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 .
This application claims priority from Provisional Application 63/607,895, filed 12/08/2023 and Provisional Application 63/607,891, filed 12/08/2023.
This communication is responsive to the amendment filed on 02/18/2026.
Status of claims:
Claims 1, 4, 7-15, 18 and 20 are presented for examination.
Claims 1-20 are pending for examination.
Response to Arguments
Applicant's arguments filed on 02/18/2026 with respect to the amended limitations have been considered in view of the new ground(s) of rejection necessitated by amendment.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(B) CONCLUSION. —The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 1, 8 and 15: recite the newly added limitations:
“obtaining a summary for the one or more sets of queries using the artificial intelligence generative model”, which is not mentioned/supported by the Applicant’s specification. For the purpose examination, Examiner interprets a summary for the one or more sets of queries as queries are extracted from query historical logs. Applicant is required for clarification.
“vectorizing, by the one or more processors, each of a plurality of the historical queries using a large language model; calculating, by the one or more processors, semantic similarities of each of the plurality of the vectorized historical queries using an artificial intelligence generative model”. The claims provide no guidance as to how the features vectorizing …and calculating … are identified/determined and performed/calculated as such. Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims (See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). The applicant is suggested to clarify the claims base on the novelty of the invention. Applicant is required for clarification/correction.
All dependent claims are rejected under the same rational as the base claims above.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Lauritzen et al. (US 2023012909 A1), hereinafter “Lauritzen”, in further view of Tiwari et al. (US 20210133224 A1), hereinafter “Tiwari”
Claim 1, Lauritzen discloses A method, implemented by one or more processors, for automatic query and response generation (abstract and par. [0008], a computer-implemented method for training of a query ranking machine-learning model to provide an answer for a user query in a search engine), the method comprising:
- obtaining a query log of historical queries within a predetermined knowledge domain (par. [0022], the first training set may be obtained by collecting sets of queries and answers developed for different enterprises; and par. [0052], wherein queries can be extracted from historical logs);
- obtaining a summary for the one or more sets of queries using the artificial intelligence generative model (par. [0022], the first training set may be obtained by collecting sets of queries and answers developed for different enterprises; and par. [0052], wherein queries can be extracted from historical logs);
- receiving a new query by a user at a user interface on a user computing device (par. [0022], obtaining by collecting sets of queries and answers developed for different enterprises; and par. [0052], wherein queries can be extracted from historical logs);
- generating a new response to the new query using the large language model, wherein the new response is a preferred response for a set of queries including the new query, the preferred response based on the user-generated feedback data and providing the highest level of engagement of the one or more responses (abstract & pars. [0032]-[0034], The first filtered group is identified generated queries that the query ranking machine learning model (i.e., large language model )cannot rank correctly, wherein the filtering generated queries that the query-ranking machine-learning model cannot rank correctly, it is computationally cheap to use the generation model to get queries and then rank them with the existing ranking model; and par. [0018]-[0019], retraining the query ranking machine learning model at least partially based on the filtered group of queries with associated answers from the second training set, and repeating the generating, filtering and retraining steps zero or more times; and pars. [0033]-[0034], the section or answer with the highest score is compared to the section or answer that was used to generate the query. If the section or answer with the highest score is not identical to the section or answer used to generate the query, then the query is not ranked correctly. Preferable, when a query is entered, the ranking model should score the section or answer, for which the query originally was derived, as the highest ranked section or answer).
However, does not disclose the limitations “vectorizing, by the one or more processors, each of a plurality of the historical queries using a large language model; calculating, by the one or more processors, semantic similarities of each of the plurality of the vectorized historical queries using an artificial intelligence generative model”.
