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
Applicant’s Amendments, filed March 30, 2026, have been entered. No claims have been amended, and claims 1-19 are currently pending.
Response to Arguments
Applicant’s arguments, see, filed March 30, 2026, with respect to the 35 U.S.C. 101 rejections of claims 1-19 have been fully considered and are persuasive. The 35 U.S.C. 101 rejection of claims 1-19 has been withdrawn.
Applicant's arguments filed March 30, 2026, with respect to the 35 U.S.C. 103 rejections of claims 1-19 have been fully considered but they are not persuasive.
Applicant argues that an “executable query” refers to computer code that, when executed, is capable of retrieving information from a database and that cited prior art Tan does not generate such executable query code using the LLM.
First, Xu et al. (Pub. No. US 2024/0095460 A1, hereinafter “Xu”) is cited as teaching the claim 1 recitation “generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query…”, (See Non-Final Rejection, dated December 30, 2025, hereinafter “Non-Final Rejection”, pp. 29-30). Second, Xu modified by Tan is cited as teaching “execute the executable query for retrieving the portion of the telematics data from the at least one telematics database”, where Tan explicitly teaches that the search query may be a query for search for items in a database (Tan [0063], see Non-Final Rejection pp. 3-4, 33-34), which given the broadest reasonable interpretation discloses an executable query.
Applicant argues that Xu does not teach an isolated LLM that generates an executable query that is then executed to retrieve telematics data from a telematics database while the LLM itself lacks access to that database (Remarks p. 13). In response, examiner respectfully submits that the combination of Xu and Tan is cited as generating the executable query (Xu) that is then executed (Tan) from a telematics database (Xu) (see Non-Final Rejection pp. 29-31, 33-34).
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1, 7, 8, 10, 16, 17 and 19 rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 3, and 4 of U.S. Patent No. 12481649 (hereinafter 649) in view of Xu in view of Tan.
Regarding claim 1, see chart below:
Instant Application
649
1. A system for retrieving telematics data, the system comprising:
at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database;
and at least one processor in communication with the at least one data storage, the at least one processor operable to:
receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database;
generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM;
identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one telematics database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request;
and inputting the portion of contextual information into the LLM;
execute the executable query for retrieving the portion of the telematics data from the at least one telematics database;
and return at least the portion of the telematics data to the user, whereby the natural language request is responded to without providing the LLM with access to the telematics data stored on the at least one telematics database and the at least one context database.
1. A system for retrieving telematics data, the system comprising:
at least one data storage operable to store at least a plurality of databases, each database storing telematics data originating from a plurality of telematics devices installed in a plurality of vehicles; and at least one processor in communication with the at least one data storage, the at least one processor operable to:
receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within one of the databases;
generate, using a large language model (LLM) that does not have access to the plurality of databases, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the database by inputting into the LLM at least: a contextual prompt, the contextual prompt providing to the LLM at least one or more features of the database, an expected structure of the executable query, and one or more example natural language requests and corresponding executable query outputs, and the natural language request;
execute the executable query for retrieving the portion of the telematics data from the database;
and return at least the portion of the telematics data to the user, whereby the natural language request is responded to without providing the LLM with access to the telematics data stored on the plurality of databases.
649 does not appear to teach:
and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database
identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database
However, Xu teaches:
at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database (Xu – the vehicle may further include the infotainment SoC which may include a combination of hardware and software that may be used to provide audio, video, phone, network connectivity, and/or information services (e.g. navigation systems, vehicle related information such as fuel level, brake fuel level, oil level, i.e. telematics) to the vehicle, and may include a telematics device [0176]. The vehicle may further include data stores (see Fig. 9c, 928) [0147]. Retrieval component may use one or more techniques to retrieve, from the information database(s) 112, contextual information that is associated with the text data (see Fig. 1, 112 information database, which may store information associated with the vehicle and Fig. 1, 116 contextual data) [0047-0048].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of 649 and Xu before them, to modify the system of 649 with the teachings of Xu, as indicated above. One would have been motivated to make such a modification to provide answers associated with questions that are natural, conversational, robust, scalable, and accurate (Xu - [0004]).
