Prosecution Insights
Last updated: November 04, 2026
Application No. 18/611,910

Methods and Systems for Inserting Insights Derived Using Natural Language into Customer Relationship Management Systems

Non-Final OA §101§103§112
Filed
Mar 21, 2024
Examiner
ADESANYA, OLUJIMI A
Art Unit
2658
Tech Center
2600 — Communications
Assignee
Winn AI Labs Ltd.
OA Round
3 (Non-Final)
66%
Grant Probability
Favorable
3-4
OA Rounds
10m
Est. Remaining
93%
With Interview

Examiner Intelligence

Grants 66% — above average
66%
Career Allowance Rate
451 granted / 684 resolved
+3.9% vs TC avg
Strong +27% interview lift
Without
With
+27.3%
Interview Lift
resolved cases with interview
Typical timeline
3y 5m
Avg Prosecution
17 currently pending
Career history
716
Total Applications
across all art units

Statute-Specific Performance

§101
19.7%
-20.3% vs TC avg
§103
44.0%
+4.0% vs TC avg
§102
17.2%
-22.8% vs TC avg
§112
12.9%
-27.1% vs TC avg
Black line = Tech Center average estimate • Based on career data from 684 resolved cases

Office Action

§101 §103 §112
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 . Continued Examination under 37 CFR 1.114 A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 9/9/26 has been entered. Response to Arguments Applicant's arguments filed 9/9/26 have been fully considered but they are not persuasive. Regarding the 35 U.S.C. 101 rejection of the claims, Applicant argues that claim 1 requires execution of a trained model against source data, and as such argues that the claim as well as the similar independent claims are not directed to a mental process (Arguments, pg. 6-7). Examiner respectfully disagrees as the claims do not reflect an execution of a trained model against source data like Applicant argues. The claims 1, 10 and 18 are directed to analyzing, using one or more natural language processing algorithms, at least one source of data that is representative of an interaction between a first party and a second party to extract from the at least one source of data, information that is descriptive of at least part of the interaction (i.e., a data analysis/evaluation step) and uploading information derived from the extracted information to fill data field or electronic forms of a data management system that manages data associated with the first party (i.e., a data analysis/storage step) without significantly more, corresponding to steps achievable by a human in manually transcribing an interaction, analyzing resulting text data, as well as storing results of the analysis. Applicant also argues that pg. 12, ln 4-7 of the specification describes performing the claimed extraction using pattern detection and exploitation to identify insights for example by using patterns identified by machine learning algorithms, and that a human is limited regarding performing the claimed steps as the human while performing in the interaction, cannot perform pattern matching across the interaction or across other interactions or other data sources as presented in new claims 19-21, and as such, argues that the claims reflect an improvement to another technology or field, while further arguing that the claim do not attempt to preempt all means of applying NLP to interactions for CRM purposes (Arguments, pg. 8) Examiner respectfully disagrees as the claims do not reflect performing pattern matching according to machine learning algorithms like Applicant argues. The claim requires analyzing the real time interaction between a first party and a second party, while uploading information derived from the analysis into forms of a management system that manages data associated with one of the parties. It is not inconceivable for a human to transcribe and analyze an interaction between multiple parties to identify known words via (word/pattern matching) while transferring information obtained into forms as a human transcriptionist/stenographer can manually perform such functions. Also, utilizing information from a different source/interaction as presented in new claims 19-21 corresponds to utilizing additional interaction for subsequent analysis, where Applicant’s original and since canceled claim 3 (3/21/24) as well as the original specification (pg. 2, ln 29-30) describes a source as being a portion/part of the transcription. Therefore, utilizing a computer to perform steps that are otherwise manually attainable does not reflect an improvement to computer functioning of another technology. Furthermore, in response to the argument that the instant claims do not seek to monopolize the exception or preclude other systems or methods, the absence of complete preemption does not demonstrate patent eligibility. Applicant further argues that the claimed combination is not disclosed by the references and as such, argues that the claims recite significantly more than an abstract idea (Arguments, pg. 9). Examiner respectfully disagrees as the novelty or non-obviousness (35 U.S.C. 102/103) of the claims over prior art does not automatically confer patent eligibility in terms of statutory subject matter (35 U.S.C. 101) - “groundbreaking, innovative, or even brilliant discovery does not by itself satisfy the § 101 inquiry.” see Ass’n for Molecular Pathology v. Myriad Genetics, Inc., 569 U.S. 576, 591 (2013)., “A