Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
2. Claims 1-5, 7-17 and 19-21 are pending. claims 1, 5, 9, 19 and 20 are currently amended, claims 6 and 18 are cancelled without prejudice or disclaimer; and claims 14 and 21 remain as previously presented.
3. This office action is in response to the RCE filed 08/05/2026.
4. Claims 1, 19 and 20 are independent claims.
5. The office action is made Non-Final.
Continued Examination under 37 CFR 1.114
6. A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 08/05/2026 has been entered.
Claim Rejections – 35 USC § 101
7. 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.
8. Claims 1-5, 7-17 and 19-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: This part of the eligibility analysis evaluates whether the claim falls within any statutory category. See MPEP 2106.03.
Claim 1 recites the steps or acts…, and thus is a process (a series of steps or acts). A process is a statutory category of invention. (Step 1: YES).
Claim 19 recites a system comprising: at least one processor; and at least one non-transitory computer-readable storage medium. The claim is directed to a physical circuit, which is a machine and/or manufacture, and falls within one of the statutory categories of invention. (Step 1: YES).
Claim 20 recites a non-transitory computer-readable medium having stored thereon program instruction that, when executed by at least one processor, cause a computer system to perform a series of steps. A non-transitory computer-readable medium falls within the “manufacture” category of invention. (Step 1: YES).
Step 2A, Prong One: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
Claims 1, 19 and 20 recite in part the steps: “generating a system prompt that defines instructions on a manner of structuring a structured data source query for the data source in accordance with searchable categories of the data source and instructions to generate an application programming interface (API) call as part of the structured data source query to call an API of the data source; causing a generating of the structured data source query, translating the natural language into the structured data source query based on the searchable categories associated with the surveillance records stored in the data source; calling an API of the data source; performing a search of the data source in accordance with the particular structured data source query to identify at least one query result”.
Defining human-like behavioral rules or instructions for an AI model (a system prompt) is typically classified as an ineligible abstract idea (specifically a mental process or a method of organizing human activity/rules) under 35 U.S.C. § 101.
Instructions telling an AI how to converse, roleplay, or parse data can often be performed conceptually via pen and paper or in the human.
Simply stating that an abstract set of rules is applied "by an AI" or "on a generic computer" fails to add the required technical inventive concept. generally, apply the above abstracts idea without placing any limitation on how the large language model operates to derive the response. Therefore, the limitation represents no more than mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception. In addition, the claim confines the use of the recited judicial exception to the technological environment of a “large language model” by generally linking the use of the judicial exception to the recited “large language model”.
Therefore, those steps fall within the mental process groupings of abstract ideas because they cover concepts performed in the human mind. See MPEP 2106.04(a)(2), subsection III.
Claims 1, 8 and 15 appear to recite an abstract idea because they cover concepts performed in the human mind as a form of collecting, organizing, or manipulating data. (Step 2A, Prong One: YES).
Step 2A, Prong Two: This part of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception into a practical application of the exception or whether the claim is “directed to” the judicial exception. This evaluation is performed by (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (2) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application. See MPEP 2106.04(d).
The claims 1, 19 and 20 recite the additional elements of “obtaining an input query, the input query comprising the natural language, including a string of characters received as user input”, “transmitting the input query with the system prompt to a large language model (LLM)”, “receiving, from the LLM, a particular structured data source query based on the input query and the instruction set”, “transmitting the particular structured data source query to the data source” and “receiving the at least one query results”.
Identified as insignificant extra-solution activity.
Also, the recitation of “transmitting the input query with the system prompt to a large language model (LLM)”, “receiving, from the LLM, a particular structured data source query based on the input query and the instruction set”” also merely indicates a field of use or technological environment in which the judicial exception is performed. Although the additional element “large language model (LLM)” limits the identified judicial exceptions, this type of limitation merely confines the use of the abstract idea to a particular technological environment (large language model (LLM)) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Here, the claim recites no details about a particular “transmitting … to a large language model (LLM) and obtaining from the LLM”. The “receiving, from the LLM” is used to generally apply the abstract idea (i.e., translating the natural language into a structured data source query based on searchable categories associated with the surveillance records stored in the data source) without placing any limitation on how the large language model operates to derive the response. In addition, the claim omits any details as to how the large language model solves a technical problem and instead recites only the idea of a solution or outcome. See MPEP 2106.05(f). Therefore, the limitation represents no more than mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception. In addition, the claim confines the use of the recited judicial exception to the technological environment of a “large language model” by generally linking the use of the judicial exception to the recited “large language model”. Therefore, this general “large language model” recitation does not integrate the viewed as nothing more than an attempt to generally link the use of the judicial exception to a particular field of use or a technological environment.