649 modified by Xu does not appear to teach:
identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database
However, Tan teaches:
identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one [telematics] database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request (Tan – in Fig. 3, 300, the system receives a natural language query from a client device of the user [0054]. In Fig. 3, 310 contextual information associated with the natural language query is determined, which includes information based on information obtained in one or more previous interactions of the user with the online system [0056-0058]. The data store 240 stores data used by the online system, including user data, item data, order data and trained machine learning models, and may use databases to organize the stored data [0051]. Training data is stored in the data store 240 [0052], and includes natural language questions concatenated with contextual data describing users further concatenated with lists of items, item types, or categories of items associated with the natural language question [0044].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of 649, Xu and Tan before them, to modify the system of 649 and Xu with the teachings of Tan, as indicated above. One would have been motivated to make such a modification to respond to search queries with more relevant responses and provide a good user experience (Tan - [0003]).
Claims 10 and 19 correspond to claim 1 and are rejected accordingly.
Dependent claims 7, 8, 16 and 17 of the instant application correspond to claims 3, 4, 16 and 17 of 261 respectively, and are rejected accordingly.
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.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-3, 5-12, 14-19 are rejected under 35 U.S.C. 103 as being unpatentable over Xu in view of Tan further in view of Nia et al. (Pub. No. US 2025/0094787 A1, hereinafter “Nia”).
Regarding claim 1, Xu teaches:
at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database (Xu – the vehicle may further include the infotainment SoC which may include a combination of hardware and software that may be used to provide audio, video, phone, network connectivity, and/or information services (e.g. navigation systems, vehicle related information such as fuel level, brake fuel level, oil level, i.e. telematics) to the vehicle, and may include a telematics device [0176]. The vehicle may further include data stores (see Fig. 9c, 928) [0147]. Retrieval component may use one or more techniques to retrieve, from the information database(s) 112, contextual information that is associated with the text data (see Fig. 1, 112 information database, which may store information associated with the vehicle and Fig. 1, 116 contextual data) [0047-0048].)
and at least one processor in communication with the at least one data storage, the at least one processor operable to: receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database (Xu – in Fig. 7, B702, text data is obtained representing a question associated with a vehicle. For instance, the vehicle may use one or more microphones to generate audio data representing speech from a passenger of the vehicle (i.e. natural language request). The vehicle may then process the audio data, using the speech-processing component, in order to generate the text data representing the speech, which may include a question associated with the vehicle [0068].)
generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM (Xu – block B706 may include inputting the text data and data representing the one or more question/answer pairs into a language model [0070]. The language model may include a large language model [0029].)
one or more features of the at least one telematics database (Xu - the vehicle may further include the infotainment SoC which may include a combination of hardware and software that may be used to provide audio, video, phone, network connectivity, and/or information services (e.g. navigation systems, vehicle related information such as fuel level, brake fuel level, oil level, i.e. telematics) to the vehicle, and may include a telematics device [0176]. The vehicle may further include data stores (see Fig. 9c, 928) [0147]. Retrieval component may use one or more techniques to retrieve, from the information database(s) 112, contextual information that is associated with the text data (see Fig. 1, 112 information database, which may store information associated with the vehicle and Fig. 1, 116 contextual data) [0047-0048].)
telematics data from the at least one telematics database (Xu - the vehicle may further include the infotainment SoC which may include a combination of hardware and software that may be used to provide audio, video, phone, network connectivity, and/or information services (e.g. navigation systems, vehicle related information such as fuel level, brake fuel level, oil level, i.e. telematics) to the vehicle, and may include a telematics device [0176]. The vehicle may further include data stores (see Fig. 9c, 928) [0147]. Retrieval component may use one or more techniques to retrieve, from the information database(s) 112, contextual information that is associated with the text data (see Fig. 1, 112 information database, which may store information associated with the vehicle and Fig. 1, 116 contextual data) [0047-0048].)
