CTNF 18/940,935 CTNF 95830 DETAILED ACTION This office action is in response to Applicant’s submission filed on 11/8/2024. Claims 1-20 are pending in the application of which Claims 1, 11, and 20 are independent and have been examined. Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Information Disclosure Statement The information disclosure statement(s)(IDS) submitted on 1/2/2025 has been considered by the examiner. Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 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 – 20, are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter without significantly more. The claims as whole, considering all claim elements both individually and in combination, do not amount to significantly more than an abstract idea. The independent claims 1, 11, and 20 recites: “ … receiving an input request from a client computing device; identifying one or more first fields of a data dictionary of a data source schema for inclusion in an initial set of fields having direct matches to elements of the input request, to thereby generate an initial field listing; for each first field in the initial field listing, analyzing second fields, adjacent to the one or more first fields, in the data dictionary, to identify a set of relevant second fields; adding the set of relevant second fields to the initial field listing to generate an expanded field listing; generating a prompt to a generative artificial intelligence (AI) computer model comprising a context portion populated with data for the first fields and relevant second fields in the expanded field listing; and submitting the prompt to the generative AI computer model for processing, wherein the generative AI computer model processes the prompt and generates a response to the input request based on the context portion of the prompt. These limitations, under its broadest reasonable interpretation, cover performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting “ generative AI computer model ”, and “ processor [claim 20] ” , nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the “ generative AI computer model ”, and “ processor” language, “ receiving an input request …”, “ identifying one or more first fields …”, “ generate an initial field listing …”, “ analyzing second fields …”, “ identify a set of relevant second fields …”, “ adding the set of relevant second …”, “ generating a prompt …”, “ submitting the prompt …”, “ generates a response …”. In the context of this claim encompasses the human obtain input data and use it to identify first field in a data source where human can use a list of the data source and pick the primary or direct field of interests. Such fields are compiled (initial field listing) as a source of data which has direct relationship with the input query. Once a first field is identified then human can look around the first field and find out if there are another candidate to be picked to expand the list for a larger list (expanded list). The following steps which deal with generating a prompt is a matter of design by the user/developer. The Gen AI model is doing what a gen AI model is programmed to do which is to output a response. Therefore, the GenAI is nothing but generic tool being used to apply the abstract idea. All of these steps can be performed in the mind and/or using a pen and paper. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements - using a “ generative AI computer model ”, and “ processor [claim 13] ” to perform all of the above-mentioned steps. The use of a “ first language model ”, “ retriever component [claim 1] ” and “ processor [claim 20] ” is recited at a high-level of generality (i.e., as a generic computer device performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The only element mentioned is the usage of a “generative AI computer model”, which due to lack of specificity can be considered as a generic processor. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of a processor is merely for the purpose of data gathering and/or insignificant extra-solution activity that amount to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claim is not patent eligible. The dependent Claims do not add limitations that could help the Claim as a whole to amount to significantly more than the Abstract idea identified for the Independent Claim: Claims 2, and 12 recite: “wherein the set of relevant second fields comprises fewer fields than a total number of adjacent fields to the one or more first fields.”, which is not an inventive concept when part of a total is fewer than the total. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim directed toward abstract idea. The claims are not patent eligible. Claims 3, and 13 recite: “generating first embeddings associated with the fields of the data dictionary generating a second embedding of the input request; and performing a similarity evaluation to generate similarity metrics quantifying a similarity between each first embedding and the second embedding, wherein in response to a similarity metric meeting a predetermined criterion, a corresponding field is identified to be a first field for generation of the initial field listing.” Transforming (embedding) data (text/words/sentence) into digital representation can be conducted by a human with a pen and paper. Subsequently two vectors (embeddings) can be compared with each other. Such comparison would yield similarity measure as how relevant they are to each other. Once certain criteria are met, choose the data being considered, which can be performed in the mind (mental process) and/or using a pen and paper. