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 .
Specification
The disclosure is objected to because of the following informalities:
Pgs. 5 – 8 (equations and labels)
Pg. 10 Algorithm – 1,
Pg. 14 Table – 1,
Pg. 16 Table – 2.
The contents on these pages are not sufficiently clear or legible, making the text difficult to read and understand. Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim(s) 1 – 9 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e. an abstract idea) without significantly more.
In step 1, of the 101-analysis set forth in the MPEP 2106, the examiner has determined
that the following limitations recite a process that, under the broadest reasonable interpretation, falls within one or more statutory categories (processes).
In step 2A prong 1, of the 101-analysis set forth in MPEP 2106, the examiner has determined
that the following limitations recite a process that, under broadest reasonable interpretation, recites abstract idea but for the recitation of generic computer components:
Regarding claim 1,
generating a query-focused summarization (QFS) for a passage;
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mental process: It involves reviewing a passage to identify information relevant to a query. See (MPEP 2106.04)).
generating an initial answer based on the passage and the QFS;
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mental process: It involves generating an answer based on the summarized information. See (MPEP 2106.04)).
generating a question corresponding to the initial answer based on the initial answer, the passage, and an interrogative word;
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mental process: It involves analyzing information and formulating a question based on an answer, passage and a specified interrogative word. See (MPEP 2106.04)).
generating an answer corresponding to the question based on the question and the passage and generating a question-answer (QA) pair; and
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mental process: It involves reviewing a question and a passage, determining an answer and associating the question with the answer to form a QA pair. See (MPEP 2106.04)).
deriving a final QA pair by selecting at least one QA pair from among the QA pairs.
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mental process: It involves reviewing multiple QA pairs and selecting one or more based on information associated with the QA pairs. See (MPEP 2106.04)).
If the claim limitations, under their broadest reasonable interpretation, covers performance of the limitations as a mental process, but for the recitation of generic computer components, then it falls within the mental process. Accordingly, the claim recites an abstract idea.
Step 2A Prong 2 of the 101-analysis, set forth in MPEP 2106, the examiner has determined that
the following additional elements do not integrate this judicial exception into a practical application:
A method for question-answer pair generation performed by a computing device, the method comprising:
(i.e.: deemed insufficient to transform the judicial exception to a patentable invention because the claim recites limitation which does not amount to more than a recitation of the words "apply it" (or an equivalent), such as mere instructions to implement an abstract idea on a computer. See MPEP 2106.05(f)).
In Step 2B of the 101 – analysis set forth in the 2019 PEG, the examiner has determined that the
claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception:
Regarding limitation (I), recite mere application of the abstract idea or mere instructions to implement an abstract idea on a computer are deemed insufficient to transform the judicial exception to a patentable invention because the limitations generally apply the use of a generic computer and/or process with the judicial exception, see MPEP 2106.05(f).
As analyzed above, the additional elements, analyzed above, do not integrate the noted judicial exception into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Therefore, the claim is directed to an abstract idea.
Regarding claim 2, dependent upon claim 1, and fail to resolve the deficiencies identified above by integrating the judicial exception into a practical application, or introducing significantly more than the judicial exception. The claim recites:
wherein the generating of the QFS comprises generating the number of QFSs corresponding to the number of sentences included in the passage.
The recitation in the additional limitation simply links the judicial exception to a field of use and/or technology environment, see MPEP 2106.05(h).
Limitations directed to field of use cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Regarding claim 3, dependent upon claim 1, and fail to resolve the deficiencies identified above by integrating the judicial exception into a practical application, or introducing significantly more than the judicial exception. The claim recites:
wherein the generating of the initial answer comprises receiving a passage and a QFS, inputting the passage and the QFS into an answer generation model pretrained
The recitation in the additional limitation directed to mere data gathering as deemed insufficient to transform the judicial exception because claimed elements are considered insignificant extra-solution activity and well-understood routine and conventional (2106.05(d)).
Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TL| Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network). See MPEP 2106.05(d)(II).
The additional limitations as analyze failed to integrate a judicial exception into a practical application at Step 2A and provide an inventive concept in Step 2B, per the analysis above.
to generate an initial answer, and generating the initial answer.
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mental process: It involves determining an answer based on available information. See (MPEP 2106.04)).
