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 .
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Buchanan U.S. PAP 2025/0298988 A in view of Ramaci U.S. PAP 2019/0043501 A1.
Regarding claim 1 Buchanan teaches a computer program product, the computer program product being tangibly embodied on a non-transitory computer-readable storage medium and comprising instructions that, when executed by at least one computing device (embodiment provides a computer-readable medium comprising instructions, that when read by a processor, cause the processor to perform one or more of executing an interaction with an account via a chatbot , see par. [0004]), are configured to cause the at least one computing device to: receive a request at a virtual agent (user input such as user requests, comments, queries, questions, and/or the like, see par. [0034]); provide the topic prompt and the request to the language model ( the host platform may use artificial intelligence to ensure that a chat conversation between the user and the chatbot remains on a topic of interest, see par. [0030]); receive, from the language model and in response to the topic prompt and the request, a response to the request (an AI model may be a “generative” AI (GenAI) model such as a large language model (LLM) or a multimodal large language model, see par. [0031]; The chatbot responses may be generated by one or more AI models, such as an AI model 124 hosted by the host platform 120. To generate a chatbot response, the AI model 124 may receive conversational content from the chat window 112, including messages input by the user and messages output by the chatbot 113, see par. [0035]); and provide the response using the virtual agent (the AI model 124 generates a chatbot response 116 in response to the query 115 from the user and outputs the chatbot response 116 with the chatbot 113 via the chat window 112, see par. [0036]).
However Buchanan does not teach process the request at a router prompt to determine, from a language model, a topic prompt of a plurality of topic prompts associated with the request.
In the same field of endeavor Ramaci teaches An application selection component or intent router identifies, selects, and/or invokes installed device applications and/or installed server applications in response to user intents identified by the NLU component. In response to a determined user intent, the intent router can identify one of the installed applications capable of servicing the user intent. The application can be called or invoked to satisfy the user intent or to conduct further dialog with the user to further refine the user intent. Each of the installed applications may have an intent specification that defines the serviceable intent. The control service uses the intent specifications to detect user utterances, expressions, or intents that correspond to the applications. An application intent specification may include NLU models for use by the natural language understanding component. In addition, one or installed applications may contain specified dialog models for that create and coordinate speech interactions with the user. The dialog models may be used by the dialog management component in conjunction with the dialog models to create and coordinate dialogs with the user and to determine user intent either before or during operation of the installed applications. The NLU component and the dialog management component may be configured to use the intent specifications of the applications either to conduct dialogs, to identify expressed intents of users, identify and use the intent specifications of installed applications, in conjunction with the NLU models and dialog modes, to determine when a user has expressed an intent that can be serviced by the application, and to conduct one or more dialogs with the user, see par. [0047].
It would have been obvious to one of ordinary skill in the art to combine the Buchanan invention with the teachings of Ramaci for the benefit of identify and use the intent specifications of installed applications, in conjunction with the NLU models and dialog modes, to determine when a user has expressed an intent that can be serviced by the application, and to conduct one or more dialogs with the user, see par. [0047].
Regarding claim 2 Buchanan teaches the computer program product of claim 1, wherein the topic prompt defines at least two conversational exchanges ( the AI model may identify the original topic of interest during a first part of the conversation and continually check that the state of the conversation remains on the original topic of interest, see par. [0030]), and wherein the instructions, when executed, are further configured to cause the at least one computing device to: obtain, via the virtual agent, intermediate responses to the at least two conversational exchanges (the AI model 124 generates a chatbot response 116 in response to the query 115 from the user and outputs the chatbot response 116 with the chatbot 113 via the chat window 112, see par. [0036]); and provide the response based on the intermediate responses (he AI model 124 may receive the query 117 and may generate a chatbot response 118 and outputs the chatbot response 118 via the chat window 112, see par. [0036]).
Regarding claim 3 Buchanan teaches the computer program product of claim 1, wherein the instructions, when executed, are further configured to cause the at least one computing device to: receive, following providing the response using the virtual agent, a second request (ser provides another query 117, see par. [0036]); and provide the second request to the router prompt (In response, the AI model 124 may receive the query 117 and may generate a chatbot response 118, see par. [0036]).
Regarding claim 4 Buchanan teaches the computer program product of claim 1, wherein the instructions, when executed, are further configured to cause the at least one computing device to: detect a digression request (The model recognizes subtle signs of emotional responses, such as frustration from repeated queries on a single topic or confusion indicated by vague or off-topic responses, see par. [0079]); and provide the digression request to the router prompt (The system activates a second AI model by detecting an emotional cue that suggests the educational content might not be clear or engaging enough. The second model is specifically trained to tailor educational content based on the identified emotional state. For instance, if confusion is detected, the model might simplify the explanations, see par. [0080]).
