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 .
1. In response to the Office Action dated on 03/19/2026, applicant(s) amend the application as follow:
Claims amended: 1, 2, 4, 9 and 10 -12
Claims canceled: 3 and 11
Claims newly added: 17-18
Claims pending: 1-2, 4-10 and 12-18
Response to Arguments
2. Applicant's arguments filed 03/19/2026 have been fully considered but they are not persuasive.
Applicant argues “the amended claim 1 is patent-eligible under 35 U.S.C 101…”
Examiner respectfully disagree with applicant argument. The amended claim include additional elements: however, the determining step(s) remained mental concept which are abstract idea. The USPTO guidelines which provides the evaluation including abstract idea integrating to practical application include step 2A in both claims 1, 4, 9 and 12.
Applicant argues “Kim fails to disclose or suggest the above-emphasized claim elements recited in amended claim 1 at least because Kim is completely silent on “summary sentence corresponding to a previous round is used as a sentence to be processed in a next round…”
Please see the rejection below regarding to amended claims.
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
therefore, subject to the conditions and requirements of this title.
3. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed
to abstract idea without significantly more.
Step 1 (See MPEP 2106)
Claims 1-2, 4-10, 12-18 are directed to methods and devices which belong to a statutory class.
As to claims 1-2, 9-10 and 17
Step 2A, Prong One:
Claims 1 and 9 recites "performing clustering and summarizing processing on original
sentences of the document for at least one round by using a large model to obtain summary
sentence for each round and determining the summary sentence of each round as a second
information corresponding to the document and determining the at least one summary sentence of each round as a second information set corresponding to the document" which are processes that, under its broadest reasonable interpretation, covers performance of the limitation by Mental Process, but for the recitation of generic computer components. Nothing in the claim element precludes the steps from practically being performed in the human mind. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation by mental process, 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, i.e., the mental process, is not integrated into a practical
application. In particular, the claims only recite additional elements - "constructing a target
database based on a first information set and the second information set corresponding to the
document, wherein the first information set includes at least one original sentence
corresponding to the document, and the target database includes the first information set and
the second information set corresponding to a plurality of documents respectively." These
elements are recited at a high-level of generality (i.e., as a generic processor performing a
generic computer function amounts no more than mere instructions to apply the exception using
a generic computer component. The processing environments perform a generic function of
computing/processing queries. Accordingly, this additional element does not integrate the
abstract idea into a practical application because it does not impose any meaningful limits on
practicing the abstract idea. The claim is directed to an abstract idea.
Step 2A, Prong Two:
As to claim 9, claim recites "device... comprising one or more processor and computer
instructions stored in computer readable medium" which are computer components and these
are generic computer components and program which use to perform abstract ideas.
The limitation is thus insignificant extra-solution activity. Limitations that the courts have
found not to be enough to qualify as "significantly more" when recited in a claim with a judicial
exception include: i. Adding the words "apply it" (or an equivalent) with the judicial exception, or
mere instructions to implement an abstract idea on a computer, e.g., a limitation indicating that a
particular function such as creating and maintaining electronic records is performed by
a computer, as discussed in Alice Corp., 134 S. Ct. at 2360, 110 USPQ2d at 1984 (see
MPEP § 2106.05(f)). 2106.05(g)--Insignificant Extra-Solution Activity.
Step 2B:
The steps of "constructing a target database based on a first information set and the
second information set corresponding to the document, wherein the first information set includes
at least one original sentence corresponding to the document, and the target database includes
the first information set and the second information set corresponding to a plurality of
documents respectively" and remaining steps as a whole does not amount to significantly
more.
As to claims 2, 9 and 16 do not include additional elements to amount to significantly
more, rather information are entered by the user.
As to claims 3, 10 and 17 do not include additional element to amount to significantly
more, rather the received information is displayed via interface which generic routines.
As to claims 4-8, 12-16 and 18
Claims 4 and 12 recites "in response to receiving to-be-retrieved input information,
determining a first information set and a second information set corresponding to each
document from a target database, the first information set including one original sentence
corresponding to the document, the second information set including a summary sentence
obtained by at least one round of clustering summarizing processing on the original sentence
corresponding to the document, determining a first matching value between the input
information and a first target document corresponding to the first information set, and a second
matching value between the input information and a second target document corresponding to
the second information set which is a process that, under its broadest reasonable
interpretation, covers performance of the limitation by Mental Process, but for the recitation of
generic computer components. Nothing in the claim element precludes the steps from
practically being performed in the human mind. If a claim limitation, under its broadest
reasonable interpretation, covers performance of the limitation by mental process, 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.
