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 .
Response to Amendment
Claims 1-20 are pending in this application.
The drawing filed 5/18/2026 is accepted.
Claim rejections 35 USC 101 are withdrawn.
Applicant’s arguments on claim rejections 35 USC 102 and 35 USC 103, filed 5/18/2026, have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Ogura.
Response to Arguments
Applicant’s arguments with respect to claim rejections 35 USC 102 and 35 USC 103 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
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.
Claims 1, 5-8, 10-11, 13-17 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (US 2021/0149994, hereinafter “Kim”) in view of Ogura et al. (US 2023/0290341, hereinafter “Ogura”).
Regarding claim 1, Kim teaches A computerized method comprising:
storing query data specifying a user's question in memory (Kim, [0066]: The administrator setting unit checks the forms of the user question and the best answer to store a best answer value determined by the screener based on the semantic triple.);
detecting a specialized document associated with the query data in a database (Kim, [0008]: According to one or more embodiments, a machine reading comprehension (MRC) question and answer providing method includes receiving a user question; analyzing the user question; selecting at least one document from at least one domain corresponding to an analyzed user question and searches for a passage, which is a candidate answer determined as being suitable for the user question, in the selected at least one document;);
reviewing association between the query data and a plurality of paragraphs included in the detected specialized document (Kim, [0026]: The receiver 210 receives a user question, the analyzer 220 analyzes the user question, the passage searcher 230 selects at least one document from at least one domain corresponding to the analyzed user question, and a passage, which is a candidate answer determined as being suitable for the user question, is searched for in the at least one selected document. In this case, N passages (N is a natural number) may be retrieved.);
by performing associative selection, which extracts one or more evidential paragraphs associated with the query data from the specialized document, on the plurality of paragraphs included in the detected specialized document in accordance with the reviewed association, extracting one or more associatively selected paragraphs (Kim, [0046]: The passage searcher 330 may automatically adjust an extraction range for extracting a passage based on the statistics that correct answer candidate values determined by the MRC question and answer algorithm used by each of at least one MRC question and answer unit 340 are determined as best answers.);
storing base data based on the one or more associatively selected paragraphs and the reviewed association (Kim, [0031]: The administrator setting unit stores a best answer value determined by the screener 350 as a semantic triple and manages settings of the similar question matching unit 332, the passage searcher 330, and the MRC question and answer unit 340. Also, the administrator setting unit may store all information generated by the receiver 310, the analyzer 320, the passage searcher 330, the MRC question and answer unit 340, the screener 350, and the answer unit 360.);
performing rationale generation which generates rationale data for generating an answer to the user's question based on the extracted one or more evidential paragraphs associated with the query data from the stored base data (Kim, [0049]: According to an embodiment, the MRC question and answer unit 340 generates N*M correct answer candidate values by applying M MRC question and answer algorithms to N passages corresponding to one user question and transmits the N*M correct answer candidate values and reliability information indicating the probability of being a correct answer for each of the N*M correct answer candidate values to the screener 350.); and
performing systematic composition that generates response data specifying the answer to the user's question based on the generated rationale data (Kim, [0051]: When there are a plurality of correct answer candidate values, the screener 350 first checks whether the majority of or at least a certain percentage of the plurality of correct answer candidate values are consistent through the consistency checker 352 (operation S630). [0057]: The answer unit 360 provides a best answer or information indicating no result transmitted from the screener 350 to a user as an answer.).
Kim does not explicitly teach wherein the rationale data includes at least one of explanation sentence data including explanation for a direct answer to the user's question or auxiliary information data including background knowledge information related to the user's question.
Ogura teaches wherein the rationale data includes at least one of explanation sentence data including explanation for a direct answer to the user's question or auxiliary information data including background knowledge information related to the user's question (Ogura, [0073]: The database search unit 12 having received the above information searches the table of the background knowledge database 23 using the received information (details will be described later), and transmits the acquired check result (id of the document (e.g., document_id described later), file name, sentence extracted from the document) to the user interface application 13. The user interface application 13 forwards the received search result to the content explanation display unit 322 of each client terminal 30. [0074]: The content explanation display unit 322 displays the received search result on the display screen 32. As illustrated in FIG. 2, the content explanation display unit 322 displays the file name of the received search result and the sentence extracted from the document on the screen as the explanation, with the text part designated as the ambiguous portion being used as the title.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the question and answer providing method of Kim with the teaching about the received search result of Ogura because it can present the content explanation information in a form that the user can understand (Ogura, [0063]).
