DETAILED ACTION
This is in response to a Request for Continued Examination (RCE) filed on 03/16/2026. Claims 1 and 3-19 are pending in this Office Action. Claim 2 had been previously cancelled.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 03/16/2026 has been entered.
Remark
In response filed 03/16/2026, claims 1, 18, and 19 have been amended, no claim has been cancelled, and no new claim has been added.
The Applicant's Interview Summary is acknowledged by the Examiner and it is OK. The Examine notes that during the interview, the Examiner mentioned that that the Deo reference disclosed the feature of generating a prompt (e.g. Fig. 1A and para 37) and using AI to create summary of contents for a file and no agreement was reached regarding 35 USC 103 rejection.
The Applicant’s amendments regarding claim objection are accepted by the Examiner. Therefore, prior claim objection has been withdrawn.
Response to Arguments
Applicant's arguments filed 03/16/2026 have been fully considered but they are not persuasive.
With regard to 35 USC 101 rejection:
The Examiner respectfully disagrees that the amendments to claims 1, 18, and 19 would overcome the 35 USC 101 rejection for being directed to abstract idea.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind, then it falls within the “Mental Processes” grouping of abstract ideas (concepts performed in the human mind including an observation, evaluation, judgment, and opinion). Also, if a claim limitation, under its broadest reasonable interpretation, constitutes mathematical relationships, mathematical formulas or equations, mathematical calculations, then it falls within the “mathematical concepts” grouping of abstract ideas.
The Examiner contends that the newly amended limitations are not sufficient to integrate the recited abstract idea into a practical application and amount to more than abstract idea.
With respect to amended new limitation, the Examiner holds that the amended limitation is analyzed as follow. The step of generating…a folder summary request based at least on file content of the selected subset of files, wherein the folder summary request comprises one or more natural language instructions that define a structure of a folder summary to be generated based on the ranked list of file clusters is recited at a high level of generality and based on broadest and reasonable interpretation, it constitutes concepts of observation, evaluation, and/or judgement which could be practically performed in the human mind. A human being could mentally and manually generate a file summary request including instructions in natural language defining structure of the folder summary. Furthermore, the step of generating a request folder summary by a prompt-generating engine using one or more generative models as recited at high level of generality is merely invokes a generative (learning) model to generate a request for summarizing a folder without providing any technological details as to how a folder summary is generated. The step of using a generative model to generate a request for folder summary is an extra-solution activity to the central idea of claims. Such an insignificant extra-solution activity does not lend patent eligibility to the abstract idea of the claims by integrating the abstract idea into a practical application. Note that the applicant needs to add specific technological details regarding the steps and operations used by “the one or more generative models” as how the models accomplish the results.
As such, the new limitation fails to integrate the recited judicial exception into a practical application. Therefore, the 35 USC 101 rejections of claims 1, 18, and 19 for being directed to abstract idea are maintained.
With regard to 35 USC 103 rejection:
Applicant's arguments with respect to newly amended claims 1, 18, and 19 that cited references do not teach the newly amended limitation of “generating, by a prompt-generating engine using one or more generative models, a folder summary request based at least on file content of the selected subset of files, wherein the folder summary request comprises one or more natural language instructions that define a structure of a folder summary to be generated based on the ranked list of file clusters” have been considered but are moot in view of the new ground(s) of rejection over the new reference, Vyas et al., US 2025/0252384.
Therefore, the new combination of Ben, Deo, Lewis, and Vyas discloses all the limitations of amended claims 1, 18, and 19. See below for details.
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 and 3-19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter of abstract ideas.
Step 1:
Claims 1 and 3-19 are directed to a method/system/storage medium which is one of the statutory categories of invention.
Step 2A:
Prong 1:
Claims 1 and 18 are directed to an abstract idea without significantly more.