Further Claim 19 recites the additional elements of “a processor; and memory” and claim 20 recites the additional elements of “a non-transitory computer-readable medium and a processing unit”. Those elements are recited at a high level of generality, such that it amounts to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f).
Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application (Step 2A, Prong Two: NO), and the claims are directed to the judicial exception. (Step 2A: YES).
Step 2B: This part of the eligibility analysis evaluates whether the claim as a whole amount to significantly more than the recited exception i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim. See MPEP 2106.05.
As explained with respect to Step 2A, Prong Two, the additional elements of claim 19 “a processor; and memory” and claim 20 “a non-transitory computer-readable medium and a processing unit”. was found to be mere instructions to apply the exception using a generic computer, and the additional elements of “obtaining an input query, the input query comprising the natural language; obtaining, from the LLM, a particular structured data source query based on the input query and the instruction set; transmitting the particular structured data source query to the data source to perform a search of the data source in accordance with the particular structured data source query to identify at least one query result; and receiving the at least one query results” were found to be insignificant extra-solution activity in Step 2A, Prong Two.
However, a conclusion that an additional element is insignificant extra-solution activity in Step 2A, Prong Two should be re-evaluated in Step 2B. See MPEP 2106.05, subsection I.A. At Step 2B, the evaluation of the insignificant extra-solution activity consideration takes into account whether or not the extra-solution activity is well understood, routine, and conventional in the field. See MPEP 2106.05(g).
Here, the step of obtaining an input query, the input query comprising the natural language; obtaining, from the LLM, a particular structured data source query based on the input query and the instruction set; transmitting the particular structured data source query to the data source to perform a search of the data source in accordance with the particular structured data source query to identify at least one query result; and receiving the at least one query results “.
Identified as insignificant extra-solution activity, when re-evaluated this element is well-understood, routine, and conventional as evidenced by the court cases in MPEP 2106.05(d)(II))" ( Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); … OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) , sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network).”
Even when considered in combination, these additional elements represent insignificant extra-solution activity, which do not provide an inventive concept. (Step 2B: NO). The claim is not eligible.
The dependent claims merely incorporate additional elements that narrow the abstract idea without yielding an improvement to any technical field, the computer itself, or limitations beyond merely linking the idea to a particular technological environment.
Claims 2, (causing a display, via the user interface, of the at least one query result), was found to be insignificant extra-solution activity (post-solution activity of outputting/displaying data), Merely requesting, transmitting, receiving, or storing data records has been found to be an abstract idea by the Federal Circuit.
Claim 3 (the searchable categories are metadata categories). Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Claim 4 (wherein the searchable categories form with corresponding metadata characteristics query couplets). Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Claim 5 (wherein the causing a generating of the structured data source query comprises providing the input query to the LLM without prior parsing of the input query) was found to be insignificant extra-solution activity. Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Claim 7 (transmitting the at least one query results to the LLM; and generating and transmitting instructions to the LLM to generate a summary of the at least one query result.) Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Claim 8 (providing a permission level to the LLM, wherein the obtained structured data source query includes information related to the permission level) Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Claim 9 (transmitting the at least one query result to the LLM; generating and transmitting instructions to the LLM for causing the LLM to analyze the at least one query result; receiving the output of the analysis from the LLM; and providing a response to a user computing device having generated the input query, the response corresponding to the received output) Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Claim 10 (causing the LLM to analyze the at least one query results further cause the LLM to compare the at least one query result to the input query or the structured data source query to verify if the at least one query result satisfies the input query or the structured data source query) Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Claim 11 (cause the LLM to interpret the at least one query results to determine if additional search of the data source, or of one or more additional data sources is required) Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Claim 12 (cause the LLM to interpret the at least one query results to determine if a category of information identified in the input query is not searchable) Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Claim 13 (cause the LLM to generate as an output a suggestion of an alternative category of information instead of the category of information identified in the input query that is not searchable) was found to be insignificant extra-solution activity. Mere instructions to implement the abstract recited idea.
Claim 14 (generating and transmitting instructions to the LLM for causing the LLM to analyze the input query to determine if one or more categories of information related to the input query is not searchable; and receiving an output from the LLM regarding if one or categories of information related to the input query is not searchable) was found to be insignificant extra-solution activity. Mere instructions to implement the abstract recited idea.
Claim 15 (cause the LLM to generate one or more alternative data categories to be searched related to one or more not searchable categories of information of the one or more categories of information; and wherein the received output includes the one or more alternative data categories to be searched related to one or more not searchable categories of information of the one or more categories of information) considered an abstract idea by itself under 35 U.S.C. § 101, because they cover concepts performed in the human mind as a form of collecting, organizing, or manipulating data.