novel and non obvious claim directed to a purely abstract idea is, nonetheless, patent ineligible” see Mayo, 566 U.S. at 90, “The ‘novelty’ of any element or steps in a process, or even of the process itself, is of no relevance in determining whether the subject matter of a claim falls within the § 101 categories of possibly patentable subject matter” see also Diamond v. Diehr, 450 U.S. 175, 188–89 (1981). Nevertheless, the claims are obvious over the teachings of Sachdev and Hernandez as provided below. Regarding the 35 U.S.C. 103 rejection of the claims 1, 10, and 18 and as a result claims dependent therefrom, with references Sachdev and Hernandez, Applicant argues that Hernandez’s field population mechanism is contingent on the target field’s name appearing in textual form in the chat summary, and as such, argues that Hernandez fails to disclose limitation “uploading information derived from the extracted information to fill relevant data fields or electronic forms of a data management system that manages data associated with the first party” (Arguments, pg. 9-11). Examiner respectfully disagrees as Hernandez discloses its automated context monitoring system monitoring a chat session based on receiving customer input data and agent input data representing a series of messages exchanged between the customer and the agent, including example transcribed exchange: Customer: “I need assistance with activating my device.” Agent: “What is your name, where did you buy it, and what is the serial number on the device?” Customer: “My name is John Doe. I purchased my laptop today at 10 AM ET and the serial number is 1234567890.” (para. [0047]), and where the system generates a summary of the exchange (see fig. 6F, element 605b and para. [0014]) and populates one or more fields of a form of a provider that manages data of customers based on identified information in the summary (fig. 6F; para. [0028]; para. [0114]), corresponding to limitation “uploading information derived from the extracted information to fill relevant data fields or electronic forms of a data management system that manages data associated with the first party”. Regarding new claims 19-21, Applicant argues that the claims are allowable over the teachings of Sachdev and Hernandez (Arguments, pg. 11-12). Examiner respectfully disagrees as presented below. 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, 2 and 4-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to text/call analysis without significantly more. The claims 1, 10 and 18 recite steps of “under the control of one or more computer systems configured with executable instructions: analyzing, using one or more natural language processing algorithms, at least one source of data that is representative of an interaction between a first party and a second party to extract from the at least one source of data, information that is descriptive of at least part of the interaction (i.e., a data analysis/evaluation step) and uploading information derived from the extracted information to fill data field or electronic forms of a data management system that manages data associated with the first party (i.e., a data analysis/storage step), corresponding to steps achievable by a human in manually transcribing an interaction and analyzing resulting text as well as storing results of the analysis, and as such, the steps correspond to the mental processes category of abstract ideas. This judicial exception is not integrated into a practical application because the claims are directed to an abstract idea with an additional generic computer element, where the generically recited computer element (computer-implemented method, computer systems) do not add a meaningful limitation to the abstract idea because it amounts to simply implementing the abstract idea on a computer. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because step “uploading information derived from the extracted information to a data management system that manages data associated with the first party” corresponds to the well-understood, routine, conventional computer function of storage and retrieval of information to/from memory as recognized by the court decisions listed in MPEP § 2106.05 and as provided by cited references Sachdev, Hernandez and Xiao. The dependent claims also recite mental processes and do not add significantly more than the abstract idea and are as such similarly rejected. Claim Rejections - 35 USC § 112 The following is a quotation of the first paragraph of 35 U.S.C. 112(a): (a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention. The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112: The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention. Claims 19-21 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claims contain subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. In particular, claim 19 and 21 recite “wherein the information that is descriptive of at least part of the interaction is generated further based on one or more other interactions or other data sources, distinct from the interaction between the customer and the customer service representative” while claim 20 recites “wherein the insight data that is descriptive of at least one insight of the interaction