The claims recite the steps of:
identifying a folder to be summarized based on the request for folder
summarization; [recited at a high level of generality and based on broadest and reasonable interpretation (BRI), it constitutes concepts of observation and evaluation which could be practically performed in the human mind]
identifying a plurality of files stored within the folder; [recited at a high level
of generality and based on BRI, it constitutes concepts of observation, evaluation, and/or judgement which could be practically performed in the human mind. A human being could mentally and manually select subset of files]
selecting, from the plurality of files stored within the folder, wherein selecting comprises: [recited at a high level of generality and broadest on BRI, it constitutes concepts of observation and evaluation which could be practically performed in the human mind]
generating a content embedding for each of the plurality of files, the content embedding of a respective file numerically representing content of a respective file from the plurality of files; [recited at a high level of generality and based on BRI, it involves mathematical concept that could be practically performed in the human mind. A person (e.g., a developer) can mentally generate a digital representation for data]
grouping, based on the content embedding for each file, the plurality of files into a plurality of file clusters, wherein each file cluster includes one or more files having a similarity satisfying a similarity threshold; [recited at a high level of generality and based on BRI, it involves observation, evaluation, and/or judgement concepts that could be practically performed in the human mind. A person (e.g., a developer) can mentally group files]
ranking the plurality of file clusters to generate a ranked list of file clusters; [recited at a high level of generality and based on BRI, it [involves observation, evaluation, and/or judgement concepts that could be practically performed in the human mind. A person (e.g., a developer) can mentally rank group of files]
selecting one or more of the file clusters to form the subset of files selected from the plurality of files; [recited at a high level of generality and broadest on BRI, it constitutes concepts of observation, evaluation, and/or judgement which could be practically performed in the human mind. A human being could mentally and manually select at least one of the groups of files]
generating…a folder summary request based at least on file content of the selected subset of files, wherein the folder summary request comprises one or more natural language instructions that define a structure of a folder summary to be generated based on the ranked list of file clusters; [recited at a high level of generality and broadest on BRI, it constitutes concepts of observation, evaluation, and/or judgement which could be practically performed in the human mind. A human being could mentally and manually generate a file summary request including instructions in natural language defining structure of the folder summary]
The above-mentioned steps are processes that, under its broadest reasonable
interpretation, covers performance of the limitation in the mind. That is, nothing in the claim element precludes the step from practically being performed in a human mind or with pen and paper. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind, then it falls within the “Mental Processes” grouping of abstract ideas (concepts performed in the human mind including
an observation, evaluation, judgment, and opinion).
Prong 2:
This judicial exception recited in claims 1 and 18 is not integrated into a practical application. The claims recite the additional steps of “receiving a request for folder summarization” and “causing the folder summary to be rendered at one or more output device” which could be considered as insignificant extra-solution activities of gathering data and outputting/displaying data. See MPEP 2106.04(d) and 2106.05(g).
Moreover, the step of “processing the folder summary request using a generative model to generate a model output reflecting the folder summary” recited at high level of generality is merely invokes a generative (learning) model to process data and output a folder summary without providing any technological details as to how a folder summary is generated. The step of using a generative model to generate a folder summary is an extra-solution activity to the central idea of claims. Such an insignificant extra-solution activity does not lend patent eligibility to the abstract idea of the claims by integrating the abstract idea into a practical application.
Furthermore, the step of generating a request folder summary by “a prompt-generating engine using one or more generative models” recited at high level of generality is merely invokes a generative (learning) model to generate a request for summarizing a folder without providing any technological details as to how a folder summary is generated. The step of using a generative model to generate a request for folder summary is an extra-solution activity to the central idea of claims. Such an insignificant extra-solution activity does not lend patent eligibility to the abstract idea of the claims by integrating the abstract idea into a practical application.
Additionally, the computer components of "one or more processors" and “computer readable media” are recited so generically that they represent no more than mere instructions to apply the judicial exception on a computer. These limitations can also be viewed as nothing more than an attempt to generally link the use of the judicial exception to the technological environment of a computer. It should be noted that because the courts have made it clear that mere physicality or tangibility of an additional element or elements is not a relevant consideration in the eligibility analysis, the physical nature of these computer components does not affect this analysis. See MPEP 2106.05(I) for more information on this point, including explanations from judicial
decisions including Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 224-26 (2014).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea. See MPEP 2106.04(d) and 2106.05(g).
Step 2B:
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claims recite the additional steps of “receiving a request for folder summarization” and “causing the folder summary to be rendered at one or more output device” which could be considered as well-understood, routine, conventional activities of gathering data and outputting/displaying data. See MPEP 2106.04(d) and 2106.05(g).
