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 § 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.
Claims 1-6 and 8-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Guo et al. (US Patent No. 12,424,209).
With regard to claim 1, Guo teaches a method comprising:
analyzing a meta-specification to identify (a) a plurality of datasets needed for accessing a third-party resource ([claim 1] shortlisting available components…one or more components to perform the task), and (b) a data type associated with each of the plurality of datasets ([col. 21, lines 6–11] the API provider component 190 may include an entity recognition (ER) component 410, which may be configured to process textual or tokenized input to link one or more entity references included in the textual or tokenized input to a specific corresponding entity known to the system 100);
selecting an interface layout for generating a graphical user interface (GUI) that includes a plurality of interface elements for collecting values for the plurality of datasets ([col. 6, lines 40-48] 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 127)),
wherein a particular interface element, of the plurality of interface elements ([col. 6, lines 40-48] image data of a gesture user input, combination of different types of user inputs (e.g., gesture and button actuation)), for collecting a particular value for a particular dataset is selected based on the data type associated with the particular dataset ([col. 30, lines 45-53] a system-generated response to the user input, a value representing how many times the user input was received during the time period, a domain (e.g., routine, smart home, shopping, weather, etc.), etc.); and
generating the GUI based on the interface layout ([col. 3, lines 1-10] the language model(s) may determine that one or more components have been selected to perform the function(s) (action(s)) responsive to the user input, generate a response informing the user of the actions to be performed, and, with authorization, cause the one or more components to perform the function(s) (e.g., action(s))).
With regard to claim 2, the limitations are addressed above and Guo teaches wherein selecting the interface layout further comprises selecting a checkbox control for a Boolean data type associated with a first dataset of the plurality of the datasets ([col. 17, lines 45-65] the action response data 197a-n may indicate whether or not the corresponding component is able to respond (e.g., the action response data 197a may include a Boolean value such as “yes” or “no” or other similar indications). In some embodiments, the shortlister language model 180 may filter and/or rank the action response data 197a-n based on information included in the prompt data 320 (e.g., the user input data 127, the relevant API data 310, the context data 205, the personalized context data 215, the prompt data 220, etc.)).
With regard to claim 3, the limitations are addressed above and Guo teaches wherein selecting the interface layout further comprises selecting a form field control for a String data type associated with a first dataset of the plurality of the datasets ([col. 13, lines 16-21] the template format may instruct the task selection language model 155 as to how it should process to select the task and/or prioritize the one or more tasks. In some embodiments, as discussed above, the format may further include indications of the “User:”, “Thought:”, “Action:”, “Observation:”, and/or “Response:” indicators).
With regard to claim 4, the limitations are addressed above and Guo teaches wherein selecting the interface layout further comprises selecting a dropdown menu control for an Integer data type associated with a first dataset of the plurality of the datasets ([col. 12, lines 1-37] to generate multiple predicted tasks for a given user input, where the system 100 may parse and filter the list of tasks during downstream processing (e.g., during the processing of the task selection language model 155). For example, based on processing the first example prompt data provided above, the plan generation language model 145 may output model output data: {“turn on all of the lights except the garage light,” “turn on all lights,” “identify which garage light,” “turn on all lights then turn off garage light,” “turn on all lights where user is located,” “turn on kitchen lights, living room lights, dining room lights, hallways lights” “turn on all lights on first floor,”} or the like).
With regard to claim 5, the limitations are addressed above and Guo teaches wherein the particular value is associated with a first parameter for a first function corresponding to an Application Programming Interface (API) for the third-party database ([col. 4, lines 1-10] a system capable of determining one or more (e.g., top-k) components (e.g., APIs) to process with respect to the user input and/or tasks based on their relevance to the user input or tasks allows the system to narrow the number of components to be considered by the corresponding language model, which increases both the efficiency and accuracy of the language model; [col. 14, lines 61-67] the API shortlister component 170 may use retrieval based approaches to retrieve the one or more relevant APIs from the index storage 165 which may store various information associated with multiple APIs such as API descriptions, API arguments (e.g., parameter inputs/outputs), identifiers for components (e.g., such as personalized context component 210, skill component(s) 194, LLM agent component(s) 192, TTS component 196) that provides the API, etc.).
