Customer service interaction method and system based on artificial intelligence

Abstract

The invention is suitable for the technical field of artificial intelligence customer service, and provides a customer service interaction method and system based on artificial intelligence. The method comprises the following steps: receiving user interaction data, determining a target consulting commodity, and obtaining a plurality of live video clips and a plurality of commodity evaluation data; extracting multiple pieces of live broadcast text information and multiple pieces of evaluation text information; key interaction information is extracted, and the multiple pieces of live broadcast text information and the multiple pieces of evaluation text information are associated and compared; determining a customer service interaction mode; and matching the associated video clip and the associated evaluation data, and performing interaction expression according to a customer service interaction mode. A plurality of live video clips and a plurality of commodity evaluation data of a target consulting commodity can be obtained, text information extraction and correlation comparison are performed, correlation video clips and correlation evaluation data are matched, artificial intelligence interaction expression is performed, and the live video and evaluation data related to the commodity can be effectively utilized. Therefore, richer interactive display is realized, and the user experience is effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence customer service, and particularly relates to a customer service interaction method and system based on artificial intelligence. Background Art

[0002] Artificial intelligence customer service is the application of artificial intelligence technology in the field of customer service, mainly relying on technologies such as big data, cloud computing, and machine learning, and providing automated solutions in business scenarios such as customer service, sales, and marketing by training and understanding human language.

[0003] In the prior art, the interaction of artificial intelligence customer service only matches the literal understanding of the user's needs among multiple preset interaction messages, so as to complete the corresponding transmission and expression of information. Although it can meet the needs of basic replies to a certain extent, it limits the depth and breadth of the interaction. In particular, it cannot effectively utilize the live video and evaluation data generated in real time, and cannot achieve a more rich interaction display, resulting in an average user experience. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a customer service interaction method and system based on artificial intelligence, aiming to solve the technical problems existing in the prior art mentioned in the background art.

[0005] The embodiments of the present invention are implemented as follows: A customer service interaction method based on artificial intelligence, the method specifically includes the following steps: Receive user interaction data, identify the user interaction data, determine the target consultation product, and obtain multiple live video segments and multiple product evaluation data of the target consultation product; Extract multiple live text information from multiple live video segments, and extract multiple evaluation text information from multiple product evaluation data; Extract key interaction information from the user interaction data, make an associated comparison of multiple live text information and multiple evaluation text information, and select associated live information and associated evaluation information; Determine the customer service interaction method according to the user interaction data; Match associated video segments and associated evaluation data according to the associated live information and the associated evaluation information, and perform artificial intelligence interaction expression according to the customer service interaction method.

[0006] As a further limitation of the technical solution of the embodiments of the present invention, the step of receiving user interaction data, identifying the user interaction data, determining the target consultation product, and obtaining multiple live video segments and multiple product evaluation data of the target consultation product specifically includes the following steps: Create an interactive operation interface to receive user interaction data; Identify the user interaction data to determine the target consultation product; Obtain the internal product number of the target consultation product; According to the internal product number, obtain multiple live video segments and multiple product evaluation data of the target consultation product.

[0007] As a further limitation of the technical solution of the embodiment of the present invention, extracting multiple live text information from multiple live video segments and extracting multiple evaluation text information from multiple product evaluation data specifically includes the following steps: Extract multiple live segment audios from multiple live video segments; Perform content recognition and text conversion on multiple live segment audios to generate multiple corresponding live text information; Extract multiple evaluation text information from multiple product evaluation data.

[0008] As a further limitation of the technical solution of the embodiment of the present invention, extracting key interaction information from the user interaction data, associatively comparing multiple live text information and multiple evaluation text information, and selecting associated live information and associated evaluation information specifically includes the following steps: Extract key interaction information from the user interaction data; According to the key interaction information, perform association analysis on multiple live text information and multiple evaluation text information, and calculate multiple mutual association values; Compare and arrange multiple mutual association values, and record the comparison and arrangement data; According to the comparison and arrangement data, select associated live information from multiple live text information, and select associated evaluation information from multiple evaluation text information.

