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 .
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Ohja et al. (US Patent 12,511,282 B1)
Regarding Claim 1, discloses
A system comprising:
memory; and one or more processors coupled to the memory (a processor will receive instructions and data from a read only memory or a random access memory or both [col. 33, lines 13-15]) and configured to perform operations (can be performed by one or more programmable processors executing one or more computer programs [col. 33, lines 1-3]) comprising:
receiving (The computer system 110 receives data from and provides data to user devices [col. 4, lines 25-27]) a natural language prompt associated with a user (the user 122 can enter a prompt or natural language statement [col. 4, lines 38-39]);
identifying (the AI/ML model 940 has been trained to identify, from the inputs it receives, likely document content and interactive elements, including relevant portions of data sources, that would be used in different situations [col. 25, lines 20-23]) one or more tables in a database based on the natural language prompt (The resulting code or instructions can thus reference specific data objects (e.g., particular logical data objects such as metrics, attributes, facts, etc., which may correspond to data sets, data tables, columns, rows, fields, etc. included in or derived from an underlying data set) with 50 particularity, which can often show a distinct mapping or correspondence to a discrete portion of a data set [col. 21, lines 46-52]);
determining one or more table schemas of the one or more tables in the database (By using the AI/ML model to produce SQL content, the system obtains clear insight into the interpretation of the AI/ML model of the natural language content of the user's prompt [col. 21, lines 36-39]);
generating, using a large language model, (The system can use a deep learning model, such as a large language model or neural network [col. 4, lines 25-27]) a query to the one or more tables in the database (The user then clicks a button 133 indicating that the system should generate an SQL statement based on the entered text [col.4 lines 43-45]) based on the natural language prompt and the one or more table schemas (The AI/ML model 140 also receives at least a portion of the database schema 116 for the current data source [col. 5, lines 2-4]);
obtaining, using the query, (such as to receive a result set provided in response to a natural language query or SQL query [col. 26 lines 10-12]) data from at least one table of the one or more tables in the database (When making the request to the AI/ML model, the system can provide the chatbot a data model or data schema for the data source(s) from which to retrieve data [col. 21, lines 43-46]);
and generating, using the large language model or another large language model, a response (the chat interface 400 provides the response generated using the model 140, which includes a reference to a generated SQL statement [col. 8, lines 5-7]) to the natural language prompt based on the data obtained from the at least one table of the one or more tables in the database (such as to receive a result set provided in response to a natural language query or SQL query [col. 26 lines 10-12]);
Regarding Claim 2, in addition to the elements stated above regarding claim 1, Ojha further discloses
The system of claim 1, wherein the one or more processors are configured to perform operations (can be performed by one or more programmable processors executing one or more computer programs [col. 33, lines 1-3]) further comprising: generating, one or more statistics about the data from the at least one table of the one or more tables in the database (which creates the results 876, which may be in any of various forms, such as records retrieved, data series, aggregations of data, statistics about data in the data set 822a, subsets of the data set 822a determined to be relevant, and so on [col 19, lines 6-10]);
Regarding Claim 3, in addition to the elements stated above regarding claim 1, Ojha further discloses
The system of claim 1, wherein the one or more processors are configured to perform operations (can be performed by one or more programmable processors executing one or more computer programs [col. 33, lines 1-3]) further comprising: generating, using the large language model or an additional large language model, (The system can use a deep learning model, such as a large language model or neural network [col. 4, lines 25-27]) a description of one or more statistics about the data from the at least one table of the one or more tables in the database (this may be a summary of the results 876 and/or may include values extracted from the results 876 with added text description generated by the AI/ML models 140 [col. 20, lines 22-24], which creates the results 876, which may be in any of various forms, such as records retrieved, data series, aggregations of data, statistics about data in the data set 822a, subsets of the data set 822a determined to be relevant, and so on [col 19, lines 6-10]);
Regarding Claim 4, in addition to the elements stated above regarding claim 1, Ojha further discloses
The system of claim 1, wherein the one or more processors are configured to perform operations further comprising:
generating, using the large language model or an additional large language model, a visualization of one or more statistics about the data from the at least one table of the one or more tables in the database (In response, the AI/ML model 940 can generate a document that has features that the model predicts are most likely to be appropriate given the input set. This can include a dashboard-like interface that includes visualizations of the data in the result dataset [col. 26, lines 31- 35]);