With regard to claim 6, the limitations are addressed above and Guo teaches wherein generating the GUI further comprises:
generating the GUI ([col. 3, lines 1-10] the language model(s) may determine that one or more components have been selected to perform the function(s) (action(s)) responsive to the user input, generate a response informing the user of the actions to be performed, and, with authorization, cause the one or more components to perform the function(s) (e.g., action(s))) that includes a second plurality of interface elements for presenting a particular target dataset from executing code ([col. 24, lines 25-55] the system 100 may begin processing with respect to a second task associated with the user input) that invokes the first function using the particular value as input for the first parameter ([col. 30, lines 45-53] the global index storage 620 and/or the personalized index storage 630 may further include metadata associated with the historical user inputs, which may be further included in the global index data 625 and/or the personalized index data 635. For example, the global index storage 620 and/or the personalized index storage 630 may further include a user satisfaction associated with a system-generated response to the user input, a value representing how many times the user input was received during the time period, a domain (e.g., routine, smart home, shopping, weather, etc.), etc.).
With regard to claim 8, the limitations are addressed above and Guo teaches the particular value having a different format than the appropriate value ([col. 30, lines 45-53] a value representing how many times the user input was received during the time period; which indicates that the value can change based on the number).
With regard to claim 9, the limitations are addressed above and Guo teaches wherein the particular value for the particular dataset of the plurality of datasets ([col. 30, lines 45-53] a system-generated response to the user input, a value representing how many times the user input was received during the time period, a domain (e.g., routine, smart home, shopping, weather, etc.), etc.) corresponds to an endpoint having information in the third-party database ([col. 39, lines 15-29] components of a remote device, such as the natural language command processing system component(s), which may assist with ASR processing, and a skill system component(s) 125. A system (120/125) may include one or more servers. A “server” as used herein may refer to a traditional server as understood in a server/client computing structure but may also refer to a number of different computing components that may assist with the operations…The server(s) may be configured to operate using one or more of a client-server model), wherein the first function returns a set of attributes for an endpoint ([col. 16, lines 40-60] the on-device language processing components may be configured to handle only a subset of the natural language user inputs that may be handled by the system component(s). For example, such subset of natural language user inputs may correspond to local-type natural language user inputs; [col. 39, lines 15-29] a server may include one or more physical computing components (such as a rack server) that are connected to other devices/components either physically and/or over a network and is capable of performing computing operations. A server may also include one or more virtual machines that emulates a computer system and is run on one or across multiple devices).
With regard to claim 10, the limitations are addressed above and Guo teaches wherein the plurality of datasets further comprises a set of attributes for identifying the endpoint and accessing the information in the third-party database ([col. 16, lines 40-60] the on-device language processing components may be configured to handle only a subset of the natural language user inputs that may be handled by the system component(s). For example, such subset of natural language user inputs may correspond to local-type natural language user inputs; [col. 39, lines 15-29] a server may include one or more physical computing components (such as a rack server) that are connected to other devices/components either physically and/or over a network and is capable of performing computing operations. A server may also include one or more virtual machines that emulates a computer system and is run on one or across multiple devices).
With regard to claim 11, the limitations are addressed above and Guo teaches wherein the meta-specification identifies an attribute name and an attribute type or an attribute format for a first attribute of the set of attributes ([col. 21, lines 10-34] the NER component identifies “slots” (each corresponding to one or more particular words in text data) that may be useful for later processing. The NER component may also label each slot with a type (e.g., noun, place, city, artist name, song name, etc.)), wherein the particular interface element for collecting the particular value is selected based on the attribute type or the attribute format ([col. 21, lines 1-34] an indication(s) (e.g., slots) of one or more entities included in the user input, as determined by one or more of the language models 145, 155, 180, in which case the ER component 410 may process to link the one or more entities to the specific, referenced, entity known to the system 100…the NER component identifies “slots” (each corresponding to one or more particular words in text data) that may be useful for later processing. The NER component may also label each slot with a type (e.g., noun, place, city, artist name, song name, etc.)).