Regarding claim 4, dependent upon claim 1, and fail to resolve the deficiencies identified above by integrating the judicial exception into a practical application, or introducing significantly more than the judicial exception. The claim recites:
wherein the generating of the question comprises receiving an initial answer, a passage, and an interrogative word, inputting the initial answer, the passage, and the interrogative word into a question generation model pretrained
The recitation in the additional limitation directed to mere data gathering as deemed insufficient to transform the judicial exception because claimed elements are considered insignificant extra-solution activity and well-understood routine and conventional (2106.05(d)).
Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TL| Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network). See MPEP 2106.05(d)(II).
The additional limitations as analyze failed to integrate a judicial exception into a practical application at Step 2A and provide an inventive concept in Step 2B, per the analysis above.
to generate a question, and generating the question, and
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mental process: It involves formulating a question based on available information. See (MPEP 2106.04)).
the interrogative word includes what, why, when, who, where, and how.
The recitation in the additional limitation simply links the judicial exception to a field of use and/or technology environment, see MPEP 2106.05(h).
Limitations directed to field of use cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Regarding claim 5, dependent upon claim 1, and fail to resolve the deficiencies identified above by integrating the judicial exception into a practical application, or introducing significantly more than the judicial exception. The claim recites:
wherein the generating of the QA pair comprises receiving a question and a passage, inputting the question and the passage into a question- answering model pretrained
The recitation in the additional limitation directed to mere data gathering as deemed insufficient to transform the judicial exception because claimed elements are considered insignificant extra-solution activity and well-understood routine and conventional (2106.05(d)).
Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TL| Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network). See MPEP 2106.05(d)(II).
The additional limitations as analyze failed to integrate a judicial exception into a practical application at Step 2A and provide an inventive concept in Step 2B, per the analysis above.
to generate an answer, and generating the answer.
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mental process: It involves formulating an answer based on available information. See (MPEP 2106.04)).
Regarding claim 6, dependent upon claim 1, and fail to resolve the deficiencies identified above by integrating the judicial exception into a practical application, or introducing significantly more than the judicial exception. The claim recites:
wherein the deriving of the final QA pair comprises: deriving the ranking score of the QA pair; and selecting a QA pair with the highest ranking score.
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mental process: It involves assigning a numerical ranking to information and comparing the resulting scores to select the highest ranked QA pair. See (MPEP 2106.04)).
Regarding claim 7, dependent upon claim 6, and fail to resolve the deficiencies identified above by integrating the judicial exception into a practical application, or introducing significantly more than the judicial exception. The claim recites:
wherein the deriving of the ranking score comprises inputting the QA pair into a ranking model pretrained
The recitation in the additional limitation directed to mere data gathering as deemed insufficient to transform the judicial exception because claimed elements are considered insignificant extra-solution activity and well-understood routine and conventional (2106.05(d)).
Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TL| Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network). See MPEP 2106.05(d)(II).
The additional limitations as analyze failed to integrate a judicial exception into a practical application at Step 2A and provide an inventive concept in Step 2B, per the analysis above.
to perform binary classification regarding whether an input QA pair is a correct example or an incorrect example and deriving the ranking score.
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mental process: It involves evaluating an input QA pair, classifying it into one of two categories based on whether it is correct or incorrect, and determining a ranking score. See (MPEP 2106.04)).
Regarding claim 8, dependent upon claim 7, and fail to resolve the deficiencies identified above by integrating the judicial exception into a practical application, or introducing significantly more than the judicial exception. The claim recites:
wherein the deriving of the ranking score represents a probability that the QA pair is classified as the correct example.
The recitation in the additional limitation simply links the judicial exception to a field of use and/or technology environment, see MPEP 2106.05(h).
Limitations directed to field of use cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Regarding claim 9, dependent upon claim 6, and fail to resolve the deficiencies identified above by integrating the judicial exception into a practical application, or introducing significantly more than the judicial exception. The claim recites:
wherein the deriving of the ranking score comprises: measuring the Rouge-L score between the QA pair with the highest ranking score and remaining QA pairs;
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mental process: It involves comparing textual information between QA pairs and calculating a similarity score based on the comparison. See (MPEP 2106.04)).
deriving the adjusted ranking score of each QA pair by subtracting the product between the Rouge-L score and an absolute value of the ranking score from the ranking score;
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mathematical concept: It involves performing mathematical operations, including multiplication, determining an absolute value and subtraction to calculate an adjusted ranking score. See (MPEP 2106.04)).
selecting a QA pair with the highest adjusted ranking score.