Regarding claim 5 Buchanan teaches the computer program product of claim 4, wherein the instructions, when executed, are further configured to cause the at least one computing device to: determine, at the router prompt, a digression topic prompt from the plurality of topic prompts (When the user inputs a chat communication, the system receives the data within the chat window. The system leverages an advanced AI model trained to understand and analyze conversation contexts and user interactions, see par. [0098]); and provide the digression topic prompt and the digression request to the language model (the model uses inputs, including the current chat communication, previous conversations, and topic data, to assess. The AI model generates a strategic chatbot response upon determining that the user's input strays from the established topic of interest. The response is formulated based on the conversation's state before receiving the off-topic communication, see par. [0098]).
Regarding claim 6 Buchanan teaches the computer program product of claim 5, wherein the instructions, when executed, are further configured to cause the at least one computing device to: receive, from the language model and in response to the digression topic prompt and the digression request, a digression response to the digression request ( a second AI model 624 to generate a new chat response based on the state of the conversation between the conversation output by the first AI model 623 and the user. In this example, the first AI model 623 (or the software application 622, etc.) may transfer a conversation state 630 to the second AI model 624, see par. [0077]); and provide the digression response using the virtual agent (the second AI model 624 may generate a new chatbot response 618 (shown in process 600D in FIG. 6D) which is then output to the chat window 611 by the software application 622, see par. [0077]).
Regarding claim 7 Buchanan teaches the computer program product of claim 6, wherein the instructions, when executed, are further configured to cause the at least one computing device to: save, in response to detecting the digression request, a state of the topic prompt prior to receipt of the digression request (The system personalizes learning experiences by referencing students' previous interactions and progress. It tracks the student's learning journey, identifies strengths and weaknesses, and tailors future interactions accordingly, see par. [0069]); and return, after providing the digression response, to the state of the topic prompt prior to receipt of the digression request (the AI model 724 may generate a new chat response 718 which attempts to guide the conversation back to the original topic of interest, see par. [0089]).
Regarding claim 8 Buchanan teaches the computer program product of claim 7, wherein the instructions, when executed, are further configured to cause the at least one computing device to: provide, when returning to the state of the topic prompt and using the virtual agent, a pre-digression reminder referencing the topic prompt (a new chat response 718 which attempts to guide the conversation back to the original topic of interest, see par. [0089]).
Regarding claim 9 Buchanan teaches the computer program product of claim 1, wherein the instructions, when executed, are further configured to cause the at least one computing device to: provide the topic prompt and the request to the language model together with a digression prompt configured to use the language model to determine a digression from a topic of the topic prompt prior to providing the response (IG. 7A illustrates a view 700A of a chat conversation within a chat window 711 of a user interface of a user device 710. FIGS. 7B-7D illustrate an iterative process of analyzing a chat conversation for a topic of interest, and FIG. 7E illustrates a process of guiding a user back to the topic of interest, see par. [0088]).
Regarding claim 10 Buchanan teaches the computer program product of claim 1, wherein the language model includes a large language model (AI (GenAI) model such as a large language model (LLM), see par. [0031]).
Regarding claim 11 Buchanan teaches a computer-implemented method (method, see par. [0003]), the method comprising: receiving a request at a virtual agent (user input such as user requests, comments, queries, questions, and/or the like, see par. [0034]); providing the topic prompt and the request to the language model ( the host platform may use artificial intelligence to ensure that a chat conversation between the user and the chatbot remains on a topic of interest, see par. [0030]); receiving, from the language model and in response to the topic prompt and the request, a response to the request (an AI model may be a “generative” AI (GenAI) model such as a large language model (LLM) or a multimodal large language model, see par. [0031]; The chatbot responses may be generated by one or more AI models, such as an AI model 124 hosted by the host platform 120. To generate a chatbot response, the AI model 124 may receive conversational content from the chat window 112, including messages input by the user and messages output by the chatbot 113, see par. [0035]); and providing the response using the virtual agent (the AI model 124 generates a chatbot response 116 in response to the query 115 from the user and outputs the chatbot response 116 with the chatbot 113 via the chat window 112, see par. [0036]).
However Buchanan does not teach process the request at a router prompt to determine, from a language model, a topic prompt of a plurality of topic prompts associated with the request.
In the same field of endeavor Ramaci teaches An application selection component or intent router identifies, selects, and/or invokes installed device applications and/or installed server applications in response to user intents identified by the NLU component. In response to a determined user intent, the intent router can identify one of the installed applications capable of servicing the user intent. The application can be called or invoked to satisfy the user intent or to conduct further dialog with the user to further refine the user intent. Each of the installed applications may have an intent specification that defines the serviceable intent. The control service uses the intent specifications to detect user utterances, expressions, or intents that correspond to the applications. An application intent specification may include NLU models for use by the natural language understanding component. In addition, one or installed applications may contain specified dialog models for that create and coordinate speech interactions with the user. The dialog models may be used by the dialog management component in conjunction with the dialog models to create and coordinate dialogs with the user and to determine user intent either before or during operation of the installed applications. The NLU component and the dialog management component may be configured to use the intent specifications of the applications either to conduct dialogs, to identify expressed intents of users, identify and use the intent specifications of installed applications, in conjunction with the NLU models and dialog modes, to determine when a user has expressed an intent that can be serviced by the application, and to conduct one or more dialogs with the user, see par. [0047].