is generated further based on one or more other interactions or other data sources, distinct from the interaction between the customer and the customer service representative”. The original specification does not show how the information/insight that is descriptive of at least part of the interaction (i.e., based on an interaction or part of the interaction) is further based on one or more other interactions or other data sources, distinct from the interaction between the customer and the customer service representative. Page 12, ln 18-19 of the original specification provided by Applicant to show support for the amendment describes generating insights from other sources and interactions, but not extracting information/insights of an interaction based on other/distinct interactions. 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. 1. Claims 1, 2, and 4-21 are rejected under 35 U.S.C. 103 as being unpatentable over Sachdev US 2021/0126999 A1 (“Sachdev”) in view of Hernandez et al US 2025/0265413 A1 (“Hernandez”) Per claim 1, Sachdev discloses a computer-implemented method comprising: under the control of one or more computer systems configured with executable instructions: analyzing, using one or more natural language processing algorithms, at least one source of data that is representative of an interaction between a first party and a second party to extract from the at least one source of data, information that is descriptive of at least part of the interaction (fig. 4; A call summarization apparatus comprises a call processing engine, which is implemented on one or more computers. The engine is configured to transcribe audio data from a call when the call is still active, and generate text data of the call in real time, that is, as the parties on the call (i.e., a customer and an agent) speak…., para. [0011]; Using Natural Language Processing (NLP) techniques with built-in Natural Language Understanding & Generation (NLU, NLG) techniques, powered by deep, bi-directional Recursive Neural Networks (RNN) algorithm, the engine identifies the intents in the call, extracts various slots under each intent to further identify the sentiments, resolutions, actions and promises from the call. Intents are conversation shapers, and the issue is one of the intents…., para. [0012], transcription as source of data); and uploading information derived from the extracted information to a data management system that manages data associated with the first party (para. [0012]; A final version of the call summary 104 may is stored in the database 120 for future reference, para. [0023]; The method 200 proceeds to optional step 290, at which the summarization module 118 includes data generated in steps 240-270, or portions thereof in the summary 104. For example, such data includes the intent of the customer, a slot of the intent, a sentiment of the customer …, para. [0028]) Sachdev does not explicitly disclose uploading information derived from the extracted information to fill relevant data fields or electronic forms of a data management system that manages data associated with the first party However, this feature is taught by Hernandez (fig. 6F; para. [0014]; para. [0018]; para. [0028]; the automated context monitoring system may monitor a chat session based on receiving customer input data and agent input data representing a series of messages exchanged between a customer and an agent as follows: Customer: “I need assistance with activating my device.” Agent: “What is your name, where did you buy it, and what is the serial number on the device?” Customer: “My name is John Doe. I purchased my laptop today at 10 AM ET and the serial number is 1234567890.” …, para. [0047]-[0049]; the automated context monitoring system may parse the plurality of form files to determine the set of fields, where each field has a name and corresponds to a type of information exchanged during a chat session…. For example, the automated context monitoring system may identify the instances of filed names in a form file corresponding to fields in the summary and copy the information from the summary into the form file, para. [0050]-[0052]; In examples, the agent device 604 may provide data associated with the information communicated during the chat session to an ML model to cause the ML model to generate and/or update the summary…., para. [0113]; the agent device 604 may prepopulate the one or more fields of the form file based on the summary as last updated by the agent device after the final message is communicated between the client device 602 and the agent device 604 …, para. [0114], summary as including information that is descriptive of at least part of the interaction between user and agent, copying the information exchanged from call summary into fields of form file as uploading, fig. 6F and para. [0047] as providing example copying/uploading) It would have been obvious to one of ordinary skill in the art before the effective filing of the invention to combine the teachings of Hernandez with the method of Sachdev in arriving at the missing features of Sachdev, because such combination would have resulted in increasing the timeliness and accuracy of chat sessions (Hernandez, para. [0016]). Per claim 2, Sachdev in view