CTNF 18/918,568 CTNF 80676 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. Drawings 06-37 AIA The drawings were received on 10/17/2024 . These drawings are accepted . Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 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) 1,4,6,7,8,11,13,14,15,18,20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Dar et al (US Publication No.: 20250315486) in view of Dhar et al (US Publication No.: 20260050961) . Claim 1, Dar et al discloses At least one hardware processor (Paragraph 72); 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 (Paragraph 72,73,74) comprising: Accessing a first document (Fig. 3, label 300, processing of a document.); Dividing the first document into one or more chunks (Fig. 3, label 300,302); Augmenting each of the one or more chunks with metadata (Fig. 3, label 302 plurality of headings as metadata, Label 312 indicates chunks with heading or metadata and content and label 308 are chunks with heading.); For each chunk of the one or more chunks: Passing the chunk and corresponding metadata through an embedding machine learning model to generate an embedding (Fig. 3, label 316), the embedding being a vector of coordinates in a latent n-dimensional space (Fig. 3, label 316, paragraph 47 discloses embeddings as vector of coordinates in dimensional space.); and Storing the embedding in a vector database (Paragraph 47 discloses “content chunks and their vector embeddings (e.g. chunk embeddings 408 are stored in a database”.); Receiving a request from a user to generate content-based data (Fig. 3, label 316); Passing the data through an embedding machine learning model to generate a query embedding (Fig. 3, label 318); Finding a close embedding geometrically close to the query embedding in the vector database (Fig. 3, label 320); Retrieving a first chunk corresponding to the close embedding (Fig. 3, label 320), the first chunk having first corresponding metadata (depending on the similarity between chunk embeddings and query embedding, the chunk can have corresponding metadata. Label 312,308 describes the data in the chunks.); and Submitting, to the LLM, the data, the first chunk, the first corresponding metadata (Fig. 3, label 322,324), and a prompt instructing the LLM to generate the content based on the data, the first chunk, and the first corresponding metadata (Fig. 3, label 324, fig. 4, label 416). Dar et al discloses metadata or headings splitting chunks from a document (Fig. 3, label 302 plurality heading is determined from splitting chunks from a document.), but fails to disclose the metadata is generated by a LLM. Dhar et al discloses splitting chunks of data based on a proposition unit using a large language model and submitting a prompt to the LLM (Paragraph 47 discloses segmentation engine is used to process a document to generate multiple segments. The segmentation engine can prompt an LLM 162 to generate chunks or segments of the document. Fig. 4, label 162 receives the prompt generated using query embeddings and segmentation embeddings of the document. Fig. 3, label 320 shows the chunk or segmentation embeddings of the document, 152.). It would be obvious to one skilled in the art before the effective filing date of the application to modify Dar et al’s metadata and document chunks generation by incorporating an LLM to perform document chunks and metadata generation as disclosed by Dhar et al so to improve the generation of document chunks with content and metadata or headings. Dar et al discloses generating chunk embeddings and query embedding (Fig. 3, label 316,318), but fails to disclose an embedding model is used to generate the chunk embeddings and query embedding. Dhar et al discloses generating chunk embeddings using an embedding model (Fig. 3, label 126) and query embedding using the embedding model (Fig. 4, label 126). It would be obvious to one skilled in the art before the effective filing date of the application to modify Dar et al’s embeddings generation by incorporate an embedding model to generate the query embedding and chunk embeddings as disclosed by Dhar et al so to generate embeddings and improve prompt generation to an LLM. Claim 4, Dar et al discloses the dividing comprises divide the first document into semantically meaningful chunks (Fig. 5 shows the first document divided into chunks. Paragraph 64 discloses “document hierarchy-based chunking process 10 provides more efficient (i.e. in terms of chunk size) and effective (i.e., in terms of connecting related concepts hierarchically) …”. By connecting chunks related via concept, this indicates semantically meaningful chunks are generated.) and to generate links among related chunks (Fig. 5 shows related chunks linked) and wherein the augmenting further comprises adding the links as corresponding metadata to corresponding chunks (Fig. 5 shows chunks such as 500,512 with metadata or heading and content where the links indicate relationship between heading or metadata and content. Paragraph 60 discloses chunks with heading and content portion, indicating linking heading and content.). Claim 6, Dhar et al discloses the embedding machine learning model is part of the LLM (Fig. 3, label 126 is connected to 162 via document segments, indicating 126 is part of 162.). Claim 7, Dhar et al discloses wherein the data is natural language text (Fig. 4, label 410. Paragraph 2 discloses “the query that a user types is given as input to the LLM ...”.). Claim 8 recites similar limitations as claim 1 and is rejected on the same grounds as claim 1. Claim 11 recites similar limitations as claim 4 and is rejected on the same grounds as claim 4. Claim 13 recites similar limitations as claim 6 and is rejected on the same grounds as claim 6. Claim 14 recites similar limitations as claim 7 and is rejected on the same grounds as claim 7. Claim 15 recites similar limitations as claim 1 and is rejected on the same grounds as claim 1. Claim 18 recites similar limitations as claim 4 and is rejected on the same grounds as claim 4. Claim 20 recites similar limitations as claim 6 and is rejected on the same grounds as claim 6 . Allowable Subject Matter 12-151-08 AIA 07-43 12-51-08 Claim s 2-3,5,9-10,12,16-17,19 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to LINDA WONG whose telephone number is (571)272-6044. The examiner can normally be reached 9-5. 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 C 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. /LINDA WONG/Primary Examiner, Art Unit 2655 Application/Control Number: 18/918,568 Page 2 Art Unit: 2655 Application/Control Number: 18/918,568 Page 3 Art Unit: 2655 Application/Control Number: 18/918,568 Page 4 Art Unit: 2655 Application/Control Number: 18/918,568 Page 5 Art Unit: 2655 Application/Control Number: 18/918,568 Page 6 Art Unit: 2655 Application/Control Number: 18/918,568 Page 7 Art Unit: 2655
Prosecution Insights