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 .
DETAILED ACTION
This office action is in response to correspondence 02/25/26 regarding application 18/663,988, in which in response to a requirement for restriction/election, Applicant elected group I, which includes claims 1-10 and 21-25, cancelled non-elected claims 11-20 and 26-30 and added new claims 31-45. Claims 1-10, 21-25, 31-45 are pending in the application and have been considered.
Election/Restrictions
Applicant’s election without traverse of group I, which includes claims 1-10 and 21-25 in the reply filed on 02/25/26 is acknowledged.
Foreign Priority
Receipt is acknowledged of certified copies of papers submitted under 35 U.S.C. 119(a)-(d), which papers have been placed of record in the file.
Claim Objections
Claim 31 is objected to because of the following informalities:
-in lines 4 and 8, should “identifying, and based on” be “identifying, based on”?
-in line 12, should “selecting, and from” be “selecting, from”?
-in line 16, should “providing, the” be “providing the”?
Appropriate correction is required.
Claim 41 is objected to because of the following informalities:
-in lines 4 and 8, should “identifying, and based on” be “identifying, based on”?
-in line 12, should “selecting, and from” be “selecting, from”?
-in line 16, should “providing, the” be “providing the”?
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.
Claims 1-10, 21-25, 31-45 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
Claim 1 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites “identifying, by a summary selection system and based upon a plurality of prioritized entity categories identified in reference information, a set of prioritized entities present in content to be summarized and corresponding to one or more prioritized entity categories from the plurality of prioritized entity categories, the summary selection system comprising one or more computer systems; identifying, by the summary selection system and based upon a plurality of prioritized entity relationship categories identified in the reference information, a set of prioritized entity relationships present in the content to be summarized and corresponding to one or more prioritized entity relationship categories from the plurality of prioritized entity relationship categories; selecting, by the summary selection system and from a plurality of summaries generated for the content to be summarized, a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships; and providing, by the summary selection system, the selected summary as a summary for the content to be summarized”.
The limitation of “identifying, by a summary selection system and based upon a plurality of prioritized entity categories identified in reference information, a set of prioritized entities present in content to be summarized and corresponding to one or more prioritized entity categories from the plurality of prioritized entity categories, the summary selection system comprising one or more computer systems”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for the “by a summary selection system”, and “the summary selection system comprising one or more computer systems” language, “identifying, … based upon a plurality of prioritized entity categories identified in reference information, a set of prioritized entities present in content to be summarized and corresponding to one or more prioritized entity categories from the plurality of prioritized entity categories….” in the context of this claim encompasses mentally identifying a set of prioritized entities present in content to be summarized and corresponding to one or more prioritized entity categories from the plurality of prioritized entity categories based upon a plurality of prioritized entity categories identified in reference information such as a printed dictionary of prioritized terms.
Similarly, but for the “by the summary selection system” language, the limitation of identifying, by the summary selection system and based upon a plurality of prioritized entity relationship categories identified in the reference information, a set of prioritized entity relationships present in the content to be summarized and corresponding to one or more prioritized entity relationship categories from the plurality of prioritized entity relationship categories, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “identifying, …. based upon a plurality of prioritized entity relationship categories identified in the reference information, a set of prioritized entity relationships present in the content to be summarized and corresponding to one or more prioritized entity relationship categories from the plurality of prioritized entity relationship categories” in the context of this claim encompasses mentally identifying a set of prioritized entity relationships present in the content to be summarized and corresponding to one or more prioritized entity relationship categories from the plurality of prioritized entity relationship categories based upon a plurality of prioritized entity relationship categories identified in the reference information.
Similarly, but for the “by the summary selection system” language, the limitation of “selecting, by the summary selection system and from a plurality of summaries generated for the content to be summarized, a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “selecting, … from a plurality of summaries generated for the content to be summarized, a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships” in the context of this claim encompasses mentally selecting and circling with a pen on a sheet of paper, a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships from a plurality of summaries generated for the content to be summarized.