of Hernandez discloses the computer-implemented method of claim 1, Sachdev discloses wherein the at least one source of data includes at least one of linguistic data or textual data (para. [0011]-[0012]). Per claim 4, Sachdev in view of Hernandez discloses the computer-implemented method of claim 1, Sachdev discloses wherein the analyzing the at least one source of data includes transcribing the at least one source of data into text to produce a transcript of at least part of the interaction (The audio of such speech is converted to text using automatic speech recognition (ASR) techniques. The engine applies language processing techniques to the text data to comprehend the text data …, para. [0011]). Per claim 5, Sachdev in view of Hernandez discloses the computer-implemented method of claim 4, Sachdev discloses wherein the analyzing the at least one source of data further includes parsing the transcript into one or more transcript sections (fig. 4; para. [0011]). Per claim 6, Sachdev in view of Hernandez discloses the computer-implemented method of claim 5, Sachdev discloses wherein the analyzing the at least one source of data further includes classifying the one or more transcript sections according to a plurality of classification labels (fig. 4; para. [0011]; para. [0016]). Per claim 7, Sachdev in view of Hernandez discloses the computer-implemented method of claim 1, Sachdev discloses wherein the at least one source of data is received from a computer memory (Such elements are aggregated over the duration of the call, and upon conclusion of the call, and portions of the call that were not previously processed for summarization are processed, supplemented with the aggregated elements, and presented as a summary. In some instances, a call summary is prepared only after the call is concluded …, para. [0013]). Per claim 8, Sachdev in view of Hernandez discloses the computer-implemented method of claim 1, Sachdev discloses wherein the information derived from the extracted information includes at least one insight of the interaction (para. [0012]; para. [0028]). Per claim 9, Sachdev in view of Hernandez discloses the computer-implemented method of claim 1, Sachdev discloses modifying, by the second party, the extracted information to produce the information derived from the extracted information, prior to the information derived from the extracted information being uploaded to the system (para. [0012]; the call summary 104 is editable. The agent may edit the call summary 104 from within the call summary section of the GUI. A final version of the call summary 104 may is stored in the database 120 …, para. [0023]). Per claim 10, Sachdev discloses a computer-implemented method comprising: under the control of one or more computer systems configured with executable instructions: analyzing, using one or more natural language processing algorithms, at least one source of data that is representative of an interaction between a customer and a customer service representative to extract from the at least one source of data insight data that is descriptive of at least one insight of the interaction (fig. 4; A call summarization apparatus comprises a call processing engine, which is implemented on one or more computers. The engine is configured to transcribe audio data from a call when the call is still active, and generate text data of the call in real time, that is, as the parties on the call (i.e., a customer and an agent) speak…., para. [0011]; Using Natural Language Processing (NLP) techniques with built-in Natural Language Understanding & Generation (NLU, NLG) techniques, powered by deep, bi-directional Recursive Neural Networks (RNN) algorithm, the engine identifies the intents in the call, extracts various slots under each intent to further identify the sentiments, resolutions, actions and promises from the call. Intents are conversation shapers, and the issue is one of the intents…., para. [0012], transcription as source of data); and uploading the insight data to a customer relationship management system that manages data associated with the customer and that is managed by an organization that includes the customer service representative (para. [0012]; A final version of the call summary 104 may is stored in the database 120 for future reference, para. [0023]; The method 200 proceeds to optional step 290, at which the summarization module 118 includes data generated in steps 240-270, or portions thereof in the summary 104. For example, such data includes the intent of the customer, a slot of the intent, a sentiment of the customer …, para. [0028]) Sachdev does not explicitly disclose uploading the insight data to fill relevant data fields or electronic forms of a customer relationship management system that manages data associated with the customer and that is managed by an organization that includes the customer service representative However, this feature is taught by Hernandez (fig. 6F; para. [0014]; para. [0018]; para. [0028]; the automated context monitoring system may monitor a chat session based on receiving customer input data and agent input data representing a series of messages exchanged between a customer and an agent as follows: Customer: “I need assistance with activating my