Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
This office action is in response to the application filed on 10/30/2024. In which, claims 1-20 are pending and being considered, claims 1, 11 and 20 are independent, claims 1-20 are rejected.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 10/30/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Specification
The use of the term “Wifi” stated on page 4 lines 5-15, which is a trade name or a mark used in commerce, has been noted in this application. The term should be accompanied by the generic terminology; furthermore the term should be capitalized wherever it appears or, where appropriate, include a proper symbol indicating use in commerce such as ™, SM , or ® following the term.
Although the use of trade names and marks used in commerce (i.e., trademarks, service marks, certification marks, and collective marks) are permissible in patent applications, the proprietary nature of the marks should be respected and every effort made to prevent their use in any manner which might adversely affect their validity as commercial marks.
Claim Objections
Claims 1, 10-11 and 20 are objected to because of the following informalities:
In regards to Claims 1, 11 and 20, the applicant recites the limitation “prior to input to the language model.”, this is a typographically error as “input” has already been previously recites. The limitation should read “prior to the input to the language model”. Appropriate correction is required.
In regards to Claims 10, the applicant recites the limitation “user.”, this is a typographically error as “user” has already been previously recites. The limitation should read “the user”. Appropriate correction is required.
In regards to Claims 10, the applicant recites the limitation “a particular document”, this is a typographically error as “particular document” has already been previously recites. The limitation should read “the a particular document”.
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.
Claim(s) 1, 4, 8, 11, 14, 18 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kislal et al. (U.S Pub. No. 20240012842, hereinafter referred to as “Kislal”) further in view of Xu et al. (U.S Pub. No. 20220405245, hereinafter referred to as “Xu”)
In regards to Claim 1, Kislal teaches a method, comprising: maintaining, by a device, access permissions that control whether a user is allowed to access a particular document; (Figure 3 labels 310, 354, 370 and Par. (0116); maintaining, by a device (device processing agent) access permissions that control whether a user is allowed to access a particular document (device processing agent of system determines which user can access documents directly based on query with “output data” on which portions cannot be accessed)) (Par. (0121); administrator controlling privileges to documents and managing specific access to documents), (Par. (0123); maintaining by a device (document processing agent) access permissions that control whether a user is allowed to access a particular document (document processing agent is provided necessary information to access the document library by admin)), (Par. (0123); maintaining by a device access permission (administrator station provides to document processing agent permissions such as review and override of documents))
matching, by the device, a plurality of document chunks from a retrieval augmented generation system to a prompt issued by the user for input to a language model; (Par. (0134-0135 and 0137-0138); matching by the device (matching by query processing module 336 of device processing agent) a plurality of document chunks (one or more candidate portions of a document) to a prompt issued by the user for input to a language model (matches candidate portions of documents to query data sent by user associated with language model), (Figure 3 labels 310; by the device (document processing agent) )(Par. (0054); from a retrieval augmented generation system (models with processor in Fig. 1 being RAG the Retrieval-Augmented Generation (RAG) language model))
augmenting, by the device, the prompt using the modified set of document chunks prior to input to the language model. (Par. (0130); query processing module of document processing agent augments (transforms) the prompt (query data)), (Par. (0134); using the modified set of document chunks (candidate portions of document inside transformed source content)), (Par. (0153-0154); prior to input to the language model. (augmentation corresponding to query and segmented document that is outputted is before being provided to transformer models))
Kislal does not explicitly teach forming, by the device and based on the access permissions, a modified set of document chunks by excluding a particular document chunk from the plurality of document chunks based on the particular document chunk having a data lineage from the particular document; and