Finally, but for the “by the summary selection system” language, the limitation of “providing, by the summary selection system, the selected summary as a summary for the content to be summarized”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, “providing, …, the selected summary as a summary for the content to be summarized” in the context of this claim encompasses copying down the selected summary and providing it as a summary for the content.
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, the claim recites an abstract idea. This judicial exception is not integrated into a practical application. In particular, the claim only recites two additional elements – “summary selection system” which comprises “one or more computer systems”. The computing elements in this step are recited at a high-level of generality (i.e., as one or more generic computer systems) such that they amount to no more than mere instructions to apply the exception using generic computer elements. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea. The claim does 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 computing device to perform the identifying, selecting, and providing 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 claim is not patent eligible.
Specifically with respect to Step 2A, Prong Two, of the Alice/Mayo test, the judicial exception is not integrated into a practical application. Claim 1 does not recite any limitations that are not mental steps.
Specifically with respect to Step 2B of the Alice/Mayo test, “the claim as a whole does not amount to significantly more than the exception itself (there is no inventive concept in the claim)”. MPEP 2106.05 Il. There are no limitations in claim 1 outside of the judicial exception. As a whole, there does not appear to contain any inventive concept. As discussed above, claim 1 is a mental process that pertains to the mental process of summarizing content, which can be performed entirely by a human with physical aids.
Dependent claims 2-10 depend from claim 1, do not remedy any of the deficiencies of claim 1, and therefore are rejected on the same grounds as claim 1 above.
Generally, claims 2-10 merely recite additional steps for summarizing content, all of which could be performed mentally or by writing down relationships with a pen and paper, and do not amount to anything more than substantially the same abstract idea as explained with respect to claim 1.
Specifically:
Claim 2 recites “the plurality of summaries for the content to be summarized are generated using a machine learning (ML) model and a plurality of input parameters” which does not integrate the judicial exception into a practical application because the additional elements – “machine learning (ML) model” and “plurality of input parameters” are recited at a high-level of generality (i.e., a generic machine learning (ML) model and a generic plurality of input parameters) such that they amount to no more than mere instructions to apply the exception using generic computer elements. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Claim 3 recites “the input parameters comprise one or more of: a prompt provided to the ML model, a summarization strategy used by the ML model to generate the plurality of summaries, and a temperature setting used by the ML model to generate the plurality of summaries” which does not integrate the judicial exception into a practical application because the additional elements – “a prompt provided to the ML model”, “a summarization strategy used by the ML model “, and “a temperature setting used by the ML model” are recited at a high-level of generality (i.e., a generic a prompt provided to the ML model, a generic summarization strategy used by the ML model, and a generic temperature setting used by the ML model) such that they amount to no more than mere instructions to apply the exception using generic computer elements. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Claim 4 recites “selecting the summary from the plurality of summaries comprises: generating, by the summary selection system, a plurality of clusters, wherein each cluster in the plurality of clusters comprises one or more summaries from the plurality of summaries; selecting, by the summary selection system, a cluster from the plurality of clusters that comprises the largest number of summaries; processing, by the summary selection system, the one or more summaries from the plurality of summaries present in the selected cluster; and based on the processing, selecting, by the summary selection system, a summary from the one or more summaries present in the selected cluster as the summary for the content to be summarized” which, but for “by the summary selection system”, could be performed by writing down multiple summaries, placing them into multiple piles according to some distance criteria (e.g. word count distribution), and selecting a summary from the largest pile.
Claim 5 recites “generating, by the summary selection system, the plurality of clusters comprises: extracting, for each summary in the plurality of summaries, a set of unigrams and a set of bigrams for the summary; generating a vocabulary comprising a union of the set of unigrams and the set of bigrams extracted from the plurality of summaries; and generating, for each summary in the plurality of summaries, an incidence vector for the summary, wherein the incidence vector represents the set of unigrams and the set of bigrams from the vocabulary that are present in the summary” which, but for “by the summary selection system”, could be performed by writing down a set of unigrams and a set of bigrams for the summary; writing down a vocabulary comprising a union of the set of unigrams and the set of bigrams extracted from the plurality of summaries; and writing down for each summary in the plurality of summaries, an incidence vector for the summary, wherein the incidence vector represents the set of unigrams and the set of bigrams from the vocabulary that are present in the summary.