Claim 16 (wherein the obtained input query is accompanied by metadata providing context information surrounding the obtained input query) was found to be insignificant extra-solution activity. Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Claim 17 (wherein the input query is provided to the LLM along with the metadata providing context information or information derived from the metadata providing context information) was found to be insignificant extra-solution activity. Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Claim 21 (wherein the instruction set defining a manner of structuring a structured data source query comprises the searchable categories). Mere instructions to implement the abstract recited idea, which is equivalent to adding the words “apply it” to the recited judicial exception.
Examiner Note
9. The Examiner cites particular columns and line numbers in the references as applied to the claims below for the convenience of the Applicant(s). Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the Applicant fully consider the references in their 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.
Claim Rejections - 35 USC § 103
10. 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 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.
11. 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) A patent may not be obtained through the invention is not identically disclosed or described as set forth in section 102 of this title, if the differences between the subject matter sought to be patented and the prior art are such that the subject matter as a whole would have been obvious at the time the invention was made to a person having ordinary skill in the art to which said subject matter pertains. Patentability shall not be negatived by the manner in which the invention was made.
12. Claims 1-3, 5, 7-17 and 19-21 are rejected under 35 U.S.C.103 as being unpatentable over Brendle et al (US 20240394251 A1) hereinafter as Brendle in view of Lewis et al (US 20250258851 A1) hereinafter as Lewis.
13. Regarding claim 1, Brendle teaches A method for causing a searching of a data source records (Abstract, “The query is executed to retrieve the data set, formatted as a structured view for unified access to dispersed data”, [0016], “The system is data-source agnostic, capable of generating executable queries for various data platforms, including SQL databases, NoSQL stores, object stores, and APIs.”, [0059], “a user might input a natural language request, processes and converts into a structured SQL query capable of retrieving the relevant data from data store 103.”, [0156], “the query analysis module 302 assesses the current load on each data source”)
comprising a translation of natural language into language for querying the data source ([0010], “receives a natural language query (also referred to as a natural language question) from a user and translates it into an executable query using a structured approach.”, [0048], “utilizes advanced algorithms to interpret and transform user inputs into actionable database commands”, [0059], “formulating queries by translating user inputs into the appropriate query language. In one embodiment, a user might input a natural language request, such as “show all transactions from the last quarter,” which the query wise stateless structure engine 110, along with other components and systems, processes and converts into a structured SQL query capable of retrieving the relevant data from data store 103.”, [0069], “translate user queries into a form that can navigate these disparate formats and structures to retrieve the desired data efficiently.”, [0075], “query generation system 120 translates the structured expressions into actual database operations that execute efficiently across various data stores.”, [0079], “query generation system 120 employs trained models, including large language models (LLMs), to process and convert structured expressions into executable code…an LLM might take a structured expression and generate an optimized SQL query that minimizes execution time by leveraging database indexes and optimizing join operations”), comprising:
obtaining an input query, the input query comprising the natural language, including a string of characters received as user input ([0010], [0059], Fig 4, step 404, [0204], At step 404, a natural language question (the natural language, including a string of characters received as user input) is obtained from a user for a data set “, see also [0115], “a natural language question like “How much revenue did we generate last quarter? (the natural language, including a string of characters received as user input)””);
generating a system prompt that defines instructions on a manner of structuring a structured data source query for the data source (Fig 2, “a prompt engine 204”, [0104], “forwarding a user-generated query to the prompt engine 204 for processing.”, [0107], “prompt engine 204 generates structured prompts tailored to specific user needs and contexts, enhancing the natural language processing of the system. More specifically, it creates prompts that include various elements designed to specify and guide the query generation process effectively.”, [0109-0111], “prompt engine 204 might generate a prompt for a database administrator that includes SQL command structures tailored to optimize database performance.”, [0110], “the prompt engine 204 might initially generate a basic prompt for querying quarterly sales data.”, [0112], “The prompt engine 204 would then generate a prompt that outlines the necessary SQL query structure, dynamically incorporates the specific financial metrics requested by the user”,) in accordance with searchable categories of the data source ([0116], “the system employs natural language processing algorithms to contextually analyze verbs within the query to categorize the user's intent.”, [0129], “when a user's abstracted query such as “analyze sales trends over the last year” is processed, data recipe engine 220 selects a recipe that configures the query to aggregate sales data by month and product category.”, [0159], “To optimize this, the module suggests breaking down the query into smaller, indexed queries based on product categories, which are then executed in parallel, reducing the overall load and response time.”, [0172], “It proactively caches data related to these categories, ensuring that user queries related to popular items are served quickly and efficiently, thereby enhancing user experience and system responsiveness.”) and instructions to generate an application programming interface (API) call as part of the structured data source query to call an API of the data source ([0052], The API layer also can be responsible for reading and writing database configuration data to/from the administration data store, in response to the API calls. “, [0100], “entity relationship ingestion system 202 utilizes a client library to facilitate communication with the APIs. This library includes predefined functions and procedures that abstract the complexity of direct API calls, providing a simplified interface for data model updates and retrieval.”, [0192], [0239], “the final standardized expression language might be a well-formed SQL query or an API call that retrieves and processes the required data.”);
