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 Amendment
Claims 1, 12 and 18 are amended. Claims 1-20 are presented for examination.
Response to Arguments
103 REJECTIONS
Applicant’s arguments with respect to claims 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.
101 REJECTIONS
Applicant arguments are persuasive and hence the rejection under 101 is withdrawn.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-3, 5-6, 8, 10, 12-15, and 17-20 are rejected under 35 U.S.C. 103 as being unpatentable Wu ( US 20250272283) and further in view of Seibel (US 20240202221 )
Regarding claim 1, Wu teaches a computer-implemented method comprising: obtaining a plurality of portions of content based on a user query corresponding to one or more topics related to an organization ( The search engine communicates a search query 108 to the storage system 140 to retrieve content data 162 from stored content items 160 relevant to the search query, Para 0042, Fig 2; wherein the related content is obtained too which includes organization data, Para 0054; where in one embodiment the results ( content ) goes back to the user to select plural content, in some embodiments, before the set of search results 118 are provided to the user system 110-1, additional processing is performed. For example, one or more filtering algorithms or ranking algorithms can be applied to the set of content data 162 displayed to the user system 110-1 via the landing page. In some embodiments, credential authorization and/or verification is performed to ensure that the user system 110-1 has the proper credentials to view the set of search results 118, Para 0043 ) , wherein the plurality of portions of content is retrieved from at least one content source corresponding to the organization ( the content is relates to topic/organization, Para 0139) , wherein the at least one content source comprises at least one knowledgebase ( storage system, Fig 2) , and wherein at least one portion of the plurality of portions of content is retrieved from the at least one knowledgebase (databases/knowledge graph – storage system, Fig 2, Fig 6) ; configuring a first model instance ( rank to learn model, Para 0058-0059 or ranking manager is an LLM, Para 0060) to generate a score ( ranking manager generates scores, Para 0059) for each portion of content in the plurality of portions of content based on its relevancy ( ranking based on the content retrieved, Para 0058-0059; where ranking is based on category/keyword and category/keyword is associated with the query, Para 0042, 0113) ; filtering the plurality of portions of content based at least in part on one or more filtering criteria and the score generated for each portion ( filtering using the ranking algorithm, Para 0043; top ranked content, Para 0061) ; and generating, using a second language model instance ( summarizer can be a different LLM model than ranking model, Para 0061-0062; additionally the summarizer 128 is a different machine learning model from the category and keyword identifier 122 machine learning model, Para 0062) , a response to the user query, wherein the response is based at least in part on the portions of content resulting from the filtering ( the summarized and synthesized response is sent back to the user, Fig 2, Para 0064) ) ; wherein the method is performed by at least one processing device comprising a processor coupled to a memory ( Fig 8)
While Wu teaches model which scores based on relevance it does not teach configuring a first model instance to generate a score for each portion of content in the plurality of portions of content based on its relevancy to the user query
However, Siebel teaches first language model and configuring a first model instance to generate a score for each portion of content in the plurality of portions of content based on its relevancy to the user query (the enterprise generative artificial intelligence system determines, by a machine learning model, a relevance score based on the analysis of the query input. In some embodiments, a retrieval module (e.g., retrieval module 406) determines the relevance score, Para 0138-0143)
It would have been obvious having the teachings of Wu to further include the concept of Siebel before effective filing to identify relevant information based on the query ( Para 0004, Seibel)
Regarding claim 2, Wu as above in claim 1, teaches , wherein the first language model instance and the second language model instance correspond to different machine learning models ( ranking and LLM are different model, Fig 2)
Regarding claim 3, Wu as above in claim 2, teaches , wherein the first language model instance comprises a first context window and the second language model instance comprises a second context window that is different than the first context window ( different model, hence different context window, Fig 2, Para )
Regarding claim 5, Wu modified by Seibel as above in claim 1, teaches wherein each portion of the content corresponds to an article comprising text related to at least one of the one or more topics ( topics etc., Para 0108, 0139, 0143, Wu; topics, Para 0030, Seibel)
Regarding claim 6, Wu modified by Seibel as above in claim 1, teaches configuring at least one of the first language model instance and the second language model instance via a system prompt, wherein the system prompt is hidden from a user associated with the user query ( prompting the model, Para 0022-0023, Wu; LLM model, Para 0158, fig 10, Seibel)
Regarding claim 8, Wu does not explicitly teach processing, using the second language model instance, the user query to identify the at least one content source from a plurality of content sources associated with the organization
However, Seibel teaches processing, using the second language model instance, the user query to identify the at least one content source from a plurality of content sources associated with the organization ( fig 10)
Wu has a concept of processing the results which is based on user query to give the response, Siebel shows the user query and results can be processed by the LLM to generate the response. It would have been obvious having the concept of Wu to modify with Seibel since it would yield predictable result which is to generate a response ( Para 0127, Seibel)
Regarding claim 10, Seibel as above in clam 1, teaches wherein the one or more filtering criteria comprise at least one of: retaining a given portion of content having a score that satisfies a threshold value; and retaining a specified number of portions of content having the highest scores ( Para 0208, Seibel)
Regarding claim 12, Wu as above in claim 1, teaches , wherein the obtaining the plurality of portions of content based on the user query comprises performing a vector similarity search based on the user query and content stored in the at least one content source (cosine similarity, Para 0056)
Regarding claim 13, arguments analogous to claim 1, are applicable. In addition, Wu teaches A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device to perform the method of claim 1 ( Para 0171)
Regarding claim 14, arguments analogous to claim 2, are applicable.