Meanwhile, Tiwari discloses vectorizing, by the one or more processors, each of a plurality of the historical queries using a large language model (abstract, generating vector indexes for the multiple documents such that the vector indexes allow a computing system to quickly access the plurality of documents and identify an answer to a question associated with the corpus of data; par. [0038] and [0041], creating vectors for the document (e.g., title, sentences, and utterances) that are stored in the vector index. Wherein querying 514 an elastic search and sentence to a vector index. The elastic search and text similarity search includes traditional information retrieval methods to search for the presence of words (or synonyms) in a particular query. The vector space similarity search converts a query to a vector using sentence embedding during run time and compares the query vector to the document vectors in the index (computed offline) to find the most relevant document to the query. The method 500 ranks 516 the identified (and relevant) articles and applies filters 518 to determine the best articles; and par. [0050] and [0038], AI and a machine learning (wherein “a large language model” as claimed is a trained machine learning model, see the Specification, par. [0060]));
- calculating, by the one or more processors, semantic similarities of each of the plurality of the vectorized historical queries using an artificial intelligence generative model (par. [0050] and [0038], AI and a machine learning; and par. [0029], A vector space similarity search is performed by converting a query to a vector using sentence embedding during run time and comparing the query vector to the document vectors in the index (computed offline) to find the most relevant document to the query. Run time 104 generates an answer to question; and par. [0038], an index is created for computing similarity, which results in the vector index 412. In some embodiments, sentence embedding is used to create vectors for the document (e.g., title, sentences, and utterances) that are stored in the vector index 412. …elastic search index 416 supports various types of analysis, mapping fields, querying, and ranking results);
- clustering, by the one or more processors, the query log to identify one or more sets of queries using semantic aggregation, the semantic aggregation based on the semantic similarities of each of the vectorized historical queries (par. [0029], a text similarity search includes traditional information retrieval methods to search for the presence of words (or synonyms) in a given query. A vector space similarity search is performed by converting a query to a vector using sentence embedding during run time and comparing the query vector to the document vectors in the index (computed offline) to find the most relevant document to the query. Run time 104 generates an answer to question; par. [0038], an index is created for computing similarity, which results in the vector index 412. In some embodiments, sentence embedding is used to create vectors for the document (e.g., title, sentences, and utterances) that are stored in the vector index … analysis, mapping fields, querying, and ranking results. An elastic search system supports traditional information retrieval based searches. In some embodiments, the elastic search system is used for text indexing, traditional text searching, and the like. The indexes 412, 414, and 416 are used during run time to quickly identify answers to user questions and other user messages);
- generating, by the one or more processors, one or more responses for each of the one or more sets of queries using the large language model based on the summary for the one or more sets of queries, wherein the responses are within the predetermined knowledge domain (par. [0050], conversational AI assistants and conversational bots are growing in popularity and their ability to answer questions is an important feature. Using relevant utterances as features in answering questions has shown to improve both the precision and recall for retrieving the right answer by a conversational bot. Therefore, utterance generation has become an important problem with the goal of generating relevant utterances (e.g., sentences or phrases) from a knowledge base article that consists of a title and a description. However, generating good utterances typically requires a significant amount of manual effort, creating the need for an automated utterance generation; and par. [0051], utterance generation is an important problem in Question-Answering, Information Retrieval, and Conversational AI Assistants. Conversational skills developed for these devices need to understand various ways that an end user is asking a question, and be able to respond accurately)
- receiving user-generated feedback data for each of the one or more responses (par. [0042], a relevance score for each article is above a confidence threshold level. The confidence threshold level is determined by a precision/recall accuracy measure. For example,or a set of messages (for various thresholds), the number of correct responses from the bot are measured. Based on the number of correct responses, the right confidence threshold is determined. If no article is determined to be above the confidence threshold level, then the top three articles 522 are presented or communicated to the user. If at least one article is determined to be above the confidence threshold level, then the top article (e.g., the highest ranked article) is returned 524 to the user; and par. [0047], the methods summarize the large article and present just the summary to the user (in text or audio format). For example, during the index time, if the systems and methods find the article to be too large, they automatically create a summary of the paragraph using an extractive summarizer. The summarizer picks the salient sentences from the large number of sentences and creates a summary., if the article is too big and contains a significant amount of information (other than the relevant parts) that is not relevant to the given query, then a summary might be better to return to the user instead of the entire article).
- presenting, at the user interface on the user computing device, the new response to the new query (par. [0023], a conversational interface that includes an ability to interact with a computing system in natural language and in a conversational way. … intent and identify information to generate a response back to the user; and par. [0035], the articles or other information are above a confidence threshold and a response manager 324 returns an appropriate response to a user ).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified the combined system of Lauritzen to include the features as disclosed by Tiwari in order to improve retrieval precision and concise answer across varied users.