causing a generating of the structured data source query by transmitting providing the input query with the system prompt to a large language model (LLM), for translating the natural language into the structured data source query based on the searchable categories associated with the records stored in the data source ([0021], “By generating targeted queries based on real-time user inputs (the input query) and predefined prompts (an instruction set), the system ensures that the queries-reflecting accurate and necessary data retrieval”, [0048], “utilizes advanced algorithms to interpret and transform user inputs into actionable database commands, employing a stateless structure engine and a query generation system (e.g., a large language model (LLM) or other appropriate system) to dynamically generate database queries.”, [0059], “a user might input a natural language request, such as “show all transactions from the last quarter,” which the query wise stateless structure engine 110, along with other components and systems, processes and converts into a structured SQL query capable of retrieving the relevant data from data store 103.”, [0079], “query generation system 120 employs trained models, including large language models (LLMs), to process and convert structured expressions into executable code…an LLM might take a structured expression and generate an optimized SQL query that minimizes execution time by leveraging database indexes and optimizing join operations”, [0107-0113], “Generally, prompt engine 204 generates structured prompts (an instruction set) tailored to specific user needs and contexts, enhancing the natural language processing of the system. More specifically, it creates prompts (an instruction set) that include various elements designed to specify and guide the query generation process effectively.”, see also [0159], “To optimize this, the module suggests breaking down the query into smaller, indexed queries based on product categories, which are then executed in parallel, reducing the overall load and response time.”, [0194], “aggregating data by product category, region, and time period to provide a comprehensive view of sales performance.”);
receiving, from the LLM, a particular structured data source query based on the input query and the instruction set ([0021], “By generating targeted queries (a particular structured data source query) based on real-time user inputs (the input query) and predefined prompts (an instruction set), the system ensures that the queries-reflecting accurate and necessary data retrieval”, [0048], “utilizes advanced algorithms to interpret and transform user inputs into actionable database commands, employing a stateless structure engine and a query generation system (e.g., a large language model (LLM) or other appropriate system) to dynamically generate database queries.”, [0059], “converts the input query into a structured SQL query (a particular structured data source query) capable of retrieving the relevant data from data store 103”, [0075], “query generation system 120 translates the structured expressions into actual database operations (a particular structured data source query) that execute efficiently across various data stores.”, [0084], “Query generation system 120 then generates the necessary SQL commands that efficiently query and aggregate inventory data across multiple warehouses.”, see also [0052], [0099], [0100], “the API calls (the instruction set).”) [0107-0113], “Generally, prompt engine 204 generates structured prompts (an instruction set) tailored to specific user needs and contexts, enhancing the natural language processing of the system. More specifically, it creates prompts (an instruction set) that include various elements designed to specify and guide the query generation process effectively.”, see also [0159], “To optimize this, the module suggests breaking down the query into smaller, indexed queries based on product categories, which are then executed in parallel, reducing the overall load and response time.”, [0192], [0194], “aggregating data by product category, region, and time period to provide a comprehensive view of sales performance.”);
calling an API of the data source by transmitting the particular structured data source query to the data source (Fig 4, step 414, [0210], “the executable query is provided to a client-side agent with access to the plurality of data stores. The client-side agent executes the executable query to retrieve the data set, wherein the data set is formatted as a structured view enabling unified access to data dispersed across the plurality of data stores.”);
performing a search of the data source in accordance with the particular structured data source query to identify at least one query result (Fig 4, step 414, [0210], “The client-side agent executes the executable query to retrieve the data set, wherein the data set is formatted as a structured view enabling unified access to data dispersed across the plurality of data stores.”); and
receiving the at least one query results (Fig 4, step 416, [0211], “At step 416, the structured view of the data set is provided to the user”).
Brendle didn’t specifically teaches a data source of surveillance records.
However, Lewis explicitly teaches A method for causing a searching of a data source of surveillance records (Abstract, “systems and methods for retrieving telematics data (surveillance records).”).
Telematics data can be considered a form of surveillance data because it collects detailed information like location, driving patterns, speed, and braking, which can be used to monitor and analyze individual behavior. In line with Applicant Pre-Grant Pub [0007], [0092], [0108]:
[0007], "A surveillance repository may contain any suitable number of surveillance records, including video records, audio records, image records, text records, event records, and the like." [0092], "searching a repository of surveillance records, which may include video records, audio records, image records, text records, event records, and the like." [0108], "The data source(s) may also be one or more devices for generating surveillance records, such as a camera that generates images or video, a badge reader that generates badge read events, a microphone that generates audio files, etc."