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim directed toward abstract idea. The claims are not patent eligible. Claims 4, and 14, recite: “wherein analyzing second fields comprises performing a similarity evaluation between pairs of first embeddings associated with the adjacent fields to first embeddings associated with the one or more first fields in the initial field listing, wherein adjacent fields whose corresponding similarity metrics meet the predetermined criterion are selected as relevant second fields.” This claim is similar language as claim 3 where the similarity measure is used to select appropriate data, which can be performed in the mind (mental process) and/or using a pen and paper. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim directed toward abstract idea. The claims are not patent eligible. Claims 5, and 15 recite: “wherein the first embeddings are semantic embeddings generated based on one or more of a field name, a field category, a field sub-category, and a field description.” In the context of this claim, human can provide vectorized representation of field name, a field category etc., which can be performed in the mind (mental process) and/or using a pen and paper. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim directed toward abstract idea. The claims are not patent eligible. Claims 6, and 16 recite: “wherein a subset of the second fields are sibling fields to corresponding ones of the one or more first fields, wherein a sibling field is a field having a same category and sub-category as a corresponding first field.” In the context of this claim, defining a particular tag/label/name (sibling) for two set of data is not an inventive concept. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim directed toward abstract idea. The claims are not patent eligible. Claims 7, and 17 recite: “wherein a subset of the second fields are cousin fields to corresponding ones of the one or more first fields, wherein a cousin field is a field having a same category, but different sub-category, as a corresponding first field.” In the context of this claim, defining a particular tag/label/name (cousin) for two set of data is not an inventive concept. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim directed toward abstract idea. The claims are not patent eligible. Claims 8, and 18, recite: “wherein identifying one or more first fields comprises performing a similarity evaluation between a first embedding of the input request, and second embeddings associated with previous input requests to generate, for each second embedding, a similarity metric, wherein in response to a similarity metric associated with a second embedding meeting a predetermined criterion, relevant fields associated with a corresponding previous input request are retrieved as first fields for inclusion in the initial field listing.” In the context of this claim, human can compare the current query with the previous query and decide if the comparison is valid, then use the previous data entry. Such steps are not inventive concept and can be carried out by a human with the help of pen and paper. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim directed toward abstract idea. The claims are not patent eligible. Claims 9, and 19, recite: “wherein generating the prompt comprises inputting the expanded field listing into a retrieval augmented generation (RAG) prompt engine which generates a RAG prompt for input to the generative AI computer model.” This claim is similar to claim 1, whereby, human can provide the generated list as a set of data and the corresponding query/prompt to be entered into a generic processor (RAG) whereby it is used as generic tool being used to apply the abstract idea. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim directed toward abstract idea. The claims are not patent eligible. Claim 10, recite: “ wherein the generative AI computer model is a large language model (LLM) which receives the input request via a chatbot interface and outputs the response to the input request via the chatbot interface as a natural language response.” Using a chatbot as an interface is not an inventive concept. Both, chatbot and LLM are recited at a high level of generality and as such they are considered to be a generic processor. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim directed toward abstract idea. The claims are not patent eligible. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-23-aia AIA 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. 