data 227)…” Col. 10 Ln. 56-67, Col. 11 Ln. 1-67, Col. 12 Ln. 1-67);
generate a first prompt to prompt determination of a plan to respond to the query (Prompt Data 315) (“…In some embodiments, the LLM orchestrator component 230 may generate prompt data representing a prompt for input to the language models…As further shown in FIG. 3, the user input data 227 is received at the plan prompt generation component 310. The plan prompt generation component 310 processes the user input data 227 to generate prompt data 315 representing a prompt for input to the plan generation language model 320. The plan prompt generation component 310 may further receive context data 305 representing various contextual signals associated with the user input data 227, such as weather information, time of day, device information associated with the device that sent the user input data 227 (e.g., device ID, device states, historical device interaction data, etc.). The prompt data 315 may be generated based on combining the user input data 227 and the context data 305…” Col. 10 Ln. 56-58, Col. 14 Ln. 39-51);
transmit the first prompt to a text generation model (“…In some embodiments, the LLM orchestrator component 230 may generate prompt data representing a prompt for input to the language models…As further shown in FIG. 3, the user input data 227 is received at the plan prompt generation component 310. The plan prompt generation component 310 processes the user input data 227 to generate prompt data 315 representing a prompt for input to the plan generation language model 320. The plan prompt generation component 310 may further receive context data 305 representing various contextual signals associated with the user input data 227, such as weather information, time of day, device information associated with the device that sent the user input data 227 (e.g., device ID, device states, historical device interaction data, etc.). The prompt data 315 may be generated based on combining the user input data 227 and the context data 305…” Col. 10 Ln. 56-58, Col. 14 Ln. 39-51);
receive the plan from the text generation model in response to the first prompt (Plan Generation Component 235) (“…The user input data 227 may be received at the LLM orchestrator component 230 of the system component(s) 220. In particular, the user input data 227 may be received at the plan generation component 235, which may be configured to generate a list (e.g., one or more) of tasks (e.g., steps/actions) that are to be completed in order to perform an action responsive to the user input and select a task of the list of tasks that is to be completed first (e.g., in a current iteration of processing by the system 100), as described in detail herein below with respect to FIG. 3. In instances where the plan generation component 235 generates more than one task to be completed in order to perform the action responsive to the user input, the plan generation component 235 may further maintain and prioritize the list of tasks as the processing of the system 100 with respect to the user input is performed. In other words, as the system 100 processes to complete the list of tasks, the plan generation component 235 may (1) incorporate the potential responses associated with completed tasks into data provided to other components of the system 100; (2) update the list of tasks to indicate completed (or attempted, in-progress, etc.) tasks; (3) generate an updated prioritization of the tasks remaining to be completed (or tasks to be attempted again); and/or (4) determine an updated current task to be completed. In some embodiments, the plan generation component 235 may further be configured to, prior to generating the list of tasks, cause the modification of (e.g., removal, replacement, truncation, etc.) values included in the data input to the plan generation component 235 (e.g., the user input data 227, context data, potential responses, etc.) that are determined to not be useful to the processing of the LLM orchestrator component 230, as is discussed in detail herein below with respect to FIG. 4. The plan generation component 235 may generate and send task processing data 237 representing the selected task to be completed and various other information needed to perform further processing with respect to the task (e.g., the user input data 227, an indication of the selected task, potential responses associated with previous tasks, the remaining task(s), and context data associated with the user input data 227, as described in detail herein below with respect to FIG. 3) to the LLM shortlister component 240…” Col. 11 Ln. 66-67, Col. 12 Ln. 1-39);
