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 in this application.
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.
Claims 1-15 are rejected under 35 U.S.C. 101 because the claims are directed to an abstract idea without significantly more. Independent claim 9 recites “calculating a first similarity score between the user inquiry vector and a sentence vector corresponding to the key sentence extracted from passage of the document by inputting the user inquiry vector and the sentence vector to a bi-encoder of the bi-encoder type deep learning model;” “calculating a second similarity score between the user inquiry vector and a sentence vector corresponding to a sentence summarizing the passage of the document stored in the retrieval database;” “calculating a third similarity score between a question vector corresponding to the question generated from the passage stored in the retrieval database and the user inquiry vector;” “calculating a first weighted score based on the first similarity score, the second similarity score, and the third similarity score;” “determining a first document candidate group including first documents based on the calculated first weighted score;” “calculating a first score indicating similarity between the user retrieval query and a passage stored in the retrieval database through a phrase matching;” “calculating a second score indicating similarity between key query information including a keyword of the user retrieval query extracted through a user query analysis module and a keyword included in the passage stored in the retrieval database;” “calculating a third score indicating similarity between the user retrieval query and the passage stored in the retrieval database through a shingle matching;” “calculating a second weighted score based on the first score, the second score, and the third score;” “determining a second document candidate group including second documents based on the calculated second weighted score;” “calculating a fourth score indicating similarity between a passage of a document in the primary document candidate group and the user retrieval query by inputting the passage of the document in the primary document candidate group and the user retrieval query to a cross-encoder of cross-encoder type deep learning model;” “calculating a fifth score indicating similarity between the key query information including the keyword of the user retrieval query and a keyword included in the passage of the document in the primary document candidate group using a score calculation algorithm;” “determining a summarization target document based on one or more of the fourth score and the firth score;” and “acquiring one or more of an abstractive summarization-based first summary and an extractive summarization-based second summary from the determined summarization target document through a trained document summarization model.”
The limitations “calculating a first similarity score between the user inquiry vector and a sentence vector corresponding to the key sentence extracted from passage of the document by inputting the user inquiry vector and the sentence vector to a bi-encoder of the bi-encoder type deep learning model;” “calculating a second similarity score between the user inquiry vector and a sentence vector corresponding to a sentence summarizing the passage of the document stored in the retrieval database;” “calculating a third similarity score between a question vector corresponding to the question generated from the passage stored in the retrieval database and the user inquiry vector;” “calculating a first weighted score based on the first similarity score, the second similarity score, and the third similarity score;” “calculating a first score indicating similarity between the user retrieval query and a passage stored in the retrieval database through a phrase matching;” “calculating a second score indicating similarity between key query information including a keyword of the user retrieval query extracted through a user query analysis module and a keyword included in the passage stored in the retrieval database;” “calculating a third score indicating similarity between the user retrieval query and the passage stored in the retrieval database through a shingle matching;” “calculating a second weighted score based on the first score, the second score, and the third score;” “calculating a fourth score indicating similarity between a passage of a document in the primary document candidate group and the user retrieval query by inputting the passage of the document in the primary document candidate group and the user retrieval query to a cross-encoder of cross-encoder type deep learning model;” “calculating a fifth score indicating similarity between the key query information including the keyword of the user retrieval query and a keyword included in the passage of the document in the primary document candidate group using a score calculation algorithm;” and “acquiring one or more of an abstractive summarization-based first summary and an extractive summarization-based second summary from the determined summarization target document through a trained document summarization model”, as drafted, is a process that, under its broadest reasonable interpretation, covers mathematical calculations but from the recitation of implementing it on generic computer components. For example “calculating” various similarity scores and weighted scores in the context of this claim encompasses determining correlations between words using training data that performs mathematical calculations on vectorized words to determine similarity scores. Also, the “acquiring” of summaries through a trained document summarization model performs mathematical calculations on input vectors to determine summary vectors for corresponding sentence summaries. If a claim limitation, under its broadest reasonable interpretation, covers mathematical calculations but for the recitation of generic computer components, then it falls within the “Mathematical Concepts” grouping of abstract ideas. Accordingly, claim 9 recites an abstract idea.