(i.e.: the broadest reasonable interpretation, the claim recites abstract idea: mathematical concept: It involves comparing adjusted ranking scores and selecting the QA pair having the highest score. See (MPEP 2106.04)).
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.
Claim(s) 1 – 5 are rejected under 35 U.S.C. 103 as being unpatentable over Shevelev et al., Pub.
No.: US20220391595A1 in view of Boguraev et al., Pub. No.: US20170193088A1.
Regarding claim 1, Shevelev teaches: A method for question-answer pair generation performed by a computing device, the method comprising: generating a query-focused summarization (QFS) for a passage;
(Shevelev, “[0040] The question and answer generator engine 127 applies the text-summarization model 132 to the identified text to generate a summary of the text [generating a query-focused summarization (QFS) for a passage]. The question and answer generator engine 127 may provide the summary of the text, with a link to the entire text, to the human-readable question and answer generator model 128 to generate a human-readable answer including the summary of the text. The user communication interface application 121 generates a comment or reply, that includes the human-readable answer, in the user communication application 110.”)
generating an initial answer based on the passage and the QFS;
(Shevelev, “[0040] … The question and answer generator engine 127 applies the text-summarization model 132 to the identified text to generate a summary of the text. The question and answer generator engine 127 may provide the summary of the text [and the QFS], with a link to the entire text, to the human-readable question and answer generator model 128 to generate a human-readable answer including the summary of the text [generating an initial answer based on the passage]. The user communication interface application 121 generates a comment or reply, that includes the human-readable answer, in the user communication application 110.”)
generating a question corresponding to the initial answer based on the initial answer
(Shevelev, “[0061] The system obtains an updated user-generated question (Operation 212). For example, the system may combine the original question with any follow-up answers [corresponding to the initial answer based on the initial answer,] to generate the updated user-generated question [generating a question]”)
deriving a final QA pair by selecting at least one QA pair from among the QA pairs.
(Shevelev, “[0036] A question and answer analysis engine 124 analyzes questions and answers to initiate actions associated with the questions and answers. The question and answer analysis engine 124 pairs a single question with a single answer and stores the pairing in the data repository 126 together with any associated feedback [deriving a final QA pair by selecting at least one QA pair from among the QA pairs]. In one embodiment, a single answer is made up of multiple separate comments made by a same user. In one embodiment, any comments made by different users are stored in separate question and answer pairs.”)
Shevelev does not teach:
… the passage, and an interrogative word
generating an answer corresponding to the question based on the question and the passage and
Boguraev teaches:
… the passage, and an interrogative word
(Boguraev, “[0051] In addition to the above term matching, for a question and passage pair, [… the passage, and an interrogative word] where the passage contains one or more candidate answers to the question, QA system 102 may also have an additional custom term matcher called the “question-candidate” term matcher. This special purpose term matcher matches the “focus term” in the question (usually the wh-word or phrase) with the candidate answer in the passage.”)
generating an answer corresponding to the question based on the question and the passage and
(Boguraev, “[0043] QA system's 102 components are described below in conjunction with the Figures and EXAMPLE 2. This example includes an illustrative question-and-answer pair that QA system 102 may receive (by passage retrieval component 104 or another component), a corresponding query that QA system 102 may generate, a passage returned based on the query (the passage may be one of many stored in text corpus 120), and an entailment pair that QA system 102 may generate based on analysis it performs on the question-answer pair and the returned passage [corresponding to the question based on the question and the passage and generating a question-answer (QA) pair]. This example will be referenced from time to time throughout the remainder of the discussion that follows to illustrate functions of QA system 102 generally, and its various components specifically.”)
Boguraev and Shevelev are related to the same field of endeavor (i.e.: query execution using natural language analysis). It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teaching of Boguraev with teachings of Shevelev to determine whether a candidate answer is supported by relevant passages rather than only relying on the existence of an answer to improve model reliability and accuracy (Boguraev, Abstract).
Regarding claim 2, Shevelev in view of Boguraev teach the method of claim 1.
Boguraev further teaches: wherein the generating of the QFS comprises generating the number of QFSs corresponding to the number of sentences included in the passage.