07-21-aia AIA Claim s 1, 11, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Tong et al. (US20200334040A1)(herein "Tong"), and in further view of Khosla et al. (US12505136B2)(herein " Khosla ") . Regarding claims 1, 11 and 20 Tong teaches [ A method comprising : - claim 1], [ A computer program product comprising: one or more computer-readable storage media; and program instructions stored on the one or more computer-readable storage media to perform operations comprising : - claim 11], and [ A computer system comprising: a processor set; one or more computer-readable storage media; and program instructions stored on the one or more computer-readable storage media to cause the processor set to perform operations comprising : - claim 20] (Tong, Par. 0100:” A method provided in this application may be applied to a chip, a processor , or a central processing unit. “, and Par. 0185:” … When software is used to implement the embodiments, the embodiments may be implemented completely or partially in a form of a computer program product . The computer program product includes one or more computer instructions . When the computer program instructions are loaded and executed on the computer, ... computer instructions may be stored in a computer-readable storage medium or may be transmitted from a computer-readable storage medium to another computer-readable storage medium. .... The computer-readable storage medium may be any usable medium accessible by a computer, or a data storage device, such as a server or a data center, integrating one or more usable media.”) identifying one or more first fields of a data dictionary of a data source schema for inclusion in an initial set of fields having direct matches to elements of the input request, to thereby generate an initial field listing; (Tong, Par. 0040:” The request processing module is configured to determine the data based on the data address . “, and Par. 0041:” The result processing module is configured to obtain the data , and determine a search keyword based on the data [ data dictionary/source ] and the first search field .”) Note: data based on data address reads on direct match. for each first field in the initial field listing, analyzing second fields, adjacent to the one or more first fields, in the data dictionary, to identify a set of relevant second fields ; (Tong, Par. 0025:” … the search instruction further includes a search identifier , the search identifier is used to identify a second search field , and the determining, by the search engine unit, a search keyword based on the data and the first search field includes:”, and Par. 0026:”determining, by the search engine unit, the second search field in the data based on the search identifier ;”, and Par. 0121:” … the search identifier is used to identify the second search field . Therefore, the thread unit places the data address, the first search field , and the search identifier in the search instruction.”) Note: Search identifier is the element that ties the first and second search filed which reads on the second fields is a relevant second field. adding the set of relevant second fields to the initial field listing to generate an expanded field listing ; ( Tong, Par. 0027:” generating , by the search engine unit, the search keyword based on the first search field and the second search field .”) Note: search keyword based on the combined first and second fields read on expanded field listing. Tong does not teach, however Khosla teaches receive/ receiving an input request from a client computing device ; ( Khosla, Col. 18, ll. 63-67:” … the natural language question answering service 102 receives a natural language question (or prompt) from one of the customer [ client ] computing devices 122 (e.g., where a user of the device entered the question via UI).”) generating a prompt to a generative artificial intelligence (AI) computer model comprising a context portion populated with data for the first fields and relevant second fields in the expanded field listing ; and (Khosla, Col. 8, ll. 64-67:” … communicating with other components and/or modules of the natural language question answering service 102 to generate a prompt from passages and the natural language question .”, and claim 1:” … receive , from a customer computing device and via a user interface (UI) associated with the customer computing device, a query in natural language text; identify, via an aggregator component of the system and based on the query, supplemental search system information for submission in conjunction with the query to a large language model (LLM) component of the system, … one or more documents from a search system based on submission of the query ; … the one or more documents as pertaining to the query ; … the supplemental search system information is suitable for submission in conjunction with the query to the LLM component … in response to …, generate a prompt based on the query and including a portion of the verified supplemental search system information ; submit the prompt … to the LLM component of the system to generate , via the LLM component of the system, one or more answers based on the generated prompt ; … “). submitting the prompt to the generative AI computer model for processing, wherein the generative AI computer model processes the prompt and generates a response to the input request based on the context portion of the prompt . ( Khosla, Col. 8, ll. 64-67:” … communicating with other components and/or modules of the natural language question answering service 102 to generate a prompt from passages and the natural language question .”, and claim 1:” … submit the prompt … to the LLM component of the system to generate , via the LLM component of the system, one or more answers based on the generated prompt ; … “). Khosla is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Tong further in view of Khosla to receive an input request from a client computing device; generating a prompt to a generative artificial intelligence (AI) computer model comprising a context portion populated with data for the first fields and relevant second fields in the expanded field listing; and submitting the prompt to the generative AI computer model for processing, wherein the generative AI computer model processes the prompt and generates a response to the input request based on the context portion of the prompt. Motivation to do so would allow the submitter of the question to get more details on the referenced passages (Khosla, Col. 18, ll. 25-27) . 