With regard to claim 12, the limitations are addressed above and Guo teaches further comprising:
responsive to determining that the particular value, received via the particular interface element on the GUI ([col. 3, lines 1-10] the language model(s) may determine that one or more components have been selected to perform the function(s) (action(s)) responsive to the user input, generate a response informing the user of the actions to be performed, and, with authorization, cause the one or more components to perform the function(s) (e.g., action(s))), is compatible with the attribute type or the attribute format ([col. 21, lines 1-34] an indication(s) (e.g., slots) of one or more entities included in the user input, as determined by one or more of the language models 145, 155, 180, in which case the ER component 410 may process to link the one or more entities to the specific, referenced, entity known to the system 100…the NER component identifies “slots” (each corresponding to one or more particular words in text data) that may be useful for later processing. The NER component may also label each slot with a type (e.g., noun, place, city, artist name, song name, etc.)), generating code in which the particular value is assigned the attribute name and inserted into a function call as the first parameter for the first function ([col. 21, lines 1-34] an indication(s) (e.g., slots) of one or more entities included in the user input, as determined by one or more of the language models 145, 155, 180, in which case the ER component 410 may process to link the one or more entities to the specific, referenced, entity known to the system 100…the NER component identifies “slots” (each corresponding to one or more particular words in text data) that may be useful for later processing. The NER component may also label each slot with a type (e.g., noun, place, city, artist name, song name, etc.)).
With regard to claim 13, the limitations are addressed above and Guo teaches wherein the meta-specification comprises a first meta-specification, the method further comprising:
analyzing a second meta-specification corresponding to the API for the third-party database ([col. 4, lines 1-10] completion of a first task requires prior completion of a second task. Even further, providing a system capable of determining one or more (e.g., top-k) components (e.g., APIs) to process with respect to the user input and/or tasks based on their relevance to the user input or tasks allows the system to narrow the number of components to be considered by the corresponding language model, which increases both the efficiency and accuracy of the language model) to identify the first function that returns a particular target dataset ([col. 24, lines 25-55] the system 100 may begin processing with respect to a second task associated with the user input; [col. 30, lines 45-53] the global index storage 620 and/or the personalized index storage 630 may further include metadata associated with the historical user inputs, which may be further included in the global index data 625 and/or the personalized index data 635. For example, the global index storage 620 and/or the personalized index storage 630 may further include a user satisfaction associated with a system-generated response to the user input, a value representing how many times the user input was received during the time period, a domain (e.g., routine, smart home, shopping, weather, etc.), etc.); and
generating a first set of code that invokes the first function with the particular value ([col. 30, lines 45-53] the global index storage 620 and/or the personalized index storage 630 may further include metadata associated with the historical user inputs, which may be further included in the global index data 625 and/or the personalized index data 635. For example, the global index storage 620 and/or the personalized index storage 630 may further include a user satisfaction associated with a system-generated response to the user input, a value representing how many times the user input was received during the time period, a domain (e.g., routine, smart home, shopping, weather, etc.), etc.), received via the particular interface element on the GUI, for the first parameter that is input to the first function ([col. 3, lines 1-10] the language model(s) may determine that one or more components have been selected to perform the function(s) (action(s)) responsive to the user input, generate a response informing the user of the actions to be performed, and, with authorization, cause the one or more components to perform the function(s) (e.g., action(s))).
