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 .
Claims 1-15 are pending.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-15 are rejected under 35 U.S.C. 103 as being unpatentable over Berg (Pub No. US 2025/0298721) in view of Saligrama Shreeram et al (Pub No. US 2025/0111091, hereinafter Shreeram).
With respect to claim 1, Berg discloses a retrieval-augmented generation (RAG) configuration method of a computer device comprising at least one processor (abstract, Fig 1), the method comprising:
providing, by the at least one processor, a user with a user interface configured to receive, from the user, at least one of an input for configuration of the RAG, a selection of elements predefined for configuration of the RAG, or a combination thereof (the term “or” indicates options and only need one of the listed; [0018]: provide a user interface to a user that enables user to input information for at least configuration of the RAG with customization instructions as further described in [0032] & [0049-0052] & [0069]));
configuring, by the at least one processor, the RAG for the user using at least one of a file acquired through the input entered through the user interface or elements selected by the user from among the predefined elements ([0018]: configure the RAG for the user using a file, such as and not limited to test file, through the input received/entered from the user through at least the user interface as further described in [0031-0034);
generating, by the at least one processor, a response to a query of the user, entered through the user interface, using the configured RAG and an artificial intelligence (AI) model ([0039], Fig 12 & 16: generate a response to a user query entered through the user interface using a RAG and an AI model, such as and not limited to LLM as further described in [0079-0080] & 0095]); and
providing, by the at least one processor, the generated response to the user through the user interface ([0039], Fig 12 & 16: provide the generated response to the user via user interface for feedback as further described in [0080]).
Berg does not explicitly disclose the received input from the user for configuration of the RAG is directed to at least one of a file path for configuration of the RAG as claimed.
Although one ordinary skilled in the art before the effective filing date of the claimed invention could reasonably interpreted that Berg implicitly discloses “providing, by the at least one processor, a user with a user interface configured to receive, from the user, at least one of a file path for configuration of the RAG; configuring, by the at least one processor, the RAG for the user using at least one of a file acquired through the file path entered through the user interface” as claimed based at least on (1) the user is provided with the interface configured to received user selection of a path that involves in query response determination in the query processing ([0098-0099]), and (2) the user configured RAG is also involved in query response determination in the query processing ([0031-0034)).
Also, Shreeram discloses providing, by the at least one processor, a user with a user interface configured to receive, from the user, at least one of a file path for configuration of the RAG ([0018-0019,]Fig 8: provide a user with a user interface to receive at least one file path represented by an access path to at least one file storage, such that a path such as RAG pipeline, being configured for file data access as further described in [0069] & [0073-0074]); and
configuring, by the at least one processor, the RAG for the user using at least one of a file acquired through the file path entered ([0017-0018]: configure the RAG with the pipeline using the file via file metadata through path entered by the user via input indicating the file storage for query processing as further described in [0024] and [0073-0074]).
Since, both Berg and Shreeram are from the same field of endeavor as both are directed to retrieval-augmented generation in query processing, which is same field of endeavor as the claimed invention, it would have been obvious to one skilled in the art before the effective filing date of the claimed invention to combine their teaching by incorporate file path with respect to RAG configuration of Shreeram into Berg for query response generation as claimed. The motivation to combine is to improve query responses quality with obtaining relevant data (Berg, [0017]; and Shreeram, [0001]).
With respect to claim 11, Berg discloses a computer device (abstract, Fig 1) comprising:
at least one processor configured to execute computer-readable instructions ([0020], Fig 1); and a non-transitory computer-readable recording medium storing instructions that, when executed by a processor ([0020], Fig 1), cause the computer device to
provide a user with a user interface configured to receive, from the user, at least one of an input for configuration of the RAG, a selection of elements predefined for configuration of the RAG, or a combination thereof (the term “or” indicates options and only need one of the listed; [0018]: provide a user interface to a user that enables user to input information for at least configuration of the RAG with customization instructions as further described in [0032] & [0049-0052] & [0069]));
configure the RAG for the user using at least one of a file acquired through the input entered through the user interface or elements selected by the user from among the predefined elements ([0018]: configure the RAG for the user using a file, such as and not limited to test file, through the input received/entered from the user through at least the user interface as further described in [0031-0034),
generate a response to a query of the user entered through the user interface using the configured RAG and an artificial intelligence (AI) model ([0039], Fig 12 & 16: generate a response to a user query entered through the user interface using a RAG and an AI model, such as and not limited to LLM as further described in [0079-0080] & 0095]), and
provide the generated response to the user through the user interface ([0039], Fig 12 & 16: provide the generated response to the user via user interface for feedback as further described in [0080]).