[0009] As a further limitation of the technical solution of the embodiment of the present invention, the calculation formula of multiple mutual association values is: ; Wherein, represents key interaction information, which consists of keywords, is the th keyword, is the th live text information or evaluation text information, is the mutual association value between key interaction information and the th live text information or evaluation text information, represents the The number of occurrences of a keyword in the live text information or evaluation text information, is the number of texts with the keyword in all the live text information and evaluation text information, and are respectively a preset first adjustment constant and a second adjustment constant, is the text length of the live text information or evaluation text information, is the average text length of all the live text information and evaluation text information.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, the matching of the associated video segment and the associated evaluation data according to the associated live information and the associated evaluation information, and the artificial intelligence interaction expression according to the customer service interaction method specifically include the following steps: Matching customer service interaction information according to the key interaction information; Matching the associated video segment and the associated evaluation data according to the associated live information and the associated evaluation information; Performing corresponding artificial intelligence interaction expressions on the customer service interaction information, the associated video segment and the associated evaluation data according to the customer service interaction method.

[0011] An artificial intelligence-based customer service interaction system, the system includes an interaction data recognition module, a text information extraction module, an association comparison and selection module, an interaction method determination module, and an intelligent interaction expression module, wherein: The interaction data recognition module is used to receive user interaction data, identify the user interaction data, determine the target consultation product, and obtain multiple live video segments and multiple product evaluation data of the target consultation product; The text information extraction module is used to extract multiple live text information from multiple live video segments, and extract multiple evaluation text information from multiple product evaluation data; The association comparison and selection module is used to extract key interaction information from the user interaction data, perform association comparison on multiple live text information and multiple evaluation text information, and select associated live information and associated evaluation information; The interaction method determination module is used to determine the customer service interaction method according to the user interaction data; The intelligent interaction expression module is used to match the associated video segment and the associated evaluation data according to the associated live information and the associated evaluation information, and perform artificial intelligence interaction expressions according to the customer service interaction method.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the text information extraction module specifically includes: An audio extraction unit, configured to extract multiple live segment audios from the multiple live video segments; An audio conversion unit, configured to perform content recognition and text conversion on the multiple live segment audios to generate multiple corresponding live text information; A text extraction unit, configured to extract multiple evaluation text information from the multiple product evaluation data.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the association comparison and selection module specifically includes: An information extraction unit, configured to extract key interaction information from the user interaction data; An association analysis unit, configured to perform association analysis on the multiple live text information and the multiple evaluation text information according to the key interaction information, and calculate multiple mutual association values; A comparison and arrangement unit, configured to compare and arrange the multiple mutual association values, and record the comparison and arrangement data; An information selection unit, configured to select associated live information from the multiple live text information and select associated evaluation information from the multiple evaluation text information according to the comparison and arrangement data.

[0014] As a further limitation of the technical solution of the embodiment of the present invention, the intelligent interaction expression module specifically includes: An information matching unit, configured to match customer service interaction information according to the key interaction information; An association matching unit, configured to match associated video segments and associated evaluation data according to the associated live information and the associated evaluation information; An interaction expression unit, configured to perform corresponding artificial intelligence interaction expressions on the customer service interaction information, the associated video segments, and the associated evaluation data according to the customer service interaction method.