device.” Agent: “What is your name, where did you buy it, and what is the serial number on the device?” Customer: “My name is John Doe. I purchased my laptop today at 10 AM ET and the serial number is 1234567890.” …, para. [0047]-[0049]; the automated context monitoring system may parse the plurality of form files to determine the set of fields, where each field has a name and corresponds to a type of information exchanged during a chat session…. For example, the automated context monitoring system may identify the instances of filed names in a form file corresponding to fields in the summary and copy the information from the summary into the form file, para. [0050]-[0052]; In examples, the agent device 604 may provide data associated with the information communicated during the chat session to an ML model to cause the ML model to generate and/or update the summary…., para. [0113]; the agent device 604 may prepopulate the one or more fields of the form file based on the summary as last updated by the agent device after the final message is communicated between the client device 602 and the agent device 604 …, para. [0114], summary as including information that is descriptive of at least part of the interaction between user and agent, copying the information exchanged from call summary into fields of form file as uploading, fig. 6F and para. [0047] as providing example copying/uploading) It would have been obvious to one of ordinary skill in the art before the effective filing of the invention to combine the teachings of Hernandez with the method of Sachdev in arriving at the missing features of Sachdev, because such combination would have resulted in increasing the timeliness and accuracy of chat sessions (Hernandez, para. [0016]). Per claim 11, Sachdev in view of Hernandez discloses the computer-implemented method of claim 10, Sachdev discloses wherein the at least one source of data includes at least one of linguistic data or textual data (para. [0011]-[0012]). Per claim 12, Sachdev in view of Hernandez discloses the computer-implemented method of claim 10, Sachdev discloses wherein the at least one source of data is a transcript of the interaction (para. [0011]-[0012]). Per claim 13, Sachdev in view of Hernandez discloses the computer-implemented method of claim 10, Sachdev discloses wherein the analyzing the at least one source of data includes transcribing the at least one source of data into text (para. [0011]). Per claim 14, Sachdev in view of Hernandez discloses the computer-implemented method of claim 10, Sachdev discloses wherein each insight of the at least one insight is an insight in a category from a set of predetermined categories (fig. 4; the engine identifies the intents in the call, extracts various slots under each intent to further identify the sentiments, resolutions, actions and promises from the call. Intents are conversation shapers, and the issue is one of the intents…., para. [0012]; para. [0028]) Per claim 15, Sachdev in view of Hernandez discloses the computer-implemented method of claim 14, Sachdev discloses wherein the set of predetermined categories includes: indications that questions or answers were provided by the customer or the customer service representative (fig. 4; para. [0028], customer input requests and agent responses as questions and answers) Hernandez discloses wherein the set of predetermined categories includes: questions and answers on topics in predefined conversation points of interest of the interaction, and indications that questions or answers were provided by the customer or the customer service representative (fig. 6F; para. [0018]; para. [0028]; the automated context monitoring system may monitor a chat session based on receiving customer input data and agent input data representing a series of messages exchanged between a customer and an agent as follows: Customer: “I need assistance with activating my device.” Agent: “What is your name, where did you buy it, and what is the serial number on the device?” Customer: “My name is John Doe. I purchased my laptop today at 10 AM ET and the serial number is 1234567890.” …, para. [0047]-[0049]) Per claim 16, Sachdev in view of Hernandez discloses the computer-implemented method of claim 10, Sachdev discloses modifying, by the customer service representative, the insight data prior to the insight data being uploaded to the customer relationship management system (para. [0012]; the call summary 104 is editable. The agent may edit the call summary 104 from within the call summary section of the GUI. A final version of the call summary 104 may is stored in the database 120 …, para. [0023]). Per claim 17, Sachdev in view of Hernandez discloses the computer-implemented method of claim 10, Sachdev discloses: wherein the at least one source of data includes a plurality of sources of data, each source of data corresponding to a different respective aspect of the interaction (fig. 4; The transcribing module 112 receives audio data of the call 102 in real-time. The transcribing module 112 transcribes the audio data to generate text data corresponding to the conversation between the caller or customer and the agent who receives the call …, para. [0016]), and wherein the insight data includes a plurality of sets