The limitations “determining a first document candidate group including first documents based on the calculated first weighted score;” “determining a second document candidate group including second documents based on the calculated second weighted score;” “determining a summarization target document based on one or more of the fourth score and the firth score”, as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process but from the recitation of implementing it on generic computer components. That is nothing in the claim element precludes the step from practically being performed in the mind. For example “determining” in the context of this claim encompasses evaluating scores for given documents and then making a judgment on the documents or portions of documents to select based on the evaluation. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, claim 9 recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim recites additional elements – using a hardware processor. The processor is recited at a high-level of generality (i.e., as a generic computer device). The other additional elements “acquiring a user inquiry vector form a user retrieval query” and “extracting a key sentence of a passage of a document stored in a retrieval database from the passage document” represent mere extra-solution activity to the judicial exception. Receiving vectors and key sentence of a passage is necessary to inputs for the abstract idea steps. Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim 9 is directed to an abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a hardware processor amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The additional limitations, “acquiring a user inquiry vector form a user retrieval query” and “extracting a key sentence of a passage of a document stored in a retrieval database from the passage document”, represent insignificant extra solution activity of mere data gathering that amount to simply appending well-understood, routine, conventional activities previously known to the industry and specified at a high level of generality. The courts have routinely held that such data gathering steps do not provide the additional elements to overcome the judicial exception. Claim 9, as a whole, is directed to an abstract idea. Accordingly, claim 9 is not patent eligible.
Claims 1 and 8 recite similar subject matter and are similarly rejected as Claim 9 above.
Claims 2-7 and 10-15 depend on claims 1 and 9 and include all the limitations of claims 1 and 9. Therefore, claims 2-7 and 10-15 recite the same abstract idea practically being performed in the mind, and the analysis must therefore proceed to Step 2A Prong Two.
Claims 2-4, 10-12 additionally recite “acquiring the user inquiry vector in a unit of sentence from the user retrieval query;” “wherein the fourth source indicates semantic similarity between the passage of the document in the primary documents candidate group and the user retrieval query;” and “wherein the score calculation algorithm includes a BM25F score calculation algorithm”, respectively. This judicial exception is not integrated into a practical application. The additional limitations merely indicate a field of use or technological environment in which to apply a judicial exception that does not amount to significantly more than the exception itself. The claims merely associate the mathematical calculations with a particular data source or particular type of data. This limitation is merely an incidental or token additional to the claim that does not alter or affect the mental process steps performed. Claims 2-4 are ineligible.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements merely indicate a field of use or technological environment in which to apply a judicial exception that does not amount to significantly more than the exception itself. The claims merely limit the mathematical calculations to a particular data source or particular type of data. Claims 2-4 are not patent eligible.
Claims 5, 13 recite the additional limitation “wherein the determining the summarization target document includes: calculating a weighted sum similarity score of each document included in the primary document candidate group based on the fourth score and the fifth score; adjusting a ranking between documents included in the primary document candidate group based on the weighted sum similarity score; and determining the summarization target document based on the adjusted ranking”. This judicial exception is not integrated into a practical application. The additional elements represent further mathematical calculations and mental process steps of mathematically “calculating a weighted sum similarity score” and mentally evaluating and making a judgement for “adjusting a ranking” and “determining” the summarization target document based on evaluating the adjusted ranking. If a claim limitation, under its broadest reasonable interpretation, covers performance of mathematical calculations or performance in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” and “Mathematical Concepts” grouping of abstract ideas. This additional step is considered an abstract idea and does not integrate the judicial exception into a practical application. Accordingly, claims 5, 13 recite an abstract idea and is ineligible.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements represent a further mathematical calculations and mental process steps. If a claim limitation, under its broadest reasonable interpretation, covers performance of mathematical calculations or performance in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” and “Mathematical Concepts” grouping of abstract ideas. This additional step is considered an abstract idea and does not integrate the judicial exception into a practical application. An additional abstract idea is not sufficient to amount to significantly more than the judicial exception. Claims 5, 13 are not patent eligible.