[0015] Compared with the prior art, the beneficial effects of the present invention are: In an embodiment of the present invention, by receiving user interaction data, a target consultation product is determined, and a plurality of live video segments and a plurality of product evaluation data are obtained; a plurality of live text information and a plurality of evaluation text information are extracted; key interaction information is extracted, and the plurality of live text information and the plurality of evaluation text information are associated and compared; a customer service interaction method is determined; associated video segments and associated evaluation data are matched, and interaction expressions are made according to the customer service interaction method. It is possible to obtain a plurality of live video segments and a plurality of product evaluation data of the target consultation product, perform text information extraction and association comparison, match associated video segments and associated evaluation data, and perform artificial intelligence interaction expressions, which can effectively utilize live videos and evaluation data related to products, thereby achieving richer interaction displays and effectively improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The flowchart of the customer service interaction method based on artificial intelligence provided by the embodiment of the present invention is shown; Figure 2 The flowchart of the user interaction data recognition and processing in the method provided by the embodiment of the present invention is shown; Figure 3 The flowchart of extracting a plurality of live text information and a plurality of evaluation text information in the method provided by the embodiment of the present invention is shown; Figure 4 The flowchart of selecting associated live information and associated evaluation information in the method provided by the embodiment of the present invention is shown; Figure 5 The flowchart of the artificial intelligence interaction expression in the method provided by the embodiment of the present invention is shown; Figure 6 The application architecture diagram of the customer service interaction system based on artificial intelligence provided by the embodiment of the present invention is shown; Figure 7 The structural block diagram of the text information extraction module in the system provided by the embodiment of the present invention is shown; Figure 8 The structural block diagram of the association comparison and selection module in the system provided by the embodiment of the present invention is shown; Figure 9 The structural block diagram of the intelligent interaction expression module in the system provided by the embodiment of the present invention is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] It can be understood that in the prior art, the interaction of artificial intelligence customer service only matches the literal understanding of the user's needs among multiple preset interaction messages to complete the corresponding transmission and expression of information. Although it can meet the needs of basic replies to a certain extent, it limits the depth and breadth of the interaction. In particular, it cannot effectively utilize the live video and evaluation data generated in real time, and cannot achieve a richer interaction display, resulting in an average user experience.

[0019] To solve the above problems, a customer service interaction method and system based on artificial intelligence disclosed in an embodiment of the present invention receive user interaction data, identify the user interaction data to determine the target consultation product, and obtain multiple live video segments and multiple product evaluation data of the target consultation product; extract multiple live text messages from the multiple live video segments, and extract multiple evaluation text messages from the multiple product evaluation data; extract key interaction information from the user interaction data, perform an associated comparison on the multiple live text messages and the multiple evaluation text messages, and select associated live information and associated evaluation information; determine the customer service interaction method according to the user interaction data; match the associated video segments and associated evaluation data according to the associated live information and associated evaluation information, and perform an interactive expression of artificial intelligence according to the customer service interaction method. It can obtain multiple live video segments and multiple product evaluation data of the target consultation product, perform text information extraction and associated comparison, match the associated video segments and associated evaluation data, and perform an interactive expression of artificial intelligence, which can effectively utilize the live video and evaluation data related to the product, thereby achieving a richer interaction display and effectively improving the user experience.

[0020] Specifically, Figure 1 shows a flowchart of the customer service interaction method based on artificial intelligence provided by an embodiment of the present invention.

[0021] In a preferred embodiment provided by the present invention, a customer service interaction method based on artificial intelligence specifically includes the following steps: Step S101, receive user interaction data, identify the user interaction data, determine the target consultation product, and obtain multiple live video segments and multiple product evaluation data of the target consultation product.

[0022] In an embodiment of the present invention, when the user has an interaction request, an interaction operation interface is created, and in the interaction operation interface, user interaction data is received, and then the content of the user interaction data is target-identified to determine the target consultation product, and the internal product number of the target consultation product in the online mall is obtained. Furthermore, according to the internal product number, multiple live video segments and multiple product evaluation data of the target consultation product are obtained.

[0023] It is understandable that multiple live video clips are obtained by pre - cutting the latest live video of the target consultation commodity, and the video clips reflect different contents such as the appearance, function, operation, ingredients and / or collocation of the target consultation commodity.

[0024] It is understandable that multiple product evaluation data are data of the latest post - purchase feedback evaluations of the target consultation commodity extracted from an online mall, including: text, pictures and / or videos.

[0025] Specifically, Figure 2 The flowchart of user interaction data recognition and processing in the method provided by the embodiment of the present invention is shown.

[0026] Among them, in another preferred embodiment provided by the present invention, the receiving of user interaction data, the recognition of the user interaction data, the determination of the target consultation commodity, and the obtaining of multiple live video clips and multiple product evaluation data of the target consultation commodity specifically include the following steps: Step S1011: Create an interactive operation interface and receive user interaction data.

[0027] Step S1012: Recognize the user interaction data to determine the target consultation commodity.

[0028] Step S1013: Obtain the internal product number of the target consultation commodity.