generate a second prompt (Prompt Data 335) to prompt determination of an application programming interface (API) call and a parsing instruction (shortlister language model 540 processes the prompt data 515 to generate one or more API calls), the second prompt including the plan (Prompt Data 335) (“…The model output data 325 is sent to the task selection prompt generation component 330, which processes the model output data 325 to generate prompt data 335 representing a prompt for input to the task selection language model 340. In some embodiments, such prompt data 335 may be generated based on combining the user input data 227, the context data 305, the personalized context data 267, the prompt data 315, and/or the model output data 325. In some embodiments, the plan generation component 235 may include another component that parses the model output data 325 to determine the one or more tasks and may send a representation of the one or more tasks to the task selection prompt generation component 330…In some embodiments, the prompt data 335 may be an instruction for the task selection language model 340 to select a task of the one or more tasks that is to be completed first (e.g., completed during the current iteration of processing) given the information (e.g., user input data 227, the personalized context data 267, and the one or more tasks) included in the prompt data 335. In some embodiments, the prompt data 335 may further include an instruction for the task selection language model 340 to determine a priority of the one or more tasks (e.g., an ordered list representing the order in which the one or more tasks are to be completed). As discussed above, with respect to the plan prompt generation component 310, in some embodiments, the task selection prompt generation component 330 may also include in the prompt data 335 a sample processing format to be used by the task selection language model 340 when processing the prompt. Similarly, in some embodiments, the task selection prompt generation component 330 may generate the prompt data 335 according to a template format, such as: { Select the top prioritized task given the ultimate goal of [user input data 227 (or a representation of a determined intent included in the user input data 227] Here are the completed tasks, their results, and user inputs so far: [completed tasks, modified data 425, dialog history, context data 305, personalized context data 267] Here are the task candidates: [remaining tasks] Return your selected task, return None if the goal is achieved or indicate existing ambiguities. }…The shortlister language model 540 processes the prompt data 515 to generate one or more API calls corresponding to request(s) that the corresponding APIs return a description of an action(s) that the APIs are configured to/will perform with respect to the user input and/or the current task. As such, in some embodiments, the shortlister language model 540 may generate API calls for a subset of the APIs represented in the prompt data 515. The shortlister language model 540 may generate the one or more APIs calls (including the required input parameters) by applying in-context learning for cold-starting APIs (e.g., one-shot/few-shot learning). For example, in embodiments where the relevant API data 535 includes the component descriptions, the shortlister language model 540 may use the one or more exemplars included in the component descriptions (included in the prompt data 515) to determine the one or more input parameters for the API call. In some embodiments, the shortlister language model 540 may be finetuned on such exemplars (e.g., during offline or runtime processing), such that the shortlister language model 540 is capable of determining the one or more input parameters for the given API call…” Col. 24 Ln. 38-67, Col. 25 Ln. 1-16, Col. 28 Ln. 44-65);
transmit the second prompt to the text generation model (Prompt Data 335) (“…In some embodiments, the prompt data 335 may be an instruction for the task selection language model 340 to select a task of the one or more tasks that is to be completed first (e.g., completed during the current iteration of processing) given the information (e.g., user input data 227, the personalized context data 267, and the one or more tasks) included in the prompt data 335. In some embodiments, the prompt data 335 may further include an instruction for the task selection language model 340 to determine a priority of the one or more tasks (e.g., an ordered list representing the order in which the one or more tasks are to be completed)…” Col. 24 Ln. 51-61).
Qiu is silent with reference to receive the API call and the parsing instruction from the text generation model in response to the second prompt,
transmit the API call to the data source,
receive a response to the API call from the data source,
generate a third prompt to prompt determination of a parsed response, the third prompt including the response and the parsing instruction,
transmit the third prompt to the text generation model,
receive the parsed response from the text generation model in response to the third prompt, and
determine an answer to the query based on the parsed response.