Wherein Xu teaches forming, by the device and based on the access permissions, a modified set of document chunks by excluding a particular document chunk from the plurality of document chunks based on the particular document chunk having a data lineage from the particular document; and (Par. (0089); by the device and based on access permission (once user logs in the metadata identifying the files have permissions included)), (Par. (0037); forming by the device a modified set of document chunks (user generates another file by copying portions from existing file into a new file with one or more selected portions) excluding a particular document chunk (excludes the non-selected portions of the first file) from the plurality of document chunks based on the particular document chunk (one or more portions of the file)), (Par. (0054); having a data lineage from the particular document (user still maintains original file with particular document chunk (excluded portions)) for access to it and sends separate files to recipient users), (Par. (0118); forming, by the device and based on the access permissions, a modified set of document chunks ( indication of access setting for group of users for selecting portions of first file)))(Examiner note: In the instant application there is no distinct example for “data lineage” only on page 12 lines 1-20 . Therefore it will be broadly and reasonably interpreted that data lineage refers to a tracking or determining of an original document or file))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal to incorporate the teaching of Xu to utilize the above feature because of the analogous concept of accessing document files that are segmented based on permissions, with the motivation of preventing access to unauthorized users that contain sensitive information while still being able to share files more freely. This eliminates concern of risk and loss of confidential information being share by portioning and selecting which portions are designated to which users based on access and thus improving the document file sharing system without security risks. (Xu Par. (0026-0027))
In regards to Claim 4, the combination of Kislal and Xu teach the method of claim 1, Xu further teaches wherein the access permissions prevent the user from accessing the particular document. (Par. (0119); user prevented to access selected portions of document with “restrictive” indication))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal to incorporate the teaching of Xu to utilize the above feature because of the analogous concept of accessing document files that are segmented based on permissions, with the motivation of implementing a restriction of access to users to prevent access to unauthorized users that contain sensitive information. This mitigates concerns of security risk and loss of confidential information because by selecting which users can have access to certain portions of the document file and which users have restricted access employees and administrators can share and regulate transfers of documents without having issues of privacy and this protecting the confidential data. (Xu Par. (0026-0027))
In regards to Claim 8, the combination of Kislal and Xu teach the method of claim 1, Xu further teaches identifying the access permissions applicable to the user based on a user authentication process. (Par. (0089); identifying permissions in metadata that show respective users are allowed access based on authentication of entering password and logging in))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal to incorporate the teaching of Xu to utilize the above feature because of the analogous concept of accessing document files that are segmented based on permissions, with the motivation of implementing authentications measures to select users with specific permission that can view the document file, this helps regulate access and prevents unauthorized access of sensitive information. By having an authentication process of logging in only accurate files with specific access rights can be viewed and helps the management system detect authorized users. (Xu Par. (0083 and 0089-0090))
In regards to Claim 11, Kislal teaches an apparatus, comprising: (Par. (0119); document processing agent as computing device))
one or more network interfaces; (Par. (0119); interfaces with network associated with document processing agent)
a processor coupled to the one or more network interfaces and configured to execute one or more processes; and (Par. (0119); document processing agent with processor- and interface))
a memory configured to store a process that is executable by the processor, the process when executed configured to: (Figure 3 labels 310 and 340; document processing agent with memory) (Par. (0128); label 340 of documenting processing agent includes memory ))
maintain access permissions that control whether a user is allowed to access a particular document; (Figure 3 labels 310, 354, 370 and Par. (0116); maintaining, by a device (device processing agent) access permissions that control whether a user is allowed to access a particular document (device processing agent of system determines which user can access documents directly based on query with “output data” on which portions cannot be accessed)), (Par. (0121); administrator controlling privileges to documents and managing specific access to documents), (Par. (0123); maintaining by a device (document processing agent) access permissions that control whether a user is allowed to access a particular document; (document processing agent is provided necessary information to access the document library by admin)), (Par. (0123); maintaining by a device access permission (administrator station provides to document processing agent permissions such as review and override of documents))
match a plurality of document chunks from a retrieval augmented generation system to a prompt issued by the user for input to a language model; (Par. (0134-0135 and 0137-0138); matching by the device (matching by query processing module 336 of device processing agent) a plurality of document chunks (one or more candidate portions of a document) to a prompt issued by the user for input to a language model (matches candidate portions of documents to query data sent by user associated with language model), (Figure 3 labels 310; by the device (document processing agent) )(Par. (0054); from a retrieval augmented generation system (models with processor in Fig. 1 being RAG the Retrieval-Augmented Generation (RAG) language model))