Claim 6 recites “using, by the summary selection system, a clustering technique to cluster the plurality of summaries using the incidence vectors generated for each summary in the plurality of summaries to generate the plurality of clusters” which, but for “by the summary selection system”, could be performed by sorting the summaries into piles of clusters according to a criteria based on the incidence vectors.
Claim 7 recites “processing, by the summary selection system, the one or more summaries from the plurality of summaries present in the selected cluster comprises: for each summary in the one or more summaries in the selected cluster, extracting one or more entities from the summary; for each summary in the one or more summaries in the selected cluster, extracting one or more entity relationships from the summary; identifying a summary from the one or more summaries in the selected cluster that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships present in the content to be summarized; and selecting the summary as the summary for the content to be summarized” which, but for “by the summary selection system”, could be performed by copying down one or more entities from the summary, and for each summary in the one or more summaries in the selected cluster, copying down one or more entity relationships from the summary, mentally identifying a summary from the one or more summaries in the selected pile that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships present in the content to be summarized, and mentally selecting the summary as the summary for the content to be summarized.
Claim 8 recites “the processing further comprises: determining that no summary in the one or more summaries in the selected cluster includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships present in the content to be summarized; based on the determining, selecting a new cluster from the plurality of clusters that comprises the largest number of summaries for processing; processing one or more summaries from the plurality of summaries present in the new cluster; and based on the processing, selecting, by the summary selection system, a summary from the one or more summaries present in the new cluster as the summary for the content to be summarized” which, but for “by the summary selection system”, could be performed by mentally determining that no summary in the one or more summaries in the selected cluster includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships present in the content to be summarized; mentally selecting a new pile from the plurality of piles of summaries that comprises the largest number of summaries for mentally considering; mentally considering one or more summaries from the plurality of summaries present in the new cluster; and based on the consideration, mentally selecting a summary from the one or more summaries present in the new cluster as the summary for the content to be summarized.
Claim 9 recites “the processing further comprises: determining that more than one summary in the one or more summaries in the selected cluster includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships present in the content to be summarized; responsive to the determining, identifying, for each summary, one or more good-to-have entities and one or more good-to-have relationships present in the summary; and selecting a summary that has the largest number of good-to-have entities and the largest number of good-to-have relationships as the summary for the content to be summarized” which could be performed by mentally determining that more than one summary in the one or more summaries in the selected cluster includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships present in the content to be summarized; responsive to the determining, mentally identifying, for each summary, one or more good-to-have entities and one or more good-to-have relationships present in the summary; and mentally selecting a summary that has the largest number of good-to-have entities and the largest number of good-to-have relationships as the summary for the content to be summarized.
Claim 10 recites “the one or more good-to-have entities and the one or more good-to-have entity relationships are identified in the summary based upon identifying a set of good-to-have entities and a set of good-to-have relationships in content to be summarized” which could be performed by mentally selecting the one or more good-to-have entities and the one or more good-to-have entity relationships are identified in the summary based upon identifying a set of good-to-have entities and a set of good-to-have relationships in content to be summarized.
In sum, claims 2-10 depend from claim 1 and further recite mental processes as explained above. None of the additional limitations recited in claims 22-10 amount to anything more than the same or a similar abstract idea as recited in claim 1. Nor do any limitations in claims 2-4 and 7-10 (a) integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea or (b) amount to significantly more than the judicial exception. Claims 2-10 are not patent eligible.