Regarding claim 5, Kim in view of Ogura teaches wherein the extracting of the one or more associatively selected paragraphs by performing the associative selection includes: generating input data based on the query data and the specialized document through prompt engineering (Kim, [0026]: The receiver 210 receives a user question, the analyzer 220 analyzes the user question, the passage searcher 230 selects at least one document from at least one domain corresponding to the analyzed user question, and a passage, which is a candidate answer determined as being suitable for the user question, is searched for in the at least one selected document.); and
extracting the one or more evidential paragraphs from the specialized document by inputting the input data into a response agent model (Kim, [0046]: The passage searcher 330 may automatically adjust an extraction range for extracting a passage based on the statistics that correct answer candidate values determined by the MRC question and answer algorithm used by each of at least one MRC question and answer unit 340 are determined as best answers.).
Regarding claim 6, Kim in view of Ogura teaches wherein the rationale data further includes main answer data including the direct answer to the user's question (Kim, [0043]: According to an embodiment, the passage searcher 330 calculates a TF-IDF value based on a user question, a query analyzed from the user question, and a result of a morphological analysis of the query. In this case, the number of passages extracted by the passage searcher 330 may be initially set to an arbitrary number and may be automatically adjusted later by using log-based statistical values. The log-based statistical values include a result value selected as the best answer by the screener 350 and a log analysis value recorded in the administrator setting unit. [0057]: The answer unit 360 provides a best answer or information indicating no result transmitted from the screener 350 to a user as an answer. Ogura, [0074]: The content explanation display unit 322 displays the received search result on the display screen 32.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the question and answer providing method of Kim with the teaching about the received search result of Ogura because it can present the content explanation information in a form that the user can understand (Ogura, [0063]).
Regarding claim 7, Kim in view of Ogura teaches wherein the generating of the answer to the user's question includes: separating the generated response data into a plurality of sentences; identifying, for each of the separated sentences, rationale information that contributed to generation of each of the separated sentences (Kim, [0037]: Referring to FIG. 5, an example in which the passage searcher 520 extracts five passages 540a, 540b, 540c, 540d, and 540e in relation to a user question “What is the name of the album that Shiny released latest?” and transmits the passages 540a, 540b, 540c, 540d, and 540e to the MRC question and answer unit 340 is shown.); and
outputting each of the separated sentences and the identified rationale information on a user interface on which the response data is displayed (Kim, [0057]: The answer unit 360 provides a best answer or information indicating no result transmitted from the screener 350 to a user as an answer.).
Regarding claim 8, Kim in view of Ogura teaches wherein the rationale information includes information indicating the one or more evidential paragraphs or the rationale data used in generating the plurality of sentences (Kim, [0046]: The passage searcher 330 may automatically adjust an extraction range for extracting a passage based on the statistics that correct answer candidate values determined by the MRC question and answer algorithm used by each of at least one MRC question and answer unit 340 are determined as best answers.).
Regarding claim 10, Kim in view of Ogura teaches wherein the outputting of each of the separated sentences and the identified rationale information includes: visualizing text information included in the response data as an interactive object; and outputting the interactive object (Kim, [0057]: The answer unit 360 provides a best answer or information indicating no result transmitted from the screener 350 to a user as an answer.).
Regarding claim 11, Kim in view of Ogura teaches wherein the outputting each of the separated sentences and the identified rationale information includes classifying the rationale information by an attribute of the rationale information (Kim, [0055]: discussing about the screener 350 classifies the correct answer candidate values according to similarity of meanings based on a word-embedding value scheme, determines whether the majority of or at least a pre-set percentage of the correct answer candidate values classified by meanings have the same value, and, when the majority of or at least a pre-set percentage of the correct answer candidate values classified by meanings have the same value, selects the corresponding value as a best answer.), and displaying a list for each item of the classified rationale information ([0057]: The answer unit 360 provides a best answer or information indicating no result transmitted from the screener 350 to a user as an answer.).
