DETAILED ACTION
Remarks
This Office Action is in response to the application 19/068993 filed on 3 March 2025.
Claims 1-20 have been examined.
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 .
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claim 1 is provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1 and 6 of copending U.S. application no. 19/066050 in view of Crabtree et al. (U.S. Patent Application Publication No. 20250258852 A1, hereinafter referred to as Crabtree). Although they are not identically worded, claims 1 and 6 of the reference application teach almost all of the features of examined claim 1, except for generating vector embeddings and a semantic vector augmentation piple. Crabtree teaches this (Crabtree para. 0083: generating vector embeddings; and Crabtree 0157 and Fig. 1: Enterprise knowledge 111 comprises documents; and Crabtree para. 0100: Retrieval augmented generation (RAG); and Crabtree para. 0125: vectors capture semantic information). It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified reference claims 1 and 6 to include the teachings of Crabtree because it enhances language models by incorporating external knowledge (Crabtree para. 0100), including semantic information about works or tokens (Crabtree para. 0125).
This is a provisional nonstatutory double patenting rejection. If the co-pending application(s) are issued as patent(s), the double patenting rejections will be converted from provisional to non-provisional.
Claim 1 is provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 6, and 7 of copending U.S. application no. 19/079190 in view of Crabtree et al. (U.S. Patent Application Publication No. 20250258852 A1, hereinafter referred to as Crabtree). Although they are not identically worded, claims 1, 6, and 7 of the reference application teach almost all of the features of examined claim 1, except for a semantic vector augmentation pipeline. Crabtree teaches a semantic vector augmentation pipeline (Crabtree para. 0100: Retrieval augmented generation (RAG); and Crabtree para. 0125: vectors capture semantic information). It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified reference claims 1, 6, and 7 to include the teachings of Crabtree because it enhances language models by incorporating external knowledge (Crabtree para. 0100), including semantic information about works or tokens (Crabtree para. 0125).
This is a provisional nonstatutory double patenting rejection. If the co-pending application(s) are issued as patent(s), the double patenting rejections will be converted from provisional to non-provisional.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
As to claims 1, 10, and 19, these claims recite a plurality of documents. The claims do not specify nor place any limits upon the number of documents, other than using the plural form of the word (i.e. “documents”). Under the broadest reasonable interpretation (BRI), the claims encompass a simple case of just two documents. In addition, the claims do not specify nor place any limits upon the length of these documents. The BRI encompasses a simple case of small documents (e.g. containing just a few words or sentences). These claims recite “generating a set of vector embeddings based at least in part on the plurality of documents and a semantic vector augmentation pipeline.” “Vector embeddings are numerical representations of data points that express different types of data, including nonmathematical data such as words or images, as an array of numbers that machine learning (ML) models can process1.” Hence, the claimed generating of a set of vector embeddings is calculating a certain set of numerical values, and this limitation amounts to no more than mathematical calculation(s). Accordingly, this limitation is an abstract idea under the “Mathematical Concepts” grouping. Furthermore, it is well known to those of ordinary skill in the art that “the specific features represented by the dimensions of vector embeddings can be established through manual feature engineering2.” Given that the BRI of the claims encompasses a simple case, as set forth above, a human could, with the aid of pencil and paper, mentally generate a set of vector embeddings, as claimed. Hence, this limitation may alternatively be deemed an abstract idea under the “Mental Processes” grouping.
These claims also recite “generating a set of knowledge graphs based at least in part on the plurality of documents and a knowledge graph augmentation pipeline, wherein a knowledge graph of the set of knowledge graphs comprises a respective plurality of knowledge graph triplets.” These claims do not specify nor place any limits upon the number of knowledge graphs or the number of knowledge graph triplets, other than using the plural forms of these words (i.e. “graphs” and “triplets”). Under the BRI, this limitation encompasses a simple case of just two knowledge graphs, each one being a simple knowledge graph comprising just a few triplets. Given that the BRI of the claims encompasses such a simple case, a human could, with the aid of pencil and paper, mentally generate graphs in the manner claimed. For example, a human could draw out on a piece of paper two simple knowledge graphs that each comprise a few triplets, as claimed. Hence, this limitation is an abstract idea under the “Mental Processes” grouping.