Claim 21 is directed to one or more non-transitory computer-readable media that corresponds to the method of claim 1 and is therefore rejected for the same reasons set for the above with respect to claim 1. While claim 21 recites generic computer components (non-transitory computer-readable media, instructions, computer system, processors), such generic computing components are recited at a high-level of generality such that they amount to no more than mere instructions to apply the exception using generic computer components. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
Claim 21 does 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 limitations of using generic computer components amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. Claim 21 is not patent eligible.
Claims 22-25 depend from claim 21, correspond to the subject matter addressed above with regard to dependent claims 2-5, do not remedy any of the deficiencies of claim 21, and therefore are rejected on the same grounds as claims 21 and 2-5 above.
Claim 31 is directed to system that corresponds to the method of claim 1 and is therefore rejected for the same reasons set forth above with respect to claim 1. Moreover, while claim 31 recites generic computing components (e.g., memory, one or more processors), such components are claimed at a high level of generality such that they amount to no more than mere instructions to apply the exception using generic computer components. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
Claim 31 does 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 limitations of using generic computer components amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. Claim 31 is not patent eligible.
Claims 32-40 depend from claim 31, correspond to the subject matter addressed above with regard to dependent claims 2-10, do not remedy any of the deficiencies of claim 31, and therefore are rejected on the same grounds as claims 31, and 2-10 above.
Claim 41 is directed to one or more non-transitory computer-readable media that corresponds to the method of claim 1 and is therefore rejected for the same reasons set for the above with respect to claim 1. While claim 41 recites generic computer components (non-transitory computer-readable media, instructions, computer system, processors), such generic computing components are recited at a high-level of generality such that they amount to no more than mere instructions to apply the exception using generic computer components. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
Claim 41 does 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 limitations of using generic computer components amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. Claim 41 is not patent eligible.
Claims 42-45 depend from claim 41, correspond to the subject matter addressed above with regard to dependent claims 2-5, do not remedy any of the deficiencies of claim 41, and therefore are rejected on the same grounds as claims 41 and 2-5 above.
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 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 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-3, 21-23, 31-33, and 41-43 are rejected under 35 U.S.C. 103 as being unpatentable over Mukherjee (US 20230122609) in view of Sakhadeo et al. (“Effective extractive summarization using frequency-filtered entity relationship graphs”. arXiv:1810.10419v1 [cs.CL] 24 Oct 2018).
Consider claim 1, Mukherjee discloses a method comprising:
identifying, by a summary selection system and based upon a plurality of prioritized entities identified in reference information, a set of prioritized entities (base summary is generated with extractive summarizer, which identifies exact words, phrases, and sentences to extract from the original document, [0033], which may be e.g. a knowledge-based articles or news articles, [0013]; the extracted words are implicitly considered to contain entities in the case of knowledge-based or news articles, which are “prioritized” since they made it into the reference summary to which the abstractive summaries are compared for selection of the best abstractive summary, [0015]), the summary selection system comprising one or more computer systems (computer system with processor, [0008]);
identifying, by the summary selection system and based upon a plurality of prioritized entity relationships identified in the reference information, a set of prioritized entity relationships present in the content to be summarized (base summary is generated with extractive summarizer, which identifies exact words, phrases, and sentences to extract from the original document, [0033], which may be e.g. a knowledge-based articles or news articles, [0013]; the extracted words are implicitly considered to contain relations in the case of knowledge-based or news articles, which are “prioritized” since they made it into the reference summary to which the abstractive summaries are compared for selection of the best abstractive summary, [0015]);
selecting, by the summary selection system and from a plurality of summaries generated for the content to be summarized, a summary that includes prioritized entities and prioritized entity relationships (the best summary from summaries generated by a group of candidate summarizers is selected by comparing evaluation metrics for the generated summaries, [0028], [0029], using a Rouge-L f-measure metric, [0037]; this is considered to measure whether the extracted words and phrases in the base summary, which implicitly include entities and relations, also appear in the candidate summaries); and
providing, by the summary selection system, the selected summary as a summary for the content to be summarized (the selected summary is provided, [0030]).