With regard to claim 14, the limitations are addressed above and Guo teaches further comprising:
analyzing the second meta-specification to identify a second function ([col. 4, lines 1-10] completion of a first task requires prior completion of a second task. Even further, providing a system capable of determining one or more (e.g., top-k) components (e.g., APIs) to process with respect to the user input and/or tasks based on their relevance to the user input or tasks allows the system to narrow the number of components to be considered by the corresponding language model, which increases both the efficiency and accuracy of the language model), defined by the API, that (a) returns a second target dataset ([col. 24, lines 30-57] the system 100 may begin processing with respect to a second task associated with the user input) and (b) accepts as an input parameter a second value of a second type that is returned by the first function ([col. 24, lines 30-57] the system 100 may begin processing with respect to a second task associated with the user input. Thereafter, the output of the personalized context component 210 may be sent to the response arbitration component 470 such that once the response arbitration component 470 receives the output of the LLM shortlister component 160, the response arbitration component 470 may resolve the ambiguity that resulted in the request for additional information in order to generate the output data 490. For further example, if the user input data 127 is generated to include the natural language representation of the user input, but the processing required to determine the corresponding contextual signals (e.g., weather data, time of data, dialog history, device information, etc.) is yet to be completed, the plan generation component 135 may begin processing with respect to the natural language representation of the user input); and
generating a second set of code that invokes the second function using the second value that is returned by the first function, as an input to the second function ([claim 1] a second component and a second prompt including a first transcript, the context data, the first task, and the first set of component descriptions, wherein the second prompt is a second instruction for a second language model to generate instructions usable to cause one or more of the first component, the second component, and the third component to process with respect to the first task; processing, using the second language model, the second prompt to: generate a first application programming interface (API) call requesting that the first component process with respect to the first task).
With regard to claim 15, the limitations are addressed above and Guo teaches wherein the meta-specification further comprises markup data for identifying the plurality of interface elements of the interface layout ([col. 15, lines 15-21] determine whether the API is semantically similar to the user input or the current task. An API description may correspond to a description of the one or more functions (e.g., actions) that the API is configured to perform and/or other information associated with the API (e.g., an API call formatting structure (e.g., including input parameters)), wherein the markup data, when rendered by an Internet content application, causes presentation of the plurality of interface elements on the GUI ([col. 3, lines 1-10] the language model(s) may determine that one or more components have been selected to perform the function(s) (action(s)) responsive to the user input, generate a response informing the user of the actions to be performed, and, with authorization, cause the one or more components to perform the function(s) (e.g., action(s))).
With regard to claim 16, the limitations are addressed above and Guo teaches further comprising:
analyzing the meta-specification corresponding to an API for the third-party database to identify a set of functions ([col. 15, lines 15-21] the encoded representation(s) to an encoded representation of an API description for the API to determine whether the API is semantically similar to the user input or the current task. An API description may correspond to a description of the one or more functions (e.g., actions) that the API is configured to perform and/or other information associated with the API (e.g., an API call formatting structure (e.g., including input parameters), historical accuracy/defect rate, historical latency value, etc.). In some embodiments, the API description may further include one or more exemplars associated with use of the API (e.g., an example user input, corresponding API call, and example API output)), defined by the API, that perform an integration task between the third-party database and a customer database ([col. 21, lines 35-45] the API provider component 190 may include a search component 420, which may be configured to query a storage (e.g., a database, repository, knowledge base, etc.) for information usable for generating a response to a user input. For example, if the action data 187a-n represents a request for information of “Who won the game between [Team 1 Name] and [Team 2 Name],” then the search component 420 may query the storage (or other sources, such as the Internet), to retrieve the information “[Team 1 Name] won the game between [Team 1 Name] and [Team 2 Name].”), wherein the meta-specification further identifies the plurality of datasets as input parameters for the set of functions ([col. 6, lines 40-48] 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 127)); and
generating code that invokes the set of functions with received values, via the GUI, for the plurality of datasets as the input parameters for the set of functions ([claim 1] a second component and a second prompt including a first transcript, the context data, the first task, and the first set of component descriptions, wherein the second prompt is a second instruction for a second language model to generate instructions usable to cause one or more of the first component, the second component, and the third component to process with respect to the first task; processing, using the second language model, the second prompt to: generate a first application programming interface (API) call requesting that the first component process with respect to the first task), wherein the GUI further includes a second plurality of interface elements for presenting integration task results from executing the generated code that invokes the set of functions with received values ([claim 1] a second component and a second prompt including a first transcript, the context data, the first task, and the first set of component descriptions, wherein the second prompt is a second instruction for a second language model to generate instructions usable to cause one or more of the first component, the second component, and the third component to process with respect to the first task; processing, using the second language model, the second prompt to: generate a first application programming interface (API) call requesting that the first component process with respect to the first task).
