CTNF 18/965,417 CTNF 85302 DETAILED ACTION This action is in response to the claims filed 12/2/2024. Claims 1-20 are pending. Independent claims 1, 8 and 15, and corresponding dependent claims are directed towards a method, system and non-transitory computer-storage medium for contextualized filtering of large language model content. Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. 07-06 AIA 15-10-15 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. Specification 07-29 AIA The disclosure is objected to because of the following informalities: the first recitation of the following acronyms is not expanded: [0012] CEO; and [0029] EU . Appropriate correction is required. Claim Rejections - 35 USC § 103 07-20-aia AIA The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. 07-21-aia AIA Claim s 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Chao et al. (US 2024/0095390 A1), published Mar. 21, 2024, in view of Alabdulkareem et al., “SecureLLM: Using Compositionality to Build Provably Secure Language Models for Private, Sensitive, and Secret Data”, published Jun.13, 2024 . As to claims 1, 8 and 15, Chao substantially discloses a computer-implemented method (Chao [0004] method ), a system (Chao [0003] system ) and a non-transitory computer-storage medium (Chao [0005] non-transitory computer-readable medium ), hereinafter referred to as a system, comprising: at least one processor (Chao [0004] processor ); and at least one memory including instructions which when executed by the at least one processor (Chao [0005] medium with executed instructions ) causes operations comprising: receiving a query to grant user access to content, the query including a user identifier (Chao Fig. 5 showing request 504 being received by attribute-based access control system 508 ; items 502-506 subject of request, request and context of request ; [0066] subject identifies user account ); verifying, based on the user identifier and using a first filter of a filter pipeline, a level of clearance associated with the user identifier (Chao [0068] subject permissions indicating what roles and/or permissions subject has with respect to requested resource ); granting, based at least on the verifying, the user access to at least a subset of the content (Chao [0003] determine from first data store and context of user account in initiating query first permissions for the user account for the resource – overlap between first permissions and second permissions results in approval of the query ); verifying, using at least a second filter of the filter pipeline, a temporal context of the query and a spatial context of the query, wherein the temporal context comprises a time at which the query is received and wherein the spatial context comprises a location from which the query is received (Chao [0066] Context identifies context in which request was made – including when the request was made and where the request was made ; [0003] determine from second data store and context of user account in initiating query second permissions for the user account for the resource – overlap between first permissions and second permissions results in approval of the query ); and providing, based at least on the verifying of the level of clearance and the verifying of the temporal context and the spatial context, at least the subset of content (Chao [0003] based on overlap of first and second permissions approve the query ; [0034] client computer accessing resource to read database records ). Chao fails to explicitly disclose content generated by a large-language model. Alabdulkareem describes securing LLMs from users who should not access them. With this in mind, Alabdulkareem discloses content generated by a large-language model (Alabdulkareem §1¶4 accessing LLM data based on user permissions ). It would have been obvious at the time the invention was made to a person having ordinary skill in the art to which said subject matter pertains to combine the SecureLLM of Alabdulkareem with the scalable access control of Chao, such that the data being accessed is the result of a secured LLM, as it would advantageously for LLMs to be deployed to secure environments (Alabdulkareem [Abstract]). As to claims 2, 9 and 16, Chao and Alabdulkareem disclose the invention as claimed as described in claims 1, 8 and 15, respectively, including wherein the user identifier comprises one or more of a login identifier, a time, or a location (Chao [0066] account or subscription used to make request, when request is made, where the request is made ). As to claims 3, 10 and 17, Chao and Alabdulkareem disclose the invention as claimed as described in claims 1, 8 and 15, respectively, including wherein the query is received from a user interface from which the query is generated (Chao Fig. 12 items 1238-1244 keyboard, touch screen and mouse used with input device interface for user interaction ). As to claims 4, 11 and 18, Chao and Alabdulkareem disclose the invention as claimed as described in claims 1, 8 and 15, respectively, including wherein the verifying the level of clearance associated with the user identifier comprises comparing a first vector embedding corresponding to the user identifier to a second vector embedding corresponding to a source on which the large-language model is trained (Alabdulkareem §1¶4 user permissions used to determine the collection of fine-tunings (of LLMs) used for access ). As to claims 5, 12 and 19, Chao and Alabdulkareem disclose the invention as claimed as described in claims 1, 8 and 15, respectively, including wherein the granting of the user access to at least the subset of the content generated by the large-language model comprises including the subset of the content in a query response (Chao [0034] read data from database records – indicates presentation of data ; Fig. 3 showing access types that include viewing data by the user ; Fig. 12 item 1246 computer monitor ). As to claims 6, 13 and 20, Chao and Alabdulkareem disclose the invention as claimed as described in claims 1, 8 and 15, respectively, including wherein the providing at least the subset of content generated by the large-language model comprises providing a query response to a user interface (Chao Fig. 3 showing access types that include viewing data by the user ; Fig. 12 item 1246 computer monitor ). As to claims 7 and 14, Chao and Alabdulkareem disclose the invention as claimed as described in claims 1 and 8, respectively, including further comprising training the large-language model using at least in part one or more documents that are non-public and/or confidential to an entity (Alabdulkareem §1¶2 LLM accessing silos of information that include collections of documents with sensitive information ) . Conclusion 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Waltermann et al. (US 2026/0105172 A1) is related to query generation from a prompt for a large language model. Hermanns et al. (US 2014/0181134 A1) is related to query building based on authorization conditions. Wang et al. (US 2025/0106221 A1) is related to access control. Any inquiry concerning this communication or earlier communications from the examiner should be directed to ERIC W SHEPPERD whose telephone number is (571)270-5654. The examiner can normally be reached Monday - Thursday, Alt. Friday, 7:30AM - 5:00PM, EST. 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, Rupal Dharia can be reached at (571)272-3880. 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. /Eric W Shepperd/Primary Examiner, Art Unit 2492 Application/Control Number: 18/965,417 Page 2 Art Unit: 2492 Application/Control Number: 18/965,417 Page 3 Art Unit: 2492 Application/Control Number: 18/965,417 Page 4 Art Unit: 2492 Application/Control Number: 18/965,417 Page 5 Art Unit: 2492 Application/Control Number: 18/965,417 Page 6 Art Unit: 2492 Application/Control Number: 18/965,417 Page 7 Art Unit: 2492 Application/Control Number: 18/965,417 Page 8 Art Unit: 2492
Prosecution Insights