Mukherjee does not specifically mention entities corresponding to one or more prioritized entity categories; entity relationships corresponding to one or more prioritized entity relationship categories; and a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships.
Sakhadeo discloses entities corresponding to one or more prioritized entity categories (important entities in the text corresponding to topics, Section 2, page 2); entity relationships corresponding to one or more prioritized entity relationship categories (relationships between the important entities corresponding to the topics, Section 2, page 2); and a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships (top N sentences including the important entities and relationships making up the summary, Figure 1, Section 2, pages 2-3).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Mukherjee by utilizing entities corresponding to one or more prioritized entity categories as in Sakhadeo; entity relationships corresponding to one or more prioritized entity relationship categories as in Sakhadeo; and generating a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships in order to improve informativeness and coherence of the generated summaries, as suggested by Sakhadeo (Section 1, page 1-2). Doing so would have led to predictable results of improved text summarization by leveraging extra-statistical information, as suggested by Sakhadeo (Section 1, page 1). The references cited are analogous art in the same field of natural language processing.
Consider claim 21, Mukherjee discloses one or more non-transitory computer-readable media storing instructions executable by a computer system that, when executed by one or more processors of the computer system (memory storing instructions executed by a processor, [0008]), cause the computer system to perform operations comprising:
identifying, based upon a plurality of prioritized entities identified in reference information, a set of prioritized entities (base summary is generated with extractive summarizer, which identifies exact words, phrases, and sentences to extract from the original document, [0033], which may be e.g. a knowledge-based articles or news articles, [0013]; the extracted words are implicitly considered to contain entities in the case of knowledge-based or news articles, which are “prioritized” since they made it into the reference summary to which the abstractive summaries are compared for selection of the best abstractive summary, [0015]), the summary selection system comprising one or more computer systems (computer system with processor, [0008]);
identifying, based upon a plurality of prioritized entity relationships identified in the reference information, a set of prioritized entity relationships present in the content to be summarized (base summary is generated with extractive summarizer, which identifies exact words, phrases, and sentences to extract from the original document, [0033], which may be e.g. a knowledge-based articles or news articles, [0013]; the extracted words are implicitly considered to contain relations in the case of knowledge-based or news articles, which are “prioritized” since they made it into the reference summary to which the abstractive summaries are compared for selection of the best abstractive summary, [0015]);
selecting, from a plurality of summaries generated for the content to be summarized, a summary that includes prioritized entities and prioritized entity relationships (the best summary from summaries generated by a group of candidate summarizers is selected by comparing evaluation metrics for the generated summaries, [0028], [0029], using a Rouge-L f-measure metric, [0037]; this is considered to measure whether the extracted words and phrases in the base summary, which implicitly include entities and relations, also appear in the candidate summaries); and
providing, by the summary selection system, the selected summary as a summary for the content to be summarized (the selected summary is provided, [0030]).
Mukherjee does not specifically mention entities corresponding to one or more prioritized entity categories; entity relationships corresponding to one or more prioritized entity relationship categories; and a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships.
Sakhadeo discloses entities corresponding to one or more prioritized entity categories (important entities in the text corresponding to topics, Section 2, page 2); entity relationships corresponding to one or more prioritized entity relationship categories (relationships between the important entities corresponding to the topics, Section 2, page 2); and a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships (top N sentences including the important entities and relationships making up the summary, Figure 1, Section 2, pages 2-3).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Mukherjee by utilizing entities corresponding to one or more prioritized entity categories as in Sakhadeo; entity relationships corresponding to one or more prioritized entity relationship categories as in Sakhadeo; and generating a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships for reasons similar to those for claim 1.