It would have been obvious to one of ordinary skill in the art to combine the Buchanan invention with the teachings of Ramaci for the benefit of identify and use the intent specifications of installed applications, in conjunction with the NLU models and dialog modes, to determine when a user has expressed an intent that can be serviced by the application, and to conduct one or more dialogs with the user, see par. [0047].
Regarding claim 12 Buchanan teaches the method of claim 11, further comprising: detecting a digression request (The model recognizes subtle signs of emotional responses, such as frustration from repeated queries on a single topic or confusion indicated by vague or off-topic responses, see par. [0079]); and providing the digression request to the router prompt (The system activates a second AI model by detecting an emotional cue that suggests the educational content might not be clear or engaging enough. The second model is specifically trained to tailor educational content based on the identified emotional state. For instance, if confusion is detected, the model might simplify the explanations, see par. [0080]).
Regarding claim 13 Buchanan teaches the method of claim 12, further comprising: determining, at the router prompt, a digression topic prompt from the plurality of topic prompts (When the user inputs a chat communication, the system receives the data within the chat window. The system leverages an advanced AI model trained to understand and analyze conversation contexts and user interactions, see par. [0098]); and providing the digression topic prompt and the digression request to the language model (the model uses inputs, including the current chat communication, previous conversations, and topic data, to assess. The AI model generates a strategic chatbot response upon determining that the user's input strays from the established topic of interest. The response is formulated based on the conversation's state before receiving the off-topic communication, see par. [0098]).
Regarding claim 14 Buchanan teaches the method of claim 13, further comprising: receiving, from the language model and in response to the digression topic prompt and the digression request, a digression response to the digression request ( a second AI model 624 to generate a new chat response based on the state of the conversation between the conversation output by the first AI model 623 and the user. In this example, the first AI model 623 (or the software application 622, etc.) may transfer a conversation state 630 to the second AI model 624, see par. [0077]); and providing the digression response using the virtual agent (the second AI model 624 may generate a new chatbot response 618 (shown in process 600D in FIG. 6D) which is then output to the chat window 611 by the software application 622, see par. [0077]).
Regarding claim 15 Buchanan teaches the method of claim 14, further comprising: saving, in response to detecting the digression request, a state of the topic prompt prior to receipt of the digression request (The system personalizes learning experiences by referencing students' previous interactions and progress. It tracks the student's learning journey, identifies strengths and weaknesses, and tailors future interactions accordingly, see par. [0069]); and returning, after providing the digression response, to the state of the topic prompt prior to receipt of the digression request (the AI model 724 may generate a new chat response 718 which attempts to guide the conversation back to the original topic of interest, see par. [0089]).
Regarding claim 16 Buchanan teaches the method of claim 15, further comprising: providing, when returning to the state of the topic prompt and using the virtual agent, a pre-digression reminder referencing the topic prompt (a new chat response 718 which attempts to guide the conversation back to the original topic of interest, see par. [0089]).
Regarding claim 17 Buchanan teaches the method of claim 11, further comprising: providing the topic prompt and the request to the language model together with a digression prompt configured to use the language model to determine a digression from a topic of the topic prompt prior to providing the response (IG. 7A illustrates a view 700A of a chat conversation within a chat window 711 of a user interface of a user device 710. FIGS. 7B-7D illustrate an iterative process of analyzing a chat conversation for a topic of interest, and FIG. 7E illustrates a process of guiding a user back to the topic of interest, see par. [0088]).
Regarding claim 18 Buchanan teaches a system (see figure 9) comprising: at least one memory including instructions (apparatus that may include a memory, see par. [0002]); and at least one processor that is operably coupled to the at least one memory and that is arranged and configured to execute instructions that, when executed (a processor coupled to the memory, the processor configured to perform one or more of execute an interaction with an account via a chatbot , see par. [0002]), cause the at least one processor to:
receive a request at a virtual agent (user input such as user requests, comments, queries, questions, and/or the like, see par. [0034]); provide the topic prompt and the request to the language model ( the host platform may use artificial intelligence to ensure that a chat conversation between the user and the chatbot remains on a topic of interest, see par. [0030]); receive, from the language model and in response to the topic prompt and the request, a response to the request (an AI model may be a “generative” AI (GenAI) model such as a large language model (LLM) or a multimodal large language model, see par. [0031]; The chatbot responses may be generated by one or more AI models, such as an AI model 124 hosted by the host platform 120. To generate a chatbot response, the AI model 124 may receive conversational content from the chat window 112, including messages input by the user and messages output by the chatbot 113, see par. [0035]); and provide the response using the virtual agent (the AI model 124 generates a chatbot response 116 in response to the query 115 from the user and outputs the chatbot response 116 with the chatbot 113 via the chat window 112, see par. [0036]).