With regard to claim 17, Guo teaches a method comprising:
using customer provided information, via an interface generated from a first meta-specification ([col. 20, lines 8-27] the LLM agent component 192a may be configured to handle user inputs/tasks related to information query, the LLM agent component 192b may be configured handle user inputs/tasks related to shopping, the LLM agent component 192c may be configured to handle user inputs/tasks related to ordering food from various restaurants, the LLM agent component 192d may be configured to handle user inputs/tasks related to ordering food from a particular restaurant (e.g., a particular pizza restaurant), the LLM agent component 192e may be configured to handle user inputs/tasks related to booking a hotel, the LLM agent component 192f may be configured to handle user inputs/tasks related to booking a flight, etc.) operative to identify (a) a plurality of datasets needed for accessing a third-party cloud ([claim 1] shortlisting available components…one or more components to perform the task), and (b) a data type associated with each of the plurality of datasets, to generate computer code to access the third-party cloud ([col. 21, lines 6–11] the API provider component 190 may include an entity recognition (ER) component 410, which may be configured to process textual or tokenized input to link one or more entity references included in the textual or tokenized input to a specific corresponding entity known to the system 100);
analyzing a meta specification corresponding to an Application Programming Interface (API) for the third-party cloud to identify a first function, defined by the API, that returns a first target dataset ([col. 4, lines 1-10] a system capable of determining one or more (e.g., top-k) components (e.g., APIs) to process with respect to the user input and/or tasks based on their relevance to the user input or tasks allows the system to narrow the number of components to be considered by the corresponding language model, which increases both the efficiency and accuracy of the language model; [col. 14, lines 61-67] the API shortlister component 170 may use retrieval based approaches to retrieve the one or more relevant APIs from the index storage 165 which may store various information associated with multiple APIs such as API descriptions, API arguments (e.g., parameter inputs/outputs), identifiers for components (e.g., such as personalized context component 210, skill component(s) 194, LLM agent component(s) 192, TTS component 196) that provides the API, etc.);
analyzing the first function to determine a first type corresponding to a first parameter that is input to the first function ([col. 3, lines 1-10] the language model(s) may determine that one or more components have been selected to perform the function(s) (action(s)) responsive to the user input, generate a response informing the user of the actions to be performed, and, with authorization, cause the one or more components to perform the function(s) (e.g., action(s))); and
generating a first set of code that invokes the first function with a first value of the first type corresponding to the first parameter that is input to the first function ([col. 30, lines 45-53] the global index storage 620 and/or the personalized index storage 630 may further include metadata associated with the historical user inputs, which may be further included in the global index data 625 and/or the personalized index data 635. For example, the global index storage 620 and/or the personalized index storage 630 may further include a user satisfaction associated with a system-generated response to the user input, a value representing how many times the user input was received during the time period, a domain (e.g., routine, smart home, shopping, weather, etc.), etc.).
With regard to claim 18, the limitations are addressed above and Guo teaches further comprising:
analyzing the API to identify a second function, defined by the API ([col. 4, lines 1-10] completion of a first task requires prior completion of a second task. Even further, providing a system capable of determining one or more (e.g., top-k) components (e.g., APIs) to process with respect to the user input and/or tasks based on their relevance to the user input or tasks allows the system to narrow the number of components to be considered by the corresponding language model, which increases both the efficiency and accuracy of the language model), that (a) returns a second target dataset ([col. 24, lines 25-55] the system 100 may begin processing with respect to a second task associated with the user input; [col. 30, lines 45-53] the global index storage 620 and/or the personalized index storage 630 may further include metadata associated with the historical user inputs, which may be further included in the global index data 625 and/or the personalized index data 635. For example, the global index storage 620 and/or the personalized index storage 630 may further include a user satisfaction associated with a system-generated response to the user input, a value representing how many times the user input was received during the time period, a domain (e.g., routine, smart home, shopping, weather, etc.), etc.) and (b) accepts as an input parameter a second value of a second type that is returned by the first function ([col. 24, lines 30-57] the system 100 may begin processing with respect to a second task associated with the user input. Thereafter, the output of the personalized context component 210 may be sent to the response arbitration component 470 such that once the response arbitration component 470 receives the output of the LLM shortlister component 160, the response arbitration component 470 may resolve the ambiguity that resulted in the request for additional information in order to generate the output data 490. For further example, if the user input data 127 is generated to include the natural language representation of the user input, but the processing required to determine the corresponding contextual signals (e.g., weather data, time of data, dialog history, device information, etc.) is yet to be completed, the plan generation component 135 may begin processing with respect to the natural language representation of the user input); and
generating a second set of code that invokes the second function using a return value, that is returned by the first function, as an input to the second function ([claim 1] a second component and a second prompt including a first transcript, the context data, the first task, and the first set of component descriptions, wherein the second prompt is a second instruction for a second language model to generate instructions usable to cause one or more of the first component, the second component, and the third component to process with respect to the first task; processing, using the second language model, the second prompt to: generate a first application programming interface (API) call requesting that the first component process with respect to the first task).