Consider claim 31, Mukherjee discloses a summary selection system (summarization service platform which selects from multiple candidate summaries, Fig 2), comprising:
a memory (memory, [0008]); and
one or more processors configured to perform processing (processor executing instructions, [0008]) comprising:
identifying, and based upon a plurality of prioritized entities identified in reference information, a set of prioritized entities (base summary is generated with extractive summarizer, which identifies exact words, phrases, and sentences to extract from the original document, [0033], which may be e.g. a knowledge-based articles or news articles, [0013]; the extracted words are implicitly considered to contain entities in the case of knowledge-based or news articles, which are “prioritized” since they made it into the reference summary to which the abstractive summaries are compared for selection of the best abstractive summary, [0015]), the summary selection system comprising one or more computer systems (computer system with processor, [0008]);
identifying, and based upon a plurality of prioritized entity relationships identified in the reference information, a set of prioritized entity relationships present in the content to be summarized (base summary is generated with extractive summarizer, which identifies exact words, phrases, and sentences to extract from the original document, [0033], which may be e.g. a knowledge-based articles or news articles, [0013]; the extracted words are implicitly considered to contain relations in the case of knowledge-based or news articles, which are “prioritized” since they made it into the reference summary to which the abstractive summaries are compared for selection of the best abstractive summary, [0015]);
selecting, and from a plurality of summaries generated for the content to be summarized, a summary that includes prioritized entities and prioritized entity relationships (the best summary from summaries generated by a group of candidate summarizers is selected by comparing evaluation metrics for the generated summaries, [0028], [0029], using a Rouge-L f-measure metric, [0037]; this is considered to measure whether the extracted words and phrases in the base summary, which implicitly include entities and relations, also appear in the candidate summaries); and
providing, the selected summary as a summary for the content to be summarized (the selected summary is provided, [0030]).
Mukherjee does not specifically mention entities corresponding to one or more prioritized entity categories; entity relationships corresponding to one or more prioritized entity relationship categories; and a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships.
Sakhadeo discloses entities corresponding to one or more prioritized entity categories (important entities in the text corresponding to topics, Section 2, page 2); entity relationships corresponding to one or more prioritized entity relationship categories (relationships between the important entities corresponding to the topics, Section 2, page 2); and a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships (top N sentences including the important entities and relationships making up the summary, Figure 1, Section 2, pages 2-3).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Mukherjee by utilizing entities corresponding to one or more prioritized entity categories as in Sakhadeo; entity relationships corresponding to one or more prioritized entity relationship categories as in Sakhadeo; and generating a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships for reasons similar to those for claim 1.
Consider claim 41, Mukherjee discloses one or more non-transitory computer-readable media storing instructions executable by a computer system that, when executed by one or more processors of the computer system (memory storing instructions executed by a processor, [0008]), cause the computer system to perform operations comprising:
identifying, based upon a plurality of prioritized entities identified in reference information, a set of prioritized entities (base summary is generated with extractive summarizer, which identifies exact words, phrases, and sentences to extract from the original document, [0033], which may be e.g. a knowledge-based articles or news articles, [0013]; the extracted words are implicitly considered to contain entities in the case of knowledge-based or news articles, which are “prioritized” since they made it into the reference summary to which the abstractive summaries are compared for selection of the best abstractive summary, [0015]), the summary selection system comprising one or more computer systems (computer system with processor, [0008]);
identifying, based upon a plurality of prioritized entity relationships identified in the reference information, a set of prioritized entity relationships present in the content to be summarized (base summary is generated with extractive summarizer, which identifies exact words, phrases, and sentences to extract from the original document, [0033], which may be e.g. a knowledge-based articles or news articles, [0013]; the extracted words are implicitly considered to contain relations in the case of knowledge-based or news articles, which are “prioritized” since they made it into the reference summary to which the abstractive summaries are compared for selection of the best abstractive summary, [0015]);
selecting, from a plurality of summaries generated for the content to be summarized, a summary that includes prioritized entities and prioritized entity relationships (the best summary from summaries generated by a group of candidate summarizers is selected by comparing evaluation metrics for the generated summaries, [0028], [0029], using a Rouge-L f-measure metric, [0037]; this is considered to measure whether the extracted words and phrases in the base summary, which implicitly include entities and relations, also appear in the candidate summaries); and
providing, by the summary selection system, the selected summary as a summary for the content to be summarized (the selected summary is provided, [0030]).
