# US 12,593,105 B2 · Comment processing method, electronic device and non-transitory computer-readable storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,593,105 B2 - Document ID: US12593105B2 - Status: Granted - Kind: B2 - Application number: 18/730,746 - Filed: 2023-01-19 - Published: 2025-03-27 - Granted: 2026-03-31 - Earliest claimed: 2022-01-20 - Assignees: Beijing Youzhuju Network Technology Co., Ltd. - Applicants: Beijing Youzhuju Network Technology Co., Ltd. - Inventors: Pei Zhou; Runfu Lin; Changcong Li - Web page: https://patentgrep.com/patent/US12593105B2 ## CPC - H04N 21/4788: communicating with other users, e.g. chatting {(arrangements for providing for computer conferences, e.g. chat rooms, to substation in data switching networks H04L12/1813; distributed application using peer-to-peer [P2P] networks H04L67/104)} - G06F 16/33: Querying - G06F 18/22: Matching criteria, e.g. proximity measures - G06F 40/30: Semantic analysis - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/08: Learning methods - H04N 21/2187: Live feed - H04N 21/2542: {for selling goods, e.g. TV shopping (payment schemes, payment architectures or payment protocols for electronic shopping systems G06Q20/12)} - H04N 21/488: Data services, e.g. news ticker {(systems specially adapted for using meteorological information in broadcast systems H04H60/71)} - Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE ## Abstract The present disclosure relates to a comment processing method and apparatus, and an electronic device, a computer-readable storage medium and a computer program. The comment processing method includes: acquiring real-time comment information for a live room; determining a similarity between a target real-time comment in the real-time comment information and historical comments in a historical comment set corresponding to the live room; when the similarity between the target real-time comment and a target historical comment is greater than or equal to a first preset threshold value, combining the target real-time comment and the target historical comment, wherein the target historical comment is any historical comment among the historical comments in the historical comment set, and the target real-time comment is any real-time comment in the real-time comment information; and displaying a combined target real-time comment and target historical comment. ## Claims ### Claim 1 A comment processing method, comprising: acquiring real-time comment information for a live room; determining a similarity between a target real-time comment in the real-time comment information and historical comments in a historical comment set corresponding to the live room; when the similarity between the target real-time comment and a target historical comment is greater than or equal to a first preset threshold value, combining the target real-time comment and the target historical comment, wherein the target historical comment is any historical comment among the historical comments in the historical comment set, and the target real-time comment is any real-time comment in the real-time comment information; and displaying a combined target real-time comment and target historical comment, wherein the displaying the combined target real-time comment and target historical comment, comprises: displaying the combined target real-time comment and target historical comment in a first comment area of a comment interface; and in a case where a sum of a quantity of the target real-time comment and a quantity of the target historical comment in the combined target real-time comment and target historical comment is less than or equal to a second preset threshold value, displaying the target real-time comment in a second comment area of the comment interface. ### Claim 2 (depends on 1) The method according to claim 1, further comprising: displaying a plurality of comment type identifications corresponding to a plurality of comment types on the comment interface; and in response to a triggering operation for a target comment type identification corresponding to a target comment type, displaying comment information corresponding to the target comment type in the comment interface, wherein the target comment type is any comment type of the plurality of the comment types, and the target comment type identification is any comment type identification of the plurality of the comment type identifications. ### Claim 3 (depends on 2) The method according to claim 2, wherein the live room comprises: a live room for an object promotion type, and the comment types include: a consultation comment type. ### Claim 4 (depends on 2) The method according to claim 2, wherein, when the similarity between the target real-time comment and the target historical comment is greater than or equal to the first preset threshold value, the combining the target real-time comment and the target historical comment, comprises: when the similarity between the target real-time comment and the target historical comment is greater than or equal to the first preset threshold value, determining a quantity of the target real-time comment and the target historical comment after being combined and a reference comment content; wherein the displaying the combined target real-time comment and target historical comment in the first comment area of the comment interface comprises: displaying the quantity of the target real-time comment and the target historical comment being combined and the reference comment content in the first comment area of the comment interface. ### Claim 5 (depends on 2) The method according to claim 2, wherein the similarity is determined by a preconfigured similar semantic model, and the similar semantic model is a neural network model. ### Claim 6 (depends on 1) The method according to claim 1, wherein, when the similarity between the target real-time comment and the target historical comment is greater than or equal to the first preset threshold value, the combining the target real- time comment and the target historical comment, comprises: when the similarity between the target real-time comment and the target historical comment is greater than or equal to the first preset threshold value, determining a quantity of the target real-time comment and the target historical comment being combined and a reference comment content; wherein the displaying the combined target real-time comment and target historical comment in the first comment area of the comment interface comprises: displaying the quantity of the target real-time comment and the target historical comment being combined and the reference comment content in the first comment area of the comment interface. ### Claim 7 (depends on 6) The method according to claim 6, wherein the combined target real-time comment and target historical comment forms a comment group, the first comment area comprises a preset quantity of display positions, each of the display positions corresponds to one comment group and is used to display a reference comment content of the comment group and a quantity of comments comprised in the comment group, and the reference comment content is a comment content of any comment in the comment group. ### Claim 8 (depends on 1) The method according to claim 1, wherein the historical comment set is stored in a buffer pool, and the method further comprises: adding the real-time comment information to the buffer pool; emptying the historical comment set in the buffer pool when a preset time period is reached. ### Claim 9 (depends on 1) The method according to claim 1, wherein the similarity is determined by a preconfigured similar semantic model, and the similar semantic model is a neural network model. ### Claim 10 (depends on 9) The method according to claim 9, wherein the historical comment set is stored in a buffer pool, and the method further comprises: adding the real-time comment information to the buffer pool; and emptying the historical comment set in the buffer pool when a preset time