augment the prompt using the modified set of document chunks prior to input to the language model. (Par. (0130); query processing module of document processing agent augments (transforms) the prompt (query data)), (Par. (0134); using the modified set of document chunks (candidate portions of document inside transformed source content)), (Par. (0153-0154); prior to input to the language model. (augmentation corresponding to query and segmented document that is outputted is before being provided to transformer models))
Kislal does not explicitly teach form, based on the access permissions, a modified set of document chunks by excluding a particular document chunk from the plurality of document chunks based on the particular document chunk having a data lineage from the particular document; and
Wherein Xu teaches form, based on the access permissions, a modified set of document chunks by excluding a particular document chunk from the plurality of document chunks based on the particular document chunk having a data lineage from the particular document; and (Par. (0089); by the device and based on access permission (once user logs in the metadata identifying the files have permissions included)), (Par. (0037); forming by the device a modified set of document chunks (user generates another file by copying portions from existing file into a new file with one or more selected portions) excluding a particular document chunk (excludes the non-selected portions of the first file) from the plurality of document chunks based on the particular document chunk (one or more portions of the file)), (Par. (0054); having a data lineage from the particular document (user still maintains original file with particular document chunk (excluded portions)) for access to it and sends separate files to recipient users), (Par. (0118); forming, by the device and based on the access permissions, a modified set of document chunks ( indication of access setting for group of users for selecting portions of first file)))(Examiner note: In the instant application there is no distinct example for “data lineage” only on page 12 lines 1-20 . Therefore it will be broadly and reasonably interpreted that data lineage refers to a tracking or determining of an original document or file))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal to incorporate the teaching of Xu to utilize the above feature because of the analogous concept of accessing document files that are segmented based on permissions, with the motivation of preventing access to unauthorized users that contain sensitive information while still being able to share files more freely. This eliminates concern of risk and loss of confidential information being share by portioning and selecting which portions are designated to which users based on access and thus improving the document file sharing system without security risks. (Xu Par. (0026-0027))
In regards to Claim 14, the combination of Kislal and Xu teach the apparatus of claim 11, Xu further teaches wherein the access permissions prevent the user from accessing the particular document. (Par. (0119); user prevented to access selected portions of document with “restrictive” indication))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal to incorporate the teaching of Xu to utilize the above feature because of the analogous concept of accessing document files that are segmented based on permissions, with the motivation of implementing a restriction of access to users to prevent access to unauthorized users that contain sensitive information. This mitigates concerns of security risk and loss of confidential information because by selecting which users can have access to certain portions of the document file and which users have restricted access employees and administrators can share and regulate transfers of documents without having issues of privacy and this protecting the confidential data. (Xu Par. (0026-0027))
In regards to Claim 18, the combination of Kislal and Xu teach the apparatus as in claim 11, Xu further teaches identify the access permissions applicable to the user based on a user authentication process. (Par. (0089); identifying permissions in metadata that show respective users are allowed access based on authentication of entering password and logging in))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal to incorporate the teaching of Xu to utilize the above feature because of the analogous concept of accessing document files that are segmented based on permissions, with the motivation of implementing authentications measures to select users with specific permission that can view the document file, this helps regulate access and prevents unauthorized access of sensitive information. By having an authentication process of logging in only accurate files with specific access rights can be viewed and helps the management system detect authorized users. (Xu Par. (0083 and 0089-0090))
In regards to Claim 20, Kislal teaches a tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising: (Par. (0166); a computer accessible storage medium may include any non-transitory storage media))