and return at least the portion of the telematics data to the user, (Xu – the output data may represent information associated with the question. The vehicle may then provide the information to the passenger [0071].)
telematics data stored on the at least one telematics database (Xu - the vehicle may further include the infotainment SoC which may include a combination of hardware and software that may be used to provide audio, video, phone, network connectivity, and/or information services (e.g. navigation systems, vehicle related information such as fuel level, brake fuel level, oil level, i.e. telematics) to the vehicle, and may include a telematics device [0176]. The vehicle may further include data stores (see Fig. 9c, 928) [0147]. Retrieval component may use one or more techniques to retrieve, from the information database(s) 112, contextual information that is associated with the text data (see Fig. 1, 112 information database, which may store information associated with the vehicle and Fig. 1, 116 contextual data) [0047-0048].)
Xu does not appear to teach:
identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one [telematics] database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request
and inputting the portion of contextual information into the LLM
execute the executable query for retrieving the portion of the [telematics] data from the at least one [telematics] database
whereby the natural language request is responded to without providing the LLM with access to the [telematics] data stored on the at least one [telematics] database and the at least one context database
However, Tan teaches:
identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one [telematics] database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request (Tan – in Fig. 3, 300, the system receives a natural language query from a client device of the user [0054]. In Fig. 3, 310 contextual information associated with the natural language query is determined, which includes information based on information obtained in one or more previous interactions of the user with the online system [0056-0058]. The data store 240 stores data used by the online system, including user data, item data, order data and trained machine learning models, and may use databases to organize the stored data [0051]. Training data is stored in the data store 240 [0052], and includes natural language questions concatenated with contextual data describing users further concatenated with lists of items, item types, or categories of items associated with the natural language question [0044].)
and inputting the portion of contextual information into the LLM (Tan – at Fig. 3, 320, the system generates a prompt for input to a machine learning based language model based on the natural language query and the contextual information, and at Fig. 3, 330, the prompt to the system provides the prompt to the machine learning based language model for execution [0061]. The response may be a parse-able string of text that the system may further analyze to identify individual attributes or may include a set of attributes including specific details of the types of items that the user may be interested in [0061]. At Fig. 3, 350, the system further generates a search query based on the set of attributes [0063].)
execute the executable query for retrieving the portion of the [telematics] data from the at least one [telematics] database (Tan – at Fig. 3, 350, the system further generates a search query based on the set of attributes. The search query may be a query for searching for items in a database. By searching through a database, the system is able to identify specific items. At Fig. 3, 360, the systems sends the search query for execution. For example, the search query may be executed using the database or the search engine [0063].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of Xu and Tan before them, to modify the system of Xu of at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database, and at least one processor in communication with the at least one data storage, the at least one processor operable to: receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database, generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM, one or more features of the at least one telematics database with the teachings of Tan of identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one [telematics] database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request, and inputting the portion of contextual information into the LLM, execute the executable query for retrieving the portion of the [telematics] data from the at least one [telematics] database. One would have been motivated to make such a modification to respond to search queries with more relevant responses and provide a good user experience (Tan - [0003]).
