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 .
This Office Action is in response to the submission filed July 26, 2024. Claims 1-24 are pending.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-24 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claims 1, 23, and 24 are directed to methods, systems and computer readable mediums. The claims recite limitations for receiving an input for a large language model (LLM), which can be achieved by a person hearing an input request or using pen and paper writing down a input; selecting one or more functions from a set of functions based on the input can be achieved by the person reading the prompt and determining functions or steps associated to the input; generating a prompt based on the input and the selected one or more functions can be achieved by the person, using pen and paper, writing down the specific task functioning request; and providing the prompt to the LLM and obtaining a response, which can be achieved by the person, using natural language rules and principles and resources generating a response to the task request. The recited limitations are directed a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of the generic LLM (recited at a high level of generality), computer, apparatus, computer readable medium, and generic computer components. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea.
This judicial exception is not integrated into a practical application because the recited generic LLM (recited at a high level of generality), computer, apparatus, computer readable medium, and generic computer components amounts to no more than mere instructions to apply the exception using generic computer components. Accordingly, the elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea. The claims are not patent eligible.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as indicated with respect to integration of the abstract idea into a practical application, the additional elements of the generic LLM (recited at a high level of generality), computer, apparatus, computer readable medium, and generic computer components to perform the various steps amounts to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claims are not patent eligible.
Dependent claims 2-22 do not integrate the judicial exception into a practical application and do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The limitations of the dependent claims are directed to steps of organizing and manipulating function characteristics and selection of functions, organizing functions using well known NLP embedding, clustering and parsing of data or elements, and utilizing mere instructions to apply the exception using generic computer components )generic machine learning or large language models).
Claim 24 rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because the claim fails to be limited to only statutory subject matter. Claim 24 is directed to a computer readable medium, which as disclosed in the specification, (para 0131 of the printed publication) can include both transitory or non-transitory media. Transitory mediums do not fall within one of the statutory categories of invention eligible for patent protection. Accordingly, the claim is directed to non-statutory subject matter and is rejected under 35 UWC 101.
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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(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.
Claims 1-9, 18-19, and 22-24 are rejected under 35 U.S.C. 102(a)(1)/(a)(2) as being anticipated by Baldua et al (US Patent Application Publication No. 2025/0110957), hereinafter Baldua.
Baldua discloses dynamic query planning and execution. Regarding claim 1, Baldua teaches a computer-implemented method [fig 7A/7B] comprising: receiving an input for a large language model (LLM) [(702); para 0047 – user input]; selecting one or more functions from a set of functions based on the input [(712); para 0086-0091; 0093-0103; 0107-0113 – determine possible function component…select function set 406]; generating a prompt based on the input and the selected one or more functions [(712/718); para 0086-0091; 0093-0103; 0104; 0107-0113 – prompt sections]; and providing the prompt to the LLM and obtaining a response [(718); para 0042; 0047; 0107-0113 – output/response generated].
Regarding claim 2, Baldua teaches, the method of claim 1, wherein the one or more functions are selected based on a limit associated with the input [para 0093-0103 – functions associated with intents].
Regarding claim 3, Baldua teaches the method of claim 1, wherein the one or more functions are selected based on a limit associated with the LLM [para 0033 – selection adjustments made based on latency or performance issues].
Regarding claim 4, Baldua teaches the method of claim 3, wherein the limit comprises a token input limit [para 0047 – selections based on size/length of prompt structure].
Regarding claim 5, Baldua teaches the method of claim 1, wherein the one or more functions are selected based on a limit associated with a number of functions [para 0036; 0058 – selection base on reduction in number of calls].
Regarding claim 6, Baldua teaches the method of claim 1, wherein a total number of functions in the set of functions is above an input limit of the LLM [para 0033; 0058 – selections based on performance issues].
Regarding claim 7, Baldua teaches the method of claim 1, wherein the selected one or more functions corresponds to a particular group of a plurality of groups of functions drawn from the set of functions [para 0056; 0093-0103 – logical groupings…index maps multiple functions to same intents].
Regarding claim 8, Baldua teaches the method of claim 7, wherein the plurality of functions are categorized into the plurality of groups using data associated with each function [para 0056; 0093-0103 – function dependency graph].
Regarding claim 9, Baldua teaches the method of claim 8, wherein the data associated with each function comprises a function definition [para 0099 – instructions and metadata].
Regarding claim 18, Baldua teaches the method of claim 1, wherein the input comprises a user query associated with a task to be completed [para 0037-0038 – information retrieval system].
Regarding claim 19, Baldua teaches the method of claim 1, wherein the input comprises contextual data obtained from a chat conversation [para 0038 –chat based information retrieval; 0064 – chat histories].