Berg does not explicitly disclose the received input from the user for configuration of the RAG is directed to at least one of a file path for configuration of the RAG as claimed.
Although one ordinary skilled in the art before the effective filing date of the claimed invention could reasonably interpreted that Berg implicitly discloses “provide a user with a user interface configured to receive, from the user, at least one of a file path for configuration of a retrieval-augmented generation (RAG), as election of elements predefined for configuration of the RAG, or a combination thereof, configure the RAG for the user using at least one of a file acquired through the file path entered through the user interface or elements selected by the user from among the predefined elements through the user interface” as claimed based at least on (1) the user is provided with the interface configured to received user selection of a path that involves in query response determination in the query processing ([0098-0099]), and (2) the user configured RAG is also involved in query response determination in the query processing ([0031-0034)).
Also, Shreeram discloses provide a user with a user interface configured to receive, from the user, at least one of a file path for configuration of a retrieval-augmented generation (RAG), ([0018-0019,]Fig 8: provide a user with a user interface to receive at least one file path represented by an access path to at least one file storage, such that a path such as RAG pipeline, being configured for file data access as further described in [0069] & [0073-0074]); and
configure the RAG for the user using at least one of a file acquired through the file path entered ([0017-0018]: configure the RAG with the pipeline using the file via file metadata through path entered by the user via input indicating the file storage for query processing as further described in [0024] and [0073-0074]).
Since, both Berg and Shreeram are from the same field of endeavor as both are directed to retrieval-augmented generation in query processing, which is same field of endeavor as the claimed invention, it would have been obvious to one skilled in the art before the effective filing date of the claimed invention to combine their teaching by incorporate file path with respect to RAG configuration of Shreeram into Berg for query response generation as claimed. The motivation to combine is to improve query responses quality with obtaining relevant data (Berg, [0017]; and Shreeram, [0001]).
With respect to claims 2 and 12, the combined teachings of Berg and Shreeram further disclose wherein the configuring of the RAG comprises configuring a knowledge pipeline for the RAG by linking elements included in the acquired file or the selected elements to actions of the knowledge pipeline (Berg, [0076-0080], Fig 12-13; Shreeram, [0019], Fig 3-6 & 8: configure a knowledge pipeline by linking elements, such as data, in the file to action represented by operations of the pipeline with data content knowledge corresponding to the knowledge pipeline), and
the generating the response comprises sequentially operating workers corresponding to elements linked to the actions in order of the actions of the knowledge pipeline (Berg, [0076-0080], Fig 12-13; Shreeram, [0019-0021], Fig 3-6 & 8: sequentially operating workers such as and not limited to retrievers linked to the operations/actions of the pipeline/workflow to generate the response).
With respect to claims 3 and 13, the combined teachings of Berg and Shreeram further disclose wherein the configuring of the RAG comprises configuring a first pipeline according to a combination of first elements, the first elements configured to index data of the user (Berg, [0032], Fig 12-13; Shreeram, [0040], Fig 3-6: configure a 1st pipeline representing by a series to operations according to different elements, such as and not limited to data processing elements/components, to collect and index data for at least query processing); and
configuring a second pipeline according to combination of second elements, the second elements configured to retrieve data of the user to the query of the user (Berg, [0039], Fig 12-13; Shreeram, [0019], Fig 3-6 & 8: configure a 2nd pipeline representing by another set of ordered operations according to a 2nd elements such as and not limited to retrieval elements/components to retrieve data in response to the user query).