of data elements, each set of data elements being descriptive of a respective insight of a plurality of insights, each insight of the plurality of insights being associated with a different respective one of the aspects (fig. 4; At step 282 of the method 200, the summarization module 118 identifies an issue of the customer based on at least one of a call transcript, an extracted intent from the call transcript, a slot of the intent, and/or a sentiment of the customer …, para. [0028]) the method further comprising: aggregating the data elements to produce an aggregated data element that is a representation of an aggregation of the plurality of insights (fig. 4; The method 200 proceeds to optional step 290, at which the summarization module 118 includes data generated in steps 240-270, or portions thereof in the summary 104. For example, such data includes the intent of the customer, a slot of the intent, a sentiment of the customer …, para. [0028]). Per claim 18, Sachdev discloses a computer-implemented method comprising: under the control of one or more computer systems configured with executable instructions: analyzing, using one or more natural language processing algorithms, at least one source of data that is representative of an interaction between a customer of an organization and a customer service representative that is a member of the organization to extract from the at least one source of data information that is descriptive of at least part of the interaction (fig. 4; A call summarization apparatus comprises a call processing engine, which is implemented on one or more computers. The engine is configured to transcribe audio data from a call when the call is still active, and generate text data of the call in real time, that is, as the parties on the call (i.e., a customer and an agent) speak…., para. [0011]; Using Natural Language Processing (NLP) techniques with built-in Natural Language Understanding & Generation (NLU, NLG) techniques, powered by deep, bi-directional Recursive Neural Networks (RNN) algorithm, the engine identifies the intents in the call, extracts various slots under each intent to further identify the sentiments, resolutions, actions and promises from the call. Intents are conversation shapers, and the issue is one of the intents…., para. [0012], transcription as source of data); and uploading information derived from the extracted information to a customer relationship management system that manages data associated with the customer and that is managed by the organization (para. [0012]; A final version of the call summary 104 may is stored in the database 120 for future reference, para. [0023]; The method 200 proceeds to optional step 290, at which the summarization module 118 includes data generated in steps 240-270, or portions thereof in the summary 104. For example, such data includes the intent of the customer, a slot of the intent, a sentiment of the customer …, para. [0028]) Sachdev does not explicitly disclose uploading information derived from the extracted information to fill relevant data fields or electronic forms of a customer relationship management system that manages data associated with the customer and that is managed by the organization However, this feature is taught by Hernandez (fig. 6F; para. [0014]; para. [0018]; para. [0028]; the automated context monitoring system may monitor a chat session based on receiving customer input data and agent input data representing a series of messages exchanged between a customer and an agent as follows: Customer: “I need assistance with activating my device.” Agent: “What is your name, where did you buy it, and what is the serial number on the device?” Customer: “My name is John Doe. I purchased my laptop today at 10 AM ET and the serial number is 1234567890.” …, para. [0047]-[0049]; the automated context monitoring system may parse the plurality of form files to determine the set of fields, where each field has a name and corresponds to a type of information exchanged during a chat session…. For example, the automated context monitoring system may identify the instances of filed names in a form file corresponding to fields in the summary and copy the information from the summary into the form file, para. [0050]-[0052]; In examples, the agent device 604 may provide data associated with the information communicated during the chat session to an ML model to cause the ML model to generate and/or update the summary…., para. [0113]; the agent device 604 may prepopulate the one or more fields of the form file based on the summary as last updated by the agent device after the final message is communicated between the client device 602 and the agent device 604 …, para. [0114], summary as including information that is descriptive of at least part of the interaction between user and agent, copying the information exchanged from call summary into fields of form file as uploading, fig. 6F and para. [0047] as providing example copying/uploading) It would have been obvious to one of ordinary skill in the art before the effective filing of the invention to combine the teachings of Hernandez with the method of Sachdev in arriving at the missing features of Sachdev, because such combination would have resulted in