With regard to claim 19, the limitations are addressed above and Guo teaches further comprising:
executing the first set of code that invokes the first function with the first value of the first type corresponding to the first parameter that is input to the first function ([col. 30, lines 45-53] the global index storage 620 and/or the personalized index storage 630 may further include metadata associated with the historical user inputs, which may be further included in the global index data 625 and/or the personalized index data 635. For example, the global index storage 620 and/or the personalized index storage 630 may further include a user satisfaction associated with a system-generated response to the user input, a value representing how many times the user input was received during the time period, a domain (e.g., routine, smart home, shopping, weather, etc.), etc.); and
executing the second set of code that invokes the second function using the return value, that is returned by the first function, as an input to the second function ([claim 1] a second component and a second prompt including a first transcript, the context data, the first task, and the first set of component descriptions, wherein the second prompt is a second instruction for a second language model to generate instructions usable to cause one or more of the first component, the second component, and the third component to process with respect to the first task; processing, using the second language model, the second prompt to: generate a first application programming interface (API) call requesting that the first component process with respect to the first task).
With regard to claim 20, the system claim corresponds to the method claim 1, respectively, and therefore is rejected with the same rationale.
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 7 is rejected under 35 U.S.C. 103 as being unpatentable over Guo et al. (US Patent No. 12,424,209) in view of Bierner at al. (U.S. 2025/0328317).
With regard to claim 7, the limitations are addressed above. However, Guo does not specifically teach:
- wherein the meta-specification further comprises a code snippet for transforming the particular value into an appropriate value for the first parameter
Bierner teaches a system and method of finding locations of targets which are related to a symbol in a source code snippet, when the snippet is external to a project codebase [abstract]. Bierner also teaches a source code snippet [abstract] for transforming the particular value into an appropriate value for the first parameter ([0099] inlay hints that show parameter names or types in function calls; 1004 feeding back resolved symbol information to an AI agent so that the AI agent can more accurately answer follow up questions about specific parts of the code snippet; providing 1012 the current value of a variable while debugging a program, or enabling renaming 1022 or other refactoring 1020 of symbols in the codebase from the code snippet). Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which said subject matter pertains to have modified the system taught by Guo, with the code snippet codebase taught by Bierner, to have achieved a natural language processing system which generates tasks to be completed in order to perform an action responsive to a user input and, for a given task, shortlisting available components to those that are relevant for the task.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Patil et al. (US 2025/0370732) teaches an analytics platform for managing information and a workspace dashboard to be sent.
Patil et al. (US 2025/0373592) teaches a system and method for generating self-serve integrations and receiving a network address of a configuration file that includes parameters to interface with a server.
Prajapat et al. (US 2024/0053966) teaches a graphical user interface on a computer device for defining a function and a parameter of an interface connector.
Montgomery et al. (US 2023/0018802) teaches a system for configuring an Application Programming Interface (API) based on inputs which received through interface elements presented within a graphical user interface (GUI).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDREA C. LEGGETT whose telephone number is (571)270-7700. The examiner can normally be reached M-F 9am-5pm.
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, Kieu Vu can be reached at 571-272-4057. 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.
/ANDREA C LEGGETT/Primary Examiner, Art Unit 2171
Prosecution Insights