Step 2A, Prong Two:
As to claim 12, claim recites "device... comprising one or more processor and computer
instructions stored in computer readable medium" which are computer components and these
are generic computer components and program which use to perform abstract ideas.
The limitation is thus insignificant extra-solution activity. Limitations that the courts have
found not to be enough to qualify as "significantly more" when recited in a claim with a judicial
exception include: i. Adding the words "apply it" (or an equivalent) with the judicial exception, or
mere instructions to implement an abstract idea on a computer, e.g., a limitation indicating that a
particular function such as creating and maintaining electronic records is performed by
a computer, as discussed in Alice Corp., 134 S. Ct. at 2360, 110 USPQ2d at 1984 (see
MPEP § 2106.05(f)). 2106.05(g)--Insignificant Extra-Solution Activity.
As to claims 5 and 13, the limitation "determining a first matching value between the
input information and a first target document corresponding to the first information set, and a
second matching value between the input information and a second target document
corresponding to the second information set; and determining at least one third target document
corresponding to the input information based on the first matching value and the second
matching value, therein the first target document is the same as or different from the second
target document, and the third target document belongs to the first target document or the
second target document" which are a processes that, under its broadest reasonable
interpretation, covers performance of the limitation by Mental Process, but for the recitation of
generic computer components. Nothing in the claim element precludes the steps from
practically being performed in the human mind. If a claim limitation, under its broadest
reasonable interpretation, covers performance of the limitation by mental process, 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.
As to claims 6 and 14, the limitation "determining a first sub-matching value of each
original sentence in the first information set corresponding to each document and the input
information; and determining a target original sentence based on the first sub-matching value of
each original sentence; and determining the first matching value between the first target
document and the input information based on the first sub-matching value corresponding to the
target original sentence belonging to the same first target document" which are a processes
that, under its broadest reasonable interpretation, covers performance of the limitation by
Mental Process, but for the recitation of generic computer components. Nothing in the claim
element precludes the steps from practically being performed in the human mind. If a claim
limitation, under its broadest reasonable interpretation, covers performance of the limitation by
mental process, 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.
As to claims 7 and 15, the limitation "determining a second sub-matching value of each
summary sentence in the second information set corresponding to each document and the input
information; determining a target summary sentence based on the second sub-matching value
of each summary sentence; and determining the second matching value between the second
target document and the input information based on the second sub-matching value corresponding to the target summary sentence belonging to the same second target document"
which are a processes that, under its broadest reasonable interpretation, covers performance of
the limitation by Mental Process, but for the recitation of generic computer components. Nothing
in the claim element precludes the steps from practically being performed in the human mind. If
a claim limitation, under its broadest reasonable interpretation, covers performance of the
limitation by mental process, 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.
As to claims 8 and 16, the limitation "determining a first document set based on the first
matching value between each first target document and the input information; determining a
second document set based on the second matching value between each second target
document and the input information; and determining at least one third target document
corresponding to the input information based on the first document set and the second
document set" which are a processes that, under its broadest reasonable interpretation, covers
performance of the limitation by Mental Process, but for the recitation of generic computer
components. Nothing in the claim element precludes the steps from practically being performed
in the human mind. If a claim limitation, under its broadest reasonable interpretation, covers
performance of the limitation by mental process, 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.
As to claim 17, the limitation “wherein the constructing the target database comprises storing, in a vector database, the at least one original sentence of the first information set, the plurality of summary sentences obtained through the plurality of rounds of the clustering and summarizing processing and feature vectors corresponding to the at least one original sentence and the plurality of summary sentences, such that the at least one original sentence and the plurality of summary sentences form a structured muti-layered tree structure, and each original sentence and each summary sentence stored in the vector database is annotated with document identification information” is defined what target database is and insignificantly to amount significantly more.
As to claim 18, the limitation “wherein the first document set comprises a first number of top document ranked by the first matching value, the second document set comprises a second number of top document ranked by the second matching value and the at least one third target document is comprised in a final document set obtained by merging the first document set and the second document set using equal recall weights for the first document set and the second document set” is what the first document set is and insignificantly to amount significantly more.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C.
102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the
statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new
ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would
be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness
rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed
invention is not identically disclosed as set forth in section 102, if the differences between the
claimed invention and the prior art are such that the claimed invention as a whole would have
been obvious before the effective filing date of the claimed invention to a person having
ordinary skill in the art to which the claimed invention pertains. Patentability shall not be
negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under
35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or
nonobviousness.