07-21-aia AIA Claim s 2, and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Tong, and Khosla, and in further view of Dash et al. (US 20140330816 A1)(herein "Dash") . Regarding claims 2, and 12 Tong, as modified above, teaches the method, and the computer program product of claims 1, and 11 respectively. Tong, as modified above, does not teach, however, Dash teaches wherein the set of relevant second fields comprises fewer fields than a total number of adjacent fields to the one or more first fields . ( Dash, Par. 0045:” … As indicated above the query summary fields may comprise a subset of the fields that are less than the total number of fields used to store the data. For example, an event schema may comprise 300-500 fields describing the event data. The query summary, for example, may comprise 10-20 fields from the schema. The query engine 272 also provides drill-down capability that allows a user to drill down on the counts to refine the search and gather more information about the data.”) Dash is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Tong, as modified above, further in view of Dash to wherein the set of relevant second fields comprises fewer fields than a total number of adjacent fields to the one or more first fields. Motivation to do so would improve execution time of the queries through query summaries (Dash, Par. 0027) . 07-21-aia AIA Claim s 3-5, and 13-15 are rejected under 35 U.S.C. 103 as being unpatentable over Tong, and Khosla, and in further view of He et al. (US 20250328540A1)(herein "He") . Regarding claims 3, and 13 Tong, as modified above, teaches the method, and the computer program product of claims 1, and 11 respectively. Tong, as modified above, does not teach, however, He teaches wherein identifying the one or more first fields comprises : generating first embeddings associated with the fields of the data dictionary ; (He, Par. 0041:” … from the database based on similarity between a field vector of the field name and the query vector . For example, multiple field vectors of the data table may be obtained, and the field vectors may be generated in advance by processing field information (for example, a field name and/or field metadata) through the pre-trained model and stored in the vector library .”) generating a second embedding of the input request ; and (He, Par. 0041:” … from the database based on similarity between a field vector of the field name and the query vector . For example, multiple field vectors of the data table may be obtained, and the field vectors may be generated in advance by processing field information (for example, a field name and/or field metadata) through the pre-trained model and stored in the vector library .”) performing a similarity evaluation to generate similarity metrics quantifying a similarity between each first embedding and the second embedding , ( He, Par. 0041:” … multiple similarities may be generated based on the multiple field vectors and the query vector , and similarity between the data table and the query vector may be determined based on the multiple similarities .”) wherein in response to a similarity metric meeting a predetermined criterion, a corresponding field is identified to be a first field for generation of the initial field listing . ( He, Par. 0045:” At block 322, second-pass field recall may be performed based on the user query and the field name. For example, the field recall may be performed based on a literal matching degree (for example, a text similarity ) between the user query and the field. … and then the literal matching degree [ similarity ] between the user query and the field may be calculated . At block 323, post-processing may be performed on the multi-pass field recall to determine the target field set .”) He is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Tong, as modified above, further in view of He to generate first embeddings associated with the fields of the data dictionary; generating a second embedding of the input request; and performing a similarity evaluation to generate similarity metrics quantifying a similarity between each first embedding and the second embedding, wherein in response to a similarity metric meeting a predetermined criterion, a corresponding field is identified to be a first field for generation of the initial field listing. Motivation to do so would improve the relevance and accuracy of query results (He, Par. 0038). Regarding claims 4, and 14 , Tong, as modified above, teaches the method, and the computer program product of claims 3, and 13 respectively. Tong, as modified above, teaches wherein analyzing second fields [ Tong Par. 0025 ] comprises performing a similarity evaluation [ He, Par. 0041 ] between pairs