# US 12,002,470 B1 · Multi-source based knowledge data for artificial intelligence characters > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,002,470 B1 - Document ID: US12002470B1 - Status: Granted - Kind: B1 - Application number: 18/401,544 - Filed: 2023-12-31 - Granted: 2024-06-04 - Earliest claimed: 2022-12-31 - Assignees: Theai, Inc. - Applicants: Theai, Inc. - Inventors: Ilya Gelfenbeyn; Mikhail Ermolenko; Kylan Gibbs; Kirill Ryzhov; Nathan Yu - Web page: https://patentgrep.com/patent/US12002470B1 ## CPC - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G06F 16/3329: Natural language query formulation - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G10L 13/033: Voice editing, e.g. manipulating the voice of the synthesiser - G10L 15/183: using context dependencies, e.g. language models - G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications - G06F 40/30: Semantic analysis - G10L 15/1822: {Parsing for meaning understanding} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Systems and methods for providing multi-source based knowledge data for Artificial Intelligence (AI) characters are provided. An example method includes providing a plurality of data sources; receiving, from a user, at least one word during a conversation between the user and an AI character; ascertaining a speech style of the AI character; analyzing the at least one word to determine a type of information needed to generate a reply to the user; selecting, based on the type of information, at least one data source from the plurality of data sources; generating, based on the at least one word, one or more queries; sending the one or more queries to the at least one data source; receiving one or more responses from the at least one data source; forming, based on the one or more responses and the speech style of the AI character, the reply for providing to the user. ## Claims ### Claim 1 A method comprising: providing, by at least one processor, a plurality of data sources; receiving, by the at least one processor, from a user, at least one word during a conversation between the user and an Artificial Intelligence (AI) character generated by an AI character model in a virtual environment; ascertaining, by the at least one processor, a speech style of the AI character based on settings of the AI character model; analyzing, by the at least one processor, the at least one word to determine a type of information needed to generate a reply to the user; selecting, by the at least one processor and based on the type of information, at least one data source from the plurality of data sources, the plurality of data sources including: a static data source storing knowledge data of the AI character, the knowledge data being stored in a memory associated with the AI character model; and a data source storing structured knowledge data of the AI character, the structured knowledge data being received in a user input of the user, wherein the structured knowledge data being prioritized over the knowledge data by setting the at least one processor to pull a portion of knowledge from the structured knowledge data when both the knowledge data and the structured knowledge data store the portion of knowledge; generating, by the at least one processor and based on the at least one word, one or more queries for the at least one data source; sending, by the at least one processor, the one or more queries to the at least one data source; receiving, by the at least one processor, one or more responses from the at least one data source; forming, by the at least one processor and based on the one or more responses and the speech style of the AI character, the reply to the user; and providing, by the at least one processor, the reply to the user. ### Claim 2 (depends on 1) The method of claim 1, wherein the plurality of data sources includes a data source providing data concerning a social event in real time. ### Claim 3 (depends on 1) The method of claim 1, wherein the plurality of data sources includes a static data storage including an indexed store of knowledge data related to the AI character. ### Claim 4 (depends on 3) The method of claim 3, wherein the knowledge data are obtained from one or more online encyclopedias including information concerning a prototype of the AI character, the prototype being a fictional character or a known person. ### Claim 5 (depends on 3) The method of claim 3, wherein the obtaining the knowledge data includes: generating at least one request concerning a prototype of the AI character to a language model, the prototype being a fictional character or a known person; and obtaining, from the language model, responses to the at least one request. ### Claim 6 (depends on 3) The method of claim 3, wherein the generating the one or more queries includes determining one or more indices for the at least one word, the one or more indices complying with a schema of the indexed store. ### Claim 7 (depends on 3) The method of claim 3, wherein the plurality of data sources includes an online data source, the online data source including further data, the further data being additional to the knowledge data included in the indexed store. ### Claim 8 (depends on 7) The method of claim 7, wherein the analyzing the at least one word to determine the type of information includes establishing that information needed to generate the reply to the user is out of scope of the knowledge data. ### Claim 9 (depends on 7) The method of claim 7, further comprising updating the indexed store with