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to incorporate the concept of searching of a data source of surveillance records suggested in Lewis’s system into Brendle’s and by incorporating Lewis into Brendle because both systems are related to data analysis and retrieval would retrieve telematics data based on a natural language request received from a user ([0002], Lewis).
13. Regarding claim 2, Brendle and Lewis teach the invention as claimed in claim 1 above and further Brendle teaches causing a display, via the user interface, of the at least one query result (Fig 4, step 416, [0211], “At step 416, the structured view of the data set is provided to the user”).
Also, Lewis teaches the limitation at (Fig 4, step 450, [0088], “return at least the portion of the telematics data to the user”, Fig 3, [0087], “The display 158 may display various visual representations of the telematics data.”).
14. Regarding claim 3, Brendle and Lewis teach the invention as claimed in claim 1 above and further Brendle teaches wherein the searchable categories are metadata categories ([0057], “This database stores embeddings of specific data, intricately linked to the entity's operational ecosystem. For example, these embeddings could represent data patterns or metadata that enhance the efficiency and relevance of query results, supporting sophisticated data analysis and decision-making processes”, [0123], “automatic adjustments to data recipes might occur when a new sales category is added to the database, ensuring that queries involving sales data automatically include this new category without manual intervention.”, [0129], “For instance, when a user's abstracted query such as “analyze sales trends over the last year” is processed, data recipe engine 220 selects a recipe that configures the query to aggregate sales data by month and product category. This recipe is selected based on its efficiency in querying large datasets and its compatibility with the database's data model.”, [0203], “The data model may include entities, attributes, and relationships describing the data structure of the plurality of data stores, along with metadata indicating data types, constraints, and relationships between data entities stored across the plurality of data stores.”).
Also, Lewis teaches the limitation at (([0026], “identifying, based on a parsing of the natural language request by the LLM, a portion of the contextual information (searchable/metadata categories) useful for generating the executable query from the at least one context database (the data source), 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”, [0033], “a type of the portion of the telematics data (searchable categories) that is responsive to the natural language request”, [0055], “Telematics data may include a wide variety of different types of information, parameters, attributes, characteristics, features (searchable categories), and the like relating to various aspects of a vehicle (searchable categories)”, [0066], “the telematics data may include, but is not limited to, location data, speed data, acceleration data, fluid level data (e.g., oil, coolant, and washer fluid), energy data (e.g., battery and/or fuel level), engine data, brake data, transmission data, odometer data, vehicle identifying data, error/diagnostic data, tire pressure data, seatbelt data, airbag data, or a combination thereof.”, [0098], “the textual question may be about a certain type of telematics data”, [0103], “For example, if the user requests a specific type of telematics data obtained from their vehicle fleet (i.e., a portion of the total telematics data included in the databases), the executable query may retrieve that type of telematics data from the relevant database.”, [0126], [0136], “the executable query may be modified based on database identifying information, a type of the portion of the telematics data that is responsive to the natural language request”).
15. Regarding claim 5, Brendle and Lewis teach the invention as claimed in claim 1 above and further Lewis teaches wherein the causing a generating of the structured data source query comprises providing the input query to the LLM without prior parsing of the input query ([0056], “such reports may include a significant amount of information and, as a result, may be time-consuming to review and difficult to parse and/or process if a user is inexperienced.” [0058], “such embodiments may reduce the amount of time spent parsing telematics data collected from a vehicle fleet by a user, as only specific, requested telematics data (or analyses thereof) may be returned.”, [0088], “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”, [0121], “the machine learning model (e.g., an LLM) may “parse” the natural language request when input thereinto to identify the meaning, or intent, thereof.”, [0122], “By parsing the natural language request, the machine learning model may determine information required to generate the executable query.”. Examiner interpretation: therefore, the input query is provided to the LLM that parse the natural language request to generate the executable query without prior parsing of the input query).
17. Regarding claim 7, Brendle and Lewis teach the invention as claimed in claim 1 above and further Brendle teaches transmitting the at least one query results to the LLM; and generating and transmitting instructions to the LLM to generate a summary of the at least one query result ([0144], “The query generation system 120 retrieves the relevant sales data (query results), and output engine 214 (comprise LLM) formats this data into a comprehensive report. The report may include tables, graphs, and summary statistics”, [0164]).
Also, Lewis teaches the limitation at (Fig 4, [0067], “Once received, the fleet management system 110 may process the telematics data obtained from the telematics devices 130 to provide various analysis, predictions, reporting, etc.”).