However Buchanan does not teach process the request at a router prompt to determine, from a language model, a topic prompt of a plurality of topic prompts associated with the request.
In the same field of endeavor Ramaci teaches An application selection component or intent router identifies, selects, and/or invokes installed device applications and/or installed server applications in response to user intents identified by the NLU component. In response to a determined user intent, the intent router can identify one of the installed applications capable of servicing the user intent. The application can be called or invoked to satisfy the user intent or to conduct further dialog with the user to further refine the user intent. Each of the installed applications may have an intent specification that defines the serviceable intent. The control service uses the intent specifications to detect user utterances, expressions, or intents that correspond to the applications. An application intent specification may include NLU models for use by the natural language understanding component. In addition, one or installed applications may contain specified dialog models for that create and coordinate speech interactions with the user. The dialog models may be used by the dialog management component in conjunction with the dialog models to create and coordinate dialogs with the user and to determine user intent either before or during operation of the installed applications. The NLU component and the dialog management component may be configured to use the intent specifications of the applications either to conduct dialogs, to identify expressed intents of users, identify and use the intent specifications of installed applications, in conjunction with the NLU models and dialog modes, to determine when a user has expressed an intent that can be serviced by the application, and to conduct one or more dialogs with the user, see par. [0047].
It would have been obvious to one of ordinary skill in the art to combine the Buchanan invention with the teachings of Ramaci for the benefit of identify and use the intent specifications of installed applications, in conjunction with the NLU models and dialog modes, to determine when a user has expressed an intent that can be serviced by the application, and to conduct one or more dialogs with the user, see par. [0047].
Regarding claim 19 Buchanan teaches the system of claim 18, wherein the instructions, when executed, are further configured to cause the at least one processor to:detect a digression request (The model recognizes subtle signs of emotional responses, such as frustration from repeated queries on a single topic or confusion indicated by vague or off-topic responses, see par. [0079]); save, in response to detecting the digression request, a state of the topic prompt prior to receipt of the digression request (The system personalizes learning experiences by referencing students' previous interactions and progress. It tracks the student's learning journey, identifies strengths and weaknesses, and tailors future interactions accordingly, see par. [0069]); determine, at the router prompt, a digression topic prompt from the plurality of topic prompts (When the user inputs a chat communication, the system receives the data within the chat window. The system leverages an advanced AI model trained to understand and analyze conversation contexts and user interactions, see par. [0098]); provide the digression topic prompt and the digression request to the language model (the model uses inputs, including the current chat communication, previous conversations, and topic data, to assess. The AI model generates a strategic chatbot response upon determining that the user's input strays from the established topic of interest. The response is formulated based on the conversation's state before receiving the off-topic communication, see par. [0098]). receive, from the language model and in response to the digression topic prompt and the digression request, a digression response to the digression request ( a second AI model 624 to generate a new chat response based on the state of the conversation between the conversation output by the first AI model 623 and the user. In this example, the first AI model 623 (or the software application 622, etc.) may transfer a conversation state 630 to the second AI model 624, see par. [0077]); and provide the digression response using the virtual agent (the second AI model 624 may generate a new chatbot response 618 (shown in process 600D in FIG. 6D) which is then output to the chat window 611 by the software application 622, see par. [0077]).
and return, after providing the digression response, to the state of the topic prompt prior to receipt of the digression request (the AI model 724 may generate a new chat response 718 which attempts to guide the conversation back to the original topic of interest, see par. [0089]).
Regarding claim 20 Buchanan teaches the system of claim 18, wherein the instructions, when executed, are further configured to cause the at least one processor to: provide the topic prompt and the request to the language model together with a digression prompt configured to use the language model to determine a digression from a topic of the topic prompt prior to providing the response (IG. 7A illustrates a view 700A of a chat conversation within a chat window 711 of a user interface of a user device 710. FIGS. 7B-7D illustrate an iterative process of analyzing a chat conversation for a topic of interest, and FIG. 7E illustrates a process of guiding a user back to the topic of interest, see par. [0088]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michael Ortiz-Sanchez whose telephone number is (571)270-3711. The examiner can normally be reached Monday- Friday 9AM-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, Bhavesh Mehta can be reached at 571-272-7453. 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.
/MICHAEL ORTIZ-SANCHEZ/ Primary Examiner, Art Unit 2656
Prosecution Insights