Konakanchi teaches receive the API call and the parsing instruction from the text generation model in response to the second prompt (an application programming interface (API) that facilitates operations by the large language model),
transmit the API call to the data source (a function call requesting performance of an API operation on a content item stored in the content management system),
receive a response to the API call from the data source (Act 806) (“…As shown in FIG. 8, the series of acts 800 includes an act 802 of integrating, into a computing environment of a large language model, a content management system plugin comprising computer code for an application programming interface (API) that facilitates operations by the large language model on content items stored in a content management system, an act 804 of receiving, from the large language model via the content management system plugin, a function call requesting performance of an API operation on a content item stored in the content management system, and an act 806 of executing the API operation on the content item stored in the content management system in response to the function call…In particular, in some implementations, the act 802 includes integrating, into a computing environment of a large language model, a content management system plugin comprising computer code for an application programming interface (API) that facilitates operations by the large language model on content items stored in a content management system, the act 804 includes receiving, from the large language model via the content management system plugin, a function call requesting performance of an API operation on a content item stored in the content management system, and the act 806 includes executing the API operation on the content item stored in the content management system in response to the function call from the content management system plugin integrated within the large language model. In some implementations, the act 802 includes integrating, into a computing environment of a large language model, a content management system plugin comprising computer code for an application programming interface (API), wherein the content management system plugin facilitates operations by the large language model on content items stored in a content management system. In some implementations, the act 804 includes receiving, via the content management system plugin, a function call requesting performance of an API operation by the large language model on a content item stored in the content management system. In some implementations, the act 806 includes executing the API operation on the content item stored in the content management system in response to the function call from the large language model via the content management system plugin…For example, in some implementations, the series of acts 800 includes integrating the content management system plugin by installing the computer code within the computing environment of the large language model to make the application programming interface available to the large language model….In addition, in some implementations, the series of acts 800 includes receiving, from the large language model via the content management system plugin, an additional function call requesting performance of an additional API operation on the content item stored in the content management system; and executing the additional API operation on the content item in response to the additional function call…Moreover, in some implementations, the series of acts 800 includes executing the API operation on the content item stored in the content management system by executing at least one of a search operation, a metadata access operation, a download operation, a copying operation, a moving operation, an editing operation, a content generation operation, a sharing operation, or an upload operation. In some implementations, the series of acts 800 includes executing the API operation on the content item stored in the content management system by executing one or more of a search operation, a metadata access operation, a download operation, a copying operation, a moving operation, an editing operation, a content generation operation, a sharing operation, or an upload operation…Furthermore, in some implementations, the series of acts 800 includes executing the API operation on the content item stored in the content management system by executing a team-based API operation on a plurality of content items stored across a plurality of user accounts of the content management system. In some implementations, the series of acts 800 includes executing the API operation on the content item stored in the content management system by: executing a team-based API operation on the content item stored for a first user account of the content management system; and executing the team-based API operation on an additional content item stored for a second user account of the content management system…” paragraphs 0006-0101).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claim invention to modify the system of Qiu with the teaching of Konakanchi because the teaching of Konakanchi would improve the system of Qiu by providing an application programming interface for accessing and retrieving content items.
Schillace teaches generate a third prompt (one or more prompts) to prompt determination of a parsed response, the third prompt including the response and the parsing instruction (Prompt Generator 128),
transmit the third prompt to the text generation model (generative large language model (LLM)),
receive the parsed response from the text generation model in response to the third prompt (generate model output responsive) (“…The prompt generator 128, receives the task objective and task request and utilizes them to generate one or more prompts for the ML model. The prompt generator 128 may generate one or more prompts that when processed a ML model, such as a generative large language model (LLM), provide sufficient context for the ML model to generate model output responsive to the task objective associated with the input. That is, the generated prompts enable a ML model to comprehend the context surrounding an input that has a task objective and task request (e.g., intent or specific meaning) previously unknown to the general ML model utilized from the model repository 130. Thus, the one or more prompts encompass the semantic context of the task objective and task request so that the ML model can generate model output responsive to the requested task and/or intent without requiring additional training or fine-tuning of the model prior to generating model output responsive to the task or intent. It will be appreciated that a prompt may be comprised of a plurality of prompt templates. A prompt template may include any of a variety of data, including, but not limited to, natural language, image data, audio data, video data, and/or binary data, among other examples. In examples, the type of data may depend on the type of ML model that will be leveraged to respond to the received input. One or more fields, regions, and/or other parts of the prompt may be populated with one or more prompt templates encompassing input and/or context, thereby generating a prompt that can be processed by an ML model of the model repository 130 according to aspects described herein…” paragraph 0024), and
determine an answer to the query based on the parsed response (“…Response evaluator 132 may process the model output to determine if it is responsive to the input. The response evaluator 132 may evaluate the model output, which may include any of a variety of types of content (e.g., text, images, programmatic output, code, instructions for a 3D printed object, etc.) which may be returned to the user, executed, parsed, and/or otherwise processed (e.g., as one or more API calls or function calls) to verify functionality…” paragraph 0029).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claim invention to modify the system of Qiu and Konakanchi with the teaching of Schillace because the teaching of Schillace would improve the system of Qiu and Konakanchi by providing an generative large language model (LLM) for processing and providing responses to queries.
