CTNF 18/388,686 CTNF 99230 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Continued Examination Under 37 CFR 1.114 07-42-04 AIA 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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 2/24/2026 has been entered. Response to Amendment Claims 1, 8, and 15 are amended. Claims 1-20 are presented for examination. Response to Arguments Rejection under 35 U.S.C. 103 Applicant’s arguments have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Claim Rejections - 35 USC § 103 07-20-aia AIA 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. 07-21-aia AIA Claim s 1, 3-8, 10-15, and 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over De Wynter et al. (US 20250117605 A1; hereinafter referred to as De Wynter) in view of Gambhir et al. (US 20240370670 A1; hereinafter referred to as Gambhir) and Saulys (SAULYS, SAULIUS, "LLM prompt optimization: Reducing token usage", [Online]. Retrieved from the Internet: URL:https:medium.com@sauliusaulyslllm-promptoptimization-reducing-tokens-usage-343f5de178a5, (92423), 7 pgs) . Regarding claim 1, De Wynter discloses: a system comprising: at least one hardware processor ([0088] processing system 902 may comprise a micro-processor and other circuitry that retrieves and executes software 905 from storage system 903 ); and a computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations comprising: receiving natural language text describing a request to generate text ([0020] The initial prompt generated by the content assistant for the user input tasks a foundation model, such as a large language model (LLM), with generating a completion for the natural language input. The completion may be a refinement or narrowing of the input topic (e.g., additional information for the input), suggestion for how the input may be addressed by foundation model (e.g., “I want to write about Norway. List ten popular tourist sites in Norway.”), or other addition to the user input based on an inference made by the foundation model of the user's intent. The completion generated by the foundation model may be one or more words which form a phrase, sentence, paragraph, etc., which may be appended to the user input resulting in revised user input ); accessing contextual information ([0051] In generating the first prompt, the computing device includes contextual information relating to the document, such as a selection of existing content (if any) which provides the foundation model with context for generating the completion ) regarding the natural language text, the contextual information being separate and distinct from the natural language text… ([0043] application 113 receives natural language input 117 entered by the user in input pane 119 of content assistant 115. Natural language input 117 relates to content of document 118, such as a request for new content to be added to document 118, to revise existing content of document 118, for content ideas, etc. Application 113 generates a first prompt including natural language input 117 which is transmitted to foundation model 130… Context information in the first prompt may also include existing content from document 118, such as a paragraph near the insertion point of input pane 119. Context information can also include metadata for document 118, such as the filename ); generating a prompt using the natural language text, the contextual information, and a system message… ([0044] first prompt includes at least a portion of the natural language input, a task associated with the natural language input, and context information associated with the document ) passing the prompt to a large language model (LLM) ([0049] The computing device generates a first prompt which tasks a foundation model, such as an LLM, with generating a completion to the user's natural language input (step 203) ); De Wynter does not explicitly, but Gambhir teaches: converting the contextual information ([0025] the user may want the AI language model to summarize or rewrite the content of the files. As will be explained in detail below, the user is able to submit the file or files to a conversion service 152. The conversion services 152 will operate on the format of the productivity application files to convert the format or condition the content of the files to a format that is compatible with AI language models. The productivity application files can be contextual files. ) into an intermediate file format in minimized format ([0044] The file bytes of the file 304/305 are submitted by the client 302 to the conversion service 120 as described above, for example, via an HTTP/gRPC service layer 310. The file bytes are passed to a native worker 306 configured to convert PPT file data to JSON format. This worker 306 includes a PPT to JSON parser 308 ), the intermediate file format being a format that enables portions of a file stored in the intermediate file format to be removed without altering semantic meaning of the file ([0045] Raw JSON data is returned to the service layer 310. Using a JSON schema, the service layer 310 can return a JSON file in simplified form to the client 302. The service layer 310 can also include a PII scrubber 314. As described above, the PII scrubber 314 produces a scrubbed JSON file that is returned to the client 302. JSON is an example of an intermediate file format and the PII scrubber minimizes the JSON file. ) , the converting comprising removing portions of the contextual information that are able to be removed without altering semantic meaning of the contextual information … ([0038] the conversion service may further process the content of the files 104 to remove or scrub any PII. Accordingly, the managed layer 129 includes a PII scrubber 126. This scrubber 126 will parse the content of any file 104 being converted and remove