Regarding claim 13, Kim in view of Ogura teaches receiving user input including additional query data by the user's selection of at least a portion of the output rationale information; and updating the specialized document based on the selected at least a portion of the output rationale information and generating an answer for the additional query data based on the updated specialized document (Kim, [0026]: The receiver 210 receives a user question, the analyzer 220 analyzes the user question, the passage searcher 230 selects at least one document from at least one domain corresponding to the analyzed user question, and a passage, which is a candidate answer determined as being suitable for the user question, is searched for in the at least one selected document. In this case, N passages (N is a natural number) may be retrieved.).
Regarding claim 14, Kim in view of Ogura teaches wherein the performing of the rationale generation or the performing of the systematic composition includes checking whether the rationale generation or the systematic composition has been performed based on a fact through an in-depth query for whether the generated rationale data or the generated response data is related to the specialized document (Kim, [0033]: The analyzer 320 may analyze the user question based on a morphological analysis, recognize the entity name, analyze a lexical meaning based on the recognized entity name, analyze the intention of the user question, extract a query by restoring an abbreviation or a substitute word, and map at least one domain information corresponding to the query based on a rule-based domain classifier.).
Regarding claim 15, Kim in view of Ogura teaches wherein the detecting of the specialized document associated with the query data includes retrieving and extracting the one or more evidential paragraphs that are related to the query data in the specialized document with reference to histories of previously stored query data and response data input and output prior to the query data ([0046]: The passage searcher 330 may automatically adjust an extraction range for extracting a passage based on the statistics that correct answer candidate values determined by the MRC question and answer algorithm used by each of at least one MRC question and answer unit 340 are determined as best answers.).
Regarding claim 16, Kim in view of Ogura teaches interpreting an intent of the query data, wherein the interpreting of the intent of the query data includes: identifying a plurality of sub-questions or requirements included in the query data; and establishing a plurality of multi-step plans based on the plurality of the identified sub-questions or requirements (Kim, [0033]: The analyzer 320 may analyze the user question based on a morphological analysis, recognize the entity name, analyze a lexical meaning based on the recognized entity name, analyze the intention of the user question, extract a query by restoring an abbreviation or a substitute word, and map at least one domain information corresponding to the query based on a rule-based domain classifier. [0064]: In FIG. 7, when a user question 710 “What is the height of Mt. Baekdu?” Is received, key words “Mt. Baekdu” and “height” may be extracted and “Mt. Baekdu” may be analyzed as an entity of the user question 710 and “height” may be analyzed as an intention of the user question 710.).
Regarding claim 17, Kim teaches A system comprising:
a memory configured to store instructions that are executable (Kim, [0081]: Examples of the computer-readable recording medium include a hardware device specially configured to store and perform program instructions, for example, a magnetic medium, such as a hard disk, a floppy disk, and magnetic tape, an optical recording medium, such as a CD-ROM, a DVD, and the like, a magneto-optical medium, such as a floptical disc, ROM, RAM, a flash memory, and the like.); and
at least one processor configured to execute one or more of the instructions to perform operations comprising (Kim, [0079]: For example, the devices and components described in the embodiments may be implemented by using one or more general purpose or special purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions.):
performing associative selection that detects a plurality of evidential paragraphs associated with query data specifying a user's question from a specialized document (Kim, [0046]: The passage searcher 330 may automatically adjust an extraction range for extracting a passage based on the statistics that correct answer candidate values determined by the MRC question and answer algorithm used by each of at least one MRC question and answer unit 340 are determined as best answers.);
performing rationale generation that generates rationale data based on the plurality of extracted evidential paragraphs (Kim, [0049]: According to an embodiment, the MRC question and answer unit 340 generates N*M correct answer candidate values by applying M MRC question and answer algorithms to N passages corresponding to one user question and transmits the N*M correct answer candidate values and reliability information indicating the probability of being a correct answer for each of the N*M correct answer candidate values to the screener 350.);
performing systematic composition that generates response data specifying an answer to the user's question based on the generated rationale data (Kim, [0051]: When there are a plurality of correct answer candidate values, the screener 350 first checks whether the majority of or at least a certain percentage of the plurality of correct answer candidate values are consistent through the consistency checker 352 (operation S630).); and
performing control to output the generated response data (Kim, [0057]: The answer unit 360 provides a best answer or information indicating no result transmitted from the screener 350 to a user as an answer.).