These claims also recite “augmenting the user query to generate an augmented prompt based at least in part on one or more vector embeddings from the set of vector embeddings and one or more knowledge graph triplets from the set of knowledge graphs.” Given that the BRI of the claims encompasses such a simple case, a human could, with the aid of pencil and paper, mentally perform the claimed augmenting as claimed. By looking at the vector embeddings and knowledge graph triplets, a human could augment the user query by adding to it appropriate keywords or context understood from the vector embeddings and/or knowledge graph triplets. Hence, this limitation is an abstract idea under the “Mental Processes” grouping. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. Other than the abstract idea, the claims recite the following:
a) “obtaining a plurality of documents for input into a query response system;”
b) “obtaining, at the query response system, a user query;”
c) “providing, as an input to a large language model (LLM), the augmented
prompt, wherein the LLM outputs a response to the augmented prompt;”
d) outputting an indication of the response to the augmented prompt as an answer to the user query;”
e) one or more processors coupled with one or more memories; and
f) a non-transitory computer-readable medium storing code.
Limitations (a) and (b) amount to no more than mere data gathering, which has been deemed by the courts to be insignificant extra-solution activity. See MPEP 2106.05(g). Limitation (c) is recited as a high level of generality and amounts to mere instructions to apply the abstract on a general purpose computer, which cannot provide a practical application. See MPEP 2106.05(f). Limitation (d) amounts to no more than merely outputting a result, which has been deemed by the courts to be insignificant extra-solution activity. See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015); Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016). See MPEP 2106.05(g). Limitations (e) and (f) are recited at a high level of generality, i.e. as generic computer components performing generic computing functions. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Looking at the additional elements as a whole adds nothing beyond the additional elements considered individually—they still represent insignificant extra-solution activity and/or generic computer implementation. Hence, the claim as a whole, looking at the additional elements individually and in combination, does not integrate the abstract idea into a practical application. The claim is directed to an abstract idea.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. Limitations (a) and (b) amount to no more than mere data gathering, which has been deemed by the courts to be insignificant extra-solution activity. See MPEP 2106.05(g). In addition, the courts have deemed receiving data to be well-understood, routine, and conventional activity, as in the following cases: Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015) (storing and retrieving information in memory). See MPEP 2106.05(d)(II). Hence, elements (a) and (b) cannot be deemed an inventive concept. Limitation (c) is recited as a high level of generality and amounts to mere instructions to apply the abstract on a general purpose computer, which cannot be deemed an inventive concept. See MPEP 2106.05(f). Limitation (d) amounts to no more than merely outputting a result, which has been deemed by the courts to be insignificant extra-solution activity. See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015); Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016). See MPEP 2106.05(g). Furthermore, Applicant’s specification provides few details about the claimed outputting an indication of the response or its functions (see para. 0077 of Applicant’s published specification). This indicates that this feature is well known in the art. Cf Hybritech Inc. v. Monoclonal Antibodies, Inc., 802 F.2d 1367, 1384 (Fed. Cir. 1986) (explaining that "a patent need not teach, and preferably omits, what is well known in the art"). As a result, the written description adequately supports that additional element (d) is conventional and performs well-understood, routine, and conventional activities. See MPEP § 2106.07(a)(III)(A)3. As discussed above with respect to integration of the abstract idea into a practical application, additional elements (e) and (f) amount to no more than mere field of use limitations and instructions to apply the exception using generic computer components. Mere instructions to apply an exception using conventional computer components and functions cannot provide an inventive concept. Looking at the additional elements as a whole adds nothing beyond the additional elements considered individually—they still represent insignificant extra-solution activity; well-understood, routine, and conventional subject matter; and/or generic computer implementation. Hence, the claim as a whole, looking at the additional elements individually and in combination, does not amount to significantly more than the abstract idea. These claims are not patent eligible.