period is reached. ### Claim 11 An electronic device, comprising: at least one processor and a memory; wherein the memory is configured to store computer executable instructions; wherein the at least one processor is configured to execute the computer executable instructions stored in the memory to cause the electronic device to implement a comment processing method and the comment processing method comprises: acquiring real-time comment information for a live room; determining a similarity between a target real-time comment in the real-time comment information and historical comments in a historical comment set corresponding to the live room; when the similarity between the target real-time comment and a target historical comment is greater than or equal to a first preset threshold value, combining the target real-time comment and the target historical comment, wherein the target historical comment is any historical comment among the historical comments in the historical comment set, and the target real-time comment is any real-time comment in the real-time comment information; and displaying a combined target real-time comment and target historical comment, wherein the displaying the combined target real-time comment and target historical comment, comprises: displaying the combined target real-time comment and target historical comment in a first comment area of a comment interface; and in a case where a sum of a quantity of the target real-time comment and a quantity of the target historical comment in the combined target real-time comment and target historical comment is less than or equal to a second preset threshold value, displaying the target real-time comment in a second comment area of the comment interface. ### Claim 12 (depends on 11) The electronic device according to claim 11, wherein the comment processing method implemented by the electronic device further comprises: displaying a plurality of comment type identifications corresponding to a plurality of comment types on the comment interface; and in response to a triggering operation for a target comment type identification corresponding to a target comment type, displaying comment information corresponding to the target comment type in the comment interface, wherein the target comment type is any comment type of the plurality of the comment types, and the target comment type identification is any comment type identification of the plurality of the comment type identifications. ### Claim 13 (depends on 12) The electronic device according to claim 12, wherein the live room comprises: a live room for an object promotion type, and the comment types include: a consultation comment type. ### Claim 14 (depends on 11) The electronic device according to claim 11, wherein when the similarity between the target real-time comment and the target historical comment is greater than or equal to the first preset threshold value, the combining the target real-time comment and the target historical comment, comprises: when the similarity between the target real-time comment and the target historical comment is greater than or equal to the first preset threshold value, determining a quantity of the target real-time comment and the target historical comment after being combined and a reference comment content; wherein the displaying the combined target real-time comment and target historical comment in the first comment area of the comment interface comprises: displaying the quantity of the target real-time comment and the target historical comment being combined and the reference comment content in the first comment area of the comment interface. ### Claim 15 (depends on 14) The electronic device according to claim 14, wherein the combined target real-time comment and target historical comment forms a comment group, the first comment area comprises a preset quantity of display positions, each of the display positions corresponds to one comment group and is used to display a reference comment content of the comment group and a quantity of comments comprised in the comment group, and the reference comment content is a comment content of any comment in the comment group. ### Claim 16 (depends on 11) The electronic device according to claim 11, wherein the historical comment set is stored in a buffer pool, and the electronic device further comprises: a module for adding the real-time comment information to the buffer pool; and a module for emptying the historical comment set in the buffer pool when a preset time period is reached. ### Claim 17 (depends on 11) The electronic device according to claim 11, wherein the similarity is determined by a preconfigured similar semantic model, and the similar semantic model is a neural network model. ### Claim 18 A non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores computer executable instructions that, when executed by a processor, cause a computing device to implement a comment processing method and the comment processing method comprises: acquiring real-time comment information for a live room; determining a similarity between a target real-time comment in the real-time comment information and historical comments in a historical comment set corresponding to the live room; when the similarity between the target real-time comment and a target historical comment is greater than or equal to a first preset threshold value, combining the target real-time comment and the target historical comment, wherein the target historical comment is any historical comment among the historical comments in the historical comment set, and the target real-time comment is any real-time comment in the real-time comment information; and displaying a combined target real-time comment and target historical comment, wherein the displaying the combined target real-time comment and target historical comment, comprises: displaying the combined target real-time comment and target historical comment in a first comment area of a comment interface; and in a case where a sum of a quantity of the target real-time comment and a quantity of the target historical comment in the combined target real-time comment and target historical comment is less than or equal to a second preset threshold value, displaying the target real-time comment in a second comment area of the comment interface. ### Claim 19 (depends on 18) The non-transitory computer-readable storage medium of claim 18, wherein the comment processing method further comprises: displaying a plurality of comment type identifications corresponding to a plurality of comment types on the comment interface; and in response to a triggering operation for a target comment type identification corresponding to a target comment type, displaying comment information corresponding to the target comment type in the comment interface, wherein the target comment type is any comment type of the plurality of the comment types, and the target comment type identification is any comment type identification of the plurality of the comment type identifications. ### Claim 20 (depends on 18) The non-transitory computer-readable storage medium of claim 18, wherein when the similarity between the target real-time comment and the target historical comment is greater than or equal to the first preset threshold value, the combining the target real-time comment and the target historical comment, comprises: when the similarity between the target real-time comment and the target historical comment is greater than or equal to the first preset threshold value, determining a quantity of the target real-time comment and the target historical comment after being combined and a reference comment content; wherein the displaying the combined target real-time comment and target historical comment in the first comment area of the comment interface comprises: displaying the quantity of the target real-time comment and the target historical comment being combined and the reference comment content in the first comment area of the comment interface.