DETAILED ACTION
Claims 1-21 are pending in the Instant Application.
Claims 10-17, 20 and 21 are withdrawn.
Claims 1-9, 18 and 19 are rejected (Non-Final Rejection).
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 .
Election/Restrictions
Applicant’s election without traverse of claims 1-9, 18 and 19 in the reply filed on 13 July 2026 is acknowledged.
Priority
Applicant is advised of possible benefits under 35 U.S.C. 119(a)-(d) and (f), wherein an application for patent filed in the United States may be entitled to claim priority to an application filed in a foreign country. Attempts to retrieve priority documents failed on 3 September 2025, and no priority documents have been otherwise filed.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 3 April 2025 was considered by the examiner.
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 are rejected under 35 U.S.C. 103 as being unpatentable over Kanchibhotla et al. (“Kanchibhotla”), United States Patent Application Publication No. 2022/0405484, in view of CHAO (“Chao”), United States Patent Application Publication No. 2020/0159773.
As per claim 1, Kanchibhotla discloses a processor-implemented method, the method comprising: separating a first document into a second document, the second document including a first metadata portion of first metadata of the first document ([0060] wherein a JSON file is created by separating metadata from a first document), and a third document, the third document including a first content portion of content of the first document ([0075] wherein the content of the first document becomes a flat text file); and indexing the second document and the third document according to a correlation of the second document and the third document ([0080]-[0087] wherein the second document and third document are indexed based on correlation), but does not disclose classifying the second document and the third document into a first material set and a second material set, respectively. However, Chao teaches classifying the metadata of the first document and the content of the document into a first material set and a second material set, respectively ([0057] wherein content metadata is stored in the content metadata store 4 (a material set), and wherein content is stored in a content store (second material set)).
Both Kanchibhotla and Chao divide documents by content and metadata. Kanchibholta describes making two physical files, but does not expressly describes making a first and second material set. Chao makes a first and second material set, but expressly describes the content in a file, but not necessarily the metadata. One could use the material sets from Chao with document division in Kanchibhotla to teach the claimed invention. It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the division of metadata and content from a file to make two files as in Kanchibhotla with the designation of two separate sets as in Chao in order to allow the system to more easily search the metadata and retrieve the content.
As per claim 2, note the rejection of claim 1, where Kanchibhotla and Chao are combined. The combination teaches the method of claim 1. Kanchibhotla further discloses wherein the indexing comprises: indexing the second document and the third document according to a parent-child relationship ([0061] wherein the JSON and a flat tree file are indexed using the tree, where flat tree file combines the two in a parent-child relationship of the two). .
As per claim 3, note the rejection of claim 1, where Kanchibhotla and Chao are combined. The combination teaches the method of claim 1. Kanchibhotla further discloses wherein the indexing comprises: assigning, to the third document, a field indicating a parent-child relationship of the third document with the second document ([0075] wherein a field is added to the flattened tree file indicating the parent-child relationship of the document).
As per claim 4, note the rejection of claim 1, where Kanchibhotla and Chao are combined. The combination teaches the method of claim 1. Kanchibhotla further discloses upon receiving an update request for the first document, determining whether the update request is related to the first metadata; and selectively performing an update only for the second document responsive to the determining indicating the update request is related to the first metadata ([0075] wherein importing a new data source is the update request for the first document, and it is determined that the metadata matches the existing first document, wherein the metadata is updated as described).
As per claim 5, note the rejection of claim 1, where Kanchibhotla and Chao are combined. The combination teaches the method of claim 1. Chao further teaches further comprising: performing filtering based on the first metadata; and searching for documents belonging to the second material set, based on a single search index included in a single search query ([0043] wherein the metadata is filtered by a query and content documents are retrieved based on the vectorized indexed metadata).