maintaining access permissions that control whether a user is allowed to access a particular document; (Figure 3 labels 310, 354, 370 and Par. (0116); maintaining, by a device (device processing agent) access permissions that control whether a user is allowed to access a particular document (device processing agent of system determines which user can access documents directly based on query with “output data” on which portions cannot be accessed)), (Par. (0121); administrator controlling privileges to documents and managing specific access to documents), (Par. (0123); maintaining by a device (document processing agent) access permissions that control whether a user is allowed to access a particular document; (document processing agent is provided necessary information to access the document library by admin)), (Par. (0123); maintaining by a device access permission (administrator station provides to document processing agent permissions such as review and override of documents))
matching a plurality of document chunks from a retrieval augmented generation system to a prompt issued by the user for input to a language model; (Par. (0134-0135 and 0137-0138); matching by the device (matching by query processing module 336 of device processing agent) a plurality of document chunks (one or more candidate portions of a document) to a prompt issued by the user for input to a language model (matches candidate portions of documents to query data sent by user associated with language model), (Figure 3 labels 310; by the device (document processing agent) )(Par. (0054); from a retrieval augmented generation system (models with processor in Fig. 1 being RAG the Retrieval-Augmented Generation (RAG) language model))
augmenting the prompt using the modified set of document chunks prior to input to the language model. (Par. (0130); query processing module of document processing agent augments (transforms) the prompt (query data)), (Par. (0134); using the modified set of document chunks (candidate portions of document inside transformed source content)), (Par. (0153-0154); prior to input to the language model. (augmentation corresponding to query and segmented document that is outputted is before being provided to transformer models))
Kislal does not explicitly teach forming, based on the access permissions, a modified set of document chunks by excluding a particular document chunk from the plurality of document chunks based on the particular document chunk having a data lineage from the particular document; and
Wherein Xu teaches forming, based on the access permissions, a modified set of document chunks by excluding a particular document chunk from the plurality of document chunks based on the particular document chunk having a data lineage from the particular document; and (Par. (0089); by the device and based on access permission (once user logs in the metadata identifying the files have permissions included)), (Par. (0037); forming by the device a modified set of document chunks (user generates another file by copying portions from existing file into a new file with one or more selected portions) excluding a particular document chunk (excludes the non-selected portions of the first file) from the plurality of document chunks based on the particular document chunk (one or more portions of the file)), (Par. (0054); having a data lineage from the particular document (user still maintains original file with particular document chunk (excluded portions)) for access to it and sends separate files to recipient users), (Par. (0118); forming, by the device and based on the access permissions, a modified set of document chunks ( indication of access setting for group of users for selecting portions of first file)))(Examiner note: In the instant application there is no distinct example for “data lineage” only on page 12 lines 1-20 . Therefore it will be broadly and reasonably interpreted that data lineage refers to a tracking or determining of an original document or file))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal to incorporate the teaching of Xu to utilize the above feature because of the analogous concept of accessing document files that are segmented based on permissions, with the motivation of preventing access to unauthorized users that contain sensitive information while still being able to share files more freely. This eliminates concern of risk and loss of confidential information being share by portioning and selecting which portions are designated to which users based on access and thus improving the document file sharing system without security risks. (Xu Par. (0026-0027))
Claim(s) 2 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kislal et al. (U.S Pub. No. 20240012842, hereinafter referred to as “Kislal”) and Xu et al. (U.S Pub. No. 20220405245, hereinafter referred to as “Xu”) further in view of Huang et al. (U.S Pub. No. 20250111151, hereinafter referred to as “Huang”)
In regards to Claim 2, the combination of Kislal and Xu do not explicitly teach reranking documents in the modified set of document chunks prior to the input to the language model.
Wherein Huang teaches reranking documents in the modified set of document chunks prior to the input to the language model. (Par. (0019); re-ranking the candidate portions of the document before prompting machine learning model to generate a result))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Huang to utilize the above feature because of the analogous concept of segmenting document files in a retrieval augmentation generation system, with the motivation of using a retrieval augmentation generation system to obtain relevant data enhance the LLM models by re-ranking documents and selected portions to ensure confidence in the user and allow the machine learning models to identify errors and select the most effective portions of the modified documents. (Huang Par. (0016-0017 and 0096))
In regards to Claim 12, the combination of Kislal and Xu do not explicitly teach perform a reranking of documents in the modified set of document chunks prior to the input to the language model.