Moreover, the step of “processing the folder summary request using a generative model to generate a model output reflecting the folder summary” recited at high level of generality is merely invokes a generative (learning) model to process data and output a folder summary without providing any technological details as to how a folder summary is generated. The step of using a generative model to generate a folder summary is conventional activity. Such a well-understood, routine, conventional activity does not lend patent eligibility to the abstract idea of the claims by amounting the abstract idea to an inventive step.
Furthermore, the step of generating a request folder summary by “a prompt-generating engine using one or more generative models” recited at high level of generality is merely invokes a generative (learning) model to generate a request for summarizing a folder without providing any technological details as to how a folder summary is generated. The step of using a generative model to generate a request for folder summary is a conventional activity. Such a well-understood, routine, conventional activity does not lend patent eligibility to the abstract idea of the claims by amounting the abstract idea to an inventive step.
Additionally, the computer components of "one or more processors" and “computer readable media” are recited so generically that they represent no more than mere instructions to apply the judicial exception on a computer. These limitations can also be viewed as nothing more than an attempt to generally link the use of the judicial exception to the technological environment of a computer. It should be noted that because the courts have made it clear that mere physicality or tangibility of an additional element or elements is not a relevant consideration in the eligibility analysis, the physical nature of these computer components does not affect this analysis. See MPEP 2106.05(I) for more information on this point, including explanations from judicial
decisions including Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 224-26 (2014).
In addition, the feature of using a machine learning model to process data is a conventional and well-understood function in the art (See for example Koudas et al., US 2009/0319518, paragraph 130) which is simply appending well-understood, routine, conventional activities previously known to the industry, specified at high level of generality to the general exception (See MPEP 2106.05(d)). Thus, the claimed additional elements individually and in combination do not amount significantly more than abstract idea.
Therefore, the claims are not patent eligible.
Regarding dependent claims 3 and 4,
the dependent claims further recite the additional step for generating
embeddings [involves mathematical concepts of generating numerical representations of data], grouping files, selecting files, and generating file summary that could be performed mentally failing to integrate the judicial exception into a practical application or to amount significantly to more than abstract idea.
Regarding dependent claims 5-14,
The dependent claims further recite the additional step for determining,
generating, and data definition that could be performed mentally failing to integrate the judicial exception into a practical application or to amount significantly to more than abstract idea.
Regarding dependent claim 15-16,
the dependent claims also lack additional elements that sufficient to integrate the
judicial exception into a practical application or amount to significantly more than
abstract idea found in the independent claims.
The dependent claims recite the additional limitations of “wherein selecting the subset of files to represent the folder is performed using a file selection model based at least on file content of the plurality of files within the folder and metadata associated with the folder” and “wherein the file selection model is a machine learning model trained to select one or more files from a given folder.”
The limitation of selecting files using a model and the model being a machine learning model trained to select files recited at a high level of generality. At that level of generality, the claims do no more than describe desired function or outcome, without providing limiting details that confine the claimed to a practical solution to an identified problem. The features of using a model to select files and training the model recited at a high level of generality are extra-solution activities the central idea of claims. An invocation to use such an old technology in the manner it is intended to be used for its ordinary purpose is both generic and well-understood and conventional activity. They do not describe any particular improvement in the manner of computer functions. See MPEP 2106.04(d) and 2106.05(g).
Furthermore, the feature of using a machine learning model to process data is a
conventional and well-understood function in the art (See for example Koudas et al., US 2009/0319518, paragraph 130) which is simply appending well-understood, routine, conventional activities previously known to the industry, specified at high level of generality to the general exception (See MPEP 2106.05(d)).
Additionally, prior art Huang et al, US 20160294759 [paragraph 50, last three lines] and Kirshenbaum, US 2003/0191726 [paragraph 120] shows that the step of “training” is a well-known and well-understood computing activity previously known to the industry that specified at high level of generality to the general exception.
Regarding claim 17,
the dependent claim also lacks additional elements that sufficient to integrate the
judicial exception into a practical application or amount to significantly more than abstract idea found in the independent claims. The claim defines data and is merely non-functional descriptive material.