With respect to claims 4 and 14, the combined teachings of Berg and Shreeram further disclose wherein the first elements include at least two of element configured to acquire the data of the user, an element configured to analyze a syntax of the data of the user, an element configured to extract at least one of a keyword, a summary, or metadata from the data of the user, an element configured to split the data of the user into a plurality of chunks, an element configured to generate a vector by embedding the data of the user, or an element configured to store the embedded vector in a vector database (“at least two” indicates only need two of the listed to read on the limitations; Also the listed elements are directed to non-functional descriptive materials that described what are being included in the 1st elements and the described elements are not necessarily being used to impact the functionally of the claimed steps; Berg, [0038-0039]; Shreeram, [0058-0063]: the elements include and not limited to syntax, extract text/word, metadata and embedded vectors in a vector database),
With respect to claims 5 and 15, the combined teachings of Berg and Shreeram further disclose wherein the second elements include at least two of an element configured to generate a vector by embedding the query of the user, an element configured to store the generated vector in a vector database, an element configured to acquire search results by searching the vector database using the generated vector, or an element configured to process the acquired search results (“at least two” indicates only need two of the listed to read on the limitations; Also the listed elements are directed to non-functional descriptive materials that described what are being included in the 2nd elements and the described elements are not necessarily being used to impact the functionally of the claimed steps; Berg, [0038-0039]; Shreeram, [0058-0063]: the elements include and not limited to generate, store, and processing the embedded vectors in a vector database to obtain search results represented by the responses),
With respect to claim 6, the combined teachings of Berg and Shreeram further disclose
wherein the element configured to preprocess the acquired search results includes an element configured to adjust a ranking of the acquired search results, an element configured to generate a summary of the search results, or a combination thereof (the term “or” indicates options and only one of the listed is needed; Berg, [0032]; Shreeram, [0027]: the elements include elements/component configured to at least generate a summary of the search results represented by the responses).
With respect to claim 7, the combined teachings of Berg and Shreeram further disclose
wherein the RAG includes a plurality of different retrievers (the limitation is directed to a non-functional descriptive material as the retrievers are not being used to impact the functionality of the claimed steps; Berg, [0093-0094], Fig 13; Shreeram, [0037], Fig 5: the RAG includes different retrievers and/or agents representing the retrievers).
With respect to claim 8, the combined teachings of Berg and Shreeram further disclose
wherein the plurality of retrievers include at least two of a first retriever configured to retrieve data corresponding to an embedded query of the user from a first vector database constructed by splitting and embedding the data of the user based on a first chunk unit with a preset first chunk size, a second retriever configured to retrieve the data corresponding to the embedded query of the user from a second vector database constructed by splitting and embedding the data of the user based on a second chunk unit with a second chunk size having a relatively larger value than the first chunk size, or a third retriever configured to search at least one of the first or second vector databases by generating a structured query using the AI model for the query (“at least two” indicates only need two of the listed to read on the limitations; Also the listed elements are directed to non-functional descriptive materials that described what are being included in the retrievers and the described retrievers are not necessarily being used to impact the functionally of the claimed steps; Berg, [0038-0039], [0093-0094],Fig 13; Shreeram, [0037], [0058-0063], Fig 5: the different retrievers or agents, including and not limited to a 1st retriever configured to retrieve data via vectors, and a 2nd retriever configured to search vectors in a database to obtain results/responses via AL model).
With respect to claim 9, the combined teachings of Berg and Shreeram further disclose wherein the second vector database is constructed by embedding metadata extracted using the AI model from data split based on the second chunk unit and the data split based on the second chunk unit (the limitation is directed to non-functional descriptive material as indicated by the term “is” and the elements being described are not necessary being used to impact the functionality of the claimed steps; Berg, [0080]; Shreeram, [0077-0078]-0043]: generate a vector database with parsing data and vectorized data chunks for query processing).
With respect to claim 10, the combined teachings of Berg and Shreeram further disclose a non-transitory computer-readable recording medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 1 (Berg, [0020], Fig 1; and Shreeram, [0104], Fig 10).
Examiner Note
Examiner has cited particular columns/paragraph and line numbers in the references applied to the claims above for the convenience of the applicant. Although the specified citations are representative of the teachings of the art and are applied to specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant in preparing responses, to fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the Examiner.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michelle Owyang whose telephone number is (571)270-1254. The examiner can normally be reached Monday-Friday, 8am-6pm 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, 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.
/MICHELLE N OWYANG/ Primary Examiner, Art Unit 2168