Xu modified by Tan does not appear to teach:
whereby the natural language request is responded to without providing the LLM with access to the [telematics] data stored on the at least one [telematics] database and the at least one context database
However, Nia teaches:
whereby the natural language request is responded to without providing the LLM with access to the [telematics] data stored on the at least one [telematics] database and the at least one context database (Nia – the hierarchical vector store may be protected by fine-grained access control rules, and may include multiple individual stores. Each vector store may have different access control rules for accessing the embeddings therein. A user may access data in a particular vector store if the user’s access privileges meet the access control rules for that vector store [0016]. The machine learning model may access the hierarchical vector store to generate responses to prompts received from users. The machine learning model may be an LLM. The retrieval is based on the prompt and is subject to any relevant access control rules that should be applied to the user [0034]. The machine learning model may generate responses to prompts from users using context retrieved from the hierarchical vector store [0032].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of Xu, Tan and Nia before them, to modify the system of Xu and Tan of at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database, and at least one processor in communication with the at least one data storage, the at least one processor operable to: receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database, generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM, identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one telematics database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request, and inputting the portion of contextual information into the LLM, execute the executable query for retrieving the portion of the telematics data from the at least one telematics database with the teachings of Nia of whereby the natural language request is responded to without providing the LLM with access to the [telematics] data stored on the at least one [telematics] database and the at least one context database. One would have been motivated to make such a modification to share knowledge while protecting private, proprietary and sensitive data (Nia - [0006]).
Claims 10 and 19 correspond to claim 1 and are rejected accordingly.
Regarding claim 2, Xu modified by Tan does not appear to teach:
wherein the context database is a vector database and the contextual information stored therein is represented by a plurality of vectors
However, Nia teaches:
wherein the context database is a vector database and the contextual information stored therein is represented by a plurality of vectors (Nia – the hierarchical vector store may be protected by fine-grained access control rules, and may include multiple individual stores. Each vector store may have different access control rules for accessing the embeddings therein. A user may access data in a particular vector store if the user’s access privileges meet the access control rules for that vector store [0016]. The machine learning model may access the hierarchical vector store to generate responses to prompts received from users. The machine learning model may be an LLM. The retrieval is based on the prompt and is subject to any relevant access control rules that should be applied to the user [0034]. The machine learning model may generate responses to prompts from users using context retrieved from the hierarchical vector store [0032].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of Xu, Tan and Nia before them, to modify the system of Xu, Tan and Nia of at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database, and at least one processor in communication with the at least one data storage, the at least one processor operable to: receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database, generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM, identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one telematics database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request, and inputting the portion of contextual information into the LLM, execute the executable query for retrieving the portion of the telematics data from the at least one telematics database, whereby the natural language request is responded to without providing the LLM with access to the telematics data stored on the at least one telematics database and the at least one context database with the teachings of Nia of wherein the context database is a vector database and the contextual information stored therein is represented by a plurality of vectors. One would have been motivated to make such a modification to share knowledge while protecting private, proprietary and sensitive data (Nia - [0006]).
Claim 11 corresponds to claim 2 and are rejected accordingly.
Regarding claim 3, Xu modified by Tan does not appear to teach:
wherein the at least one processor is operable to identify the portion of contextual information useful for generating the executable query from the at least one context database based on the parsing of the natural language request by: generating a vector representation of the parsing of the natural language request by the LLM; identifying one or more vectors of the plurality of vectors of the vector database that are similar to the vector representation of the parsing of the natural language request by the LLM; and selecting the contextual information represented by the one or more vectors that are similar to the vector representation for input into the LLM
However, Nia teaches:
wherein the at least one processor is operable to identify the portion of contextual information useful for generating the executable query from the at least one context database based on the parsing of the natural language request by: generating a vector representation of the parsing of the natural language request by the LLM; identifying one or more vectors of the plurality of vectors of the vector database that are similar to the vector representation of the parsing of the natural language request by the LLM; and selecting the contextual information represented by the one or more vectors that are similar to the vector representation for input into the LLM (Nia – in Fig. 2, 203, the machine learning model receives a prompt which may be a natural language prompt. In Fig. 2, 206, the machine learning model queries the hierarchical data store for information related to the prompt. As one example, the machine learning model may encode the prompt into a query vector in a same vector space as the embeddings stored in the hierarchical vector store (i.e. context database). In Fig. 2, 209, the machine learning model generates a response to the prompt [0050-0052].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of Xu, Tan and Nia before them, to modify the system of Xu, Tan and Nia of at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database, and at least one processor in communication with the at least one data storage, the at least one processor operable to: receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database, generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM, identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one telematics database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request, and inputting the portion of contextual information into the LLM, execute the executable query for retrieving the portion of the telematics data from the at least one telematics database, whereby the natural language request is responded to without providing the LLM with access to the telematics data stored on the at least one telematics database and the at least one context database, wherein the context database is a vector database and the contextual information stored therein is represented by a plurality of vectors with the teachings of Nia of wherein the at least one processor is operable to identify the portion of contextual information useful for generating the executable query from the at least one context database based on the parsing of the natural language request by: generating a vector representation of the parsing of the natural language request by the LLM; identifying one or more vectors of the plurality of vectors of the vector database that are similar to the vector representation of the parsing of the natural language request by the LLM; and selecting the contextual information represented by the one or more vectors that are similar to the vector representation for input into the LLM. One would have been motivated to make such a modification to share knowledge while protecting private, proprietary and sensitive data (Nia - [0006]).