As to dependent claims 2, 11, and 20, these claims recite generating a set of graph embeddings and augmenting the user query. The former is an abstract idea under the “Mathematical Concepts” and/or “Mental Processes” groupings and the latter is an abstract idea under the “Mental Processes” grouping, for the same reasons set forth above with regards to the parent claims.
As to dependent claims 3 and 12, these claims recite generating the set of knowledge graphs by making determinations of named entities and relationships and generating a knowledge graph triplet accordingly. Given that the BRI of the claims encompasses a simple case, as set forth above in the parent claims, nothing in these claims goes beyond what a human could mentally perform with the aid of pencil and paper. Hence, these claims are directed to an abstract idea under the “Mental Processes” grouping.
As to dependent claims 4 and 13, these claims recite performing coreference resolution to replace, in a document of the plurality of documents, a reference to a named entity with the named entity. Given that the BRI of the claims encompasses a simple case, as set forth above in the parent claims, nothing in these claims goes beyond what a human could mentally perform with the aid of pencil and paper. Hence, these claims are directed to an abstract idea under the “Mental Processes” grouping.
As to dependent claims 5-6 and 14-15, these claims recite certain types of documents upon which to apply the invention. This amounts to generally linking the abstract idea to a particular field of use or technological environment, which cannot provide a practical application nor an inventive concept. See MPEP 2106.05(h).
As to dependent claims 7 and 16, these claims recite “obtaining a set of structured data; and extracting a set of entities from the set of structured data; and performing entity resolution for one or more entities in the knowledge graph augmentation pipeline based at least in part on the set of entities extracted from the set of structured data.” Given that the BRI of the claims encompasses a simple case, a human could, with the aid of pencil and paper, mentally perform the claimed obtaining, extracting, and performing entity resolution, as claimed. Hence, these limitations are abstract ideas under the “Mental Processes” grouping.
As to dependent claims 8-9 and 17-18, these claims recites the use of timestamps associated with node or edges of the knowledge graph to determine whether or not to augment the user query with the corresponding graph triplets. Given that the BRI of the claims encompasses a simple case, as set forth above in the parent claims, nothing in these claims goes beyond what a human could mentally perform with the aid of pencil and paper. Hence, these claims are directed to an abstract idea under the “Mental Processes” grouping.
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 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-8, 10-17, and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Crabtree et al. (U.S. Patent Application Publication No. 20250258852 A1, hereinafter referred to as Crabtree) in view of Larson et al. (U.S. Patent Application Publication No. 20250131289 A1, hereinafter referred to as Larson).
As to claim 1, Crabtree teaches a method for data processing, comprising:
obtaining a plurality of documents for input (Crabtree 0157 and Fig. 1: Enterprise knowledge 111 comprises documents) into a query response system; (Crabtree para. 0116 and 0174: the system is a query response system);
generating a set of vector embeddings (Crabtree para. 0083: generating vector embeddings) based at least in part on the plurality of documents (Crabtree 0157 and Fig. 1: Enterprise knowledge 111 comprises documents) and a semantic vector augmentation pipeline (Crabtree para. 0100: Retrieval augmented generation (RAG); and Crabtree para. 0125: vectors capture semantic information);
generating a set of knowledge graphs based at least in part on the plurality of documents and a knowledge graph augmentation pipeline (Crabtree para. 0085: the system populates knowledge graph database 2129; and Crabtree para. 0065 and 0080: knowledge graph is enhanced/augmented);
obtaining, at the query response system, a user query (Crabtree para. 0093 and 0156: the system receives a user’s query);
augmenting the user query to generate an augmented prompt (Crabtree para. 0100: Retrieval augmented generation (RAG); and Crabtree para. 0156: prompt is augmented to include additional contextual data/elements) based at least in part on one or more vector embeddings from the set of vector embeddings and the set of knowledge graphs (Crabtree para. 0079 and Fig. 21: vectors/embeddings database 2128 adn knowledge graph database 2129; and Crabtree para. 0100: retrieval augmented generation (RAG) to augment customer's input based on knowledge graph);
providing, as an input to a large language model (LLM), the augmented prompt, wherein the LLM outputs a response to the augmented prompt (Crabtree para. 0156: augmented prompt is provided to a large language model (LLM) to produce a response); and
outputting an indication of the response to the augmented prompt as an answer to the user query (Crabtree para. 0156: response of the LLM is sent to the user).