This application currently names joint inventors. In considering patentability of the claims
the examiner presumes that the subject matter of the various claims was commonly owned as
of the effective filing date of the claimed invention(s) absent any evidence to the contrary.
Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective
filing dates of each claim that was not commonly owned as of the effective filing date of the later
invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any
potential 35 U.S.C. 102(a)(2) prior art against the later invention.
5. Claim(s) 1-2, 4-10 and 12-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (Pub. No. US 2024/0168984 A1) in view of BLACKLOCK et al. (Pub. No. 2015/0173561 A1).
As to claim 1, Kim discloses a method for establishing a database comprising:
Obtaining a document (document) (paragraph 0037);
Performing clustering and summarizing processing on at least one original sentence of the document for a plurality of rounds by using a large model to obtain at least one summary sentence for each round (extractive summarization-based on the second summarization
vector) (paragraph 0046),
Determining the summary sentence of each round as a second information set
corresponding to the document (extractive summarization-based on the second summarization
vector) (paragraph 0046).
Kim does not explicitly wherein the performing the clustering and summarizing processing comprises, for each round: using an embedding model to extract features from sentences to be processed in the round to obtain feature vector corresponding to each sentence; clustering feature vectors to obtain at least one cluster, and summarizing sentences in each cluster based on the large language model to obtain at least one summary sentence corresponding to the ground, wherein a summary sentence corresponding to previous round is used as a sentence to be processed in a next round, the clustering and summarizing processing is iteratively executed until a targeting stopping condition is reached, and the target stopping condition includes that a position of a cluster center of a cluster no long changes, or a number of execution and summarizing processing reaches a target number of executions and constructing a target database on a first information set and the second information set corresponding to the document, wherein the first information set includes at least one original sentence corresponding to the document and the target database includes the first information set and the second information set corresponding to a plurality of document respectively. However, Kim discloses the acquiring of a first document candidate group may further include: calculating first similarity sore between the user inquiry vector and sentence vector extracted from a passage of the document stored in the retrieval database. BLACKROCK discloses wherein the performing the clustering and summarizing processing comprises, for each round: using an embedding model to extract features from sentences to be processed in the round to obtain feature vector corresponding to each sentence (a position embedding 510 may be applied to maintain information related to the order of the tokens 506…) (paragraph 0066); clustering feature vectors to obtain at least one cluster (, and summarizing sentences in each cluster based on the large language model to obtain at least one summary sentence corresponding to the ground (this allows the LLM to perform a wide range of language-related tasks… summarization…) (paragraph 0024), wherein a summary sentence corresponding to previous round is used as a sentence to be processed in a next round (in the context of language models, the autoregressive model may predict a text word in a sentence given all the previous word) (paragraph 0078), the clustering and summarizing processing is iteratively executed until a targeting stopping condition is reached, and the target stopping condition includes that a position of a cluster center of a cluster no long changes, or a number of execution and summarizing processing reaches a target number of executions (Stochastic gradient descent may be repeated until the achievable error rate has reached a target level) (paragraph 0045). This suggests wherein the performing the clustering and summarizing processing comprises, for each round: using an embedding model to extract features from sentences to be processed in the round to obtain feature vector corresponding to each sentence; clustering feature vectors to obtain at least one cluster, and summarizing sentences in each cluster based on the large language model to obtain at least one summary sentence corresponding to the ground, wherein a summary sentence corresponding to previous round is used as a sentence to be processed in a next round, the clustering and summarizing processing is iteratively executed until a targeting stopping condition is reached, and the target stopping condition includes that a position of a cluster center of a cluster no long changes, or a number of execution. Therefore, it would have been obvious to one ordinary skill in art before the effective filing date of the instant application to modify teaching of Kim to include wherein the performing the clustering and summarizing processing comprises, for each round: using an embedding model to extract features from sentences to be processed in the round to obtain feature vector corresponding to each sentence; clustering feature vectors to obtain at least one cluster, and summarizing sentences in each cluster based on the large language model to obtain at least one summary sentence corresponding to the ground, wherein a summary sentence corresponding to previous round is used as a sentence to be processed in a next round, the clustering and summarizing processing is iteratively executed until a targeting stopping condition is reached, and the target stopping condition includes that a position of a cluster center of a cluster no long changes, or a number of execution as disclosed by BRACKDOCK in order to provide summarization of sentences.
