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 .
Drawings
The drawings were received on 1/2/2025. These drawings are accepted.
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 1-7 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea in the form mental process without significantly more. The claim(s) recite(s) language directed towards conversations between a user and agent, where transcripts of interaction history or previous conversations are used to determine interactions semantically similar to the user’s issue indicated in a user’s query or audio. A LLM prompt (interpreted as merely a prompt) is generated using semantically similar interactions to user’s issue or query and executing the prompt to display a recommendation for a response to the agent. Such claimed language can be performed by a human mentally using a library or dictionary of previous interactions with response and feedback. Using pen and paper, a human can search for previous interactions similar to the user’s query or issue and write a prompt including the previous interactions. Execution of the prompt can be done mentally using pen and paper to follow instructions to generate and display a response. This judicial exception is not integrated into a practical application because the recited claimed language fails to include positively recite language indicating practical application integrating the abstract idea. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the recited claimed language fails to include positively recited language indicating significantly more than the judicial exception.
Claims 2-7 are dependent claims and recites language adding to the abstract idea, but fails to include positively recited language indicating significantly more than the judicial exception and/or integrating the abstract idea into practical application.
Claims 8-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea in the form mental process without significantly more. The claim(s) recite(s) language directed towards conversations between a user and agent, where transcripts of interaction history or previous conversations are used to determine interactions semantically similar to the user’s issue indicated in a user’s query or audio. A LLM prompt (interpreted as merely a prompt) is generated using semantically similar interactions to user’s issue or query and executing the prompt to display a recommendation for a response to the agent. Such claimed language can be performed by a human mentally using a library or dictionary of previous interactions with response and feedback. Using pen and paper, a human can search for previous interactions similar to the user’s query or issue and write a prompt including the previous interactions. Execution of the prompt can be done mentally using pen and paper to follow instructions to generate and display a response. This judicial exception is not integrated into a practical application because the recited claimed language fails to include positively recite language indicating practical application integrating the abstract idea. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the recited claimed language fails to include positively recited language indicating significantly more than the judicial exception.
Claims 9-14 are dependent claims and recites language adding to the abstract idea, but fails to include positively recited language indicating significantly more than the judicial exception and/or integrating the abstract idea into practical application.
Claims 15-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea in the form mental process without significantly more. The claim(s) recite(s) language directed towards conversations between a user and agent, where transcripts of interaction history or previous conversations are used to determine interactions semantically similar to the user’s issue indicated in a user’s query or audio. A LLM prompt (interpreted as merely a prompt) is generated using semantically similar interactions to user’s issue or query and executing the prompt to display a recommendation for a response to the agent. Such claimed language can be performed by a human mentally using a library or dictionary of previous interactions with response and feedback. Using pen and paper, a human can search for previous interactions similar to the user’s query or issue and write a prompt including the previous interactions. Execution of the prompt can be done mentally using pen and paper to follow instructions to generate and display a response. In addition, the claim recites “non-transitory computer readable medium …”. Such language is directed towards a generic device performing the abstract idea and does not indicate positively recited language indicating significantly more and/or integrate the abstract idea into practical application. This judicial exception is not integrated into a practical application because the recited claimed language fails to include positively recite language indicating practical application integrating the abstract idea. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the recited claimed language fails to include positively recited language indicating significantly more than the judicial exception.
Claims 16-20 are dependent claims and recites language adding to the abstract idea, but fails to include positively recited language indicating significantly more than the judicial exception and/or integrating the abstract idea into practical application.
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(s) 1,3-5,7-8,10-12,14-15,17-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang (CN 117251547) in view of Nakazawa et al (US Publication No.: 20080195378), further in view of McCloskey et al (US Publication No.: 20160232221).
Claim 1, Wang discloses
a processor (Page 19, lines 31-40 discloses a processor.) and a non-transitory computer readable medium (Page 19, lines 31-40 discloses computer readable storage medium, which includes non-transitory computer readable medium) operably coupled thereto (Page 19, lines 31-40), the non-transitory computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform operations (Page 19, lines 31-40, Page 20, lines 7-11) which comprise:
receiving an audio interaction between a customer and an agent (Page 6, lines 37-51, Page 7, lines 1-6 discloses interaction between a customer and an agent. Page 1, line 18 discloses multi-turn dialogue, indication interactions are audio based.);
the audio interaction into text (Page 12, lines 11-17 discloses the historical chat records consist of multiple Q&A texts generated by the user’s multiple conversations, where the conversations are dialogue based (page 1, line 18).);
identifying a customer issue in the text of the interaction (Page 6, line 38 discloses latest questions from the current user, lines 39-51 discloses chat-based conversation where users can input a query. The query is the identified customer issue.);
performing a semantic search in a vector database for the customer issue in past customer interactions of a plurality of customers (Page 7, lines 43-52 discloses historical chat records can be filtered tin advance to remove dialogue Q&A texts that are not sufficiently relevant in topic and/or topic to the user’s latest question, highlighting the semantic relevance between the historical chat records and the user’s latest question. Filtering process for relevant Q&A dialogue text indicates semantic search.);
obtaining a plurality of transcripts of past customer interactions from the vector database that match the customer issue (Page 7, lines 43-52 discloses historical chat records can be filtered tin advance to remove dialogue Q&A texts that are not sufficiently relevant in topic and/or topic to the user’s latest question, highlighting the semantic relevance between the historical chat records and the user’s latest question;
constructing a large language model (LLM) prompt based on the obtained plurality of transcripts and the customer issue (Page 8, lines 1-12 discloses LLM prompt generation based on historical chat records and the latest user question (customer issue).);
executing the LLM prompt to return a recommendation to resolve the customer issue (Page 8, lines 34-38, Page 9, lines 19-21, Page 10, lines 33-34 discloses executing the LLM prompt to return a recommendation for resolution or response to the customer’s issue or user’s query.); and
displaying the recommendation to the agent in real-time (Page 12, lines 1-10 discloses customer service chat interface environment (indicates real time) where the user enters text. Once submission is received, the customer service robot responds to it. Page 8, lines 34-38, Page 9, lines 19-21, Page 10, lines 33-34 discloses the LLM generates a response. Such sections indicates a display of the response to the agent in real time as well as to the user.).