Crabtree does not appear to explicitly disclose wherein a knowledge graph of the set of knowledge graphs comprises a respective plurality of knowledge graph triplets.
However, Larson teaches:
obtaining a plurality of documents for input into a query response system (Larson para. 0012: document retrieval);
generating a set of vector embeddings based at least in part on the plurality of documents and a semantic vector augmentation pipeline (Larson para. 0012 and 0014-0015: retrieval augmented generation (RAG) generates vector embeddings of documents);
generating a set of knowledge graphs based at least in part on the plurality of documents and a knowledge graph augmentation pipeline (Larson para. 0017: knowledge graph construction), wherein a knowledge graph of the set of knowledge graphs comprises a respective plurality of knowledge graph triplets (Larson para. 0017: knowledge graph comprised of triplets);
obtaining, at the query response system, a user query (Larson para. 0012 and 0017: user query/question);
augmenting the user query to generate an augmented prompt based at least in part on one or more vector embeddings from the set of vector embeddings (Larson para. 0010, 0052, and 0062: retrieval augmented generation (RAG) generates augmented prompt for a large language model (LLM) based on vector embeddings and knowledge graph) and one or more knowledge graph triplets from the set of knowledge graphs (Larson para. 0017: knowledge graph comprised of triplets);
providing, as an input to a large language model (LLM), the augmented prompt, wherein the LLM outputs a response to the augmented prompt (Larson para. 0052: prompt is designed for an LLM to generate a response to the user’s ask (i.e. user’s question/query)); and
outputting an indication of the response to the augmented prompt as an answer to the user query (Larson para. 0012 and Fig. 1: response 110).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Crabtree to include the teachings of Larson because it allows combining LLM based graph construction and inference, providing enhanced reasoning capabilities (Larson para. 0017).
As to claim 2, Crabtree as modified by Larson teaches further comprising:
generating a set of graph embeddings based at least in part on the set of knowledge graphs, a set of structured data, or both (Crabtree para. 0083: generating vector embeddings based on graph data and Structured Query Language (SQL) data; and see Larson para. 0012 and 0014-0015: retrieval augmented generation (RAG) generates vector embeddings of documents); and
augmenting the user query based at least in part on one or more graph embeddings from the set of graph embeddings (Crabtree para. 0100: Retrieval augmented generation (RAG); and Crabtree para. 0156: prompt is augmented to include additional contextual data/elements; and see Larson para. 0010, 0052, and 0062: retrieval augmented generation (RAG) generates augmented prompt for a large language model (LLM) based on vector embeddings and knowledge graph).
As to claim 3, Crabtree as modified by Larson teaches wherein generating the set of knowledge graphs comprises:
determining a plurality of named entities from the plurality of documents (Crabtree para. 0085: named entity recognition performed on documents);
determining a relationship between a first named entity and a second named entity of the plurality of named entities based at least in part on the plurality of documents (Crabtree para. 0085: extraction of relations between named entities based on documents); and
generating a knowledge graph triplet that indicates the first named entity, the relationship, and the second named entity (Crabtree para. 0085: knowledge graph is populated based named entity recognition and relation extraction, and the knowledge graph is stored in a triple store; and see Larson para. 0017: knowledge graph triplets).
As to claim 4, Crabtree as modified by Larson teaches wherein determining the plurality of named entities comprises:
performing coreference resolution to replace, in a document of the plurality of documents, a reference to a named entity with the named entity (Crabtree para. 0085: co-reference resolution of named entities).
As to claim 5, this claim merely describes particular types of documents upon which to apply the invention, without any limiting of the claimed technique. Hence, this claim is merely an intended use of the claimed invention that has no patentable weight. However, assuming arguendo that the claim has patentable weight, prior art is cited.