Regarding claim 19,
The claim recites the steps of:
identifying a folder to be summarized based on the request for folder summarization; [recited at a high level of generality and based on broadest and reasonable interpretation (BRI), it constitutes concepts of observation and evaluation which could be practically performed in the human mind]
identifying a plurality of files stored within the folder; [recited at a high level of generality and broadest on BRI, it constitutes concepts of observation, evaluation, and/or judgement which could be practically performed in the human mind. A human being could mentally and manually select subset of files]
selecting, from the plurality of files stored within the folder, a subset of files to represent folder; [recited at a high level of generality and based on BRI, it constitutes concepts of observation and evaluation which could be practically performed in the human mind]
generating…a folder summary request based at least on file content of the selected subset of files, wherein the folder summary request comprises one or more natural language instructions that define a structure of a folder summary to be generated based on the ranked list of file clusters; [recited at a high level of generality and broadest on BRI, it constitutes concepts of observation, evaluation, and/or judgement which could be practically performed in the human mind. A human being could mentally and manually generate a file summary request including instructions in natural language defining structure of the folder summary]
The above-mentioned steps are processes that, under its broadest reasonable
interpretation, covers performance of the limitation in the mind. That is, nothing in the claim element precludes the step from practically being performed in a human mind or with pen and paper. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind, then it falls within the “Mental Processes” grouping of abstract ideas (concepts performed in the human mind including an observation, evaluation, judgment, and opinion).
Prong 2:
This judicial exception recited in claim 19 is not integrated into a practical application. The claim recites the additional steps of “receiving a request for folder summarization” and “causing the folder summary to be rendered at one or more output devices” which could be considered as insignificant extra-solution activities of gathering data and outputting/displaying data. See MPEP 2106.04(d) and 2106.05(g).
Moreover, the step of “processing the folder summary request using a generative model to generate a model output reflecting the folder summary” recited at high level of generality is merely invokes a generative (learning) model to process data and output a folder summary without providing any technological details as to how a folder summary is generated. The step of using a generative model to generate a folder summary is an extra-solution activity to the central idea of claims. Such an insignificant extra-solution activity does not lend patent eligibility to the abstract idea of the claims by integrating the abstract idea into a practical application.
Furthermore, the step of generating a request folder summary by “a prompt-generating engine using one or more generative models” recited at high level of generality is merely invokes a generative (learning) model to generate a request for summarizing a folder without providing any technological details as to how a folder summary is generated. The step of using a generative model to generate a request for folder summary is an extra-solution activity to the central idea of claims. Such an insignificant extra-solution activity does not lend patent eligibility to the abstract idea of the claims by integrating the abstract idea into a practical application.
Additionally, the computer components of "one or more processors" and “computer readable media” are recited so generically that they represent no more than mere instructions to apply the judicial exception on a computer. These limitations can also be viewed as nothing more than an attempt to generally link the use of the judicial exception to the technological environment of a computer. It should be noted that because the courts have made it clear that mere physicality or tangibility of an additional element or elements is not a relevant consideration in the eligibility analysis, the physical nature of these computer components does not affect this analysis. See MPEP 2106.05(I) for more information on this point, including explanations from judicial
decisions including Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 224-26 (2014).
Accordingly, these additional elements do not integrate the abstract idea into a
practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea. See MPEP 2106.04(d) and 2106.05(g).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim recites the additional steps of “receiving a request for folder summarization” and “causing the folder summary to be rendered at one or more output devices” which could be considered as well-understood, routine, conventional activities of gathering data and outputting/displaying data. See MPEP 2106.04(d) and 2106.05(g).
Moreover, the step of “processing the folder summary request using a generative model to generate a model output reflecting a folder summary” recited at high level of generality is merely invokes a generative (learning) model to process data and output a folder summary without providing any technological details as to how a folder summary is generated. The step of using a generative model to generate a folder summary is conventional activity. Such a well-understood, routine, conventional activity does not lend patent eligibility to the abstract idea of the claims by amounting the abstract idea to an inventive step.
Furthermore, the step of generating a request folder summary by “a prompt-generating engine using one or more generative models” recited at high level of generality is merely invokes a generative (learning) model to generate a request for summarizing a folder without providing any technological details as to how a folder summary is generated. The step of using a generative model to generate a request for folder summary is a conventional activity. Such a well-understood, routine, conventional activity does not lend patent eligibility to the abstract idea of the claims by amounting the abstract idea to an inventive step.