Regarding Claim 5, in addition to the elements stated above regarding claim 1, Ojha further discloses
The system of claim 1, wherein identifying the one or more tables comprises:
identifying a table in the database based on the natural language prompt (the AI/ML model 940 has been trained to identify, from the inputs it receives, likely document content and interactive elements, including relevant portions of data sources, that would be used in different situations [col. 25, lines 20-23]);
receiving user feedback with respect to the table (The chat interface 310 includes a text field 312 in which a user can make requests and ask questions about the current document and the underlying data source that is represented in the visualizations, tables and other data shown [col. 28, lines 45-48]) or the response to the natural language prompt (The computer system 110 can receive from the user device 806c information identifying a particular data set 822a that is active at the user device 806c (e.g., being used or edited, etc.) or that is associated with a portion of a user interface at the user device 806c [col. 13, lines 50-55]);
and based on the user feedback, identifying the one or more tables, (As another example, the user may have recently interacted with or selected particular data elements or content items, and so the user device can indicate the data sets associated with those content items [col. 13, lines 61]) wherein the one or more tables comprise at least one of the table and a different table (With this information, the computer system 110 identifies one or more data sets 822a-822b that are identified as or estimated to be most relevant to the prompt 870 [col. 14, lines 27-31]);
Regarding Claim 6, in addition to the elements stated above regarding claim 1, Ojha further discloses
The system of claim 1, wherein the one or more processors are configured to perform operations further comprising:
determining an amount of at least one of computation resources and computation time used by the system to process the natural language prompt; (In many cases, the amount of data in the data set 822a may be orders of magnitude larger than the maximum context size that the LLM can process [col. 19, lines 32-34]) and
in response to determining that the amount of at least one of the computation resources and the computation time exceeds a threshold, (Due to limits on LLM context sizes, it may be impractical or inefficient for an LLM to analyze the data set 822 a to generate the results 876 [col. 19, lines 37-39]) modifying the natural language prompt prior to identifying the one or more tables in the database (In some implementations, the computer system 110 can send a second request to the AI/ML service provider 830 [col. 19, lines 40-41], As with the request 872, the computer system 110 can provide the user context data 856 and conversation history 857 for the user 805 c in or with the second request, so the AI/ML model 140 can generate a response based on the context of the user's situation and the user's previous conversations [col. 19, lines 57-62] Examiner notes: A person of ordinary skill in the art would have understood that when the amount of data exceeds the context size that the LLM can process, sending a second request with user context and conversation history reduces the amount of information needed for the AI/ML model to generate a response. Thus, the second request constitutes a modified natural language prompt used before identifying the one or more tables);
Regarding Claim 7, in addition to the elements stated above regarding claim 1, Ojha further discloses
The system of claim 1, wherein identifying the one or more tables comprises identifying the one or more tables based on one or more previous natural language prompts (For example, given the user interactions or feedback received through previous prompt-response cycles with the user 805c and/or other users the long-term memory 848 may include information that can clarify what users intend [col. 17, lines 28-32]) and one or more summaries of one or more responses (in whole or in part (e.g., in summary form) and from the current session and/or previous sessions [col. 17, lines 47-48]) determined for the one or more previous natural language prompts, the one or more previous natural language prompts comprising one or more natural language prompts received or processed by the large language model prior to the large language model receiving or processing the natural language prompt (As a result, information about previous prompts from the user 805c and previous responses, in whole or in part (e.g., in summary form) and from the current session and/or previous sessions, can be retrieved and used to supplement the prompt 870 [col. 17, lines 45-49]);
Regarding Claim 8, in addition to the elements stated above regarding claim 1, Ojha further discloses
The system of claim 1, wherein the one or more processors are configured to perform operations further comprising:
determining a respective similarity between the natural language prompt and each previous natural language prompt (the computer system 110 can perform keyword matching to identify portions of a knowledge base 847 that match terms of the prompt 870. As another example, portions of the knowledge bases 847 or other knowledge assets can be selectively retrieved using semantic similarity [col. 16, lines 32-34]) from a plurality of previous natural language prompts received or processed by the large language model prior to the large language model receiving or processing the natural language prompt (the knowledge base 847 can provide additional context for all of the subsequent interactions with the AI/ML model 140 [col. 11, lines 52-54]); and