Crabtree as modified by Larson teaches wherein the plurality of documents comprises one or more websites (Crabtree para. 0252: data sources include websites), one or more Really Simple Syndication (RSS) feed objects, one or more communication platform feeds (Crabtree para. 0252: data sources include social media), or a combination thereof.
As to claim 6, this claim merely describes particular types of documents upon which to apply the invention, without any limiting of the claimed technique. Hence, this claim is merely an intended use of the claimed invention that has no patentable weight. However, assuming arguendo that the claim has patentable weight, prior art is cited.
Crabtree as modified by Larson teaches wherein the plurality of documents comprises public unstructured data (Crabtree para. 0157: enterprise documents such as regulatory documents; and see Crabtree para. 0252: public unstructured data such as websites), private unstructured data (Crabtree para. 0157: enterprise documents such as those provided by customer relationship management (CRM) systems, enterprise resource planning (ERP) systems, rules and policies databases, and transactional databases), or both.
As to claim 7, Crabtree as modified by Larson teaches further comprising:
obtaining a set of structured data (Crabtree para. 0252: input data is received from structured data sources);
extracting a set of entities from the set of structured data (Crabtree para. 0252: extracting entities); and
performing entity resolution for one or more entities in the knowledge graph augmentation pipeline based at least in part on the set of entities extracted from the set of structured data (Crabtree para. 0085 and 0252: named entity recognition and co-reference resolution are performed).
As to claim 8, Crabtree as modified by Larson teaches wherein the set of knowledge graphs comprises one or more nodes, one or more edges, or both that are associated with respective timestamps, and wherein augmenting the user query is further based at least in part on the respective timestamps (Crabtree para. 0065: knowledge graph has temporal representations based on age or Gregorian calendar; and see Crabtree para. 0089: knowledge graph is queried based on contextual factors including time; and Crabtree para. 0156: prompt is augmented to include additional contextual data/elements).
As to claim 10, Crabtree teaches an apparatus for data processing, comprising:
one or more memories storing processor-executable code (Crabtree para. 0256 and Fig. 32: computing device 10 having one or more processors 20 coupled to system memory 30); and
one or more processors coupled with the one or more memories (Crabtree para. 0256 and Fig. 32: computing device 10 having one or more processors 20 coupled to system memory 30) and
individually or collectively operable to execute the code to cause the apparatus to:
obtaining a plurality of documents for input (Crabtree 0157 and Fig. 1: Enterprise knowledge 111 comprises documents) into a query response system; (Crabtree para. 0116 and 0174: the system is a query response system);
generating a set of vector embeddings (Crabtree para. 0083: generating vector embeddings) based at least in part on the plurality of documents (Crabtree 0157 and Fig. 1: Enterprise knowledge 111 comprises documents) and a semantic vector augmentation pipeline (Crabtree para. 0100: Retrieval augmented generation (RAG); and Crabtree para. 0125: vectors capture semantic information);
generating a set of knowledge graphs based at least in part on the plurality of documents and a knowledge graph augmentation pipeline (Crabtree para. 0085: the system populates knowledge graph database 2129; and Crabtree para. 0065 and 0080: knowledge graph is enhanced/augmented);
obtaining, at the query response system, a user query (Crabtree para. 0093 and 0156: the system receives a user’s query);
augmenting the user query to generate an augmented prompt (Crabtree para. 0100: Retrieval augmented generation (RAG); and Crabtree para. 0156: prompt is augmented to include additional contextual data/elements) based at least in part on one or more vector embeddings from the set of vector embeddings and the set of knowledge graphs (Crabtree para. 0079 and Fig. 21: vectors/embeddings database 2128 adn knowledge graph database 2129; and Crabtree para. 0100: retrieval augmented generation (RAG) to augment customer's input based on knowledge graph);
providing, as an input to a large language model (LLM), the augmented prompt, wherein the LLM outputs a response to the augmented prompt (Crabtree para. 0156: augmented prompt is provided to a large language model (LLM) to produce a response); and
outputting an indication of the response to the augmented prompt as an answer to the user query (Crabtree para. 0156: response of the LLM is sent to the user).