Additionally, the computer components of "one or more processors" and
“computer readable media” are recited so generically that they represent no more than mere instructions to apply the judicial exception on a computer. These limitations can also be viewed as nothing more than an attempt to generally link the use of the judicial exception to the technological environment of a computer. It should be noted that because the courts have made it clear that mere physicality or tangibility of an additional element or elements is not a relevant consideration in the eligibility analysis, the physical nature of these computer components does not affect this analysis. See MPEP 2106.05(I) for more information on this point, including explanations from judicial decisions including Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 224-26 (2014).
In addition, the feature of using a machine learning model to process data is a conventional and well-understood function in the art (See for example Koudas et al., US 2009/0319518, paragraph 130) which is simply appending well-understood, routine, conventional activities previously known to the industry, specified at high level of generality to the general exception (See MPEP 2106.05(d)). Thus, the claimed additional elements individually and in combination do not amount significantly more than abstract idea.
Therefore, the claim is not patent eligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 3, 4, 9, 14, 18, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Ben, US 8,473,532 in view of Deo et al., US 2024/362467 (Deo, hereafter) and further in view of Lewis et al., US 9,367,814 (Lewis, hereafter) and further in view of Vyas et al., US 2025/0252384 (Vyas, hereafter).
Regarding claim 1,
Ben discloses a method implemented using one or more processors, the method comprising:
identifying a folder to be summarized based on the request for folder summarization (See Ben: at least 4:21-24, 4:28-29, 5:29-37, and 6:15-39, identifying at least one or more folders/directories to be summarized based on a call);
identifying a plurality of files stored within the folder (See Ben: at least 4:21-24, 4:28-29, 5:29-37, and 6:15-39, identifying files within folders);
selecting, from the plurality of files stored within the folder, a subset of files to represent the folder (See Ben: at least 4:21-24, 4:28-29, 5:29-37, and 6:15-39, identifying one or more of files to generate a summary or description for the folder/directory), wherein selecting comprises:
wherein selecting, from the plurality of files stored within the folder, the subset of files to represent the folder comprises: generating a content embedding for each file from the plurality of files, the content embedding of a respective file numerically representing content of a respective file from the plurality of files (See Ben: at least 2:57 to 3:67 and 6:15-67, generating vectors (i.e., embeddings) for files);
grouping, based on the content embedding for each file, the plurality of
files into a plurality of file clusters, wherein each file cluster includes one or more files having a similarity satisfying a similarity threshold (See Ben: at least 2:57 to 3:67 and 6:15-67, grouping/clustering in categories the files based on similarities);
selecting one or more of the file clusters to form the subset of files selected from the plurality of files (See Ben: at least 2:57 to 3:67 and 6:15-67).
Although, Ben discloses generating vectors and learning techniques, Ben does not explicitly teach receiving a request for folder summarization; processing the folder summary request using a generative model to generate a model output reflecting the folder summary; and causing the folder summary to be rendered at one or more output devices.
On the other hand, Deo discloses receiving a prompt from a user, and generating summary of contents of a folder using a generative AI, and providing the response to a user on a user interface (See Deo: at least Fig. 2-3, Fig. 6B, and para 11, 83-84, and 95-97). Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of Ben with Deo’s teaching in order to implement above function with reasonable expectation of success. The motivation for doing so would have been to improve functionality of the method by allowing a user to prompt an AI entity for AI-generated summary of contents of a
particular folder.
The combination of Ben and Deo discloses the limitations as stated above including a plurality of clusters/groups of files. However, it does not expressly teach ranking the plurality of file clusters to generate a ranked list of file clusters.
On the other hand, Lewis discloses ranking document clusters and to generate a
set or list of document clusters (See Lewis: at least Fig. 1 and 8:27-51). Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of the combination of Ben and Deo with Lewis’s teaching in order to implement above function with reasonable expectation of success. The motivation for doing so would have been to improve functionality of the method by creating an ordered list of file clusters prioritizing some file clusters based on one or more metrics.
The combination of Ben, Deo, and Lewis discloses the limitations as stated above including generating a folder summary or description based on the files and generating summary of contents of a folder using a generative AI. However, it does not explicitly teach generating, by a prompt-generating engine using one or more generative models, a summary request based at least on content of the selected subset of files, wherein the folder summary request comprises one or more natural language instructions that define a structure of a summary to be generated based on the file.