Mukherjee does not specifically mention entities corresponding to one or more prioritized entity categories; entity relationships corresponding to one or more prioritized entity relationship categories; and a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships.
Sakhadeo discloses entities corresponding to one or more prioritized entity categories (important entities in the text corresponding to topics, Section 2, page 2); entity relationships corresponding to one or more prioritized entity relationship categories (relationships between the important entities corresponding to the topics, Section 2, page 2); and a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships (top N sentences including the important entities and relationships making up the summary, Figure 1, Section 2, pages 2-3).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Mukherjee by utilizing entities corresponding to one or more prioritized entity categories as in Sakhadeo; entity relationships corresponding to one or more prioritized entity relationship categories as in Sakhadeo; and generating a summary that includes each entity in the set of prioritized entities and each entity relationship in the set of prioritized entity relationships for reasons similar to those for claim 1.
Consider claim 2, Mukherjee discloses the plurality of summaries for the content to be summarized are generated using a machine learning (ML) model and a plurality of input parameters (each candidate summarizer is an abstractive summarizer trained using a different corpus of documents, [0024]).
Consider claim 3, Mukherjee does not, but Sakhadeo discloses input parameters comprise one or more of: a prompt provided to the ML model, a summarization strategy used by the ML model to generate the plurality of summaries, and a temperature setting used by the ML model to generate the plurality of summaries (we assign scores to each sentence based on the presence of nodes and their connectivity; the adjacency matrix is considered a set of “input parameters” that make up a summarization strategy that selects for sentences based on presence of nodes and connectivity in the matrix, page 3, Section 2, noting the claim language “one or more” only requiring one of the following in the alternative).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Mukherjee such that input parameters comprise one or more of: a prompt provided to the ML model, a summarization strategy used by the ML model to generate the plurality of summaries, and a temperature setting used by the ML model to generate the plurality of summaries for reasons similar to those for claim 1.
Consider claim 22, Mukherjee discloses the plurality of summaries for the content to be summarized are generated using a machine learning (ML) model and a plurality of input parameters (each candidate summarizer is an abstractive summarizer trained using a different corpus of documents, [0024]).
Consider claim 23, Mukherjee does not, but Sakhadeo discloses input parameters comprise one or more of: a prompt provided to the ML model, a summarization strategy used by the ML model to generate the plurality of summaries, and a temperature setting used by the ML model to generate the plurality of summaries (we assign scores to each sentence based on the presence of nodes and their connectivity; the adjacency matrix is considered a set of “input parameters” that make up a summarization strategy that selects for sentences based on presence of nodes and connectivity in the matrix, page 3, Section 2, noting the claim language “one or more” only requiring one of the following in the alternative).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Mukherjee such that input parameters comprise one or more of: a prompt provided to the ML model, a summarization strategy used by the ML model to generate the plurality of summaries, and a temperature setting used by the ML model to generate the plurality of summaries for reasons similar to those for claim 1.
Consider claim 32, Mukherjee discloses the plurality of summaries for the content to be summarized are generated using a machine learning (ML) model and a plurality of input parameters (each candidate summarizer is an abstractive summarizer trained using a different corpus of documents, [0024]).
Consider claim 33, Mukherjee does not, but Sakhadeo discloses input parameters comprise one or more of: a prompt provided to the ML model, a summarization strategy used by the ML model to generate the plurality of summaries, and a temperature setting used by the ML model to generate the plurality of summaries (we assign scores to each sentence based on the presence of nodes and their connectivity; the adjacency matrix is considered a set of “input parameters” that make up a summarization strategy that selects for sentences based on presence of nodes and connectivity in the matrix, page 3, Section 2, noting the claim language “one or more” only requiring one of the following in the alternative).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Mukherjee such that input parameters comprise one or more of: a prompt provided to the ML model, a summarization strategy used by the ML model to generate the plurality of summaries, and a temperature setting used by the ML model to generate the plurality of summaries for reasons similar to those for claim 1.