of first embeddings [ He, Par. 0041 ] associated with the adjacent fields [ Tong, Par. 0025 ] to first embeddings [ He, Par. 0041 ] associated with the one or more first fields [ Tong, Par. 0040 ] in the initial field listing [ Tong, Par. 0040 ], wherein adjacent fields [ Tong, Par. 0025 ] whose corresponding similarity metrics [ He, Par. 0041 ] meet the predetermined criterion [ He, Par. 0045 ] are selected as relevant second fields [ Tong, Par. 0025 ]. As established above, the combination of Tong and He teaches every element of the claim. A person of ordinary skill in the art (PHOSITA) would understand how to utilize these elements to identify data as relevant second fields upon satisfaction of the similarity criteria, as described above. Regarding claims 5, and 15 , Tong, as modified above, teaches the method, and the computer program product of claims 3, and 13 respectively. Tong, as modified above, does not teach, however, He further teaches wherein the first embeddings are semantic embeddings generated based on one or more of a field name, a field category, a field sub-category, and a field description . (He, Par. 0041:” At block 312, second-pass recall of data tables may be performed based on the user query and the field name . In some embodiments, a data table set (also referred to as a second data table set) may be recalled from the database based on similarity between a field vector of the field name and the query vector.”) 07-21-aia AIA Claim s 6-7, and 16-17 are rejected under 35 U.S.C. 103 as being unpatentable over Tong, and Khosla, and in further view of Singh et al. (US 20240020618A1)(herein " Singh ") . Regarding claims 6, and 16 Tong, as modified above, teaches the method, and the computer program product of claims 1, and 11 respectively. Tong, as modified above, does not teach, however, Singh teaches wherein a subset of the second fields are sibling fields to corresponding ones of the one or more first fields, wherein a sibling field is a field having a same category and sub-category as a corresponding first field . (Singh, Par. 0060]:”As shown in FIG. 9, the taxonomy 800 includes classes and subclasses of data that may be defined by tables of one or more databases .”, and Par. 0061:” A primary skills class 828 [ field ] defines skills possessed and/or demonstrated by employees in which each skill possessed and/or demonstrated by an employee …”, and Par. 0062:” Child skill classes 836, 834 define skills that have a parent/child relationship with skills in the primary skills class 828. For example, a skill in the primary skills class 828 may be software development, whereas skills in the child skill classes 836, 834 may include, for example, programming in JAVA, Python, HMTL, C#, and so forth . Skills in different child skill classes 836, 834 that share a parent primary skills class 828 are considered sibling skills .”) PNG media_image1.png 144 672 media_image1.png Greyscale Singh is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Tong, as modified above, further in view of Singh to wherein a subset of the second fields are sibling fields to corresponding ones of the one or more first fields, wherein a sibling field is a field having a same category and sub-category as a corresponding first field. Motivation to do so would employ dashboards including information about employee skills and skill gaps may be provided to supervisors, managers, vice presidents, executives, etc. via a workspace or mobile application (Singh, Par. 0053). Regarding claims 7, and 17 Tong, as modified above, teaches the method, and the computer program product of claims 1, and 11 respectively. Tong, as modified above, does not teach, however, Singh teaches wherein a subset of the second fields are cousin fields to corresponding ones of the one or more first fields, wherein a cousin field is a field having a same category, but different sub-category, as a corresponding first field . (Singh, Par. 0064:” The skill BB class 838 shown in FIG. 9 represents another skills class , separate from, and not directly related to, the primary skills class 828. As shown, the skill BB class 838 has child classes that include a skills BB1 class 840 and a skills BB2 class 842 . As illustrated, the skills BB1 class 840 is related to the child skills class 834 . Accordingly, the skills BB1 class 840 and the child skills class 834 may include skills that are related to one another , but whose parent classes are not related to one another . For example, the child skills class 834 may include skills related to proficiency in programming certain software language and the skills BB1 class 840 may include skills associated with using a debugging software package or cloud-based document management service used to store software code.”) Note: as depicted in the figure, the two sets/fields are each other’s relative (cousin). Singh is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Tong, as modified above, further in view of Singh to wherein a subset of the second fields are cousin fields to corresponding ones of the one or more first fields, wherein a cousin field is a field having a same category, but different sub-category, as a corresponding first field. Motivation to do so would employ dashboards including information about employee skills and skill gaps may be provided to supervisors, managers, vice presidents, executives, etc. via a workspace or mobile application (Singh, Par. 0053) . 