Claims 6, 14 additionally recite “wherein the determining the summarization target document based on the adjusted ranking includes: determining n document in order of the adjusted ranking among the documents included in the primary document candidate group as the summarization target document”, respectively. This judicial exception is not integrated into a practical application. The additional limitations merely indicate a field of use or technological environment in which to apply a judicial exception that does not amount to significantly more than the exception itself. The claims merely associate the mathematical calculations with a particular data source or particular type of data. This limitation is merely an incidental or token additional to the claim that does not alter or affect the mental process steps performed. Claims 6, 14 are ineligible.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements merely indicate a field of use or technological environment in which to apply a judicial exception that does not amount to significantly more than the exception itself. The claims merely limit the mathematical calculations to a particular data source or particular type of data. Claims 6, 14 are not patent eligible.
Claims 7, 15 additionally recite “wherein the acquiring one or more of the abstractive summarization-based first summary and the extractive summarization-based second summary includes: inputting the determined summarization target document to an input layer of the trained document summarization model; acquiring a first summarization vector through a first output layer of the document summarization model; generating the abstractive summarization-based first summary based on the first summarization vector; acquiring a second summarization vector through a second output layer of the document summarization model; and generating the extractive summarization-based second summary based on the second summarization vector.” This judicial exception is not integrated into a practical application. The additional elements represent further mathematical calculations. The limitations require specific mathematical calculations to perform acquiring summarization vectors and generating summaries based on the vectors.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements represent a further performance of mathematical calculations. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. This additional step is considered an abstract idea (mental process step) and does not integrate the judicial exception into a practical application. An additional abstract idea (mental process step) is not sufficient to amount to significantly more than the judicial exception. Claims 7 and 15 are not patent eligible.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-2, 4-5, 8-10, 12-13 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 4-7 of U.S. Patent No. 12,259,917 in view of Simard et al., US 2022/0391756 (hereinafter Simard).
Instant Application
US 12,259,917
1. A method for summarizing a document, by an apparatus for summarizing a document, the method comprising:
acquiring a user inquiry vector from a user retrieval query;
extracting a key sentence of a passage of a document stored in a retrieval database from the passage of the document;
calculating a first similarity score between the user inquiry vector and a sentence vector corresponding to the key sentence extracted from the passage of the document by inputting the user inquiry vector and the sentence vector to a bi-encoder of a bi-encoder type deep learning model;
calculating a second similarity score between the user inquiry vector and a sentence vector corresponding to a sentence summarizing the passage of the document stored in the retrieval database;
generating a question from the passage of the document stored in the retrieval database through a generation model;
calculating a third similarity score between a question vector corresponding to the question generated from the passage stored in the retrieval database and the user inquiry vector;
calculating a first weighted score based on the first similarity score, the second similarity score, and the third similarity score;
determining a first document candidate group including first documents based on the calculated first weighted score;
calculating a first score indicating similarity between the user retrieval query and a passage stored in the retrieval database through a phrase matching;
calculating a second score indicating similarity between key query information including a keyword of the user retrieval query extracted through a user query analysis module and a keyword included in the passage stored in the retrieval database;
calculating a third score indicating similarity between the user retrieval query and the passage stored in the retrieval database through a shingle matching;
calculating a second weighted score based on the first score, the second score, and the third score;
determining a second document candidate group including second documents based on the calculated second weighted score;
acquiring a primary document candidate group including the first documents of the first document candidate group and the second documents of the second document candidate group;
calculating a fourth score indicating similarity between a passage of a document in the primary document candidate group and the user retrieval query by inputting the passage of the document in the primary document candidate group and the user retrieval query to a cross-encoder of cross-encoder type deep learning model;
calculating a fifth score indicating similarity between the key query information including the keyword of the user retrieval query and a keyword included in the passage of the document in the primary document candidate group using a BM25F score calculation algorithm;
determining a summarization target document based on one or more of the fourth score and the firth score; and
1. A method of retrieving, by an apparatus for retrieving a document, a document based on a user retrieval query, the method comprising:
acquiring a user retrieval query; calculating a user inquiry vector in a unit of sentence from the user retrieval query;
[…]
wherein the acquiring of the first document candidate group through the bi-encoder type deep learning model includes:
extracting a key sentence of a passage of the document stored in the retrieval database from the passage of the document,
calculating a first similarity score between the user inquiry vector and a sentence vector corresponding to the key sentence extracted from the passage of the document by inputting the user inquiry vector and the sentence vector to a bi-encoder of the bi-encoder type deep learning model,
calculating a second similarity score between the user inquiry vector and a sentence vector corresponding to a sentence summarizing the passage of the document stored in the retrieval database,
generating a question from the passage of the document stored in the retrieval database through a generation model,
calculating a third similarity score between a question vector corresponding to the question generated from the passage stored in the retrieval database and the user inquiry vector, and
calculating a first weighted score based on the first similarity score, the second similarity score, and the third similarity score, and
determining the first document candidate group based on the calculated first weighted score
and wherein the acquiring of the second document candidate group through the text matching-based retrieval includes:
calculating a first score indicating similarity between the user retrieval query and a passage stored in the retrieval database through a phrase matching;
calculating a second score indicating similarity between key query information including a keyword of the user retrieval query extracted through a user query analysis module and a keyword included in the passage stored in the retrieval database;
calculating a third score indicating similarity between the user retrieval query and the passage stored in the retrieval database through a shingle matching; and
calculating a second weighted score based on the first score, the second score, and the third score and
determining the second document candidate group based on the calculated second weighted score.