Regarding claim 15, arguments analogous to claim 3, are applicable.
Regarding claim 17, arguments analogous to claim 5, are applicable.
Regarding claim 18, arguments analogous to claim 1, are applicable. In addition, Wu teaches An apparatus comprising: at least one processing device comprising a processor coupled to a memory; the at least one processing device being configured to perform the method of claim 1 ( fig 8)
Regarding claim 19, arguments analogous to claim 2, are applicable.
Regarding claim 20, arguments analogous to claim 3, are applicable.
Claims 4 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Wu ( US 20250272283) and further in view of Seibel (US 20240202221 ) and further in view of Gurgu (US 20230297887 )
Regarding claim 4, Wu modified by Seibel as above in claim 1, does not explicitly teach wherein the first language model instance and the second language model instance each comprise a hyperparameter for controlling output randomness, wherein the hyperparameter is set to a first value for the first language model instance and the hyperparameter is set to a different, second value for the second language model instance
While Wu modified by Seibel teaches different language model, they don’t explicitly mention wherein the first language model instance and the second language model instance each comprise a hyperparameter for controlling output randomness, wherein the hyperparameter is set to a first value for the first language model instance and the hyperparameter is set to a different, second value for the second language model instance
However Gurgu in the same filed of endeavor teaches wherein the first language model instance and the second language model instance each comprise a hyperparameter for controlling output randomness, wherein the hyperparameter is set to a first value for the first language model instance and the hyperparameter is set to a different, second value for the second language model instance( The first language model may be different from the second large language model in terms of type, and/or value of one or more hyperparameters. The prompt structure used to generate a prompt for the first large language model may be the same or different from the prompt structure used to generate a prompt for the second large language model, Para 0110-0112; wherein the temperature hyperparameter is to control the randomness; and top-k parameter for a language model )
It would have been obvious having the teachings of Wu and Seibel to further include the concept of Gurgu before effective filing date to optimize the performance of the language model and to output creativity and determinism these parameters provide ( Para 0111-0112, Gurgu)
Regarding claim 16, arguments analogous to claim 4, are applicable.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Wu ( US 20250272283) and further in view of Seibel (US 20240202221 ) and further in view of Rabindran (US 20250252367 )
Regarding claim 9, Wu as above in claim 1, mentions structured formal but does not explicitly teach wherein the first language model instance outputs the scores for the plurality of portions of content in a structured data object
However, Rabindran teaches wherein the first language model instance outputs the scores for the plurality of portions of content in a structured data object ( output scores in JSON format, Para 0039)
It would have been obvious having the teachings of Wu and Seibel to further include the concept of Rabindran before effective filing date for further processing like comparing etc. ( Para 0040, Rabindran)
Claims 7 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Seibel (US 20240202221 ) and further in view of Mann ( US 20250217576) and further in view of Londner ( US 20250111145 )
Regarding claim 7, Wu modified by Seibel as above in claim 1, Wu mentions different LLM models and Seibel mentions the second model is basically an expert model which gives the answer based on selected prompts, however does not explicitly teach wherein at least one of: a size of the second language model instance is larger than the first language model instance; the second language model instance and the first language model instance have a different set of capabilities; and the second language model instance utilizes more computing resources than the first language model instance
In the same field of endeavor Londner teaches wherein at least one of: a size of the second language model instance is larger than the first language model instance; the second language model instance and the first language model instance have a different set of capabilities; and the second language model instance utilizes more computing resources than the first language model instance (At step 126, another LLM (and potentially a larger or more complex language model), referred to as an expert model, for example, T0++ or Google's Flan-T5-XL models, may be implemented to further evaluate the interaction transcript 202 and engineered prompt 204, Para 0051)
It would have been obvious having the teachings of Wu and Siebel to further include the concept of Londner before effective filing date since by doing so would generate output from the expert model which can be used as the new detected intent narrative or to correct the intent detected by the previous iteration of the LLMs ( Para 0051)
Regarding claim 11, Wu modified by Siebel as above in claim 1, does not teach wherein the user query is received via a chatbot interface, and the generated response is provided to a user via the chatbot interface
However, Londner teaches wherein the user query is received via a chatbot interface, and the generated response is provided to a user via the chatbot interface ( chatbot system, Para 0021)
It would have been obvious having the teachings of Wu and Seibel to further include the concept of Londner before effective filing date to support the customer service support which relies on the bots ( Para 0004, Londner )
Conclusion
THIS ACTION IS MADE FINAL. 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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Richa Sonifrank whose telephone number is (571)272-5357. The examiner can normally be reached M-T 7AM - 5:30PM.
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, Phan Hai can be reached at (571)272-6338. 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.
/Richa Sonifrank/Primary Examiner, Art Unit 2654