On the other hand, Vyas a program generating module using at least a generative model (e.g., GenAI, LLM) to generate a request to summarize text from documents including instruction and configurations to define structure for summary of documents (See Vyas: at least para 7, 10, 54-56, Fig. 5A-B, and Fig. 8A-E). Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of combination of Ben, Deo, and Lewis with Vyas’s teaching in order to generate, by a prompt-generating engine using one or more generative models, a folder summary request based at least on file content of the selected subset of files, wherein the folder summary request comprises one or more natural language instructions that define a structure of a folder summary to be generated based on the ranked list of file clusters with reasonable expectation of success. The motivation for doing so would have been to improve functionality of the method by giving instructions and input to the generative model on what and how to summarize of a folder.
Regarding claim 3,
the combination of Ben, Deo, Lewis, and Vyas discloses wherein the content embedding of the respective file is generated based on processing file content, or a file summary, of the respective file using a text encoder (See Ben: at least 2:57 to 3:67 and 6:15-67, generating vectors (i.e., embeddings) for files).
Regarding claim 4,
the combination of Ben, Deo, Lewis, and Vyas discloses wherein the file summary of the respective file is generated based on processing file content of the respective file using the generative model or an additional generative model (See Ben: at least 2:57 to 3:67 and 6:15-67 and Deo: at least Fig. 2-3, Fig. 6B, and para 11, 83-84, and 95-97).
Regarding claim 9,
the combination of Ben, Deo, Lewis, and Vyas discloses wherein the folder
summary for the folder identifies one or more key files from the folder (See Ben: at least 4:21-24, 4:28-29, 5:29-37, and 6:15-39).
Regarding claim 14,
the combination of Ben, Deo, Lewis, and Vyas discloses wherein the folder summary for the folder includes an overview summarizing an update to the folder within a default period of time before receiving the request (See Ben: at least 5:5-8 and 9:28-67 and Deo: at least Fig. 2-3, Fig. 6B, and para 11, 83-84, and 95-97).
Regarding claim 18,
the scope of the claim is substantially the same as claim 1, and is rejected on the same basis as set forth for the rejection of claim 1.
Regarding claim 19,
Ben discloses a non-transitory computer-readable media storing computer-readable instructions that when executed by one or more processors cause the one or more processors to perform operations, the operations comprising:
identifying a folder to be summarized based on the request for folder summarization (See Ben: at least 4:21-24, 4:28-29, 5:29-37, and 6:15-39, identifying at least one or more folders/directories to be summarized based on a call);
identifying a plurality of files stored within the folder (See Ben: at least 4:21-24, 4:28-29, 5:29-37, and 6:15-39, identifying files within folders); and
selecting, from the plurality of files stored within the folder, a subset of files to represent the folder (See Ben: at least 4:21-24, 4:28-29, 5:29-37, and 6:15-39, identifying one or more of files to generate a summary or description for the folder/directory).
Although, Ben discloses generating vectors and learning techniques, Ben does not explicitly teach receiving a request for folder summarization; processing the folder summary request using one or more generative models to generate a model output reflecting a folder summary; and causing the folder summary to be rendered at one or more output devices at one or more output devices.
On the other hand, Deo discloses receiving a prompt from a user, and generating summary of contents of a folder using a generative AI, and providing the response to a user on a user interface (See Deo: at least Fig. 2-3, Fig. 6B, and para 11, 83-84, and 95-97). Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of Ben with Deo’s teaching in order to implement above function with reasonable expectation of success. The motivation for doing so would have been to improve functionality of the method by allowing a user to prompt an AI entity for AI-generated summary of contents of a particular folder.
The combination of Ben and Deo discloses the limitations as stated above including generating a folder summary or description based on the files and generating summary of contents of a folder using a generative AI. However, it does not explicitly teach generating, by a prompt-generating engine using one or more generative models, a summary request based at least on content of the selected subset of files, wherein the folder summary request comprises one or more natural language instructions that define a structure of a summary to be generated based on the file.