increasing the timeliness and accuracy of chat sessions (Hernandez, para. [0016]). Per claim 19, Sachdev in view of Hernandez discloses the computer-implemented method of claim 1, Sachdev discloses herein the information that is descriptive of at least part of the interaction is generated further based on one or more other interactions or other data sources, distinct from the interaction between the first party and the second party (para. [0019]-[0020]) Hernandez discloses wherein the information that is descriptive of at least part of the interaction is generated further based on one or more other interactions or other data sources, distinct from the interaction between the first party and the second party (fig. 2; fig. 6F; At operation 204, for a first state of a chat session, an ML model (e.g., a large language model (LLM) and/or the like) is executed on the customer input data and the agent input data at a first state to generate a first summary …, para. [0045]; At operation 206, for a second state of the chat session, the LLM is executed on customer input data and agent input data to generate a second summary. …, para. [0056]; para. [0069]; para. [0114]). Per claim 20, Sachdev in view of Hernandez discloses the computer-implemented method of claim 10, Sachdev discloses wherein the insight data that is descriptive of at least one insight of the interaction is generated further based on one or more other interactions or other data sources, distinct from the interaction between the customer and the customer service representative (para. [0019]-[0020]) Hernandez discloses wherein the insight data that is descriptive of at least one insight of the interaction is generated further based on one or more other interactions or other data sources, distinct from the interaction between the customer and the customer service representative (fig. 2; fig. 6F; At operation 204, for a first state of a chat session, an ML model (e.g., a large language model (LLM) and/or the like) is executed on the customer input data and the agent input data at a first state to generate a first summary …, para. [0045]; At operation 206, for a second state of the chat session, the LLM is executed on customer input data and agent input data to generate a second summary. …, para. [0056]; para. [0069]; para. [0114]). Per claim 21, Sachdev in view of Hernandez discloses the computer-implemented method of claim 18, Sachdev discloses wherein the information that is descriptive of at least part of the interaction is generated further based on one or more other interactions or other data sources, distinct from the interaction between the customer and the customer service representative (para. [0019]-[0020]) Hernandez discloses wherein the information that is descriptive of at least part of the interaction is generated further based on one or more other interactions or other data sources, distinct from the interaction between the customer and the customer service representative (fig. 2; fig. 6F; At operation 204, for a first state of a chat session, an ML model (e.g., a large language model (LLM) and/or the like) is executed on the customer input data and the agent input data at a first state to generate a first summary …, para. [0045]; At operation 206, for a second state of the chat session, the LLM is executed on customer input data and agent input data to generate a second summary. …, para. [0056]; para. [0069]; para. [0114]). Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See PTO 892 form. Any inquiry concerning this communication or earlier communications from the examiner should be directed to OLUJIMI A ADESANYA whose telephone number is (571)270-3307. The examiner can normally be reached Monday-Friday 8:30-5:00pm. 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, Richemond Dorvil can be reached at 571-272-7602. 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. /OLUJIMI A ADESANYA/Primary Examiner, Art Unit 2658
Read full office action

Prosecution Timeline

Mar 21, 2024
Application Filed
Sep 26, 2025
Non-Final Rejection mailed — §101, §103, §112
Feb 25, 2026
Response Filed
Mar 09, 2026
Final Rejection mailed — §101, §103, §112
Sep 09, 2026
Request for Continued Examination
Sep 14, 2026
Response after Non-Final Action
Sep 21, 2026
Non-Final Rejection mailed — §101, §103, §112 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12783808
DIGITAL ASSISTANT GENERATION VIA LARGE LANGUAGE MODELS
3y 1m to grant Granted Nov 03, 2026
Patent 12769953
LANGUAGE MODEL PROMPT AUTHORING AND EXECUTION IN A DATABASE SYSTEM
2y 9m to grant Granted Oct 20, 2026
Patent 12763090
ADJUSTING AUDIO AND NON-AUDIO FEATURES BASED ON NOISE METRICS AND SPEECH INTELLIGIBILITY METRICS
4y 4m to grant Granted Oct 13, 2026
Patent 12743415
MACHINE LEARNING MODEL PROMPT HYDRATION VIA PROMPT REGISTRY AND CONTEXT STORE
2y 7m to grant Granted Sep 22, 2026
Patent 12724967
MULTI-TASK LEARNING FOR NATURAL LANGUAGE PROCESSING TASKS USING A SHARED PRE-TRAINED LANGUAGE MODEL
2y 6m to grant Granted Sep 01, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

3-4
Expected OA Rounds
66%
Grant Probability
93%
With Interview (+27.3%)
3y 5m (~10m remaining)
Median Time to Grant
High
PTA Risk
Based on 684 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month