Kim does not explicitly teach wherein the rationale data includes at least one of explanation sentence data including explanation for the direct answer or auxiliary information data including background knowledge information related to the user's question.
Ogura teaches wherein the rationale data includes at least one of explanation sentence data including explanation for the direct answer or auxiliary information data including background knowledge information related to the user's question (Ogura, [0073]: The database search unit 12 having received the above information searches the table of the background knowledge database 23 using the received information (details will be described later), and transmits the acquired check result (id of the document (e.g., document_id described later), file name, sentence extracted from the document) to the user interface application 13. The user interface application 13 forwards the received search result to the content explanation display unit 322 of each client terminal 30. [0074]: The content explanation display unit 322 displays the received search result on the display screen 32. As illustrated in FIG. 2, the content explanation display unit 322 displays the file name of the received search result and the sentence extracted from the document on the screen as the explanation, with the text part designated as the ambiguous portion being used as the title.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the question and answer providing method of Kim with the teaching about the received search result of Ogura because it can present the content explanation information in a form that the user can understand (Ogura, [0063]).
Regarding claim 20, Kim in view of Ogura teaches wherein the processor is configured to: perform control to output at least one related document retrieved through a query-related document detection model on a user interface; and determine, when receiving user selection input for the at least one related document, the specialized document for generating the response data based on the received user selection input (Kim, [0026]: The receiver 210 receives a user question, the analyzer 220 analyzes the user question, the passage searcher 230 selects at least one document from at least one domain corresponding to the analyzed user question, and a passage, which is a candidate answer determined as being suitable for the user question, is searched for in the at least one selected document. In this case, N passages (N is a natural number) may be retrieved. [0057]: The answer unit 360 provides a best answer or information indicating no result transmitted from the screener 350 to a user as an answer.).
Claims 2-4 and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Kim in view of Ogura and further in view of Collard et al. (US 2022/0207465, hereinafter “Collard”).
Regarding claim 2, Kim in view of Ogura teaches the method of claim 1 as discussed above. Kim also teaches wherein the specialized document comprises a specialized document retrieved through a query-related document detection model based on the query data (Kim, [0026]: The receiver 210 receives a user question, the analyzer 220 analyzes the user question, the passage searcher 230 selects at least one document from at least one domain corresponding to the analyzed user question, and a passage, which is a candidate answer determined as being suitable for the user question, is searched for in the at least one selected document.).
Kim in view of Ogura does not explicitly teach wherein the specialized document comprises at least one of a specialized document uploaded by the user, a specialized document retrieved based on specialized document identification information input by the user.
Collard teaches wherein the specialized document comprises at least one of a specialized document uploaded by the user, a specialized document retrieved based on specialized document identification information input by the user (Collard, [0025]: The questions interface may provide documentation upload fields, permitting the user to upload documents containing information from which answers to the questions previously described can be calculated or otherwise determined by the platform rather than imposing the requirement on the user to answer every single question.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the question and answer providing method of Kim and Ogura with the teaching about uploading documents of Collard because it would transform document management from a physical, time-consuming task into a fast, secure, and efficient digital process, saving time, money, and resources.
Regarding claim 3, Kim in view of Ogura and Collard teaches wherein the detecting of the specialized document associated with the query data includes inputting the query data into the query-related document detection model, and retrieving at least one related document corresponding to the query data from the database through the query-related document detection model that has received the query data (Kim, [0026]: The receiver 210 receives a user question, the analyzer 220 analyzes the user question, the passage searcher 230 selects at least one document from at least one domain corresponding to the analyzed user question, and a passage, which is a candidate answer determined as being suitable for the user question, is searched for in the at least one selected document. In this case, N passages (N is a natural number) may be retrieved.).