(Boguraev, “[0043] QA system's 102 components are described below in conjunction with the Figures and EXAMPLE 2. This example includes an illustrative question-and-answer pair that QA system 102 may receive (by passage retrieval component 104 or another component), a corresponding query that QA system 102 [wherein the generating of the QFS comprises generating the number of QFSs] may generate, a passage returned based on the query (the passage may be one of many stored in text corpus 120) [corresponding to the number of sentences included in the passage], and an entailment pair that QA system 102 may generate based on analysis it performs on the question-answer pair and the returned passage. This example will be referenced from time to time throughout the remainder of the discussion that follows to illustrate functions of QA system 102 generally, and its various components specifically.”)
It would have been obvious to one of ordinary skill in the art before the effective filling date of the present application to combine the teachings of Boguraev with teachings of Shevelev for the same reasons disclosed for claim 1.
Regarding claim 3, Shevelev in view of Boguraev teach the method of claim 1.
Boguraev further teaches: wherein the generating of the initial answer comprises receiving a passage and a QFS,
(Boguraev, “[0043] QA system's 102 components are described below in conjunction with the Figures and EXAMPLE 2. This example includes an illustrative question-and-answer pair that QA system 102 may receive (by passage retrieval component 104 or another component), a corresponding query that QA system 102 [receiving a passage and a QFS,] may generate, a passage returned based on the query (the passage may be one of many stored in text corpus 120), and an entailment pair that QA system 102 may generate based on analysis it performs on the question-answer pair and the returned passage.”)
Shevelev further teaches: inputting the passage and the QFS into an answer generation model pretrained to generate an initial answer, and generating the initial answer.
(Shevelev, “[0040] … The question and answer generator engine 127 applies the text-summarization model 132 [inputting the passage and the QFS into an answer generation model pretrained] to the identified text to generate a summary of the text. The question and answer generator engine 127 may provide the summary of the text [and the QFS], with a link to the entire text, to the human-readable question and answer generator model 128 to generate a human-readable answer including the summary of the text [to generate an initial answer, and generating the initial answer]. The user communication interface application 121 generates a comment or reply, that includes the human-readable answer, in the user communication application 110.”)
It would have been obvious to one of ordinary skill in the art before the effective filling date of the present application to combine the teachings of Boguraev with teachings of Shevelev for the same reasons disclosed for claim 1.
Regarding claim 4, Shevelev in view of Boguraev teach the method of claim 1.
Boguraev further teaches: wherein the generating of the question comprises receiving an initial answer, a passage, and an interrogative word, inputting the initial answer, the passage, and the interrogative word into a question generation model pretrained
(Boguraev, “[0047] Referring to EXAMPLE 2, above, passage retrieval component 104 [inputting the initial answer, the passage, and the interrogative word into a question generation model pretrained] may receive the question “What is a common benign cause of congenital hyperbilirubinemia?” [and an interrogative word] and the answer “Gilbert's Syndrome” as an input; [receiving an initial answer] generate the query “#combine [passage20:6] (cause common benign hyperbilirubinemia congenital indirect gilberts syndrome)”; and retrieve the passage [a passage] “In many patients, Gilbert's syndrome is commonly a benign explanation for congenital hyperbilirubinemia.” In this example, “passage20:6” is part of the query instruction to the passage retrieval engine that tells the retrieval engine what size of passages to retrieve; about 20 word passages by including words in 6 word increments (until sentence boundary is reached).”)
generating the question, and the interrogative word includes what, why, when, who, where, and how.
(Boguraev, “[0051] In addition to the above term matching, for a question and passage pair, where the passage contains one or more candidate answers to the question, QA system 102 may also have an additional custom term matcher called the “question-candidate” term matcher. This special purpose term matcher matches the “focus term” in the question (usually the wh-word or phrase) [generating the question, and the interrogative word includes what, why, when, who, where, and how] with the candidate answer in the passage.”)
Shevelev further teaches: … to generate a question, and
(Shevelev, “[0061] The system obtains an updated user-generated question (Operation 212). For example, the system may combine the original question with any follow-up answers to generate the updated user-generated question [to generate a question,]”)
It would have been obvious to one of ordinary skill in the art before the effective filling date of the present application to combine the teachings of Boguraev with teachings of Shevelev for the same reasons disclosed for claim 1.
Regarding claim 5, Shevelev in view of Boguraev teach the method of claim 1.