As to claim 2, Kim discloses the method of claim 1 further comprising:
Performing sentence segmentation processing on the document to obtain at least one
original sentence corresponding to the document (the apparatus 1000 for summarizing a
document may be implemented to segment each document included in the original data
source...) (paragraph 0064); and
Determining at least one of the original sentences as the first information set
corresponding to the document (the apparatus 1000 for summarizing a document may be
implemented to segment each document included in the original data source...) (paragraph
0064).
Claim 9 is rejected under the same reason as to claim 1, Kim discloses a device
(apparatus 1000) (paragraph 0054) for establishing a database (retrieval database) (paragraph
0055) comprising one or more processors (processor 1030, paragraph 0054) and computer
program instructions (program) (paragraph 0043) stored in computer readable storage medium
(a computer-readable recording medium) (paragraph 0043), when executed by the one or more
processors (processor 1030, paragraph 0054), the computer instructions (program) (paragraph
0043) implementing a method for establishing the database (retrieval database) (paragraph
0055).
Claim 10 is rejected under the same reason as to claim 2.
As to claim 4, Kim discloses an information retrieval method comprising:
In response to receiving to-be-retrieved input information, determining a firs information
set and a second information set corresponding to each document from a target database, the
first information set including at least one original sentence corresponding to the document (a sentence vector extracted from a passage of the document stored in the retrieval database) (paragraph 0037), the second information set including a plurality of summary sentences obtained by a plurality of rounds of clustering summarizing processing on the at least original sentence corresponding to the document (sentence vector summarization the passage of the document stored in the retrieval database) (paragraph 0037);
Determining a first matching value between the input information and a first target
document corresponding to the first information set (a step S1220 of calculating a second similarity score between the user input vector and sentence vector summarizing the passage of
the document stored in the retrieval database) (paragraph 0108), and a second matching value
between the input information and a second target document corresponding to the second
information set (a step S1220 of calculating a second similarity score between the user input
vector and sentence vector summarizing the passage of the document stored in the retrieval
database) (paragraph 0108); and
Kim does not explicitly disclose determining at least one third target document
corresponding to the input information based on the first matching value and the second
matching value, therein the first target document is the same as or different from the second
target document, and the third target document belongs to the first target document or the
second target document and wherein the plurality of summary sentences are obtained through the plurality of rounds of an iterative clustering and summarizing process that, in each round, in each round, cluster feature vectors of sentences into at least one cluster having a cluster center and summarizes sentences in each cluster using a large model, and the iterative clustering and summarizing process continue until a target stopping condition is reached, the target stopping condition includes that a position of a cluster center of a cluster no longer changes, or a number of execution reaches a target number of execution, such that that at least one original sentence and plurality of summary sentence of the plurality of rounds from nodes of a structured, multi-layer tree structure in the target database. However, Kim discloses the step S1200 of acquiring the first document candidate group according to an embodiment of the present application may further include a step S1200 of calculating a first similarity score between the user inquiry vector and a sentence vector extracted from a massage of the document stored in the retrieval database 1100, a step S1220 of calculating a second similarity score between the user input vector and sentence vector summarizing the passage of the document stored in the retrieval database, a step S1230 of calculating a third similarity score between the question vector generated from the passage stored in the retrieval database and the user inquiry vector through a generation model, and a step S1240 of calculating a firs weight score based on a first similarity score, the second similarity score, and third similarity score and determining a first document candidate group based on the calculated first weighted score (paragraph 0108). BLACKDOCK discloses wherein the plurality of summary sentences are obtained through the plurality of rounds of an iterative clustering and summarizing process that, in each round, in each round, cluster feature vectors of sentences into at least one cluster having a cluster center and summarizes sentences in each cluster using a large model (this allows the LLM to perform a wide range of language-related tasks… summarization…) (paragraph 0024), and the iterative clustering and summarizing process continue until a target stopping condition is reached (in the context of language models, the autoregressive model may predict a text word in a sentence given all the previous word) (paragraph 0078), the target stopping condition includes that a position of a cluster center of a cluster no longer changes, or a number of execution reaches a target number of execution, such that that at least one original sentence and plurality of summary sentence of the plurality of rounds from nodes of a structured, multi-layer tree structure in the target database (Deep belief network (DBNs) are probabilistic models comprising multiple layers of hidden nodes…) (paragraph 0046). Therefore, it would have been obvious to one ordinary skill in the art before the effective filing date of the instant application to modify similar scores for matching document as to determining at least one third target document corresponding to the input information based on the first matching value and the second matching value, therein the first target document is the same as or different from the second target document, and the third target document belongs to the first target document or the second target document and wherein the plurality of summary sentences are obtained through the plurality of rounds of an iterative clustering and summarizing process that, in each round, in each round, cluster feature vectors of sentences into at least one cluster having a cluster center and summarizes sentences in each cluster using a large model, and the iterative clustering and summarizing process continue until a target stopping condition is reached, the target stopping condition includes that a position of a cluster center of a cluster no longer changes, or a number of execution reaches a target number of execution, such that that at least one original sentence and plurality of summary sentence of the plurality of rounds from nodes of a structured, multi-layer tree structure in the target database as disclosed by BLACKROCK in order to provide documents matching.