Wherein Huang teaches perform a reranking of documents in the modified set of document chunks prior to the input to the language model. (Par. (0019); re-ranking the candidate portions of the document before prompting machine learning model to generate a result))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Huang to utilize the above feature because of the analogous concept of segmenting document files in a retrieval augmentation generation system, with the motivation of using a retrieval augmentation generation system to obtain relevant data enhance the LLM models by re-ranking documents and selected portions to ensure confidence in the user and allow the machine learning models to identify errors and select the most effective portions of the modified documents. (Huang Par. (0016-0017 and 0096))
Claim(s) 3 and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kislal et al. (U.S Pub. No. 20240012842, hereinafter referred to as “Kislal”) and Xu et al. (U.S Pub. No. 20220405245, hereinafter referred to as “Xu”) further in view of Fu et al. (U.S Pub. No. 20240184570, hereinafter referred to as “Fu”)
In regards to Claim 3, the combination of Kislal and Xu teach the method of claim 1, Xu further teaches wherein that data lineage identifies an originating document for a corresponding document chunk. (Par. (0054); data lineage identifies an originating document (user still maintains original file for access to it and sends separate files to recipient users), (Par. (0125) user maintains original format of first file corresponding to portions of document))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal to incorporate the teaching of Xu to utilize the above feature because of the analogous concept of accessing document files that are segmented based on permissions, with the motivation of maintaining a history of original files and data lineage to allow the user to separately store the original file and keep track and have access of information along with the modified and copied file portions. (Xu Par. (00053-0054))
Kislal and Xu do not explicitly teach associating a data lineage to each document chunk ingested into the retrieval augmented generation system,
Wherein Fu teaches associating a data lineage to each document chunk ingested into the retrieval augmented generation system, (Par. (0019, 0021 and 0023); associating a data lineage to each document chunk (chunks of code associated to original code/file) ingested into the retrieval augmented generation system (chunks of the code are part of the retrieval augmented model review)), (Par. (0066, 0069 and 0098); associating a data lineage (original file included) to each document chunk (with each chunk of code) ingested into the retrieval augmented generation system (a part of retrieval augmented code completion and associated tracking of each file and code))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Fu to utilize the above feature because of the analogous concept of accessing document files in a retrieval augmentation system, with the motivation of associating data lineage using retrieval augmentation to review possible candidate files and documents to allow the machine models to make a prediction along with identify changes from original file and use a form of reference with file changes and chunks stored in a database. (Fu Par. (0015-0019))
In regards to Claim 13, the combination of Kislal and Xu teach the apparatus of claim 11, Xu further teaches wherein that data lineage identifies an originating document for a corresponding document chunk. (Par. (0054); data lineage identifies an originating document (user still maintains original file for access to it and sends separate files to recipient users), (Par. (0125) user maintains original format of first file corresponding to portions of document))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal to incorporate the teaching of Xu to utilize the above feature because of the analogous concept of accessing document files that are segmented based on permissions, with the motivation of maintaining a history of original files and data lineage to allow the user to separately store the original file and keep track and have access of information along with the modified and copied file portions. (Xu Par. (00053-0054))
Kislal and Xu do not explicitly teach associate a data lineage to each document chunk ingested into the retrieval augmented generation system,
Wherein Fu teaches associate a data lineage to each document chunk ingested into the retrieval augmented generation system, (Par. (0019, 0021 and 0023); associating a data lineage to each document chunk (chunks of code associated to original code/file) ingested into the retrieval augmented generation system (chunks of the code are part of the retrieval augmented model review)), (Par. (0066, 0069 and 0098); associating a data lineage (original file included) to each document chunk (with each chunk of code) ingested into the retrieval augmented generation system (a part of retrieval augmented code completion and associated tracking of each file and code))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Fu to utilize the above feature because of the analogous concept of accessing document files in a retrieval augmentation system, with the motivation of associating data lineage using retrieval augmentation to review possible candidate files and documents to allow the machine models to make a prediction along with identify changes from original file and use a form of reference with file changes and chunks stored in a database. (Fu Par. (0015-0019))
Claim(s) 5-6 and 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kislal et al. (U.S Pub. No. 20240012842, hereinafter referred to as “Kislal”) and Xu et al. (U.S Pub. No. 20220405245, hereinafter referred to as “Xu”) further in view of Nahamoo et al. (U.S Pub. No. 20210406735, hereinafter referred to as “Nahamoo”)
In regards to Claim 5, the combination of Kislal and Xu do not explicitly teach maintaining a data lineage repository associating chunk identifiers that identify each document chunk ingested into the retrieval augmented generation system with originating document identifiers that identify an originating document for a corresponding document chunk.