18. Regarding claim 8, Brendle and Lewis teach the invention as claimed in claim 1 above and further Brendle teaches providing a permission level to the LLM, wherein the obtained structured data source query includes information related to the permission level ([0006], [0014-0015], [0022], “Privacy and data security are also prioritized within this system”, [0051], “leveraging multi-factor authentication methods to ensure authorized access to database information”, [0052], “The interface layer can be responsible for Web service front-end features such as authenticating customers based on credentials, authorizing the customer, throttling customer requests to the API servers, validating user input, and marshaling or un-marshaling requests and responses.”, [0137], “query generation system interface 212 can employ large language models (LLMs) or other trained models to process and convert the structured expressions into executable code, such as SQL commands, that directly access the source databases to retrieve the requested data.”, [0192], “the quality assurance module 316 evaluates the resulting SQL or API call. It checks for common errors like incorrect date formats or unauthorized data access attempts”).
Also, Lewis teaches the limitation at ([0102], “it may in some cases be necessary to insert into the executable query after the generation thereof, certain database identifying information so that the executable query, when executed, may access and retrieve the information stored in the databases. Examples of such database identifying information include, database names, user IDs associated with particular databases, etc.”, [0119], [0134], [0148]).
19. Regarding claim 9, Brendle and Lewis teach the invention as claimed in claim 1 above and further Brendle teaches transmitting the at least one query result to the LLM; generating and transmitting instructions to the LLM for causing the LLM to analyze the at least one query result; receiving the output of the analysis from the LLM; and providing a response to a user computing device having generated the input query, the response corresponding to the received output ([0144], “The query generation system 120 retrieves the relevant sales data (query results), and output engine 214 (comprise LLM) formats this data into a comprehensive report. The report may include tables, graphs, and summary statistics”, [0164]).
20. Regarding claim 10, Brendle and Lewis teach the invention as claimed in claim 9 above and further Brendle teaches wherein the instructions for causing the LLM to analyze the at least one query results further cause the LLM to compare the at least one query result to the input query or the structured data source query to verify if the at least one query result satisfies the input query or the structured data source query ([0185], “this engine might automatically compare query results against a repository of known data patterns to identify anomalies or discrepancies that could indicate processing errors or misinterpretation of the user's original query intent.”, [0226], [0230]).
21. Regarding claim 11, Brendle and Lewis teach the invention as claimed in claim 10 above and further Lewis teaches wherein the instructions further cause the LLM to interpret the at least one query results to determine if additional search of the data source, or of one or more additional data sources is required ([0012], “identify additional contextual information based on one or more previous natural language requests received from the user.”, [0096], “the contextual information may include a plurality of example natural language requests and corresponding executable query outputs that may exemplify to a machine learning model how to generate an executable query for accessing the at least one telematics database. Additional types of contextual information that may be stored in the at least one context database will be discussed herein.”, [0141], “by inputting the error message, additional context may be provided to the machine learning model. For example, the machine learning model, may use the error message to adjust or “correct” the executable query based on the textual description of why the telematics data was not retrieved included therein so as to generate a corrected executable query that is capable of retrieving the portion of the telematics data that is responsive to the natural language request from the at least one telematics database.”, [0147], “the executable query (or the corrected executable query, as the case may be) may be returned to the user to provide additional information to the user about how the telematics data was retrieved.”).
22. Regarding claim 12, Brendle and Lewis teach the invention as claimed in claim 10 above and further Lewis teaches wherein the instructions further cause the LLM to interpret the at least one query results to determine if a category of information identified in the input query is not searchable ([0141], “by inputting the error message, additional context may be provided to the machine learning model. For example, the machine learning model, may use the error message to adjust or “correct” the executable query based on the textual description of why the telematics data was not retrieved (not searchable) included therein so as to generate a corrected executable query that is capable of retrieving the portion of the telematics data that is responsive to the natural language request from the at least one telematics database.”).
23. Regarding claim 13, Brendle and Lewis teach the invention as claimed in claim 12 above and further Lewis teaches wherein the instructions further cause the LLM to generate as an output a suggestion of an alternative category of information instead of the category of information identified in the input query that is not searchable ([0141], “by inputting the error message, additional context may be provided to the machine learning model (a suggestion of an alternative category of information). For example, the machine learning model, may use the error message to adjust or “correct” the executable query based on the textual description of why the telematics data was not retrieved (not searchable) included therein so as to generate a corrected executable query that is capable of retrieving the portion of the telematics data that is responsive to the natural language request from the at least one telematics database.”, [0147], “the executable query (or the corrected executable query, as the case may be) may be returned to the user to provide additional information to the user about how the telematics data was retrieved.”).
