DETAILED ACTION
This office action is in response to the claimed amendment filed on January 22, 2026, in which claim 12 was canceled, claim 22 is added and claims 1-11 and 13-22 are presented for further examination.
Response to Arguments
Applicant’s arguments with respect to claims 1-11 and 13-22 have been considered but are moot in view of a new ground of rejection necessitated by amendment.
Remark
After further reviewed Applicant’s arguments in light of the original specification, it is conceivable that the generative large language model and natural language supposition are integrated into a practical application that render claims 1-11 and 13-22 eligible under 35 USC 101.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-11 and 13-22 are rejected under 35 U.S.C. 103 as being unpatentable over Tan et al., (hereinafter “Tan”) US 20250217351 in view of Enrico et al., (hereinafter “Enrico”) Article entitled “Visual Representation of Natural Language Scene Descriptions” and Agrawal et al., (hereinafter “Agrawal”) US 20180203924.
As to claim 1, Tan discloses a method comprising:
generating, based on text that describes a data table, a lexical prompt (see [0022], generating an MLM prompt that requests the LLM to generate a database query),
accepting, by a large language model (LLM), the lexical prompt as input (see [0020], receive a text prompt as an input prompt); and
generating, by the LLM, natural language that describes the data table (see [0026] and [0029], generate a prompt to have the MLM correct any uncorrectable errors, wherein a prompt element may include one or more of natural language text that describes the at least one error, a location in the database query that contains the error, a suggestion on how to correct the error, or other information and generate an MLM prompt, submit the MLM prompt to the server, receive a response from the server, and provide at least a portion of the response to the query compiler),
wherein the method is performed by one or more computers (see [0087]-[0088], computer system).
Tan fails to disclose to contain a lexical prompt reusable predefined natural language supposition.
However, Enrico discloses that a lexical prompt that contains a reusable predefined natural language supposition (see page 582, col.1, par. [1] and page 586, col.2, par. [1], Note that the term supposition refers to an idea or belief that is assumed to be true without concrete evidence. It often involves making an assumption based on limited information. Using natural language supposition can help convey hypothetical scenarios or conjectures, which allow for exploration of possibilities. Therefore, Agrawal reviews how the disambiguation process is carried out by analyzing the system’s behavior in response to the sentences chair on floor and picture on wall. The Natural Language interface (see Fig. l), by applying a simple pattern matching algorithm to the input sentence, builds and communicates to the Symbolic Module a set of bindings (which, in the case of the sentence chair on floor, are prep/on, sbj/chair, and obj/floor). Hence the Symbolic Module looks up the set of the spatial relation rules for an applicable rule. This is done by checking the preconditions of the rules against the current mental image. So, whenever NALIG does not succeed in positioning the object on the cylinder-shape basis, it switches to considering the effective shape of the object for which we begin considering one possible orientation. Note that, given an orientation and supposing the object is “little”-intersecting, local heuristics are applied to correct the position of the center of mass).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Tan to use a reusable predefined natural language supposition, in order to enhance communication, thereby improving project quality, and streamline the requirements elicitation process.
Moreover, Agrawal discloses the claimed “wherein the text comprises at least one selected from a group consisting of: a name of the data table, a structured query language (SQL) schema of the data table, and names of multiple columns in the data table (see par. [0028]-[0030]).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified the combined system of Tan and Enrico to use a structured query language (SQL) schema of the data table, in order to enhance accessibility and management processes, thereby transferring database objects between schemas.
As to claims 2-3, the combination of Tan, Enrico and Agrawal discloses the invention as claimed. In addition, Tan discloses the claimed generating, by the LLM, a hybrid table schema of the data table that contains the natural language that describes the data table (see [0026] and [0029], generate a prompt to have the MLM correct any uncorrectable errors, wherein a prompt element may include one or more of natural language text that describes the at least one error, a location in the database query that contains the error, a suggestion on how to correct the error, or other information and generate an MLM prompt, submit the MLM prompt to the server, receive a response from the server, and provide at least a portion of the response to the query compiler).
As to claim 4, the combination of Tan, Enrico and Agrawal discloses the invention as claimed. In addition, Agrawal discloses the claimed wherein the data table is a first data table; the lexical prompt contains example natural language that describes a second data table (see [0028]-[0030]).
As to claim 5, the combination of Tan, Enrico and Agrawal discloses the invention as claimed. In addition, Agrawal discloses the claimed selecting the second data table based on names of multiple columns in the first data table (see [0028]-[0030]).
As to claims 6-7, the combination of Tan, Enrico and Agrawal discloses the invention as claimed. In addition, Agrawal discloses the claimed wherein said selecting the second data table comprises comparing the fixed-size encoding to a fixed-size encoding of a table schema of the second data table (see [0028]-[0030]).
As to claims 8-10, the combination of Tan, Enrico and Agrawal discloses the invention as claimed. In addition, Agrawal discloses the claimed wherein said generating the fixed-size encoding is performed by a second LLM (see [0020]-[0022]).
As to claims 11-14, the combination of Tan, Enrico and Agrawal discloses the invention as claimed. In addition, Agrawal discloses the claimed wherein the lexical prompt contains example natural language that describes at least one selected from a group consisting of a third data table and a table schema of the second data table (see [0028]-[0030]).
As to claim 15, the combination of Tan, Enrico and Agrawal discloses the invention as claimed. In addition, Agrawal wherein the data table is one selected from a group consisting of a table in a natural language document, a spreadsheet, and a database table (see [0028], natural language key terms from the query string may be used to identify relevant data tables/spreadsheets. When the query string includes key terms such as “growth,” “monthly,” “sales,” data tables/spreadsheet that have a column or a row recording monthly sales may be identified. As another example, data tables/spreadsheet can also be identified based on previously used data tables for similar query strings, e.g., when a natural language query “what is the monthly distribution of sales” identified a certain data table, the same data table may be identified for the query “how's the growth of monthly total sales” as well).
As to claims 16-22, claims 16-22 are one or more computer-readable non-transitory media storing instructions to execute the method of claims 1-11 and 13-15. They are rejected under the same rationale.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Nelken US 20050187913 (L101) discloses the claimed “lexical prompt that contains a reusable predefined natural language supposition” (see [0033], the language analysis server 210 computes, for each predefined category, a match score based upon concepts associated with the predefined categories, concepts extracted from the query, and metadata. In an exemplary embodiment of the invention, suppose that the customer service interface services a motorcycle parts and equipment distribution house. Additionally, suppose that the knowledge base 215 has the following three predefined categories: a first predefined category entitled "new parts order," a second predefined category entitled "complaints," and a third predefined category entitled "suggestions." A client correspondent submits to the server 205 a query comprising a natural language text that states, for example, "I am unhappy with the head gasket that you shipped me for my 1955 BMW R50/2).
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 JEAN M CORRIELUS whose telephone number is (571)272-4032. The examiner can normally be reached Monday-Friday 6:30a-10p(Midflex).
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, Ann J Lo can be reached at (571)272-9767. 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.
/JEAN M CORRIELUS/Primary Examiner, Art Unit 2159 March 10, 2026