Regarding claim 4, Kim in view of Ogura and Collard teaches wherein the detecting of the specialized document associated with the query data includes providing the retrieved at least one related document corresponding to the query data to the user (Kim, [0026]: The receiver 210 receives a user question, the analyzer 220 analyzes the user question, the passage searcher 230 selects at least one document from at least one domain corresponding to the analyzed user question, and a passage, which is a candidate answer determined as being suitable for the user question, is searched for in the at least one selected document. In this case, N passages (N is a natural number) may be retrieved.), and detecting the specialized document associated with the query data according to selection of the user (Kim, [0008]: According to one or more embodiments, a machine reading comprehension (MRC) question and answer providing method includes receiving a user question; analyzing the user question; selecting at least one document from at least one domain corresponding to an analyzed user question and searches for a passage, which is a candidate answer determined as being suitable for the user question, in the selected at least one document;).
Claim 18 is rejected under the same rationale as claim 2.
Claim 19 is rejected under the same rationale as claim 3.
Claims 9 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Kim in view of Ogura and further in view of Berajawala et al. (US 2016/0098737, hereinafter “Berajawala”).
Regarding claim 9, Kim in view of Ogura teaches the method of claim 7 as discussed above. Kim in view of Ogura does not explicitly teach wherein the outputting of each of the separated sentences and the identified rationale information includes, when a specific sentence is selected in accordance with user input through the user interface, highlighting the rationale information associated with the selected specific sentence.
Berajawala teaches wherein the outputting of each of the separated sentences and the identified rationale information includes, when a specific sentence is selected in accordance with user input through the user interface, highlighting the rationale information associated with the selected specific sentence (Berajawala, [0085]: FIG. 5B illustrate an example GUI output illustrating the supporting evidence passage for the question with the answer being highlighted in the text of the supporting evidence passage. As shown in FIG. 5B, the GUI output again reproduces the question followed by the citation to the evidence passage 550, e.g., Wikipedia in the depicted example, with the answer “Old Trafford” highlighted to show where in the evidence passage the answer to the question is found.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the question and answer providing method of Kim and Ogura with the teaching about highlighting the answer of Berajawala because it would make large amounts of reading more manageable, promote deeper understanding through selection, create a quick review tool for major points and help isolate crucial info from the bulk of text.
Regarding claim 12, Kim in view of Ogura teaches the method of claim 7 as discussed above. Kim in view of Ogura does not explicitly teach wherein the outputting each of the separated sentences and the identified rationale information includes, when any one sentence constituting the response data is positioned in a user selection region in accordance with user input, highlighting the sentence positioned in the user selection region and the rationale information matched to the sentence positioned in the user selection region.
Berajawala teaches wherein the outputting each of the separated sentences and the identified rationale information includes, when any one sentence constituting the response data is positioned in a user selection region in accordance with user input, highlighting the sentence positioned in the user selection region and the rationale information matched to the sentence positioned in the user selection region (Berajawala, [0085]: FIG. 5B illustrate an example GUI output illustrating the supporting evidence passage for the question with the answer being highlighted in the text of the supporting evidence passage. As shown in FIG. 5B, the GUI output again reproduces the question followed by the citation to the evidence passage 550, e.g., Wikipedia in the depicted example, with the answer “Old Trafford” highlighted to show where in the evidence passage the answer to the question is found.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the question and answer providing method of Kim and Ogura with the teaching about highlighting the answer of Berajawala because it would make large amounts of reading more manageable, promote deeper understanding through selection, create a quick review tool for major points and help isolate crucial info from the bulk of text.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, 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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Khanwalkar et al. (US 12,057,032) discloses that when a user uploads a document through an intelligent scanning workflow, as part of enhancing the document, in addition to identifying questions and determining recommendations for related documents, the auto-solving system is configured to automatically generate answers and explanations for identified questions that are determined to be unanswered.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PHONG H NGUYEN whose telephone number is (571)270-1766. The examiner can normally be reached Monday-Friday, 8:30am-5pm 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, Ajay Bhatia can be reached at (571) 272-3906. 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.
/PHONG H NGUYEN/ Primary Examiner, Art Unit 2156
June 17, 2026
Prosecution Insights