As to claims 8 and 15, see the rejection of claim of 1 except for one or more non-transitory computer-readable media.
Qiu teaches one or more non-transitory computer-readable media (Storage 1208).
Claims 2, 3, 9, 10 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Pat. No. 12,670,899 B1 issued to Qiu et al. in view of U.S. Pub. No. 2025/0190501 A1 to Konakanchi et al. and further in view of U.S. Pub. No. 2024/0202452 A1 to Schillace et al. as applied to claims 1, 8 and 15 above, and further in view of U.S. Pub. No. 2024/0427631 A1 to Corlatescu et al.
As to claim 2, Qiu as modified by Konakanchi and Schillace teaches the system of Claim 1, however it is silent with reference to wherein the first prompt includes the query and an API specification.
Corlatescu teaches wherein the first prompt includes the query and an API specification (Service API Documentation 170 (170a, 170b, 170c)) (“…LLM 125 passes the message to agent interface 140, and agent interface 140 sends the message to the corresponding one of service agents 160. Each of service agents 160 use service API documentation 170 (170a, 170b, 170c) to construct prompts for their corresponding LLM 165 (165a, 165b, 165c). Service API documentation 170 includes details about the inner workings of an API endpoint and may include technical specifications, data models, error codes, rate limits, security considerations, and other intricacies related to the API endpoint's implementation. Service agent 160 inputs the prompt into its LLM 165, and LLM 165 produces an agent response. In some embodiments, the agent response includes API calls to its corresponding service (e.g., Service A, Service B, Service C)…” paragraph 0129).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claim invention to modify the system of Qiu, Konakanchi and Schillace with the teaching of Corlatescu because the teaching of Corlatescu would improve the system of Qiu, Konakanchi and Schillace by providing documentation that outlines the various endpoints, methods, parameters, and data formats developers use t access and manipulate functionality by application or service.
As to claim 3, Qiu teaches the system of Claim 2, wherein the plan includes a sequence of two or more API calls (one or more API calls) (“…The shortlister language model 540 processes the prompt data 515 to generate one or more API calls corresponding to request(s) that the corresponding APIs return a description of an action(s) that the APIs are configured to/will perform with respect to the user input and/or the current task. As such, in some embodiments, the shortlister language model 540 may generate API calls for a subset of the APIs represented in the prompt data 515. The shortlister language model 540 may generate the one or more APIs calls (including the required input parameters) by applying in-context learning for cold-starting APIs (e.g., one-shot/few-shot learning). For example, in embodiments where the relevant API data 535 includes the component descriptions, the shortlister language model 540 may use the one or more exemplars included in the component descriptions (included in the prompt data 515) to determine the one or more input parameters for the API call. In some embodiments, the shortlister language model 540 may be finetuned on such exemplars (e.g., during offline or runtime processing), such that the shortlister language model 540 is capable of determining the one or more input parameters for the given API call…” Col. 28 Ln. 44-65).
As to claim 9, see the rejection of claim 2 above.