[…]
acquiring a first document candidate group including first documents from a retrieval database through a bi-encoder type deep learning model based on similarity between the calculated user inquiry vector and an embedding vector of a document stored in the retrieval database; acquiring a second document candidate group including second documents from the retrieval database through a text matching-based retrieval based on similarity between a text included in the user retrieval query and a text of the document stored in the retrieval database
[…]
3. The method of claim 2, wherein the retrieval ranking adjusting module is configured to calculate a fourth similarity score indicating semantic similarity between the candidate document and the user retrieval query from the candidate document included in the primary document candidate group and the user retrieval query using the cross-encoder type deep learning model.
4. The method of claim 3, wherein the retrieval ranking adjusting module is configured to calculate a fifth similarity score between the key query information extracted from the user retrieval query and a keyword included in the candidate document included in the primary document candidate group using a BM25F score calculation algorithm.
5. The method of claim 4, wherein the selecting of the summarization target document includes: calculating a weighted sum similarity score of each candidate document included in the primary document candidate group based on the fourth similarity score and the fifth similarity score; adjusting a ranking between the candidate documents included in the primary document candidate group based on the weighted sum similarity score; and determining the summarization target document based on the adjusted ranking.
Claim 1 of the reference patent recites all the limitations of claim 1 of the instant application except “acquiring one or more of an abstractive summarization-based first summary and an extractive summarization-based second summary from the determined summarization target document through a trained document summarization model.” However, Simard teaches a method of “acquiring one or more of an abstractive summarization-based first summary and an extractive summarization-based second summary from the determined summarization target document through a trained document summarization model” (see Simard, [0042], “summarizes information, in a selected document” that includes acquiring a “first summary” and a “second summary” through “training of the AI model,” [0069]). It would have been obvious to one skilled in the art at the time of the invention to generate a first and second summary for a document via a summarization model, as disclosed in Simard, with the method of claim 1 of the reference patent, to enable summarization based on specific contexts associated with the document (see Simard, [0042], “first summary represents context information from the first content location in the selected document” and “the second summary represents context information from the second boundary location of the region of interest to the second content location in the selected document”).
Claims 8 and 9 of the instant application are similarity rejected as Claim 1 above. Claims 8 and 9 correspond to claims 6 and 7, respectively, of the reference patent.
Claims 2, 10 of the instant application recites the same limitation as Claim 1 limitation of the reference patent that discloses “acquiring a user retrieval query; calculating a user inquiry vector in a unit of sentence from the user retrieval query.”
Claims 4, 12 of the instant application recites the same limitation as Claim 4 of the reference patent.
Claims 5, 13 of the instant application recites the same limitation as Claim 5 of the reference patent.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Lee et al., US 2023/0131259.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JENSEN HU whose telephone number is (571)270-3803. The examiner can normally be reached Monday - Friday 9-5 PT.
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, Sherief Badawi can be reached at 571-272-9782. 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.
/JENSEN HU/Primary Examiner, Art Unit 2169