Claim 12 corresponds to claim 3 and are rejected accordingly.
Regarding claim 5, Xu does not appear to teach:
wherein the at least one data storage is further operable to store at least one chat database, the at least one chat database storing each natural language request received from the user
However, Tan teaches:
wherein the at least one data storage is further operable to store at least one chat database, the at least one chat database storing each natural language request received from the user (Tan – in Fig. 3, 300, the system receives a natural language query from a client device of the user [0054]. In Fig. 3, 310 contextual information associated with the natural language query is determined, which includes information based on information obtained in one or more previous interactions of the user with the online system [0056-0058]. The data store 240 stores data used by the online system, including user data, item data, order data and trained machine learning models, and may use databases to organize the stored data [0051]. Training data is stored in the data store 240 [0052], and includes natural language questions (i.e. chat database) concatenated with contextual data describing users further concatenated with lists of items, item types, or categories of items associated with the natural language question [0044].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of Xu, Tan and Nia before them, to modify the system of Xu, Tan and Nia of at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database, and at least one processor in communication with the at least one data storage, the at least one processor operable to: receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database, generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM, identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one telematics database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request, and inputting the portion of contextual information into the LLM, execute the executable query for retrieving the portion of the telematics data from the at least one telematics database, whereby the natural language request is responded to without providing the LLM with access to the telematics data stored on the at least one telematics database and the at least one context database with the teachings of Tan of wherein the at least one data storage is further operable to store at least one chat database, the at least one chat database storing each natural language request received from the user. One would have been motivated to make such a modification to respond to search queries with more relevant responses and provide a good user experience (Tan - [0003]).
Claim 14 corresponds to claim 5 and are rejected accordingly.
Regarding claim 6, Xu does not appear to teach:
wherein the at least one processor is further operable to identify additional contextual information based on one or more previous natural language requests received from the user
However, Tan teaches:
wherein the at least one processor is further operable to identify additional contextual information based on one or more previous natural language requests received from the user (Tan - in Fig. 3, 310 contextual information associated with the natural language query is determined, which includes information based on information obtained in one or more previous interactions of the user with the online system [0056-0058]. The data store 240 stores data used by the online system, including user data, item data, order data and trained machine learning models, and may use databases to organize the stored data [0051]. Training data is stored in the data store 240 [0052], and includes natural language questions concatenated with contextual data describing users further concatenated with lists of items, item types, or categories of items associated with the natural language question [0044].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of Xu, Tan and Nia before them, to modify the system of Xu, Tan and Nia of at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database, and at least one processor in communication with the at least one data storage, the at least one processor operable to: receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database, generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM, identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one telematics database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request, and inputting the portion of contextual information into the LLM, execute the executable query for retrieving the portion of the telematics data from the at least one telematics database, whereby the natural language request is responded to without providing the LLM with access to the telematics data stored on the at least one telematics database and the at least one context database, wherein the at least one data storage is further operable to store at least one chat database, the at least one chat database storing each natural language request received from the user with the teachings of Tan of wherein the at least one processor is further operable to identify additional contextual information based on one or more previous natural language requests received from the user. One would have been motivated to make such a modification to respond to search queries with more relevant responses and provide a good user experience (Tan - [0003]).