As to claim 10, see the rejection of claim 3 above.
As to claim 16, see the rejection of claims 2 and 3 above.
Claims 4, 5, 11, 12, 17 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Pat. No. 12,670,899 B1 issued to Qiu et al. in view of U.S. Pub. No. 20250190501 A1 to Konakanchi et al. and further in view of U.S. Pub. No. 20240202452 A1 to Schillace et al. as applied to claims 1, 8 and 15 above, and further in view of U.S. Pub. No. 2025/0363156 A1 to Dong et al.
As to claim 4, Qiu as modified by Konakanchi and Schillace teaches the system of Claim 1, however it is silent with reference to wherein determination of an answer to the query based on the parsed response comprises: generate a fourth prompt including the plan and the parsed response; transmit the fourth prompt to the text generation model; and receive the answer from the text generation model in response to the fourth prompt.
Dong teaches wherein determination of an answer to the query based on the parsed response comprises:
generate a fourth prompt including the plan and the parsed response (tree 400 for cascading prompts);
transmit the fourth prompt to the text generation model (Generative Machine Learning (ML) Model 130) (“…FIG. 4 is a graph illustrating an example tree 400 for cascading prompts, as utilized by the prompt module 116. As shown, the example tree 400 may include four levels of prompts, labelled as 401, 402, 403, and 404. The prompt module 116 may proceed through the tree 400 by transmitting a prompt to a model (e.g., model 130) and proceeding to a subsequent prompt on the next level (e.g., 402 after 401) based on the output of the model. The tree 400 may begin with prompt 410, which the prompt module 116 may transmit to the model for response. The prompt module 116 may then analyze the resultant content from the model, and may determine the subsequent prompt from the tree based on the analysis. In one example, which is highlighted in FIG. 4 as critical path 4, the prompt module 116 may analyze the content generated by the model in response to prompt 410 and may determine that the next prompt is prompt 412 on level 402. The logical relationship between the content responsive to prompt 410 and the provision of prompt 412 may be based on domain-specific knowledge and prior model testing, as may all logical relationships for progressing through the tree 400, as discussed further below. After transmitting prompt 412 to the model and analyzing the resultant output, the prompt module 116 may move to prompt 425 at level 403 and, finally, prompt 446 at level 404. In the decision tree 400 shown in FIG. 4, prompt 446 is a “final” node, such that there is no subsequent prompt or level that follows prompt 446. Accordingly, the model output responsive to prompt 446 may be considered a “final” output, and may be post-processed according to the methods described herein…” paragraph 0043); and
receive the answer from the text generation model in response to the fourth prompt (“…The method 600 may include, at block 680, outputting a combined summary to the user device based on the summaries for the chunks provided by the model. To synthesize the combined summary, a correct version of each summary generated for each respective chunk may be stitched (or pieced) together by ordering the summaries based on an order of the respective chunks from the original document…” paragraph 0059).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claim invention to modify the system of Qiu, Konakanchi and Schillace with the teaching of Dong because the teaching of Dong would improve the system of Qiu, Konakanchi and Schillace by providing a casacade of related functions/tasks that work cooperatively to process the functions/tasks.
As to claim 5, Qiu as modified by Konakanchi and Schillace teaches system of Claim 4, however it is silent with reference to wherein the fourth prompt comprises the second prompt and the parsed response.