Crabtree does not appear to explicitly disclose wherein a knowledge graph of the set of knowledge graphs comprises a respective plurality of knowledge graph triplets.
However, Larson teaches:
obtaining a plurality of documents for input into a query response system (Larson para. 0012: document retrieval);
generating a set of vector embeddings based at least in part on the plurality of documents and a semantic vector augmentation pipeline (Larson para. 0012 and 0014-0015: retrieval augmented generation (RAG) generates vector embeddings of documents);
generating a set of knowledge graphs based at least in part on the plurality of documents and a knowledge graph augmentation pipeline (Larson para. 0017: knowledge graph construction), wherein a knowledge graph of the set of knowledge graphs comprises a respective plurality of knowledge graph triplets (Larson para. 0017: knowledge graph comprised of triplets);
obtaining, at the query response system, a user query (Larson para. 0012 and 0017: user query/question);
augmenting the user query to generate an augmented prompt based at least in part on one or more vector embeddings from the set of vector embeddings (Larson para. 0010, 0052, and 0062: retrieval augmented generation (RAG) generates augmented prompt for a large language model (LLM) based on vector embeddings and knowledge graph) and one or more knowledge graph triplets from the set of knowledge graphs (Larson para. 0017: knowledge graph comprised of triplets);
providing, as an input to a large language model (LLM), the augmented prompt, wherein the LLM outputs a response to the augmented prompt (Larson para. 0052: prompt is designed for an LLM to generate a response to the user’s ask (i.e. user’s question/query)); and
outputting an indication of the response to the augmented prompt as an answer to the user query (Larson para. 0012 and Fig. 1: response 110).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Crabtree to include the teachings of Larson because it allows combining LLM based graph construction and inference, providing enhanced reasoning capabilities (Larson para. 0017).
As to claim 11, see the rejection of claim 2 above.
As to claim 12, see the rejection of claim 3 above.
As to claim 13, see the rejection of claim 4 above.
As to claim 14, see the rejection of claim 5 above.
As to claim 15, see the rejection of claim 6 above.
As to claim 16, see the rejection of claim 7 above.
As to claim 17, see the rejection of claim 8 above.
As to claim 19, Crabtree teaches a non-transitory computer-readable medium storing code for data processing, the code comprising instructions executable by one or more processors to (Crabtree para. 0256, 0258, and Fig. 32: computing device 10 having storage devices):
obtaining a plurality of documents for input (Crabtree 0157 and Fig. 1: Enterprise knowledge 111 comprises documents) into a query response system; (Crabtree para. 0116 and 0174: the system is a query response system);
generating a set of vector embeddings (Crabtree para. 0083: generating vector embeddings) based at least in part on the plurality of documents (Crabtree 0157 and Fig. 1: Enterprise knowledge 111 comprises documents) and a semantic vector augmentation pipeline (Crabtree para. 0100: Retrieval augmented generation (RAG); and Crabtree para. 0125: vectors capture semantic information);
generating a set of knowledge graphs based at least in part on the plurality of documents and a knowledge graph augmentation pipeline (Crabtree para. 0085: the system populates knowledge graph database 2129; and Crabtree para. 0065 and 0080: knowledge graph is enhanced/augmented);
obtaining, at the query response system, a user query (Crabtree para. 0093 and 0156: the system receives a user’s query);
augmenting the user query to generate an augmented prompt (Crabtree para. 0100: Retrieval augmented generation (RAG); and Crabtree para. 0156: prompt is augmented to include additional contextual data/elements) based at least in part on one or more vector embeddings from the set of vector embeddings and the set of knowledge graphs (Crabtree para. 0079 and Fig. 21: vectors/embeddings database 2128 adn knowledge graph database 2129; and Crabtree para. 0100: retrieval augmented generation (RAG) to augment customer's input based on knowledge graph);
providing, as an input to a large language model (LLM), the augmented prompt, wherein the LLM outputs a response to the augmented prompt (Crabtree para. 0156: augmented prompt is provided to a large language model (LLM) to produce a response); and
outputting an indication of the response to the augmented prompt as an answer to the user query (Crabtree para. 0156: response of the LLM is sent to the user).