providing, to a device associated with the user, a previous natural language prompt from the plurality of previous natural language prompts and a previous response to the previous natural language prompt, the previous natural language prompt being selected from the plurality of previous natural language prompts based on the respective similarity (As a result, information about previous prompts from the user 805c and previous responses, in whole or in part (e.g., in summary form) and from the current session and/or previous sessions, can be retrieved and used to supplement the prompt [col. 17, lines 46-49]) between the natural language prompt each previous natural language prompt from the plurality of previous natural language prompts (The request 872 can be generated or adjusted based on information in the long-term memory 848 and/or information related to the user [col. 17, lines 26-28]);
Regarding Claim 9, in addition to the elements stated above regarding claim 1, Ojha further discloses
The system of claim 1, wherein the one or more processors are configured to perform operations further comprising:
identifying the one or more tables in the database (As another example, the computer system 110 can examine the prompt 870 itself to determine which data set(s) 822a-822n are relevant) based on a respective confidence metric of each of the one or more tables in the database (In some implementations, the values of weights of a neural network such as the LLM 200 are updated through training based on the examples 210 [col. 5, lines 50-52]);
Regarding Claim 10, in addition to the elements stated above regarding claim 1, Ojha further discloses
The system of claim 1, wherein the one or more processors are configured to perform operations further comprising:
generating, using the large language model, a plurality of responses to the natural language prompt, (In response, the system uses the model 140 to generate different options that can carry out a type of change as requested by the user [col. 28, lines 54-56]) wherein each response from the plurality of responses is generated based on data obtained from a respective table in the database (For example, three different modified versions of the bar chart are shown with a question posed to the user of which option is preferred [col. 28, lines 56-58]); and
identifying one or more differences between the plurality of responses (The AI/ML models 140 can then be used to specify the parameters for the visualization, such as the type of visualization (e.g., line chart, bar chart, line graph, geographical map, heat map, etc.), and identification of which data items are shown on different axes or dimensions of the visualization, the ranges to show, the labels to use, the color scheme, and or other properties [col. 20, lines 7-13] Examiner notes: A person of ordinary skill in the art would have understood that because the AI/ML model generates a plurality of multiple possibles responses, the responses include information that can be compared to understand the differences between those responses) that are generated from different tables (the attributes or metrics may correspond to different columns of tables of a dataset, or may represent data that can be derived from those columns, such as by applying a function or equation to data in one or more columns of tables of a data set [col. 7, lines 31-35]);
Claim 11 contains similar limitations to claim 1, and therefore is rejected for the same reasons.
Claim 12 contains similar limitations to claim 2, and therefore is rejected for the same reasons.
Claim 13 contains similar limitations to claim 3, and therefore is rejected for the same reasons.
Claim 14 contains similar limitations to claim 4, and therefore is rejected for the same reasons.
Claim 15 contains similar limitations to claim 5, and therefore is rejected for the same reasons.
Claim 16 contains similar limitations to claim 6, and therefore is rejected for the same reasons.
Claim 17 contains similar limitations to claim 7, and therefore is rejected for the same reasons.
Claim 18 contains similar limitations to claim 8, and therefore is rejected for the same reasons.
Claim 19 contains similar limitations to claim 9, and therefore is rejected for the same reasons.
Claim 20 contains similar limitations to claim 1, and therefore is rejected for the same reasons. Additionally, Ohja further discloses:
A non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more processors (Embodiments of the invention can be implemented as one or more computer program products, e.g., one or more modules of computer program instructions encoded on a computer readable medium for execution by, or to control the operation of, data processing apparatus [col. 32, lines 29-34]);
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Kyle Espinas whose telephone number is (571)270-0596. The examiner can normally be reached Monday Friday, 8 a.m. 5 p.m. ET..
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, Andrew Flanders can be reached at (571) 272-7516. 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.
/Kylenino Espinas/
Patent Examiner
Art Unit 2655
7/13/2026
/ANDREW C FLANDERS/Supervisory Patent Examiner, Art Unit 2655
Prosecution Insights