07-21-aia AIA Claim s 8, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Tong, and Khosla, and in further view of Karmakar et al. (US20260010963A1)(herein " Karmakar ") . Regarding claims 8, and 18 Tong, as modified above, teaches the method, and the computer program product of claims 1, and 11 respectively. Tong, as modified above, does not teach, however, Karmakar teaches wherein identifying one or more first fields comprises performing a similarity evaluation between a first embedding of the input request, and second embeddings associated with previous input requests to generate, for each second embedding, a similarity metric, wherein in response to a similarity metric associated with a second embedding meeting a predetermined criterion, relevant fields associated with a corresponding previous input request are retrieved as first fields for inclusion in the initial field listing . (Karmakar, Par. 0022:” … In block 164, the component then compares [ similarity evaluation ] the user query [ input request ] to prior queries [ previous input requests ] that are mapped to documents [ relevant fields ] used in prior responses to those prior queries . If it is determined in block 166 that there are one or more matching prior queries (e.g., with a similarity above a defined threshold [ predetermined criterion ]), the routine continues to block 168 to retrieve the one or more documents mapped to those matching one or more prior queries , and otherwise continues to block 172 to check if the determined topic for the user query corresponds to one of multiple defined tools.”) Karmakar is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Tong, as modified above, further in view of Karmakar to wherein identifying one or more first fields comprises performing a similarity evaluation between a first embedding of the input request, and second embeddings associated with previous input requests to generate, for each second embedding, a similarity metric, wherein in response to a similarity metric associated with a second embedding meeting a predetermined criterion, relevant fields associated with a corresponding previous input request are retrieved as first fields for inclusion in the initial field listing. Motivation to do so would indicate that a prior response was inaccurate and/or irrelevant to the user query (Karmakar, Par. 0018) . 07-21-aia AIA Claim s 9-10, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Tong, and Khosla, and in further view of Cao et al. (US 20260099693 A1)(herein "Cao") . Regarding claims 9, and 19 Tong, as modified above, teaches the method, and the computer program product of claims 1, and 11 respectively. Tong, as modified above, does not teach, however, Cao teaches wherein generating the prompt comprises inputting the expanded field listing into a retrieval augmented generation (RAG) prompt engine which generates a RAG prompt for input to the generative AI computer model. ( Cao, Par. 0017:” The RAG system 102 is part of a chat platform that utilizes a RAG assistant 106 as an intermediary between a large language model (LLM) 108 and a chatbot application 110 that interacts with a user through a user interface of a client device 112. In response to receiving a query 116 from a user, the chatbot application 110 provides the user inputs (e.g., the query along with other recent conversation data) to the RAG assistant 106, as shown by arrow “A.” In response , the RAG assistant 106 vectorizes the user inputs and transmits a search query 118 to a source index 114 to identify stored data documents [ field listing ] or portions of documents with corresponding vector representations that satisfy some degree of similarity with the vectorized user inputs . For example, the source index 114 is a file repository or database that includes a corpus of user-selected documents or portions of such documents . In some cases, the documents in the source index 114 pertain to a particular subject matter domain for which the user is primarily using the system. The source index 114 is shown to include various data chunks (e.g., Chunk A, Chunk B), which may, for example, represent documents, portions of documents, or even data derived from portions of documents (e.g., document summaries, translations).”) Cao is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Tong, as modified above, further in view of Cao to wherein generating the prompt comprises inputting the expanded field listing into a retrieval augmented generation (RAG) prompt engine which generates a RAG prompt for input to the generative AI computer model. Motivation to do so would improve the quality and informativeness of the LLM outputs (Uthaman, Par. 0034), and provide a software tool that facilitates objective evaluation of content generated by RAG systems (Cao, Par. 0014). Regarding claim 10 Tong, as modified above, teaches the method of claim 1. Tong, as modified above, does not teach, however, Cao teaches wherein the generative AI computer model is a large language model (LLM) which receives the input request via a chatbot interface and outputs the response to the input request via the chatbot interface as a natural language response . (Cao, Par. 0017:” The RAG system 102 is part of a chat platform that utilizes a RAG assistant 106 as an