Boguraev further teaches: wherein the generating of the QA pair comprises receiving a question and a passage, inputting the question and the passage into a question- answering model pretrained to generate an answer, and generating the answer.
(Boguraev, “[0051] In addition to the above term matching, for a question and passage pair, [receiving a question and a passage, inputting the question and the passage into a question- answering model pretrained] where the passage contains one or more candidate answers to the question [to generate an answer, and generating the answer], QA system 102 may also have an additional custom term matcher called the “question-candidate” term matcher. This special purpose term matcher matches the “focus term” in the question (usually the wh-word or phrase) with the candidate answer in the passage.”)
It would have been obvious to one of ordinary skill in the art before the effective filling date of the present application to combine the teachings of Boguraev with teachings of Shevelev for the same reasons disclosed for claim 1.
Claim(s) 6 – 7 are rejected under 35 U.S.C. 103 as being unpatentable over Shevelev in view of Boguraev and in further view of Wang et al., Pub. No.: US20230135625A1.
Regarding claim 6, Shevelev in view of Boguraev teach the method of claim 1.
Shevelev in view of Boguraev do not teach:
wherein the deriving of the final QA pair comprises: deriving the ranking score of the QA pair; and selecting a QA pair with the highest ranking score
Wang teaches:
wherein the deriving of the final QA pair comprises: deriving the ranking score of the QA pair; and selecting a QA pair with the highest ranking score.
(Wang, “[0011] … In some embodiments, the AI may perform four operations: (i) parsing a new input document; (ii) extracting key concepts from the input document, and then using those key concepts to generate candidate answers; (iii) for each candidate answer, generating one or more questions that may lead to that answer, thereby forming a plurality of question and answer (QA) pairs; and (iv) ranking all of the QA pairs, and then selecting/returning a predetermined number of the highest ranked QA pairs [wherein the deriving of the final QA pair comprises: deriving the ranking score of the QA pair; and selecting a QA pair with the highest ranking score]...”)
Wang, Shevelev and Boguraev are related to the same field of endeavor (i.e.: query execution using natural language analysis). It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teaching of Wang with teachings of Shevelev and Boguraev to automate and structure the generation of question-answer content to populate the knowledge based and dialogue interactions more efficiently. (Wang, Abstract).
Regarding claim 7, Shevelev in view of Boguraev and Wang teach the method of claim 6.
Wang further teaches: wherein the deriving of the ranking score comprises inputting the QA pair into a ranking model pretrained to perform binary classification regarding whether an input QA pair is a correct example or an incorrect example and deriving the ranking score.
(Wang, “[0093] … (iii) parse a new input document (e.g., feeding the document's text into the document reading subsystem 720, generating a plurality of QA pairs therefrom, then selecting a plurality of the highest ranked QA pairs [and deriving the ranking score] as “anchor” questions 735 for inclusion in the dialogue flow structure 750, and identifying corresponding document location for each anchor question 735); (iv) generate a plurality of alternative answers and incorrect answers for each anchor question 735; (v) feed the anchor questions, correct answers 742, alternative correct answers 744, incorrect answers 746 into the dialogue flow structure 750; [inputting the QA pair into a ranking model pretrained to perform binary classification regarding whether an input QA pair is a correct example or an incorrect example] and (vi) by the dialogue subsystem 740, read the input document to a new SRE, pausing when it reaches one of the document locations associated with the anchor questions 735 and then triggering the dialogue subsystem 740 to handle new SREs responses pursuant to dialogue flow structure 750.”)
It would have been obvious to one of ordinary skill in the art before the effective filling date of the present application to combine the teachings of Wang with teachings of Shevelev and Boguraev for the same reasons disclosed for claim 6.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Shevelev in view of Boguraev, Wang and in further view of Oh et al., Pub. No.: US20200034722A1.
Regarding claim 8, Shevelev in view of Boguraev and Wang teach the method of claim 7.
Shevelev in view of Boguraev and Wang do not teach:
wherein the deriving of the ranking score represents a probability that the QA pair is classified as the correct example
Oh teaches:
wherein the deriving of the ranking score represents a probability that the QA pair is classified as the correct example.
