# US 2025/0147993 A1 · Graph and vector usage for automated qa system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0147993 A1 - Document ID: US20250147993A1 - Status: Published application - Kind: A1 - Application number: 18/500,761 - Filed: 2023-11-02 - Published: 2025-05-08 - Earliest claimed: 2023-11-02 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Ming Jin CHEN; Yuan LI; Tong LIU; Yuan Yuan LI; Yuan ZHANG - Web page: https://patentgrep.com/patent/US20250147993A1 ## CPC - G06F 16/3344: {using natural language analysis} - G06F 16/3329: Natural language query formulation - G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A method for conversational query resolution includes receiving a query input from a user. The query input is decomposed into a plurality of tasks. A knowledge graph is queried to identify one or more relevant entities based on at least one of the plurality of tasks. A vector database is searched to identify one or more text chunks that correspond to the one or more relevant entities. Content relevant to at least one of the plurality of tasks is identified from the one or more text chunks. An answer is generated based on the identified content. ## Claims ### Claim 1 A computer-implemented method comprising: receiving a query input from a user; decomposing the query input into a plurality of tasks; querying a knowledge graph to identify one or more relevant entities based on at least one of the plurality of tasks; searching a vector database to identify one or more text chunks comprising natural language text in the form of structured sentences that correspond to the one or more relevant entities; identifying content relevant to at least one of the plurality of tasks by parsing the natural language text in the form of structured sentences, within the one or more text chunks; and generating an answer based on the identified content. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the knowledge graph comprises a plurality of entities, and each entity of the plurality of entities in the knowledge graph is associated with a respective text chunk within the vector database using a chunk identifier. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, wherein each of the respective text chunks comprises text extracted from a corpus of unstructured documents. ### Claim 4 (depends on 2) The computer-implemented method of claim 2, wherein each respective text chunk is vectorized into a respective vector representation using an embedding model. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the content relevant to the plurality of tasks from the one or more text chunks is identified using a vector-based similarity technique. ### Claim 6 (depends on 5) The computer-implemented method of claim 5, wherein the vector-based similarity technique used to identify the content comprises comparing at least one of (i) cosine similarity or (ii) distance similarity between vector representations of the one or more text chunks and each of the plurality of tasks. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, further comprising: receiving feedback from the user regarding an accuracy of the answer; and updating the knowledge graph based on the feedback. ### Claim 8 (depends on 7) The computer-implemented method of claim 7, wherein updating the knowledge graph and the vector database based on the feedback comprises adding one or more new entities to the knowledge graph, wherein each of the one or more new entities comprises data derived from the answer. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein generating the answer based on the identified content comprises: aggregating the identified content based on logical relationships between each of the plurality of tasks; and generating the answer in natural language based on the aggregated content using natural language processing algorithms. ### Claim 10 A system comprising: one or more memories collectively storing computer-executable instructions; and one or more processors configured to collectively execute the computer-executable instructions and cause the system to: receive a query input from a user; decompose the query input into a plurality of tasks; query a knowledge graph to identify one or more relevant entities based on at least one of the plurality of tasks; searching a vector database to identify one or more text chunks comprising natural language text in the form of structured sentences that correspond to the one or more relevant entities; identifying content relevant to at least one of the plurality of tasks by parsing the natural language text in the form of structured sentences, within the one or more text chunks; and generate an answer based on the identified content. ### Claim 11 (depends on 10) The system of claim 10, wherein the knowledge graph comprises a plurality of entities, and each entity of the plurality of entities in the knowledge graph is associated with a respective text chunk within the vector database using a chunk identifier. ### Claim 12 (depends on 11) The system of claim 11, wherein each of the respective text chunks comprises text extracted from a corpus of unstructured documents. ### Claim 13 (depends on 11) The system of claim 11, wherein each respective text chunk is vectorized into a respective vector representation using an embedding model. ### Claim 14 (depends on 10) The system of claim 10, wherein the content relevant to the plurality of tasks from the one or more text chunks is identified using a vector-based similarity technique. ### Claim 15 (depends on 14) The system of claim 14, wherein the vector-based similarity technique used to identify the content comprises comparing at least one of (i) cosine similarity or (ii) distance similarity between vector representations of the one or more text chunks and each of the plurality of tasks. ### Claim 16 (depends on 10) The system of claim 10, wherein the computer-executable instructions, when executed by the one or more processors, further cause the system to: receive feedback from the user regarding an accuracy of the answer; and update the knowledge graph based on the feedback. ### Claim 17 (depends on 16) The system of claim 16, wherein the computer-executable instructions, when executed by the one or more processors, further cause the system to add one or more new entities to the knowledge graph based on the feedback, wherein each of the one or more new entities comprises data derived from the answer. ### Claim 18 (depends on 10) The system of claim 10, wherein, to generate the answer based on the identified content, the computer-executable instructions, when executed by the one or more processors, further cause the system to: aggregate the identified content based on logical relationships between each of the plurality of tasks; and generate the answer in natural language based on the aggregated content using natural language processing algorithms. ### Claim 19 A computer program product, comprising: a computer-readable storage medium having computer-readable program code executable by a computer to cause the computer to: receive a query input from a user; decompose the query input into a plurality of tasks; query a knowledge graph to identify one or more relevant entities based on at least one of the plurality of tasks; searching a vector database to identify one or more text chunks comprising natural language text in the form of structured sentences that correspond to the one or more relevant entities; identifying content relevant to at least one of the plurality of tasks by parsing the natural language text in the form of structured sentences, within the one or more text chunks; and generate an answer based on the identified content. ### Claim 20 (depends on 19) The computer program product of claim 19, wherein the knowledge graph comprises a plurality of entities, and each entity of the plurality of entities in the knowledge graph is associated with a respective text chunk within the vector database using a chunk identifier.