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 .
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 of this title, 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 1, 5, 7, 9, 13, 16, 17 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over NISHIDA et al (“NISHIDA” US 2022/0043972 A1), published on February 10, 2022 in view of OH et al (“OH” US 2022/0253599 A1), published on August 11, 2022.
As to claim 1, NISHIDA teaches “obtaining text content in relation to the input question; partitioning the obtained text content into one or more paragraphs based on a predefined rule” in par. 0015 (obtained text from answer generation from input question) and in par. 0239 (paragraph as a unit of evidence span).
NISHIDA teaches “extracting, usinq a trained lanquaqe model and based on the obtained text content and the input question, one or more evidence spans that are one or more portions of , the one or more evidence spans being relevant to the input question and performing semantic search, based on the input question, on the one or more paragraphs and the extracted one or more evidence spans ” in par. 0015 (evidence spans are extracted from input text using pre-trained extracting model).
It appears NISHIDA does not explicitly teach “to rank a set of candidate passages comprising:
the one or more paragraphs from the partitioning”.
However, OH teaches “to rank a set of candidate passages comprising:
the one or more paragraphs from the partitioning” par. 0005 (ranking answer passages are produced from ranking unit; noting that passage comprises of number of sentences or paragraph).
NISHIDA and OH are analogous art because they are in the same field of endeavor, information retrieval. It would have been obvious to one of ordinary skill in the art before the effective filling date of the claim invention to process candidate passages (disclosed by NISHIDA) to include “to rank a set of candidate passages comprising:
the one or more paragraphs from the partitioning” as suggested by OH in order to provide ranking passages in the querying result (see OH par. 0005).
NISHIDA teaches “b) the one or more evidence spans independently extracted from the obtained text content” in par. 0015 (“…estimating, for each of the spans, an evidence score indicating a degree to which the span is suitable as evidence for extracting the answer…”. Noting that the scoring result provides ranking based on scores).
As to claim 13, it is rejected for similar reasons as claim 1.
As to claim 5, NISHIDA teaches “wherein performing the semantic search comprises inputting the one or more paragraphs, the extracted one or more evidence spans, and the input question to a retriever configured to rank the candidate passages based on semantic similarity between each of the candidate passages and the input question” in par. 0015.
As to claim 16, it is rejected for similar reasons as claim 5.
As to claim 7, OH teaches “wherein the candidate passages are ranked based on one or more criteria selected from the group consisting of relevance in relation to the input question, coverage, and self-containment, wherein the self-containment represents one of the candidate passages containing complete information to answer the input question” in par. 0005.
As to claim 17, it is rejected for similar reasons as claim 7.
As to claim 9, NISHIDA teaches “wherein the trained language model is an encoder-only transformer model” in par. 0010 (pre-trained encoding model).
As to claim 19, it is rejected for similar reasons as claim 9.
Claims 2 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over NISHIDA et al (“NISHIDA” US 2022/0043972 A1), published on February 10, 2022 in view of OH et al (“OH” US 2022/0253599 A1), published on August 11, 2022 in further view of SAKAKIBARA (US 2021/0397662 A1), published on December 21, 2021.
As to claim 2, it appears NISHIDA and OH do not explicitly teach: “wherein obtaining the text content comprises conducting a search based on the input question using an Internet-based or Intranet-based search engine”.
However, SAKAKIBARA teaches “wherein obtaining the text content comprises conducting a search based on the input question using an Internet-based or Intranet-based search engine” in paragraphs [0075-0076] (Search engine connected to the internet for searching).
NISHIDA, SAKAKIBARA and OH are analogous art because they are in the same field of endeavor, information retrieval. It would have been obvious to one of ordinary skill in the art before the effective filling date of the claim invention to process searching (disclosed by NISHIDA) to include “wherein obtaining the text content comprises conducting a search based on the input question using an Internet-based or Intranet-based search engine” in order to provide internet searching (see SAKAKIBARA paragraphs [0075-0076]).
As to claim 14, it is rejected for similar reasons as claim 2.
Claims 8 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over NISHIDA et al (“NISHIDA” US 2022/0043972 A1), published on February 10, 2022 in view of OH et al (“OH” US 2022/0253599 A1), published on August 11, 2022 in further view of Balsara et al (“Balsara” US 12373505 B2), published on July 29, 2025.
As to claim 8, it appears NISHIDA and OH do not explicitly teach “further comprising caching the obtained text content associated with the input question for subsequent queries related to the input question”.
However, Balsara teaches “further comprising caching the obtained text content associated with the input question for subsequent queries related to the input question” in col. 14: 1-20 (search result is stored in cache for sub-sequent search).
NISHIDA, SAKAKIBARA and Balsara are analogous art because they are in the same field of endeavor, information retrieval. It would have been obvious to one of ordinary skill in the art before the effective filling date of the claim invention to process searching (disclosed by NISHIDA) to include “further comprising caching the obtained text content associated with the input question for subsequent queries related to the input question” in order to fasten searching process (see Balsara col. 14).
As to claim 18, it is rejected for similar reasons as claim 8.
Response to Arguments
Regarding Applicant’s argument, on page 11 of the remarks, Applicant argues “Nishida describes selecting a passage most likely to include an answer based on its embedding similarity to a question (see, e.g., Nishida, [0056]-[0064]), but it does not teach generating separate evidence spans independent from the paragraph segmentation, nor performing ranking across both the paragraph(s) and the evidence span(s) together. Accordingly, Nishida's ranking operates solely at the paragraph (or passage) level, not over a hybrid candidate set combining paragraph(s) and distinct evidence span(s)”. Applicant’s argument is respectfully considered, but is not persuasive. According to par. 0015, Nishida teaches evidence spans that are extracted from input text using pre-trained extracting model. The ranking aspect the claim language is being disclosed by OH in par. 0015 (“…estimating, for each of the spans, an evidence score indicating a degree to which the span is suitable as evidence for extracting the answer…”. Noting that the scoring result provides ranking based on scores).
Regarding Applicant’s argument, on page 11 of the remarks, Applicant argues “Oh's model functions as an answer-verification network rather than a retrieval-ranking engine. As such, Oh does not teach or suggest unified semantic ranking across both paragraph-level and span-level candidates. Neither Sakakibara nor Balsara cures these deficiencies”. Applicant’s argument is respectfully considered, but is not persuasive. According to par. 0005, OH is disclosed of ranking answer passages from ranking unit. It is noted that passage comprises of number of sentences or paragraph.
Allowable Subject Matter
Claims 10-12 are allowed.
Claims 3-4, 6 and 15 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
THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Loc Tran whose telephone number is (571)272-8485. The examiner can normally be reached on Mon - Fri (8:00 am - 5:00 pm).
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Amy Ng can be reached on 571-272-3676. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/LOC TRAN/
Primary Examiner, Art Unit 2164