Claim 2, The combination of Lauritzen and Tiwari discloses the invention as claimed. Lauritzen further discloses prior to receiving feedback data, prioritizing the one or more responses, based on frequency of queries in the query log (par. [0092], this may be discovered if queries generated for answer A is often classified by the ranking model as answer B and vice versa. If this happens beyond a certain threshold frequency then, it is an indicator that the two answers are similar. Generated questions for answers that meet the frequency threshold can therefore be associated with these two answers. The method can also be applied to identify three or more similar answers; also see pars. [0126]- [0128]).
Claim 3, The combination of Lauritzen and Tiwari discloses the invention as claimed. Lauritzen further discloses prior to generating one or more responses, prioritizing the one or more sets of queries, based on frequency of queries in the query log (par. [0092], this may be discovered if queries generated for answer A is often classified by the ranking model as answer B and vice versa. If this happens beyond a certain threshold frequency then, it is an indicator that the two answers are similar. Generated questions for answers that meet the frequency threshold can therefore be associated with these two answers. The method can also be applied to identify three or more similar answers; also see pars. [0126]- [0128]).
Claim 4, The combination of Lauritzen and Tiwari discloses the invention as claimed. Lauritzen further discloses associating one or more queries with the one or more responses based on the user-generated feedback data (par. [0126]- [0128], the generation model generate 10 queries per answer from the knowledge database, wherein each of these queries is ranked with the ranking model trained on the first dataset. Top 1 rankings are compared for queries generated from two different answers. If these produce the same/most similar top 1 rankings, then the answers will be duplicate/redundant).
Claim 5, The combination of Lauritzen and Tiwari discloses the invention as claimed. Lauritzen further discloses receiving queries based on keywords obtained from the one or more sets of queries (pars. [0026]-[0027], a query is a question with a question mark, but it may also be a sequence of one or more words for searching or evaluating an answer. A query is a question or search terms received from a user or generated by question generation. In this document the terms “question” and “query” is used interchangeable. The queries have in the past been generated and/or annotated manually by human annotators. The sets collected to form the first training set may be queries manually generated for documents or sections of documents by human annotators based on documents from different enterprises; and generating the one or more responses based on the received queries (pars. [0126]- [0128]).
Claim 6, The combination of Lauritzen and Tiwari discloses the invention as claimed. Lauritzen further discloses highlighting sources used for generating queries for receiving feedback data for each of the one or more responses (par. par. [0092] and [0126]- [0128]).
Claim 7, The combination of Lauritzen and Tiwari discloses the invention as claimed. Lauritzen further discloses after a first query is selected, preloading one or more queries related to the first query, wherein the first query is based on the feedback user-generated data, wherein the one or more queries are generated using a large language model and/or semantic aggregation (abstract and pars. [0032]-[0034], The first filtered group is identified generated queries that the query ranking machine learning model cannot rank correctly, wherein the filtering generated queries that the query-ranking machine-learning model cannot rank correctly, it is computationally cheap to use the generation model to get queries and then rank them with the existing ranking model, also see par. [0008]-[0013]).
Claims 8-14, are system claims, which are corresponding to the method claims 1-7. Therefore, claims 8-14 are rejected under the same rational as claims 1-7 above.
Claims 15-20, are non-transitory computer-readable medium claims, which are corresponding to the method claims 1-6. Therefore, claims 15-20 are rejected under the same rational as claims 1-6 above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure (see PTO-892).
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Loan T. Nguyen whose telephone number is (571) 270-3103. The examiner can normally be reached on Monday from 10:00 am - 6:00 pm, Thursday-Friday from 10:00 am - 2:00 pm. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Aleksandr Kerzhner can be reached on (571) 270-1760. The fax phone number for the organization where this application or proceeding is assigned is 571-270-4103. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
08/21/2026
/LOAN T NGUYEN/Examiner, Art Unit 2165
/ALEKSANDR KERZHNER/Supervisory Patent Examiner, Art Unit 2165
Prosecution Insights