one or more responses received from the online data source. ### Claim 10 (depends on 7) The method of claim 7, wherein the AI character is associated with a known person and the further data additional to the knowledge data include recent news concerning the known person. ### Claim 11 A computing system comprising: a processor; and a memory storing instructions that, when executed by the processor, configure the computing system to: provide a plurality of data sources; receive, from a user, at least one word during a conversation between the user and an Artificial Intelligence (AI) character generated by an AI character model in a virtual environment; ascertain a speech style of the AI character based on settings of the AI character model; analyze the at least one word to determine a type of information needed to generate a reply to the user; select, based on the type of information, at least one data source from the plurality of data sources, the plurality of data sources including: a static data source storing knowledge data of the AI character, the knowledge data being stored in a memory associated with the AI character model; and a data source storing structured knowledge data of the AI character, the structured knowledge data being received in a user input of the user, wherein the structured knowledge data being prioritized over the knowledge data by setting the at least one processor to pull a portion of knowledge from the structured knowledge data when both the knowledge data and the structured knowledge data store the portion of knowledge; generate, based on the at least one word, one or more queries for the at least one data source; send the one or more queries to the at least one data source; receive one or more responses from the at least one data source; form, based on the one or more responses and the speech style of the AI character, the reply to the user; and provide the reply to the user. ### Claim 12 (depends on 11) The computing system of claim 11, wherein the plurality of data sources includes a data source providing data concerning a social event in real time. ### Claim 13 (depends on 11) The computing system of claim 11, wherein the plurality of data sources includes a static data storage including an indexed store of knowledge data related to the AI character. ### Claim 14 (depends on 13) The computing system of claim 13, wherein the knowledge data are obtained from one or more online encyclopedias including information concerning a prototype of the AI character, the prototype being a fictional character or a known person. ### Claim 15 (depends on 13) The computing system of claim 13, wherein the obtaining the knowledge data includes: generating at least one request concerning a prototype of the AI character to a language model, the prototype being a fictional character or a known person; and obtaining, from the language model, responses to the at least one request. ### Claim 16 (depends on 13) The computing system of claim 13, wherein the generating the one or more queries includes determining one or more indices for the at least one word, the one or more indices complying with a schema of the indexed store. ### Claim 17 (depends on 13) The computing system of claim 13, wherein the plurality of data sources includes an online data source, the online data source including further data, the further data being additional to the knowledge data included in the indexed store. ### Claim 18 (depends on 17) The computing system of claim 17, wherein the analyzing the at least one word to determine the type of information includes establishing that information needed to generate the reply to the user is out of scope of the knowledge data. ### Claim 19 (depends on 17) The computing system of claim 17, wherein the instructions further configure the computing system to update the indexed store with one or more responses received from the online data source. ### Claim 20 A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that, when executed by a computing system, cause the computing system to: provide a plurality of data sources; receive, from a user, at least one word during a conversation between the user and an Artificial Intelligence (AI) character generated by an AI character model in a virtual environment; ascertain a speech style of the AI character based on settings of the AI character mode; analyze the at least one word to determine a type of information needed to generate a reply to the user; select, based on the type of information, at least one data source from the plurality of data sources, the plurality of data sources including: a static data source storing knowledge data of the AI character, the knowledge data being stored in a memory associated with the AT character model; and a data source storing structured knowledge data of the AT character, the structured knowledge data being received in a user input of the user, wherein the structured knowledge data being prioritized over the knowledge data by setting the at least one processor to pull a portion of knowledge from the structured knowledge data when both the knowledge data and the structured knowledge data store the portion of knowledge; generate, based on the at least one word, one or more queries for the at least one data source; send the one or more queries to the at least one data source; receive one or more responses from the at least one data source; form, based on the one or more responses and the speech style of the AT character, the reply to the user; and provide the reply to the user.