Claim 15 corresponds to claim 6 and are rejected accordingly.
Regarding claim 7, Xu does not appear to teach:
wherein the at least one processor is further operable to modify the executable query based on database identifying information, a type of the portion of the telematics data that is responsive to the natural language request, an identity of the user, or a combination thereof
However, Tan teaches:
wherein the at least one processor is further operable to modify the executable query based on database identifying information, a type of the portion of the telematics data that is responsive to the natural language request, an identity of the user, or a combination thereof (Tan – the system determines contextual information associated with the natural language query. The system may determine contextual information that allows the system to identify specific details of the items that the user should purchase. The system may determine contextual information including user profile information of the user (i.e. identity of the user) of the client device [0056].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of Xu, Tan and Nia before them, to modify the system of Xu, Tan and Nia of at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database, and at least one processor in communication with the at least one data storage, the at least one processor operable to: receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database, generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM, identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one telematics database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request, and inputting the portion of contextual information into the LLM, execute the executable query for retrieving the portion of the telematics data from the at least one telematics database, whereby the natural language request is responded to without providing the LLM with access to the telematics data stored on the at least one telematics database and the at least one context database with the teachings of Tan of wherein the at least one processor is further operable to modify the executable query based on database identifying information, a type of the portion of the telematics data that is responsive to the natural language request, an identity of the user, or a combination thereof. One would have been motivated to make such a modification to respond to search queries with more relevant responses and provide a good user experience (Tan - [0003]).
Claim 16 corresponds to claim 7 and are rejected accordingly.
Regarding claim 8, Xu does not appear to teach:
wherein the at least one processor is further operable to revert modifying of the executable query after the execution thereof
However, Tan teaches:
wherein the at least one processor is further operable to revert modifying of the executable query after the execution thereof (Tan – the user data also may include default settings established by the user, such as a default retailer/retailer location, delivery location, or delivery timeframe (i.e. to revert) [0035].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of Xu, Tan and Nia before them, to modify the system of Xu, Tan and Nia of at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database, and at least one processor in communication with the at least one data storage, the at least one processor operable to: receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database, generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM, identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one telematics database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request, and inputting the portion of contextual information into the LLM, execute the executable query for retrieving the portion of the telematics data from the at least one telematics database, whereby the natural language request is responded to without providing the LLM with access to the telematics data stored on the at least one telematics database and the at least one context database, wherein the at least one processor is further operable to modify the executable query based on database identifying information, a type of the portion of the telematics data that is responsive to the natural language request, an identity of the user, or a combination thereof with the teachings of Tan of wherein the at least one processor is further operable to revert modifying of the executable query after the execution thereof. One would have been motivated to make such a modification to respond to search queries with more relevant responses and provide a good user experience (Tan - [0003]).
Claim 17 corresponds to claim 8 and are rejected accordingly.