As to claim 5, Kim discloses the information retrieval method of claim 4 further
comprising:
using the corresponding at least one third target document as prompt information,
processing the prompt information and the input information through the large model to
obtain corresponding target search result information (model) ( calculating a third similarity
score between question vector generated from the passage stored in the retrieval database
through a generation model...) (paragraph 0108).
As to claim 6, Kim discloses the information retrieval method of claim 4, wherein
determining the first matching value between the input information and the first target document
corresponding to the first information set includes:
determining a first sub-matching (text matching includes sub-matching) (paragraph
0072) value of each original sentence in the first information set corresponding to each
document and the input information a step S1200 of calculating a first similarity score between
the user inquiry vector and a sentence vector extracted from a massage of the document stored
in the retrieval database 1100) (paragraph 0108); and
determining a target original sentence based on the first sub-matching value of each
original sentence (a step S1200 of calculating a first similarity score between the user inquiry
vector and a sentence vector extracted from a massage of the document stored in the retrieval
database 1100) (paragraph 0108); and
determining the first matching value between the first target document and the input
information based on the first sub-matching value corresponding to the target original
sentence belonging to the same first target document (a step S1200 of calculating a first
similarity score between the user inquiry vector and a sentence vector extracted from a
massage of the document stored in the retrieval database 1100) (paragraph 0108).
As to claim 7, Kim discloses the information retrieval method of claim 4, wherein
determining the second matching value of the second target document corresponding to the
input information and the second information set includes:
determining a second sub-matching value (text matching includes sub-matching) of each
summary sentence in the second information set corresponding to each document and the input
information (a step S1220 of calculating a second similarity score between the user input vector
and sentence vector summarizing the passage of the document stored in the retrieval database)
(paragraph 0108);
determining a target summary sentence based on the second sub-matching value of
each summary sentence (a step S1220 of calculating a second similarity score between the
user input vector and sentence vector summarizing the passage of the document stored in the
retrieval database) (paragraph 0108); and
determining the second matching value between the second target document and the
input information based on the second sub-matching value corresponding to the target summary
sentence belonging to the same second target document (a step S1220 of calculating a second
similarity score between the user input vector and sentence vector summarizing the passage of
the document stored in the retrieval database) (paragraph 0108).
As to claim 8, Kim discloses the information retrieval method of claim 6, wherein
determining at least one third target document corresponding to the input information based on
the first matching value and the second matching value includes:
determining a first document set based on the first matching value between each first
target document and the input information (a step S1200 of calculating a first similarity score
between the user inquiry vector and a sentence vector extracted from a massage of the
document stored in the retrieval database 1100) (paragraph 0108);
determining a second document set based on the second matching value between each
second target document and the input information (a step S1220 of calculating a second
similarity score between the user input vector and sentence vector summarizing the passage of
the document stored in the retrieval database) (paragraph 0108); and
determining at least one third target document corresponding to the input information
based on the first document set and the second document set (third similarity score and
determining a first document candidate group based on the calculated first weighted score
(paragraph 0108).
Claim 12 is rejected under the same reason as to claim 1, Kim discloses a device
(apparatus 1000) (paragraph 0054) for establishing a database (retrieval database) (paragraph
0055) comprising one or more processors (processor 1030, paragraph 0054) and computer
program instructions (program) (paragraph 0043) stored in computer readable storage medium
(a computer-readable recording medium) (paragraph 0043), when executed by the one or more
processors (processor 1030, paragraph 0054), the computer instructions implemented the
method for establishing database (retrieval database) (paragraph 0055).
Claim 13 is rejected under the same reason as to claim 5.
Claim 14 is rejected under the same reason as to claim 6.