On the other hand, Vyas a program generating module using at least a generative model (e.g., GenAI, LLM) to generate a request to summarize text from documents including instruction and configurations to define structure for summary of documents (See Vyas: at least para 7, 10, 54-56, Fig. 5A-B, and Fig. 8A-E). Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of the combination of Ben and Deo with Vyas’s teaching in order to generate, by a prompt-generating engine using one or more generative models, a folder summary request based at least on file content of the selected subset of files, wherein the folder summary request comprises one or more natural language instructions that define a structure of a folder summary to be generated based on the ranked list of file clusters with reasonable expectation of success. The motivation for doing so would have been to improve functionality of the method by giving instructions and input to the generative model on what and how to summarize of a folder.
Claims 5-8 and 10-13 are rejected under 35 U.S.C. 103 as being unpatentable over Ben, US 8,473,532 in view of Deo et al., US 2024/0362467 further in view of Lewis et al., US 9,367,814 further in view of Vyas et al., US 2025/0252384 and further in view of Peng et al., US 10,963,273 (Peng, hereafter).
Regarding claim 5,
the combination of Ben, Deo, Lewis, and Vyas discloses the limitations as stated above including generating folder summary based a user request. However, it does not explicitly teach determining metadata associated with a user who submitted the request; wherein generating the folder summary request based at least on the file content of the subset of files comprises: generating the folder summary request based further on the metadata associated with the user who submitted the request.
On the other hand, Peng discloses generating summarization of an object based on the requested user profile or metadata (See Peng: at least 2:35-40 and 20:30-43). Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of the combination of Ben, Deo, Lewis, and Vyas with Peng’s teaching in order to implement above function with reasonable expectation of success. The motivation for doing so would have been to personalize the content summarization based the user profile/metadata.
Regarding claim 6,
the combination of Ben, Deo, Lewis, and Vyas discloses the limitations as stated above including generating folder summary based a user request. However, it does not explicitly teach determining metadata associated with a user who submitted the request; wherein selecting the subset of files to represent the folder is based at least on the metadata associated with the user who submitted the request.
On the other hand, Peng discloses selecting content objects to generate summarization of an object based on the requested user profile or metadata (See Peng: at least 2:35-40, 2:63 to 3:10, and 20:30-43). Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of the combination of Ben, Deo, Lewis, and Vyas with Peng’s teaching in order to implement above function with reasonable expectation of success. The motivation for doing so would have been to personalize the content summarization based the user profile/metadata.
Regarding claim 7,
the combination of Ben, Deo, Lewis, and Vyas discloses the limitations as stated above including generating folder summary based a user request. However, it does not explicitly teach determining metadata associated with a user who submitted the request; wherein the folder summary varies in dependence on the metadata
associated with the user who submitted the request.
On the other hand, Peng discloses generating summarization of an object based on the requested user profile or metadata (See Peng: at least 2:35-40, 2:63 to 3:10, and 20:30-43). It would have been obvious to a person of ordinary skill in the art, that the content summarization would be different for different users because each user has his/her own user profile. Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of the combination of Ben, Deo, Lewis, and Vyas with Peng’s teaching in order to implement above function with reasonable expectation of success. The motivation for doing so would have been to personalize the content summarization based the user profile/metadata.
Regarding claim 8,
the combination of Ben, Deo, Lewis, and Vyas discloses the limitations as stated above including wherein the folder summary request includes an instruction to summarize updates to the folder that occurred within a predefined period of time, the predefined period of time being determined based on the metadata associated with the user indicating a most recent time the user accessed the folder (See Ben: at least 5:5-8 and 9:28-67, updating folder summary whenever files are added to or removed from a category implying that the system determine the addition or removing of the files since the last time it accessed the category). However, it does not explicitly teach determining metadata associated with a user who submitted the request.
On the other hand, Peng discloses selecting content objects to generate summarization of an object based on the requested user profile or metadata (See Peng: at least 2:35-40, 2:63 to 3:10, and 20:30-43). Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of the combination of Ben, Deo, Lewis, and Vyas with Peng’s teaching in order to determine metadata associated with a user who submitted the request; wherein the folder summary request includes an instruction to summarize updates to the folder that occurred within a predefined period of time, the predefined period of time being determined based on the metadata associated with the user indicating a most recent time the user accessed the folder, with reasonable expectation of success. The motivation for doing so would have been to personalize the content summarization based the user profile/metadata.