Wang et al discloses the historical chat history includes Q&A texts of customer agent interactions (dialogue), but fails to disclose converting the conversations or dialogue or customer agent interactions into text.
Nakazawa et al discloses converting the audio interaction into text (Paragraph 61 discloses dialogue history data is obtained via converting a recording of a dialogue into text. (paragraph 61) It would be obvious to one skilled in the art before the effective filing date of the application to modify Wang et al’s historical chat records by converting recordings of a dialogue into text as disclosed by Nakazawa et al so to improve storage of dialogue and enable readily available past dialogue for generating response to a query.)
Wang et al discloses performing semantic search (Page 7, lines 43-52), but fails to disclose the semantic search yields past customer interactions similar to customer issue. where the customer issue was resolved, and that have a threshold customer satisfaction score.
McCloskey et al discloses semantic search yield past customer interactions similar to customer issue, where the customer issue was resolved and that have a threshold customer satisfaction score (Paragraph 42 discloses QA database via tracking the questions asked, answers returned, answer confidence values, user feedback given for each user into a question history database. Paragraph 42 further discloses “QA system 100 programmatically returns a set of recommended questions that are relevant to user input and for which QA system 100 can return high confidence answers”. This indicates semantic search of matching user input with similar questions in the database with corresponding answers where the question is answers (customer issue resolved) and the answer has a threshold customer satisfaction score (high confidence answers).). It would be obvious to one skilled in the art before the effective filing date of the application to modify Wang et al’s semantic searching by searching for questions and answers or historical chat dialogue similar to the customer issue or user query as disclosed by McCloskey et al so to improve the response or answer the agent provides the user, hence improving user’s experience with virtual agent correspondence.
Claim 3, Wang discloses identifying the customer issue in the text of the interaction comprises using the LLM to identify the customer issue; or receiving input from the agent to identify the customer issue (Page 12, lines 1-10 discloses reception of submission event which indicates receiving an input from the agent (customer service robot interface) identifying the customer issue or user’s query.).
Claim 4, Wang et al discloses creating an article based on the recommendation; and saving the article in the knowledge base (Page 16, lines 24-25 discloses “Step S5500, append the user’s latest question and its corresponding practical reply text storage to the historical chat history”. By appending the latest question and corresponding practical reply, this indicates creation of an article based on the recommendation (practical reply) and saving the article in the knowledge base (historical chat history).).
Claim 5, Wang et al discloses updating the customer issue with the recommendation in a knowledge base (Page 16, lines 24-25).
Claim 7, Wang et al discloses the LLM prompt further comprises a system context (Page 8, lines 1-25 discloses the prompt includes context such as instructions to rewrite the latest user question based on previous chat history, supplementing missing key information, answer the rewritten questions based on historical chat records and common sense.).
Claim 8 recites similar limitations as claim 1 and is rejected on the same grounds as claim 1.
Claim 10 recites similar limitations as claim 3 and is rejected on the same grounds as claim 3.
Claim 11 recites similar limitations as claim 4 and is rejected on the same grounds as claim 4.
Claim 12 recites similar limitations as claim 5 and is rejected on the same grounds as claim 5.
Claim 14 recites similar limitations as claim 7 and is rejected on the same grounds as claim 7.
Claim 15 recites similar limitations as claim 1 and is rejected on the same grounds as claim 1.
Claim 17 recites similar limitations as claim 3 and is rejected on the same grounds as claim 3.
Claim 18 recites similar limitations as claim 4 and is rejected on the same grounds as claim 4.
Claim 19 recites similar limitations as claim 5 and is rejected on the same grounds as claim 5.
Allowable Subject Matter
Claims 2,6,9,13,16,20 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Note: All rejections and/or objections must be overcome prior to placing the case in condition for allowance.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LINDA WONG whose telephone number is (571)272-6044. The examiner can normally be reached 9-5.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew C Flanders can be reached at 571-272-7516. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/LINDA WONG/Primary Examiner, Art Unit 2655
Prosecution Insights