Regarding claim 9, Xu does not appear to teach:
wherein the at least one processor is further operable to send the natural language request and the executable query that is responsive thereto to the at least one data storage for storage in the context database
However, Tan teaches:
wherein the at least one processor is further operable to send the natural language request and the executable query that is responsive thereto to the at least one data storage for storage in the context database (Tan – in Fig. 3, 300, the system receives a natural language query from a client device of the user [0054]. In Fig. 3, 310 contextual information associated with the natural language query is determined, which includes information based on information obtained in one or more previous interactions of the user with the online system [0056-0058]. The data store 240 stores data used by the online system, including user data, item data, order data and trained machine learning models, and may use databases to organize the stored data [0051]. Training data is stored in the data store 240 [0052], and includes natural language questions (i.e. chat database) concatenated with contextual data describing users further concatenated with lists of items, item types, or categories of items associated with the natural language question [0044].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of Xu, Tan and Nia before them, to modify the system of Xu, Tan and Nia of at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database, and at least one processor in communication with the at least one data storage, the at least one processor operable to: receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database, generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM, identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one telematics database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request, and inputting the portion of contextual information into the LLM, execute the executable query for retrieving the portion of the telematics data from the at least one telematics database, whereby the natural language request is responded to without providing the LLM with access to the telematics data stored on the at least one telematics database and the at least one context database with the teachings of Tan of wherein the at least one processor is further operable to send the natural language request and the executable query that is responsive thereto to the at least one data storage for storage in the context database. One would have been motivated to make such a modification to respond to search queries with more relevant responses and provide a good user experience (Tan - [0003]).
Claim 18 corresponds to claim 9 and are rejected accordingly.
Claims 4 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Xu in view of Tan further in view of Nia further in view of Madnani (Pub. No. US 2025/0045314 A1, hereinafter “Madnani”).
Regarding claim 4, Xu modified by Tan and Nia does not appear to teach:
wherein the at least one processor is operable to identify the one or more vectors that are similar to the vector representation based on the real distance between the vector representation and each of the plurality of vectors of the vector database, based on an angle between the vector representation and the plurality of vectors of the vector database, or a combination thereof
However, Madnani teaches:
wherein the at least one processor is operable to identify the one or more vectors that are similar to the vector representation based on the real distance between the vector representation and each of the plurality of vectors of the vector database, based on an angle between the vector representation and the plurality of vectors of the vector database, or a combination thereof (Madnani – based on the context, the embeddings store (i.e. vector database) finds similar embeddings. The embeddings store may then sort the similar embeddings by relevance. The embeddings store may then create a contextual prompt from the closest embedding. Here, the closest embeddings is the embedding with the shortest distance for similar queries [0029].)
Accordingly, it would have been obvious to a person of ordinary skill in the art at the time the invention was effectively filed, having the teachings of Xu, Tan, Nia and Madnani before them, to modify the system of Xu, Tan and Nia of at least one data storage operable to store at least one telematics database, the at least one telematics database storing telematics data originating from a plurality telematics devices installed in a plurality of vehicles, and at least one context database, the at least one context database storing contextual information relating to the at least one telematics database, and at least one processor in communication with the at least one data storage, the at least one processor operable to: receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within the at least one telematics database, generate, using an isolated large language model (LLM) that does not have access to the at least one telematics database, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the at least one telematics database by: inputting the natural language request into the LLM, identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information useful for generating the executable query from the at least one context database, the portion of the contextual information comprising one or more features of the at least one telematics database and one or more example natural language requests and corresponding executable query outputs that are relevant to the natural language request, and inputting the portion of contextual information into the LLM, execute the executable query for retrieving the portion of the telematics data from the at least one telematics database, whereby the natural language request is responded to without providing the LLM with access to the telematics data stored on the at least one telematics database and the at least one context database with the teachings of Madnani of wherein the at least one processor is operable to identify the one or more vectors that are similar to the vector representation based on the real distance between the vector representation and each of the plurality of vectors of the vector database, based on an angle between the vector representation and the plurality of vectors of the vector database, or a combination thereof. One would have been motivated to make such a modification to understand the context and intent behind a user’s query (Tan - [0003]).
Claim 13 corresponds to claim 4 and are rejected accordingly.
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 RANJIT P DORAISWAMY whose telephone number is (571)270-5759. The examiner can normally be reached Monday-Friday 9:00 AM - 5:00 PM.
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, Sanjiv Shah can be reached at (571) 272-4098. 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.
/RANJIT P DORAISWAMY/Examiner, Art Unit 2166
/SANJIV SHAH/Supervisory Patent Examiner, Art Unit 2166
Prosecution Insights