Crabtree does not appear to explicitly disclose wherein a knowledge graph of the set of knowledge graphs comprises a respective plurality of knowledge graph triplets.
However, Larson teaches:
obtaining a plurality of documents for input into a query response system (Larson para. 0012: document retrieval);
generating a set of vector embeddings based at least in part on the plurality of documents and a semantic vector augmentation pipeline (Larson para. 0012 and 0014-0015: retrieval augmented generation (RAG) generates vector embeddings of documents);
generating a set of knowledge graphs based at least in part on the plurality of documents and a knowledge graph augmentation pipeline (Larson para. 0017: knowledge graph construction), wherein a knowledge graph of the set of knowledge graphs comprises a respective plurality of knowledge graph triplets (Larson para. 0017: knowledge graph comprised of triplets);
obtaining, at the query response system, a user query (Larson para. 0012 and 0017: user query/question);
augmenting the user query to generate an augmented prompt based at least in part on one or more vector embeddings from the set of vector embeddings (Larson para. 0010, 0052, and 0062: retrieval augmented generation (RAG) generates augmented prompt for a large language model (LLM) based on vector embeddings and knowledge graph) and one or more knowledge graph triplets from the set of knowledge graphs (Larson para. 0017: knowledge graph comprised of triplets);
providing, as an input to a large language model (LLM), the augmented prompt, wherein the LLM outputs a response to the augmented prompt (Larson para. 0052: prompt is designed for an LLM to generate a response to the user’s ask (i.e. user’s question/query)); and
outputting an indication of the response to the augmented prompt as an answer to the user query (Larson para. 0012 and Fig. 1: response 110).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Crabtree to include the teachings of Larson because it allows combining LLM based graph construction and inference, providing enhanced reasoning capabilities (Larson para. 0017).
As to claim 20, see the rejection of claim 2 above.
Claims 9 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Crabtree and Larson as applied to claims 8 and 17 above, and further in view of Britton et al. (U.S. Patent Application Publication No. 20020174126A1, hereinafter referred to as Britton).
As to claim 9, Crabtree as modified by Larson does not appear to explicitly disclose further comprising: determining that a timestamp indicates that a corresponding knowledge graph triplet is expired; and refraining from augmenting the user query with the corresponding knowledge graph triplet based at least in part on the timestamp.
However, Britton teaches further comprising:
determining that a timestamp indicates that a corresponding knowledge graph triplet is expired (Britton abstract and para. 0054: RDF graph triples have corresponding timestamps; and Britton para. 0057: triples that are expired are ignored or deleted); and
refraining from augmenting the user query with the corresponding knowledge graph triplet based at least in part on the timestamp (Britton para. 0054 and 0057: triples that are expired are ignored or deleted).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Crabtree as modified by Larson to include the teachings of Britton because it helps to prevent utilizing expired, stale, or outdated data (Britton para. 0054 and 0057), enhancing information integrity.
As to claim 18, see the rejection of claim 9 above.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to UMAR MIAN whose telephone number is (571)270-3970. The examiner can normally be reached Monday to Friday, 10 am to 6:30 pm.
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, Tony Mahmoudi can be reached on (571) 272-4078. 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.
/Umar Mian/
Examiner, Art Unit 2163
1 Bergmann, David and Strykyer, Cole. "What is vector embedding?" Published 12 June 2024 by IBM. Accessed 28 August 2025 from https://www.ibm.com/think/topics/vector-embedding
2 Bergmann, David and Strykyer, Cole. "What is vector embedding?" Published 12 June 2024 by IBM. Accessed 28 August 2025 from https://www.ibm.com/think/topics/vector-embedding
3 MPEP § 2106.07(a)(III)(A) explains that a specification demonstrates the well-understood, routine, conventional nature of additional elements when it describes the additional elements as well-understood or routine or conventional ( or an equivalent term) or in a manner that indicates that the additional elements are sufficiently well-known that the specification does not need to describe the particulars of such additional elements to satisfy 35 U.S.C. § 112(a).