24. Regarding claim 14, Brendle and Lewis teach the invention as claimed in claim 1 above and further Lewis teaches generating and transmitting instructions to the LLM for causing the LLM to analyze the input query to determine if one or more categories of information related to the input query is not searchable; and receiving an output from the LLM regarding if one or more categories of information related to the input query is not searchable ([0141], “by inputting the error message, additional context may be provided to the machine learning model (a suggestion of an alternative category of information). For example, the machine learning model, may use the error message to adjust or “correct” the executable query based on the textual description of why the telematics data was not retrieved (not searchable) included therein so as to generate a corrected executable query that is capable of retrieving the portion of the telematics data that is responsive to the natural language request from the at least one telematics database.”, [0147], “the executable query (or the corrected executable query, as the case may be) may be returned to the user to provide additional information to the user about how the telematics data was retrieved.”).
25. Regarding claim 15, Brendle and Lewis teach the invention as claimed in claim 14 above and further Lewis teaches wherein the instructions to the LLM for causing the LLM to analyze the input query to determine if one or more categories of information related to the input query is not searchable, are to further cause the LLM to generate one or more alternative data categories to be searched related to one or more not searchable categories of information of the one or more categories of information; and wherein the received output includes the one or more alternative data categories to be searched related to one or more not searchable categories of information of the one or more categories of information ([0141], “by inputting the error message, additional context may be provided to the machine learning model (a suggestion of an alternative category of information). For example, the machine learning model, may use the error message to adjust or “correct” the executable query based on the textual description of why the telematics data was not retrieved (not searchable) included therein so as to generate a corrected executable query that is capable of retrieving the portion of the telematics data that is responsive to the natural language request from the at least one telematics database.”, [0147], “the executable query (or the corrected executable query, as the case may be) may be returned to the user to provide additional information to the user about how the telematics data was retrieved.”).
26. Regarding claim 16, Brendle and Lewis teach the invention as claimed in claim 1 above and further Brendle teaches wherein the obtained input query is accompanied by metadata providing context information surrounding the obtained input query ([0057], “these embeddings could represent data patterns or metadata that enhance the efficiency and relevance of query results, supporting sophisticated data analysis and decision-making processes…predictive analytics and contextual data responses, which are integral to dynamic business environments”, [0107], “prompt engine 204 generates structured prompts tailored to specific user needs and contexts, enhancing the natural language processing of the system”, [0116], “the system employs natural language processing algorithms to contextually analyze verbs within the query to categorize the user's intent…abstraction language interface 213 performs a semantic analysis to ensure the contextual and relational dynamics among the identified query components are correctly interpreted, preserving the intended meaning of the query within its newly standardized format.”, [0146], “ensures that the query results are not only accurate but also actionable within the context of the enterprise's data infrastructure.”, [0203-0204], “The data model may include entities, attributes, and relationships describing the data structure of the plurality of data stores, along with metadata indicating data types, constraints, and relationships between data entities stored across the plurality of data stores.”).
Also, Lewis teaches the limitation at ([0026-0029], [0088], “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…inputting the portion of contextual information into the LLM (430)”).
27. Regarding claim 17, Brendle and Lewis teach the invention as claimed in claim 16 above and further Brendle teaches wherein the input query is provided to the LLM along with the metadata providing context information or information derived from the metadata providing context information ([0057], “these embeddings could represent data patterns or metadata that enhance the efficiency and relevance of query results, supporting sophisticated data analysis and decision-making processes…predictive analytics and contextual data responses, which are integral to dynamic business environments”, [0107], “prompt engine 204 generates structured prompts tailored to specific user needs and contexts, enhancing the natural language processing of the system”, [0116], “the system employs natural language processing algorithms to contextually analyze verbs within the query to categorize the user's intent…abstraction language interface 213 performs a semantic analysis to ensure the contextual and relational dynamics among the identified query components are correctly interpreted, preserving the intended meaning of the query within its newly standardized format.”, [0146], “ensures that the query results are not only accurate but also actionable within the context of the enterprise's data infrastructure.”, [0203-0204], “The data model may include entities, attributes, and relationships describing the data structure of the plurality of data stores, along with metadata indicating data types, constraints, and relationships between data entities stored across the plurality of data stores.”).
Also, Lewis teaches the limitation at ([0026-0029], [0088], “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…inputting the portion of contextual information into the LLM (430)”).
28. Regarding claim 19, this claim recites a system performs the method of claim 1 and is rejected under the same rationale.
29. Regarding claim 20, this claim recites a non-transitory computer-readable medium having stored thereon program instructions performs the method of claim 1 and is rejected under the same rationale.