Regarding claim 10,
the combination of Ben, Deo, Lewis, and Vyas discloses the limitations as stated above including generating folder summary based a user request. However, it does not explicitly teach determining metadata associated with one or more users having access to the folder, the metadata associated with the one or more users having access to the folder indicating user activities of the one or more users with
respect to the folder or user relations between the one or more users.
On the other hand, Peng discloses selecting content objects to generate
summarization of an object based on the requested user profile or metadata, wherein the profile could be based on user activity or user relationship with other users (See Peng: at least 2:35-40, 2:63 to 3:10, 8:19-54, and 20:30-43). Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of the combination of Ben, Deo, Lewis, and Vyas with Peng’s teaching in order to implement above function with reasonable expectation of success. The motivation for doing so would have been to personalize the content summarization based the user profile/metadata.
Regarding claim 11,
the combination of Ben, Deo, Lewis, Vyas, and Peng discloses wherein generating the folder summary request is further based on the user activities of the one or more users, or based on the user relations between the one or more users (See Peng: at least 2:35-40, 2:63 to 3:10, 8:19-54, and 20:30-43).
Regarding claim 12,
the combination of Ben, Deo, Lewis, Vyas, and Peng discloses wherein the subset of files to represent the folder are selected based on the user activities of the one or more users, or based on the user relations between the one or more users (See Ben: at least 4:21-24, 4:28-29, 5:29-37, and 6:15-39 and Peng: at least 2:35-40, 2:63 to 3:10, 8:19-54, and 20:30-43).
Regarding claim 13,
the combination of Ben, Deo, Lewis, Vyas, and Peng discloses determining content associated with one or more of the user activities that alter one or more files within the folder, wherein the folder summary for the folder further includes one or more actions suggested for a user who submitted the request for folder summarization based on the one or more of the user activities (See Peng: at least 2:35-40, 2:63 to 3:10, 8:19-54, and 20:30-43).
Claims 15 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Ben, US 8,473,532 in view of Deo et al., US 2024/0362467 further in view of Lewis et al., US 9,367,814 further in view of Vyas et al., US 2025/0252384 and further in view of Wolf et al., US 2024/0273150 (Wolf, hereafter).
Regarding claim 15,
the combination of Ben, Deo, Lewis, and Vyas discloses the limitations as stated above including selecting subset of files for generating folder summary based on content and metadata. However, it does not explicitly teach using a file selection model based at least on file content of the plurality of files within the folder.
On the other hand, Wolf discloses using machine leaning to generate file selection models to select data/files based on content and metadata (See Wolf: at least para 54 and 58). Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of the combination of Ben, Deo, Lewis, and Vyas with Wolf’s teaching in order to perform selecting the subset of files to represent the folder using a file selection model based at least on file content of the plurality of files within the folder and metadata associated with the folder, with reasonable expectation of success. The motivation for doing so would have been to improve efficiency of file selection for folder summary generation.
Regarding claim 16,
the combination of Ben, Deo, Lewis, Vyas, and Wolf discloses wherein the file selection model is a machine learning model trained to select one or more files from a given folder (See Wolf: at least para 54 and 58).
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Ben, US 8,473,532 in view of Deo et al., US 2024/0362467 further in view of Lewis et al., US 9,367,814 further in view of Vyas et al., US 2025/0252384 and further in view of Fleizach et al., US 2009/0254345 (Fleizach, hereafter).
The combination of Ben, Deo, Lewis, and Vyas discloses the limitations as stated above including generating folder summary using one or more of files. However, it does not explicitly teach wherein the file content of the subset of files include a file summary for each file from the subset of files.
On the other hand, Fleizach discloses generating file summary for one or more files included in a folder (See Fleizach: at least para 68). Therefore, it would have been obvious to one of ordinary skill in the art before the time the invention was effectively filed to modify the teachings of the combination of Ben, Deo, Lewis, and Vyas with Fleizach’s teaching in order to perform above with reasonable expectation of success. The motivation for doing so would have been to improve quick review of selected files included in the folder and speed up the generation of a folder summary.
Points of Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HARES JAMI whose telephone number is (571)270-1291. The examiner can normally be reached M-F 9:00a-5:00p.
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, Amy Ng can be reached at 571-270-1698. 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.
/Hares Jami/ Primary Examiner, Art Unit 2164
07/17/2026
Prosecution Insights