(Oh, “[0043] … An answer passage refers to a text passage extracted from existing documents as a possible answer to a question. The selected causality expression is input along with the question and its answer passage to a convolutional neural network. A score indicating probability that it is a correct answer to the question is added to each answer passage, and an answer that seems to be the best answer to the question is selected [wherein the deriving of the ranking score represents a probability that the QA pair is classified as the correct example]. In the following description, causality expressions extracted from a text archive are called archive causality expressions, and causality expressions extracted from answer passages are called in-passage causality expressions. In the following embodiment, archive causality expressions that are most relevant to both a question and its answer passage are extracted and used. They will be called relevant causality expressions.”)
Oh, Shevelev, Boguraev and Wang are related to the same field of endeavor (i.e.: query execution using natural language analysis). It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teaching of Oh with teachings of Shevelev, Boguraev and Wang to improve the ability to select reliable answers from available information by evaluating candidate answers based on causal relationships and semantic relevance. (Oh, Abstract).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Shevelev in view of Boguraev, Wang and in further view of Cucerzan et al., Pub. No.: US20070214131A1.
Regarding claim 9, Shevelev in view of Boguraev and Wang teach the method of claim 6.
Wang further teaches: wherein the deriving of the ranking score comprises: measuring the Rouge-L score between the QA pair with the highest ranking score and remaining QA pairs;
(Wang, “[0089] At operation 630, the DPS 100 may rank the plurality the question-answer pairs based on one or more criteria, such as a RougeL sore and/or how closely the QA pairs resemble the questions received at operation 605 [measuring the Rouge-L score between the QA pair with the highest ranking score and remaining QA pairs]. In some embodiments, this ranking may be performed by an ML model. Next, a predetermined number of the highest ranked QA pairs may be selected, and then returned to a user, at operation 635.”)
selecting a QA pair with the highest adjusted ranking score.
(Wang, “[0089] At operation 630, the DPS 100 may rank the plurality the question-answer pairs based on one or more criteria, such as a RougeL sore and/or how closely the QA pairs resemble the questions received at operation 605. In some embodiments, this ranking may be performed by an ML model. Next, a predetermined number of the highest ranked QA pairs may be selected [selecting a QA pair with the highest adjusted ranking score], and then returned to a user, at operation 635.”)
It would have been obvious to one of ordinary skill in the art before the effective filling date of the present application to combine the teachings of Wang with teachings of Shevelev and Boguraev for the same reasons disclosed for claim 6.
Shevelev in view of Boguraev and Wang do not teach:
deriving the adjusted ranking score of each QA pair by subtracting the product between the Rouge-L score and an absolute value of the ranking score from the ranking score; and
Cucerzan teaches:
deriving the adjusted ranking score of each QA pair by subtracting the product between the Rouge-L score and an absolute value of the ranking score from the ranking score; and
(Cucerzan, “[0079] Such diversity can be accomplished by employing an iterative process or re-ranking scheme [from the ranking score] to build the search result set to be output or displayed to a user [deriving the adjusted ranking score of each QA pair by subtracting the product between the Rouge-L score]. In each iteration, one search result can be added to that set or re-ranked list in each iteration based on its similarity with the query language model associated with that iteration, which can then be modified by discounting the terms that matched the search result selected.”)
Cucerzan, Shevelev, Boguraev and Wang are related to the same field of endeavor (i.e.: query execution using natural language analysis). It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teaching of Cucerzan with teachings of Shevelev, Boguraev and Wang to improve the relevance of information retrieval for answering user questions. (Cucerzan, Abstract).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Kryscinski et al., Pub. No.: US20220277135.
Kryscinski teaches a query-focused summarization model that employs a single or dual encoder model. A two-step approach may be adopted that first extracts parts of the source document and then synthesizes the extracted segments into a final summary.
Xiao et al., Pub. No.: US20210216577.
Xiao teaches predicting answers in response to one or more input queries, text from a corpus of text can be processed by a reader to generate one or multiple questions and answer spaces. A question and answer space can include answerable questions and the answers associated with the questions (referred to as “question and answer pairs”).
Any inquiry concerning this communication or earlier communications from the examiner
should be directed to MATIYAS T MARU whose telephone number is (571)270-0902 or via email: matiyas.maru@uspto.gov. The examiner can normally be reached Monday 8:00am - Friday 4:00pm 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,
Michelle Bechtold can be reached on (571)431-0762. The fax phone number for the organization were 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.
/M.T.M./ Examiner, Art Unit 2148 /MICHELLE T BECHTOLD/Supervisory Patent Examiner, Art Unit 2148
Prosecution Insights