Consider claim 42, Mukherjee discloses the plurality of summaries for the content to be summarized are generated using a machine learning (ML) model and a plurality of input parameters (each candidate summarizer is an abstractive summarizer trained using a different corpus of documents, [0024]).
Consider claim 43, Mukherjee does not, but Sakhadeo discloses input parameters comprise one or more of: a prompt provided to the ML model, a summarization strategy used by the ML model to generate the plurality of summaries, and a temperature setting used by the ML model to generate the plurality of summaries (we assign scores to each sentence based on the presence of nodes and their connectivity; the adjacency matrix is considered a set of “input parameters” that make up a summarization strategy that selects for sentences based on presence of nodes and connectivity in the matrix, page 3, Section 2, noting the claim language “one or more” only requiring one of the following in the alternative).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Mukherjee such that input parameters comprise one or more of: a prompt provided to the ML model, a summarization strategy used by the ML model to generate the plurality of summaries, and a temperature setting used by the ML model to generate the plurality of summaries for reasons similar to those for claim 1.
Allowable Subject Matter
Claims 4-10, 24, 25, 34-40, 44, and 45 are would be allowable if amended to overcome the 35 U.S.C. 101 rejections and rewritten in independent form including all limitations of the base and any intervening claims.
The following is the examiner’s statement of reasons for indicating subject matter allowable over the prior art of record:
Consider claim 4, the prior art, alone or in combination, does not fairly teach or suggest: “…wherein selecting the summary from the plurality of summaries comprises: generating, by the summary selection system, a plurality of clusters, wherein each cluster in the plurality of clusters comprises one or more summaries from the plurality of summaries; selecting, by the summary selection system, a cluster from the plurality of clusters that comprises the largest number of summaries; processing, by the summary selection system, the one or more summaries from the plurality of summaries present in the selected cluster; and based on the processing, selecting, by the summary selection system, a summary from the one or more summaries present in the selected cluster as the summary for the content to be summarized.”
Mallick et al. (“Ensemble summarization of bio-medical articles integrating lustering and multi-objective evolutionary algorithms”. Applied Soft Computing 106 (2021) 107347) discloses generating multiple extractive base summaries of a representation of an article in terms of a set of concepts, using various clustering algorithms and centrality measures, and a multi-objective evolutionary algorithm is applied on these base summaries for generating an ensemble summary of the given article. However, this is not equivalent to the above limitations of dependent claim 4, and the techniques of Mallick integrated into the other prior art of record still would not have resulted in the above limitations of dependent claim 4.
Claims 5-10 are allowable over the prior art because they depend on and further limit the allowable subject matter of dependent claim 4.
Claims 24, 34, and 44 recite limitations similar to those discussed above with regard to claim 4, and are allowable over the prior art for similar reasons.
Claims 25 and 45 are allowable over the prior art because they depends on and further limit the allowable subject matter of respective dependent claims 24 and 44.
Claims 35-40 are allowable over the prior art because they depend on and further limit the allowable subject matter of dependent claim 34.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 12008332 Gardner discloses controllable summarization of content
US 20220067284 He discloses controllable text summarization with important and unimportant entities (see [0053])
DE 202022100824 U1 Bansod discloses creating summaries from short stories by identifying key entities and including sentences containing them
US 20140222834 Parikh discloses a content summarization and recommendation apparatus
Zhang et al. (“FAR-ASS: Fact-aware reinforced abstractive sentence summarization”. Information Processing and Management 58 (2021) 102478) discloses leveraging OpenIE to extract structured fact tuples from the source document for verifying factual correctness of generated summaries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Jesse Pullias whose telephone number is 571/270-5135. The examiner can normally be reached on M-F 8:00 AM - 4:30 PM. The examiner’s fax number is 571/270-6135.
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, Andrew Flanders can be reached on 571/272-7516.
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.
/Jesse S Pullias/
Primary Examiner, Art Unit 2655 03/19/26