Dong teaches wherein the fourth prompt comprises the second prompt and the parsed response (tree 400 for cascading prompts) (“…FIG. 4 is a graph illustrating an example tree 400 for cascading prompts, as utilized by the prompt module 116. As shown, the example tree 400 may include four levels of prompts, labelled as 401, 402, 403, and 404. The prompt module 116 may proceed through the tree 400 by transmitting a prompt to a model (e.g., model 130) and proceeding to a subsequent prompt on the next level (e.g., 402 after 401) based on the output of the model. The tree 400 may begin with prompt 410, which the prompt module 116 may transmit to the model for response. The prompt module 116 may then analyze the resultant content from the model, and may determine the subsequent prompt from the tree based on the analysis. In one example, which is highlighted in FIG. 4 as critical path 4, the prompt module 116 may analyze the content generated by the model in response to prompt 410 and may determine that the next prompt is prompt 412 on level 402. The logical relationship between the content responsive to prompt 410 and the provision of prompt 412 may be based on domain-specific knowledge and prior model testing, as may all logical relationships for progressing through the tree 400, as discussed further below. After transmitting prompt 412 to the model and analyzing the resultant output, the prompt module 116 may move to prompt 425 at level 403 and, finally, prompt 446 at level 404. In the decision tree 400 shown in FIG. 4, prompt 446 is a “final” node, such that there is no subsequent prompt or level that follows prompt 446. Accordingly, the model output responsive to prompt 446 may be considered a “final” output, and may be post-processed according to the methods described herein…” paragraph 0043).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claim invention to modify the system of Qiu, Konakanchi and Schillace with the teaching of Dong because the teaching of Dong would improve the system of Qiu, Konakanchi and Schillace by providing a cascade of related functions/tasks that work cooperatively to process the functions/tasks.
As to claims 11 and 17, see the rejection of claim 4 above.
As to claims 12 and 18, see the rejection of claim 5 above.
Allowable Subject Matter
Claims 6, 7, 13, 14, 19 and 20 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Reasons for allowance
The following is an examiner’s statement of reasons for allowance:
The closest prior art of records, (U.S. Pat. No. 12,670,899 B1 issued to Qiu et al., U.S. Pub. No. 2025/0190501 A1 to Konakanchi et al. and U.S. Pub. No. 2024/0202452 A1 to Schillace et al.), taken alone or in combination do not specifically disclose or suggest the claimed recitations (claims 6, 7, 13, 14, 19 and 20), when taken in the context of claims as a whole.
Any comments considered necessary by applicant must be submitted no later than the payment of the issue fee and, to avoid processing delays, should preferably accompany the issue fee. Such submissions should be clearly labeled “Comments on Statement of Reasons for Allowance.”
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. Pub. No. 2025/0094717 A1 to Kanuga et al. and directed to returning references for answers generated by a language model.
U.S. Pub. No. 2024/0289545 A1 to Miller et al. and directed to a system for creating solution plans to solve problems in an AI system including a large language model (LLM), a plan creation component, a plan working memory, and a plan execution component.
U.S. Pub. No. 2025/0139447 A1 to Agarwal et al. and directed to domain-specific prompt processing and answering via large language models and artificial intelligence planners.
U.S. Pub. No. 2025/0272305 A1 to Kshrsagar et al. and directed to generative language model planner and agent determination in a database system.
U.S.. Pub. No. 2025/0272510 A1 to Kshrsagar et al. generative language model human readable plan generation and refinement in a database system.
U.S. Pub. No. 2025/0094465 A1 to XU et al. and directed to executing an execution plan with a digital assistant and using large language models.
U.S. Pub. No. 2026/0188312 A1 to Shi et al. and directed to natural language processing.
U.S. Pub. No. 2024/0273309 A1 to Heller et al. and directed to text generation interface system.
U.S. Pub. No. 2025/0005299 A1 to Padmanabhan et al. and directed to language model prompt authoring and execution in a database system.
U.S. Pub. No. 20250110957 A1 to Baldua et al. and directed to dynamic query planning.
U.S. Pub. No. 2025/0053754 A1 to Heller et al. and directed to text generation interface system.
U.S. Pub. No. 2024/0403290 A1 to Hawes et al. and directed to large language model response optimization using custom computer languages.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHARLES E ANYA whose telephone number is (571)272-3757. The examiner can normally be reached Mon-Fir. 9-6pm.
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, KEVIN YOUNG can be reached at 571-270-3180. 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.
/CHARLES E ANYA/Primary Examiner, Art Unit 2194
Prosecution Insights