Wherein Nahamoo teaches maintaining a data lineage repository associating chunk identifiers that identify each document chunk ingested into the retrieval augmented generation system with originating document identifiers that identify an originating document for a corresponding document chunk. (Par. (0075 and 0121); a data lineage repository associating chunk identifiers (in the repository portions of the documents include document identifiers for start and end locations of the portion of document)), (Par. (0072 and 0075); a data lineage repository (original document form ingested at repository) associating chunk identifiers (document identifiers with portion of source document) that identify each document chunk ingested (start and end location of portion of source document in repository) into the retrieval augmented generation (question and answer system))), (Par. (0069, 0109 ); into the retrieval augmented generation (question and answer system corresponding to repository and question and answering system with language model)) (Par. (0075); with originating document identifiers (source document with identifiers associated with portion of document) that identify an originating document for a corresponding document chunk (source document is included in portion of document that has document identifiers that has start and end locations of the portion of the document)), (Examiner Note: Examiner with ordinary skill in the art interprets types of retrieval augmented generation system to be Q&A systems, chat box etc. associated with A.I))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Nahamoo to utilize the above feature because of the analogous concept of accessing document files in a retrieval augmentation using Q&A systems, with the motivation of fixing data privacy and security concerns with large documents by using models to regulate access and portions of documents with pointers to be able to improve speed and accuracy of documents storage and retrieval. (Nahamoo Par. (0005-0007))
In regards to Claim 6, the combination of Kislal and Xu do not explicitly teach referencing the data lineage repository to identify the data lineage of the particular document chunk.
Wherein Nahamoo teaches referencing the data lineage repository to identify the data lineage of the particular document chunk. (Par. (0075); identifying the source document in the repository and the portion of the source document)(Par. (0062, 0072); original portion and original content of document is stored and identified)), (Examiner Note: Examiner equates data lineage to original document or source document that is identified and stored in the repository))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Nahamoo to utilize the above feature because of the analogous concept of accessing document files in a retrieval augmentation using Q&A systems, with the motivation of referencing identifier, pointers and other data in data lineage repository to improve speed and accuracy of documents storage and retrieval as well as have a history of start and end locations of documents during transfer. (Nahamoo Par. (0005-0007 and 0075))
In regards to Claim 15, the combination of Kislal and Xu do not explicitly teach maintain a data lineage repository associating chunk identifiers that identify each document chunk ingested into the retrieval augmented generation system with originating document identifiers that identify an originating document for a corresponding document chunk.
Wherein Nahamoo teaches maintain a data lineage repository associating chunk identifiers that identify each document chunk ingested into the retrieval augmented generation system with originating document identifiers that identify an originating document for a corresponding document chunk. (Par. (0075 and 0121); a data lineage repository associating chunk identifiers (in the repository portions of the documents include document identifiers for start and end locations of the portion of document)), (Par. (0072 and 0075); a data lineage repository (original document form ingested at repository) associating chunk identifiers (document identifiers with portion of source document) that identify each document chunk ingested (start and end location of portion of source document in repository) into the retrieval augmented generation (question and answer system))), (Par. (0069, 0109 ); into the retrieval augmented generation (question and answer system corresponding to repository and question and answering system with language model)) (Par. (0075); with originating document identifiers (source document with identifiers associated with portion of document) that identify an originating document for a corresponding document chunk (source document is included in portion of document that has document identifiers that has start and end locations of the portion of the document)), (Examiner Note: Examiner with ordinary skill in the art interprets types of retrieval augmented generation system to be Q&A systems, chat box etc. associated with A.I))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Nahamoo to utilize the above feature because of the analogous concept of accessing document files in a retrieval augmentation using Q&A systems, with the motivation of fixing data privacy and security concerns with large documents by using models to regulate access and portions of documents with pointers to be able to improve speed and accuracy of documents storage and retrieval. (Nahamoo Par. (0005-0007))
In regards to Claim 16, the combination of Kislal and Xu do not explicitly teach reference the data lineage repository to identify the data lineage of the particular document chunk.