As per claim 6, Kanchibhotla discloses a processor-implemented method, the method comprising: separating a first document into a second document and a third document, the second document including a first metadata portion of the first document ([0060] wherein a JSON file is created by separating metadata from a first document) and the third document including a first content portion of content of the first document ([0075] wherein the content of the first document becomes a flat text file) and indexing the second document and the third document according to a correlation of the second document and the third document([0080]-[0087] wherein the second document and third document are indexed based on correlation); but does not disclose disposing an embedding vector based on the second document and an embedding vector based on the third document in a same field; and indexing the second document and the third document according to a correlation of the second document and the third document. However, Chao teaches disposing an embedding vector based on metadata and an embedding vector based on content in a same field ([0234] wherein a single vector, thus in a same field, is created for each piece of content (first document), where some of the embedding vectors are based on the metadata, such as the title, and others can be based on the content like New York cop in [0130]).
Both Kanchibhotla and Chao divide documents by content and metadata. Kanchibholta describes making two physical files, but does not expressly describes making a first and second material set. Chao stores embedding vectors for metadata and content in the same field. Combining of descriptive vectors in a field as in Chao with document division in Kanchibhotla to teach the claimed invention. It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the division of metadata and content from a file to make two files as in Kanchibhotla with the storing of embedding vectors based on metadata and content in the same field in Chao in order generate results with much less comparisons.
As per claim 7, note the rejection of claim 6, where Kanchibhotla and Chao are combined. The combination teaches the method of claim 6. Chao further teaches wherein the first metadata portion comprises a title of the first document ([0064]).
As per claim 8, note the rejection of claim 6, where Kanchibhotla and Chao are combined. The combination teaches the method of claim 6. Kanchibhotla discloses a second document of metadata and the third document of content (see claim 6), but does not disclose wherein the indexing comprises: assigning a field indicating a sequence to the second document and the third document. However, Chao further teaches wherein the indexing comprises: assigning a field indicating a sequence to the metadata and the content ([0234] wherein a single sequence is assigned for both the metadata and the content) .
Both Kanchibhotla and Chao divide documents by content and metadata. Kanchibholta describes making two physical files, but does not expressly describes making a first and second material set. Chao stores embedding vectors for metadata and content in the same field. Combining of descriptive vectors in a field as in Chao with document division in Kanchibhotla to teach the claimed invention. It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the division of metadata and content from a file to make two files as in Kanchibhotla with the storing of embedding vectors based on metadata and content in the same field in Chao in order generate results with much less comparisons.
As per claim 9, note the rejection of claim 6, where Kanchibhotla and Chao are combined. The combination teaches the method of claim 6. Kanchibhotla discloses a second document of metadata and the third document of content (see claim 6), but does not disclose returning the third document responsive to the second document being included in a search result for a search query. However, Chao teaches returning the third document responsive to the metadata being included in a search result for a search query ([0043] wherein the metadata is filtered by a query and content documents are retrieved based on the vectorized indexed metadata).
Both Kanchibhotla and Chao divide documents by content and metadata. Kanchibholta describes making two physical files, but does not expressly describes making a first and second material set. Chao stores embedding vectors for metadata and content in the same field. Combining of descriptive vectors in a field as in Chao with document division in Kanchibhotla to teach the claimed invention. It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the division of metadata and content from a file to make two files as in Kanchibhotla with the storing of embedding vectors based on metadata and retrieving content as in Chao in order generate results with much less comparisons.
As per claim 18, Kanchibhotla discloses an apparatus, comprising: a processor configured to execute instructions ([0027]); and a memory storing the instructions([0027]), wherein execution of the instructions configures the processor to perform the method of claim 1. This claim 18 is rejected by the combination of Kanchibhotla and Chao as described for claim 1.
As per claim 19, Kanchibhotla discloses an apparatus, comprising: a processor configured to execute instructions ([0027]); and a memory storing the instructions([0027]), wherein execution of the instructions configures the processor to perform the method of claim 1. This claim 19 is rejected by the combination of Kanchibhotla and Chao as described for claim 6.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KANNAN SHANMUGASUNDARAM whose telephone number is (571)270-7763. The examiner can normally be reached M-F 9:00 AM -6:00 PM.
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, Charles Rones can be reached at (571) 272-4085. 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.
/KANNAN SHANMUGASUNDARAM/Primary Examiner, Art Unit 2168
Prosecution Insights