intermediary between a large language model (LLM) 108 and a chatbot application 110 that interacts with a user through a user interface of a client device 112. In response to receiving a query 116 from a user, the chatbot application 110 provides the user inputs (e.g., the query along with other recent conversation data) to the RAG assistant 106, as shown by arrow “A.” In response , the RAG assistant 106 vectorizes the user inputs and transmits a search query 118 to a source index 114 to identify stored data documents [ field listing ] or portions of documents with corresponding vector representations that satisfy some degree of similarity with the vectorized user inputs . For example, the source index 114 is a file repository or database that includes a corpus of user-selected documents or portions of such documents . In some cases, the documents in the source index 114 pertain to a particular subject matter domain for which the user is primarily using the system. The source index 114 is shown to include various data chunks (e.g., Chunk A, Chunk B), which may, for example, represent documents, portions of documents, or even data derived from portions of documents (e.g., document summaries, translations).”, and Par. 0018:”In response to receiving the search query 118, the RAG assistant 106 performs vector analysis to identify data chunks residing in the source index 114 that are most similar to the user inputs and, therefore, assumed to be relevant to the query 116. These identified similar data chunks are returned, e.g., as “ relevant chunks 120” to the RAG assistant 106. … The RAG assistant 106 then generates a context-enhanced query 124 that is passed to the LLM 108. This enhanced query typically includes the query 116, the relevant chunks 120 (also referred to herein as “context data”), and a directive instructing the LLM 108 to utilize the context data to answer the user query . The LLM 108 responds to the context-enhanced query 124 with LLM response 126, which is conveyed back to the user as RAG response 128. In various implementations, the RAG response 128 is either verbatim identical to the LLM response 126 or modified somehow by the RAG assistant 106 (via re-formatting, addition of citations to source document(s)).”) Note as shown in Fig. 1, the LLM response is directed thru RAG Assistant to the Chatbot interface to the client device. Cao is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Tong, as modified above, further in view of Cao to wherein the generative AI computer model is a large language model (LLM) which receives the input request via a chatbot interface and outputs the response to the input request via the chatbot interface as a natural language response. Motivation to do so would improve the quality and informativeness of the LLM outputs (Uthaman, Par. 0034), and provide a software tool that facilitates objective evaluation of content generated by RAG systems (Cao, Par. 0014) . Conclusion 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. Jain et al. (US 12481666 B1) teaches in Col. 5. Line 65- Col. 6, line 15:” Yet another technical benefit achieved by the information retrieval system described herein is constructing and identifying additional details associated with a search result to provide a more complete context and thorough details associated with the search result. For example, returning to the GraphQL example, the language section of the GraphQL specification may further include subsections related to operations, types and fields, arguments, and the like used in the GraphQL language, which provide in-depth details, such as for use in writing a GraphQL query. Certain aspects described herein enable identification of related additional information and sections of documents to provide expanded details and descriptions of search results. Additional details may be identified based on forward tracing the search result to identify one or more child nodes associated with the search result, each child node containing additional information. Thus, additional information associated may be identified and supplement the search result.” Examiner's Note: Examiner has cited particular columns and line numbers and/or paragraph numbers in the references applied to the claims above for the convenience of the applicant. Although the specified citations are representative of the teachings of the art and are applied to specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant in preparing responses, to fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the Examiner. In the case of amending the Claimed invention, Applicant is respectfully requested to indicate the portion(s) of the specification which dictate(s) the structure relied on for proper interpretation and also to verify and ascertain the metes and bounds of the claimed invention. Any inquiry concerning this communication or earlier communications from the examiner should be directed to DARIOUSH AGAHI whose telephone number is (408)918-7689. The examiner can normally be reached Monday - Thursday and alternate Fridays, 7:30-4:30 PT. 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 on 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. DARIOUSH AGAHI, P.E. Primary Examiner /DARIOUSH AGAHI/Primary Examiner, Art Unit 2656 Application/Control Number: 18/940,935 Page 2 Art Unit: 2656
Prosecution Insights