Wherein Nahamoo teaches reference the data lineage repository to identify the data lineage of the particular document chunk. (Par. (0075); identifying the source document in the repository and the portion of the source document)(Par. (0062, 0072); original portion and original content of document is stored and identified), (Examiner Note: Examiner equates data lineage to original document or source document that is identified and stored in the repository))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Nahamoo to utilize the above feature because of the analogous concept of accessing document files in a retrieval augmentation using Q&A systems, with the motivation of referencing identifier, pointers and other data in data lineage repository to improve speed and accuracy of documents storage and retrieval as well as have a history of start and end locations of documents during transfer. (Nahamoo Par. (0005-0007 and 0075))
Claim(s) 7 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kislal et al. (U.S Pub. No. 20240012842, hereinafter referred to as “Kislal”) and Xu et al. (U.S Pub. No. 20220405245, hereinafter referred to as “Xu”) further in view of Iitsuka et al. (U.S Pub. No. 20230208894, hereinafter referred to as “Iitsuka”)
In regards to Claim 7, the combination of Kislal and Xu teach the method of claim 1, Kislal further teaches retrieval augmented generation system (Par. (0054); from a retrieval augmented generation system (models with processor in Fig. 1 being RAG the Retrieval-Augmented Generation (RAG) language model))
Kislal and Xu do not explicitly teach updating, based on a change in document access rights associated with the user, which of the plurality of document chunks from the … system are included in the modified set of document chunks.
Wherein Iitsuka teaches updating, based on a change in document access rights associated with the user, which of the plurality of document chunks from the … system are included in the modified set of document chunks. (Par. (0023-0025); updating which plurality of documents chunks are included (updating the privilege portions of file) from the system (blockchain system) are included in the modified set of documents ( updating privilege portions of file that are included and not non-privileged portions)), (Par. (0025); based on a change in document access rights (consensus to edit and add changes to privilege portion of shared file)), (Par. (0019); updating which of the plurality of document chunks are included ( document/ file is edited and updates on privilege section not non-privileged section))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Iitsuka to utilize the above feature because of the analogous concept of accessing document files and segmenting portions, with the motivation of updating portions of electronic documents for simplified presentation to users and to manage and create accessibility to the users. (Iitsuka Par. (0003-0005 and 0040))
In regards to Claim 17, the combination of Kislal and Xu teach the apparatus of claim 11, Kislal further teaches retrieval augmented generation system (Par. (0054); from a retrieval augmented generation system (models with processor in Fig. 1 being RAG the Retrieval-Augmented Generation (RAG) language model))
Kislal and Xu do not explicitly teach update, based on a change in document access rights associated with the user, which of the plurality of document chunks from the……system are included in the modified set of document chunks.
Wherein Iitsuka teaches update, based on a change in document access rights associated with the user, which of the plurality of document chunks from the……system are included in the modified set of document chunks. (Par. (0023-0025); updating which plurality of documents chunks are included (updating the privilege portions of file) from the system (blockchain system) are included in the modified set of documents ( updating privilege portions of file that are included and not non-privileged portions)), (Par. (0025); based on a change in document access rights (consensus to edit and add changes to privilege portion of shared file)), (Par. (0019); updating which of the plurality of document chunks are included ( document/ file is edited and updates on privilege section not non-privileged section))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Iitsuka to utilize the above feature because of the analogous concept of accessing document files and segmenting portions, with the motivation of updating portions of electronic documents for simplified presentation to users and to manage and create accessibility to the users. (Iitsuka Par. (0003-0005 and 0040))
Claim(s) 9 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kislal et al. (U.S Pub. No. 20240012842, hereinafter referred to as “Kislal”) and Xu et al. (U.S Pub. No. 20220405245, hereinafter referred to as “Xu”) further in view of Tan et al. (U.S Pub. No. 20130332723, hereinafter referred to as “Tan”)
In regards to Claim 9, the combination of Kislal and Xu teach the method of claim 1, Kislal further teaches retrieval augmented generation system (Par. (0054); from a retrieval augmented generation system (models with processor in Fig. 1 being RAG the Retrieval-Augmented Generation (RAG) language model))
Kislal and Xu do not explicitly teach requiring the user to reauthenticate responsive to a new document being ingested into the …… system.