any PII. Personal identifiable information can be removed without altering semantic meaning. ); receiving, from the LLM, generated text in the intermediate file format ([0046] the client can submit the converted file to an AI language model 110. This submission may include both the content of the file and a text prompt stating what the AI language model 110 is to do with or to the file content. Thus both text and JSON data may be part of the input to the AI language model 110. The AI language model 110 will then return a response to the client 302. Because of the conversion of the file to an AI compatible format, this response should be more useful than would have been the case otherwise ) in minimized form ([0028] a large number of textual documents, with or without accompanying graphics, could be submitted to the conversion service 152 and then, with the content reformatted, submitted to the AI service 154 with an instruction to summarize the documents. The AI service 154 may then output a document that summarizes all the input documents. That summary document can then be converted into the format used by the original productivity application through the conversion service 156 and then returned to the requesting user. The output of the LLM can be a reformatted JSON file that can be converted back to the original input file type. ); and parsing, using a specialized parser designed to understand the minimized format ([0027] The flow may include additional conversion service 156 to convert the output from the AI service 154 back into the original productivity application file format. The user can then receive new productivity application files 158 and will be able to open them with the original productivity application. The user will then have access to the content as it has been changed or augmented by the AI service 154 in the manner requested. The conversion service can act as a parser to output parsed text in the original file format. ), the generated text, producing parsed generated text ([0028] The AI service 154 may then output a document that summarizes all the input documents. That summary document can then be converted into the format used by the original productivity application through the conversion service 156 and then returned to the requesting user ). De Wynter and Gambhir are considered analogous in the field of large language models (LLMs). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of De Wynter to combine the teachings of Gambhir because doing so would allow for contextual input files to be converted into more compatible and user-desired formats for use in prompts to LLMs, leading to improved scalability of LLMs and better generated LLM responses in specific formats (Gambhir [0024] formats, such as proprietary formats, that are used only by the application or applications of a specific developer will not likely be readily ingestible by AI language models, unless the AI model has been specifically constructed to ingest that specific file format or formats. Consequently, the present disclosure will introduce more effective systems and methods for converting productivity application files into a format that can be ingested and utilized by current AI language models with additional features to promote the security and scalability of using AI language models to process the information in file repositories ). The combination of De Wynter and Gambhir does not explicitly, but Saulys teaches: the system message including instructions to produce generated text in the intermediate file format in minimized form… ([Page 3] Then I tried to send the same prompt and just add ‘Return a single-line minified JSON’ at the end. Also see custom format. ). De Wynter, Gambhir, and Saulys are considered analogous in the field of LLMs. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of De Wynter and Gambhir to combine the teachings of Saulys because doing so would reduce the processing power and resources required by an LLM to process a prompt and generate a response output by using a specialized file format with non-semantic content portions removed to generate the prompt (Saulys [Page 4] Creating a custom format that uses as little symbols and white spaces as possible to generate an answer, can save you significant amount of money by using fewer tokens ). Regarding claim 3, the combination of De Wynter, Gambhir, and Saulys teaches: the system of claim 1. De Wynter further teaches: wherein the contextual information is retrieved after receiving the natural language text ([0029] The application generates the initial prompt, including the natural language input, to task the foundation model with generating a continuation or completion of the input which refines, focuses, redirects, or otherwise augments the input to produce a higher quality output in accordance with existing content or other the contextual information and the task associated with the input ). Regarding claim 4, the combination of De Wynter, Gambhir, and Saulys teaches: the system of claim 3. De Wynter further teaches: wherein the LLM has a hard limit on a number of input tokens it will process for a single prompt ([0051] the computing device selects content for the first prompt according to a token limit of the first prompt, the quantity of available content, and a token limit on the output from the foundation model ) and the prompt includes fewer tokens than the hard limit ([0035] The application also generates the initial prompt by selectively including contextual information in a way that balances the size (e.g., token count) of the initial prompt with the quantity of existing content to be included in the prompt which will allow the foundation model to generate a more useful completion to the input ). Regarding claim 5, the combination of De Wynter, Gambhir, and