As to claim 18, the limitation “wherein the first document set comprises a first number of top document ranked by the first matching value, the second document set comprises a second number of top document ranked by the second matching value and the at least one third target document is comprised in a final document set obtained by merging the first document set and the second document set using equal recall weights for the first document set and the second document set” is what the first document set is and insignificantly to amount significantly more.
6. Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (Pub. No. US 2024/0168984 A1) in view of BLACKLOCK et al. (Pub. No. 2015/0173561 A1) and further in view of Kohda et al. (Pub. No. US 2002/0186241 A1).
As to claim 17, Kim disclose the method of claim 1 excepting for wherein the constructing the target database comprises storing, in a vector database, the at least one original sentence of the first information set, the plurality of summary sentences obtained through the plurality of rounds of the clustering and summarizing processing and feature vectors corresponding to the at least one original sentence and the plurality of summary sentences, such that the at least one original sentence and the plurality of summary sentences form a structured muti-layered tree structure, and each original sentence and each summary sentence stored in the vector database is annotated with document identification information. Kohda discloses the constructing the target database comprises storing, in a vector database, the at least one original sentence of the first information set, the plurality of summary sentences obtained through the plurality of rounds of the clustering and summarizing processing and feature vectors corresponding to the at least one original sentence and the plurality of summary sentences, such that the at least one original sentence and the plurality of summary sentences form a structured muti-layered tree structure, and each original sentence and each summary sentence stored in the vector database is annotated with document identification information (the viewing history stored in the viewing history database 50 is a group of view data that reflect the state of digital document displayed on the display device by the user interface 10. Specifically, this data group includes in a view ID for specifying each history, a sentence in a digital document that is used for summarizing, the conditions (the summarizing rate, the summarization keyword, etc.) for preparing summaries) (paragraph 0090). This suggests claim language the constructing the target database comprises storing, in a vector database, the at least one original sentence of the first information set, the plurality of summary sentences obtained through the plurality of rounds of the clustering and summarizing processing and feature vectors corresponding to the at least one original sentence and the plurality of summary sentences, such that the at least one original sentence and the plurality of summary sentences form a structured muti-layered tree structure, and each original sentence and each summary sentence stored in the vector database is annotated with document identification information as disclosed by Kohda in order to provide a database for retrieval.
7. Claim(s) 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (Pub. No. US 2024/0168984 A1) in view of BLACKLOCK et al. (Pub. No. 2015/0173561 A1) and further in view of KATZMAN et al. (Pub No. US 2021/0157861 A1).
As to claim 18, Kim discloses the information retrieval method of claim 8 excepting for
wherein the first document set comprises a first number of top document ranked by the first matching value, the second document set comprises a second number of top document ranked by the second matching value and the at least one third target document is comprised in a final document set obtained by merging the first document set and the second document set using equal recall weights for the first document set and the second document set. However, KATZMAN discloses the first document set comprises a first number of top document ranked by the first matching value, the second document set comprises a second number of top document ranked by the second matching value and the at least one third target document is comprised in a final document set obtained by merging the first document set and the second document set using equal recall weights for the first document set and the second document set (… fetch documents are reranked using the first model (e.g., DCN model) according to relevance scores and then a second model (e.g., 100) and uses top passages from the retrieved passages for those top documents to determine a relevance score per document. The relevance scores from the first and second models are combined to generate a set of top ranked document…) (paragraph 0062). This suggests wherein the first document set comprises a first number of top document ranked by the first matching value, the second document set comprises a second number of top document ranked by the second matching value and the at least one third target document is comprised in a final document set obtained by merging the first document set and the second document set using equal recall weights for the first document set and the second document set. Therefore, it would have been obvious to one ordinary skill in the art before the effective filing date of the instant application to modify teaching of Kim to include the first document set comprises a first number of top document ranked by the first matching value, the second document set comprises a second number of top document ranked by the second matching value and the at least one third target document is comprised in a final document set obtained by merging the first document set and the second document set using equal recall weights for the first document set and the second document set as disclosed by KATZMAN in order to provide relevance documents.
Conclusion
8. Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BAOQUOC N TO whose telephone number is (571)272-4041. The examiner can normally be reached Mon-Fri 9AM - 6PM.
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, Boris Gorney can be reached at 571-270-5626. 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.
BAOQUOC N. TO
Examiner
Art Unit 2154
/BAOQUOC N TO/Primary Examiner, Art Unit 2154
Prosecution Insights