Wherein Tan teaches requiring the user to reauthenticate responsive to a new document being ingested into …… system. (Par. (0026, 0058); requiring the user to reauthenticate (re-validate the user session), responsive to a new document being ingested (file is received and desired changes made, uploading to sending application the revalidating occurs))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Tan to utilize the above feature because of the analogous concept of accessing segmented portions of document files in system based on permissions, with the motivation of re-validating users to ensure secure protection of documents and regulating access for users to collaborate and have specific access to different pieces of the document. (Tan Par. (0003-0005 and 0040))
In regards to Claim 19, the combination of Kislal and Xu teach apparatus as in claim 11, Kislal further teaches retrieval augmented generation system (Par. (0054); from a retrieval augmented generation system (models with processor in Fig. 1 being RAG the Retrieval-Augmented Generation (RAG) language model))
Kislal and Xu do not explicitly teach require the user to reauthenticate responsive to a new document being ingested into the …..system.
Wherein Tan teaches require the user to reauthenticate responsive to a new document being ingested into the …..system. (Par. (0026, 0058); requiring the user to reauthenticate (re-validate the user session), responsive to a new document being ingested (file is received and desired changes made, uploading to sending application the revalidating occurs))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Tan to utilize the above feature because of the analogous concept of accessing segmented portions of document files in system based on permissions, with the motivation of re-validating users to ensure secure protection of documents and regulating access for users to collaborate and have specific access to different pieces of the document. (Tan Par. (0003-0005 and 0040))
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kislal et al. (U.S Pub. No. 20240012842, hereinafter referred to as “Kislal”) and Xu et al. (U.S Pub. No. 20220405245, hereinafter referred to as “Xu”) further in view of Shafer et al. (U.S Pub. No. 20180059775, hereinafter referred to as “Shafer”)
In regards to Claim 10, the combination of Kislal and Xu do not explicitly teach recomputing the access permissions that control whether a user is allowed to access a particular document responsive to a push notification of a permission change for a document.
Wherein Shafer teaches recomputing the access permissions that control whether a user is allowed to access a particular document responsive to a push notification of a permission change for a document. (Par. (0046); recomputing the access permissions (administrator changes particular role of users)), (Par. (0012-0013); access permissions that control whether a user is allowed to access a particular document (roles corresponding to access to confidential information)), (Par. (0076); responsive to a push notification of a permission change for a document (push notification provided when permissions for a role have been changed)), (Par. (0072); roles corresponding to accessing files))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kislal and Xu to incorporate the teaching of Shafer to utilize the above feature because of the analogous concept of accessing segmented portions of document files in system based on permissions, with the motivation of improving security based on roles and accessing sensitive and private files of patients by managing roles and giving push notification to parties the users are more securely protected and aware of changes. (Shafer Par. (0013-0016))
Relevant Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Geng; Shijie (U.S Pub. No. 20230153531) “ENHANCED DOCUMENT VISUAL QUESTION ANSWERING SYSTEM VIA HIERARCHICAL ATTENTION”. Considered this reference because it addressed Q&A systems of retrieval augmentation and tagging document sections with lineage repository.
Hahn; Michael (U.S Pub. No. 20230246860) “DOCUMENT MANAGEMENT IN A COMMUNICATION PLATFORM”. Considered this application because it relates to the excluding of portions of documents and an updating process based on permissions and access.
Pereira; Carlos Goncalves (WO Pub. No. 20250342152) “DYNAMIC PRIORITIZATION OF CONTEXT AND SIMILARITY SEARCH FOR HETEROGENOUS DATA SOURCES”. Considered this application because it addressed similar concepts of instant application with same inventors and assignee discussing retrieval augmentations.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HASSAN A HUSSEIN whose telephone number is (571)272-3554. The examiner can normally be reached on 7:30am-5pm.
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, Eleni Shiferaw can be reached on (571)272-3867. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/HASSAN A HUSSEIN/ Examiner, Art Unit 2497