# US 12,118,992 B2 · Voice interaction method and apparatus, device and computer storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,992 B2 - Document ID: US12118992B2 - Status: Granted - Kind: B2 - Application number: 17/622,402 - Filed: 2021-06-02 - Published: 2023-09-14 - Granted: 2024-10-15 - Earliest claimed: 2020-11-20 - Assignees: Beijing Baidu Netcom Science Technology Co., Ltd. - Applicants: Beijing Baidu Netcom Science and Technology Co., Ltd. - Inventors: Jizhou Huang; Shiqiang Ding - Web page: https://patentgrep.com/patent/US12118992B2 ## CPC - G06F 40/279: Recognition of textual entities - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G06F 16/90332: {Natural language query formulation or dialogue systems} - G06F 40/30: Semantic analysis - G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning} - G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G10L 2015/223: {Execution procedure of a spoken command} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract Technical solutions relate to the fields of artificial intelligence technologies and voice technologies. A technical solution includes: performing voice recognition and demand analysis on a voice instruction input by a user; in response to an unknown demand obtained by the demand analysis, acquiring information of a query entity and query content using a result of the demand analysis, and acquiring reply information corresponding to the query content by communication with the query entity; and returning a first voice response to the user using the reply information. ## Claims ### Claim 1 A voice interaction method, comprising: performing voice recognition and demand analysis on a voice instruction input by a user; in response to an unknown demand obtained by the demand analysis, acquiring information of a query entity, which is an entity object corresponding to information to be acquired by the user, and query content from a result of the demand analysis, acquiring communication mode of the query entity, sending the query content to the query entity in the communication mode and acquiring reply information corresponding to the query content returned by the query entity; returning a first voice response to the user using the reply information, acquiring information of at least one candidate entity corresponding to the information of the query entity; acquiring candidate reply information by communication with the at least one candidate entity; and returning a third voice response to the user using the information of the at least one candidate entity and the candidate reply information. ### Claim 2 (depends on 1) The method according to claim 1, further comprising: after obtaining the unknown demand by the demand analysis and before returning the first voice response to the user, returning a second voice response to the user to indicate that the reply information will be provided later. ### Claim 3 (depends on 1) The method according to claim 1, further comprising: after acquiring the reply information corresponding to the query content, recording the result of the demand analysis as a known demand and correspondingly storing the reply information. ### Claim 4 (depends on 1) The method according to claim 1, wherein acquiring the information of at least one candidate entity corresponding to the information of the query entity comprises: obtaining entities of a same type as the query entity from a domain knowledge base to which the query entity belongs; and based on a correlation between the obtained entities and the query entity, selecting at least one of the obtained entities as the at least one candidate entity, and obtaining the information of the candidate entity. ### Claim 5 (depends on 1) The method according to claim 1, wherein acquiring the candidate reply information by communication with the candidate entity comprises: if no reply information corresponding to the query content is acquired by communication with the query entity, or if negative reply information is acquired by communication with the query entity, acquiring the candidate reply information by communication with the candidate entity. ### Claim 6 (depends on 1) The method according to claim 1, wherein acquiring the reply information corresponding to the query content by communication with the query entity comprises: performing at least one round of interaction with the query entity according to a communication mode corresponding to the information of the query entity, so as to send the query content to the query entity and acquire the reply information returned by the query entity. ### Claim 7 (depends on 1) The method according to claim 1, further comprising: if the reply information and the candidate reply information are not acquired within a preset duration, returning a preset fourth voice response to the user. ### Claim 8 An electronic device, comprising: at least one processor; and a memory connected with the at least one processor communicatively; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a voice interaction method, which comprises: performing voice recognition and demand analysis on a voice instruction input by a user; in response to an unknown demand obtained by the demand analysis, acquiring information of a query entity, which is an entity object corresponding to information to be acquired by the user, and query content from a result of the demand analysis, acquiring communication mode of the query entity, sending the query content to the query entity in the communication mode and acquiring reply information corresponding to the query content returned by the query entity; returning a first voice response to the user using the reply information; acquiring information of at least one candidate entity corresponding to the information of the query entity; acquiring candidate reply information by communication with the at least one candidate entity; and returning a third voice response to the user using the information of the at least one candidate entity and the candidate reply information. ### Claim 9 A non-transitory computer readable storage medium comprising computer instructions, which, when executed by a computer, cause the computer to perform a voice interaction method, which comprises: performing voice recognition and demand analysis on a voice instruction input by a user; in response to an unknown demand obtained by the demand analysis, acquiring information of a query entity, which is an entity object corresponding to information to be acquired by the user, and query content from a result of the demand analysis, acquiring communication mode of the query entity, sending the query content to the query entity in the communication mode and acquiring reply information corresponding to the query content returned by the query entity; returning a first voice response to the user using the reply information; acquiring information of at least one candidate entity corresponding to the information of the query entity; acquiring candidate reply information by communication with the at least one candidate entity; and returning a third voice response to the user using the information of the at least one candidate entity and the candidate reply information. ### Claim 10 (depends on 8) The electronic device according to claim 8, wherein the method further comprises: after obtaining the unknown demand by the demand analysis and before returning the first voice response to the user, returning a second voice response to the user to indicate that the reply information will be provided later. ### Claim 11 (depends on 8) The electronic device according to claim 8, wherein the method further comprises: after acquiring the reply information corresponding to the query content, recording the result of the demand analysis as a known demand and correspondingly storing the reply information. ### Claim 12 (depends on 8) The electronic device according to claim 8, wherein acquiring the information of at least one candidate entity corresponding to the information of the query entity comprises: obtaining entities of a same type as the query entity from a domain knowledge base to which the query entity belongs; and based on a correlation between the obtained entities and the query entity, selecting at least one of the obtained entities as the at least one candidate entity, and obtaining the information of the candidate entity. ### Claim 13 (depends on 8) The electronic device according to claim 8, wherein acquiring the candidate reply information by communication with the at least one candidate entity comprises: if no reply information corresponding to the query content is acquired by communication with the query entity, or if negative reply information is acquired by communication with the query entity, acquiring the candidate reply information by communication with the at least one candidate entity. ### Claim 14 (depends on 8) The electronic device according to claim 8, wherein acquiring the reply information corresponding to the query content by communication with the query entity comprises: performing at least one round of interaction with the query entity according to a communication mode corresponding to the information of the query entity, so as to send the query content to the query entity and acquire the reply information returned by the query entity. ### Claim 15 (depends on 8) The electronic device according to claim 8, wherein the method further comprising: if the reply information and the candidate reply information are not acquired within a preset duration, returning a preset fourth voice response to the user. ### Claim 16 (depends on 9) The non-transitory computer readable storage medium according to claim 9, wherein the method further comprises: after obtaining the unknown demand by the demand analysis and before returning the first voice response to the user, returning a second voice response to the user to indicate that the reply information will be provided later. ### Claim 17 (depends on 9) The non-transitory computer readable storage medium according to claim 9, wherein the method further comprises: after acquiring the reply information corresponding to the query content, recording the result of the demand analysis as a known demand and correspondingly storing the reply information.