30. Regarding claim 21, Brendle and Lewis teach the invention as claimed in claim 1 above and further Brendle teaches wherein the instruction set defining a manner of structuring a structured data source query comprises the searchable categories ([0021], “By generating targeted queries based on real-time user inputs (the input query) and predefined prompts (an instruction set), the system ensures that the queries-reflecting accurate and necessary data retrieval”, [0048], “utilizes advanced algorithms to interpret and transform user inputs into actionable database commands, employing a stateless structure engine and a query generation system (e.g., a large language model (LLM) or other appropriate system) to dynamically generate database queries.”, [0059], “a user might input a natural language request, such as “show all transactions from the last quarter,” which the query wise stateless structure engine 110, along with other components and systems, processes and converts into a structured SQL query capable of retrieving the relevant data from data store 103.”, [0079], “query generation system 120 employs trained models, including large language models (LLMs), to process and convert structured expressions into executable code…an LLM might take a structured expression and generate an optimized SQL query that minimizes execution time by leveraging database indexes and optimizing join operations”, [0107-0113], “Generally, prompt engine 204 generates structured prompts (an instruction set) tailored to specific user needs and contexts, enhancing the natural language processing of the system. More specifically, it creates prompts (an instruction set) that include various elements designed to specify and guide the query generation process effectively.”, see also [0159], “To optimize this, the module suggests breaking down the query into smaller, indexed queries based on product categories, which are then executed in parallel, reducing the overall load and response time.”, [0194], “aggregating data by product category, region, and time period to provide a comprehensive view of sales performance.”).
31. Claims 4 is rejected under 35 U.S.C.103 as being unpatentable over Brendle et al (US 20240394251 A1) in view of Lewis et al (US 20250258851 A1) and further in view of Ying-li Tian, hereinafter as Ying.
Ying-li Tian was cited in the IDS received 04/10/2025 (IDS. NPL Row 6)
32. Regarding claim 4, Brendle and Lewis teaches the invention as claimed in claim 3 above, Lewis further implicitly teaches wherein the searchable categories form with corresponding metadata characteristics query ([0066], “The telematics data may include any information, parameters, attributes, characteristics, and/or features associated with the vehicles 120”, [0098], search by metadata tag”).
However, Ying explicitly teaches wherein the searchable categories form with corresponding metadata characteristics query couplets (page 23, compound search (query with key-value pairs)).
In line with Applicant Pre-Grant Pub [0130], “For instance, the one or more searchable categories may be metadata tags or categories, where corresponding values for each of the metadata tags or categories may be related, as couplets, to the metadata tags or categories. For instance, exemplary metadata tags may be {time}, {date}, {location}, {object_type}, etc.”
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to incorporate the concept of teachings suggested in Ying’s system into Brendle and Lewis combined system and by incorporating Ying into Brendle and Lewis combined system because all systems are related to data analysis and retrieval would enable large scale searching of surveillance video (page 3, Ying).
Respond to Amendments and Arguments
33. In the remarks received 08/05/2026, Applicant respectfully submits that, under Step 2A Prong One of the Test for subject matter eligibility, amended claim 1 is not directed to a mental process, and is therefore directed towards patent eligible subject matter.
Examiner presents the following responses to Applicant’s arguments:
Applicant’s arguments (see REM, filed 08/05/2026), with respect to the rejection(s) of claim(s) under 35 USC § 101 have been fully considered and are not persuasive. Referring to the previous Office action, as a means of providing further clarification, Examiner has expanded the analysis for comprehensibility while maintaining the rejection of the claims under 35 USC § 101.
34. In the remarks received 08/05/2026, Applicant has amended the independent claims to further distinguish over Lewis.
In particular, Applicant submits that: Brende does not at least teach:
- generating a system prompt that defines instructions on a manner of structuring a structured data source query for the data source in accordance with searchable categories of the data source and instructions to generate an application programming interface (API) call as part of the structured data source query to call an API of the data source; and - calling an API of the data source by transmitting the particular structured data source query to the data source.
Moreover, Applicant could not locate where in Lewis does Lewis teach those same limitations of claim 1. In fact, nowhere does Lewis’s mention "API" or "application programming interface". Therefore, Applicant respectfully submits that Lewis also does not teach any of these limitations.
Examiner presents the following responses to Applicant’s arguments:
Applicant’s arguments (see REM, filed 08/05/2026), with respect to the rejection(s) of claim(s) under 35 USC § 102 have been fully considered and are persuasive. Referring to the previous Office action, Examiner has cited relevant portions of the references as a means to illustrate the systems as taught by the prior art. As a means of providing further clarification as to what is taught by the references used in the first Office action, Examiner has expanded the teachings for comprehensibility while maintaining the same grounds of rejection of the claims, except as noted above in the section labeled “Status of Claims.” This information is intended to assist in illuminating the teachings of the references while providing evidence that establishes further support for the rejections of the claims.
CONCLUSION
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HICHAM SKHOUN whose telephone number is (571)272-9466. The examiner can normally be reached Normal schedule: Mon-Fri 10am-6:30pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Amy Ng can be reached at 5712701698. 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.
/HICHAM SKHOUN/Primary Examiner, Art Unit 2164
Prosecution Insights