Saulys teaches: the system of claim 1. Saulys further teaches: wherein the minimized form includes having no spaces ([Pages 3-4] to create a custom format I got inspiration from YAML, that uses way less symbols than JSON. I took a step even further and removed all unnecessary white spaces and symbols. But I still wanted to have structure that JSON can provide ). Regarding claim 6, the combination of De Wynter, Gambhir, and Saulys teaches: the system of claim 1. Saulys further teaches: wherein the minimized form includes having no carriage returns ([Pages 3-4] to create a custom format I got inspiration from YAML, that uses way less symbols than JSON. I took a step even further and removed all unnecessary white spaces and symbols. But I still wanted to have structure that JSON can provide... Carriage returns can be considered unnecessary symbols. ). Regarding claim 7, the combination of De Wynter, Gambhir, and Saulys teaches: the system of claim 1. Gambhir further teaches: wherein the intermediate file format is Javascript Object Notation (JSON) ([0044] The file bytes of the file 304/305 are submitted by the client 302 to the conversion service 120 as described above, for example, via an HTTP/gRPC service layer 310. The file bytes are passed to a native worker 306 configured to convert PPT file data to JSON format. This worker 306 includes a PPT to JSON parser 308 ). Regarding claim 8, it recites similar limitations as claim 1 and therefore is rejected similarly. Regarding claims 10 and 17, they recite similar limitations as claim 3 and therefore are rejected similarly. Regarding claims 11 and 18, they recite similar limitations as claim 4 and therefore are rejected similarly. Regarding claims 12 and 19, they recite similar limitations as claim 5 and therefore are rejected similarly. Regarding claims 13 and 20, they recite similar limitations as claim 6 and therefore are rejected similarly. Regarding claim 14, it recites similar limitations as claim 7 and therefore is rejected similarly. Regarding claim 15, De Wynter teaches: a non-transitory machine-readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations... ([0097] aspects of the present invention may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon ). The rest of the claim recites similar limitations as claim 1 and therefore is rejected similarly . 07-22-aia AIA Claim s 2, 9, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over De Wynter in view of Gambhir and Saulys , as applied to claim s 1, 3-8, 10-15, and 17-20 above, and further in view of Jones et al. (US 20250111220 A1; hereinafter referred to as Jones) . Regarding claim 2, the combination of De Wynter, Gambhir, and Saulys teaches: the system of claim 1. The combination of De Wynter, Gambhir, and Saulys does not explicitly, but Jones teaches: wherein the parsed generated text ([0026] Domain-specific text includes domain-specific machine-readable text. Domain-specific machine-readable text encompasses domain-specific text that is structured and formatted in a way that is easily understandable by machines, particularly computers and automated systems. This type of text is designed to be processed, analyzed, and interpreted by software applications more quickly and more accurately than natural language text ) is compilable computer code ([0037] the domain-specific text to be generated by an LLM according to the prompt 126 falls within a specific domain, which encompass: (1) a text-based structured data interchange format, (2) a text-based structured database query language, or (3) code expressed in a specific programming language ). De Wynter, Gambhir, Saulys, and Jones are considered analogous in the field of LLMs. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of De Wynter, Gambhir, and Saulys to combine the teachings of Jones because doing so would allow for the LLM to generate a wider variety of answers to user prompts, which would provide an improvement to the quality and specificity of outputs generated by the LLM (Jones [0078] This assortment might encompass an array of prompts, including those that involve code generation. Each of these prompts encapsulates a natural language expression or another high-level specification of code, destined for a LLM service to process to generate in a domain-specific or alternative lower-level language (e.g., Structured Query Language (SQL) queries). Once acquired, this collection of prompts is dispatched by service 110 to a range of LLM services, leading to the generation of corresponding answers to the prompts by these LLM services ). Regarding claims 9 and 16, the claims recite similar limitations as claim 2 and therefore are rejected similarly. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to Nathan Tengbumroong whose telephone number is (703)756-1725. The examiner can normally be reached Monday - Friday, 11:30 am - 8:00 pm EST. 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, Hai Phan can be reached at 571-272-6338. 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. /NATHAN TENGBUMROONG/Examiner, Art Unit 2654 /HAI PHAN/Supervisory Patent Examiner, Art Unit 2654 Application/Control Number: 18/388,686 Page 2 Art Unit: 2654 Application/Control Number: 18/388,686 Page 3 Art Unit: 2654 Application/Control Number: 18/388,686 Page 4 Art Unit: 2654 Application/Control Number: 18/388,686 Page 5 Art Unit: 2654 Application/Control Number: 18/388,686 Page 6 Art Unit: 2654 Application/Control Number: 18/388,686 Page 7 Art Unit: 2654 Application/Control Number: 18/388,686 Page 8 Art Unit: 2654 Application/Control Number: 18/388,686 Page 9 Art Unit: 2654 Application/Control Number: 18/388,686 Page 10 Art Unit: 2654 Application/Control Number: 18/388,686 Page 11 Art Unit: 2654 Application/Control Number: 18/388,686 Page 12 Art Unit: 2654
Prosecution Insights