Regarding claim 22, Baldua teaches the method of claim 1, wherein the response indicates that a recommended one of the selected one or more functions identified from the prompt could not be determined by the LLM, the method further comprising: re-selecting one or more functions from the set of functions; and re-prompting the LLM [para 0063 – recommendations to improve the first query, where one the query is improved the systems continues processing to determine the most correct prompt].
Regarding claims 23 and 24, claims 23 and 24 are directed to systems and computer readable mediums [Baldua at Fig 8; para 0202-0214] and are rejected under similar rationale as claim 1.
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.
Claims 10-12 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Baldua in view of Madnani (US Patent Application Publication No. 0025/0045314).
Regarding claim 10, Baldua fails to teach each of the functions in the set of functions comprises a vector representation generated using a text-to-vector embedding process. In a similar field of endeavor, Madnani teaches converting a user’s query into embeddings [para 0024-0030], and specifically teaches the process provides more accurate and relevant responses, where an embedding database may be used to enrich the raw user text and use similarity metrics to identify relevant context. By using the latest and most contextual information, the generated prompts may provide more accurate and useful responses to a user's query [para 0012]. One having ordinary skill in the art at the time of the invention would have recognized the advantages of implementing the vector embedding techniques suggested by Madnani, in the system of Baldua, for the purpose of generating prompts that provide more accurate and useful responses to a user's query, as suggested by Madnani, and thereby improve the user’s experience.
Regarding claim 11, the combination of Baldua and Madnani teaches the plurality of groups are formed by clustering function embeddings [Baldua’s grouped functions [0093-00103] in combination with Madnani embedding processing para 0024-0030].
Regarding claim 12, the combination of Baldua and Madnani teaches the plurality of groups are clustered using a vector similarity search [Madnani’s similarity processing para 0024-0031; 0042].
Regarding claim 20, Baldua fails to teach wherein each of the functions in the set of functions comprises a vector representation generated using a text-to-vector embedding process, and wherein the input comprises a query, the method further comprising: embedding the query into a vector representation; and performing a vector similarity search using the vector representation of the query and the vector representations of the set of functions. In a similar field of endeavor, Madnani teaches converting a user’s query into embeddings and performing similarity searching [para 0024-0030], and specifically teaches the process provides more accurate and relevant responses, where an embedding database may be used to enrich the raw user text and use similarity metrics to identify relevant context. By using the latest and most contextual information, the generated prompts may provide more accurate and useful responses to a user's query [para 0012]. One having ordinary skill in the art at the time of the invention would have recognized the advantages of implementing the vector embedding and similarity searching techniques suggested by Madnani, in the system of Baldua, for the purpose of generating prompts that provide more accurate and useful responses to a user's query, as suggested by Madnani, and thereby improve the user’s experience.
Claims 13-17 are rejected under 35 U.S.C. 103 as being unpatentable over Baldua in view of Solomon et al (US Patent Application Publication No. 2025/0272504(, hereinafter Solomon.
Regarding claims 13-17, Baldua fails to teach parsing the input to determine information used in selecting the one or more functions. In a similar field of endeavor, Solomon teaches processing text to divide [“parse’] the text into words/segments and categorize the text into classes or categories [0070] for developing prompts for LLM [Abstract; para 0006] and specifically teaches the system enables an LLM to provide richer synthesized responses [para 0009]. One having ordinary skill in the art at the time of the invention would have recognized the advantages of implementing the parsing processing techniques suggested by Solomon, in the system of Baldua, for the purpose of improving the output results generated by the LLM, as suggested by Solomon.
Claim 21 are rejected under 35 U.S.C. 103 as being unpatentable over Baluba in view of Madnani as applied to claim 20 above, and further in view of Solomon.
Regarding claim 21, the combination of Baldua and Madnani fail to teach parsing the query using a separate LLM. In a similar field of endeavor, Solomon teaches processing text to divide [“parse’] the text into words/segments and categorize the text into classes or categories [0070] for developing prompts for LLM [Abstract; para 0006] and specifically teaches the system enables an LLM to provide richer synthesized responses [para 0009]. One having ordinary skill in the art at the time of the invention would have recognized the advantages of implementing the parsing processing techniques suggested by Solomon, in the system of Baldua/Madnani, for the purpose of improving the output results generated by the LLM, as suggested by Solomon.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANGELA A ARMSTRONG whose telephone number is (571)272-7598. The examiner can normally be reached M,T,TH,F 11:30-8:00.
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, Pierre Desir can be reached at 571-272-7799. 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.
ANGELA A. ARMSTRONG
Primary Examiner
Art Unit 2659
/ANGELA A ARMSTRONG/Primary Examiner, Art Unit 2659
Prosecution Insights