[0029] Step S1014: According to the internal product number, obtain multiple live video clips and multiple product evaluation data of the target consultation commodity.

[0030] Furthermore, the customer service interaction method based on artificial intelligence further includes the following steps: Step S102: Extract multiple live text information from multiple live video clips, and extract multiple evaluation text information from multiple product evaluation data.

[0031] In the embodiment of the present invention, multiple live clip audios are extracted from multiple live video clips, then the content of the multiple live clip audios is recognized, and text conversion is performed to obtain multiple corresponding live text information, and multiple evaluation text information is extracted from multiple product evaluation data.

[0032] Specifically, Figure 3 The flowchart of extracting multiple live text information and multiple evaluation text information in the method provided by the embodiment of the present invention is shown.

[0033] Among them, in another preferred embodiment provided by the present invention, extracting multiple live text information from multiple live video segments and extracting multiple evaluation text information from multiple product evaluation data specifically include the following steps: Step S1021: Extract multiple live segment audios from multiple live video segments.

[0034] Step S1022: Perform content recognition and text conversion on multiple live segment audios to generate multiple corresponding live text information.

[0035] Step S1023: Extract multiple evaluation text information from multiple product evaluation data.

[0036] Furthermore, the customer service interaction method based on artificial intelligence further includes the following steps: Step S103: Extract key interaction information from the user interaction data, perform correlation comparison on multiple live text information and multiple evaluation text information, and select associated live information and associated evaluation information.

[0037] In the embodiment of the present invention, by extracting key interaction information from user interaction data, then performing correlation analysis on multiple live text information and multiple evaluation text information according to multiple keywords in the key interaction information, calculating multiple mutual correlation values, then comparing and arranging multiple mutual correlation values from large to small, recording the comparison and arrangement data, and further according to the comparison and arrangement data, selecting the associated live information ranked first from multiple live text information, and selecting the associated evaluation information ranked first from multiple evaluation text information. Specifically, the calculation formula for multiple mutual correlation values is: ; Wherein, represents key interaction information, which consists of keywords, is the th keyword, is the th live text information or evaluation text information, is the mutual correlation value between key interaction information and the th live text information or evaluation text information, represents the existence quantity of the th keyword in the th live text information or evaluation text information, is the text quantity with the th keyword among all live text information and evaluation text information, and They are respectively a preset first adjustment constant and a second adjustment constant, is the text length of the nth live text information or evaluation text information, is the average text length of all the live text information and evaluation text information.

[0038] It can be understood that the user interaction data may be text information or audio data, which is determined by the user interaction method. If the user interaction data is text information, direct content recognition and key extraction are performed on the user interaction data to obtain key interaction information; if the user interaction data is audio data, the audio data is converted into text information and then content recognition and key extraction are performed to obtain key interaction information.

[0039] Specifically, Figure 4 shows a flowchart of selecting associated live information and associated evaluation information in the method provided by an embodiment of the present invention.

[0040] Among them, in another preferred embodiment provided by the present invention, extracting key interaction information from the user interaction data, making an associated comparison between multiple pieces of the live text information and multiple pieces of the evaluation text information, and selecting associated live information and associated evaluation information specifically include the following steps: Step S1031: Extract key interaction information from the user interaction data.

[0041] Step S1032: Perform an associated analysis on multiple pieces of the live text information and multiple pieces of the evaluation text information according to the key interaction information, and calculate multiple mutual association values.

[0042] Step S1033: Compare and arrange multiple mutual association values, and record the comparison and arrangement data.

[0043] Step S1034: Select associated live information from multiple pieces of the live text information and select associated evaluation information from multiple pieces of the evaluation text information according to the comparison and arrangement data.

[0044] Further, the customer service interaction method based on artificial intelligence further includes the following steps: Step S104: Determine the customer service interaction method according to the user interaction data.

[0045] In an embodiment of the present invention, by identifying the data type of user interaction data, the user interaction method is determined, and then according to the user interaction method, the same customer service interaction method is determined. Specifically, if the data type of the user interaction data is text, the user interaction method is text interaction, and the customer service interaction method is also text interaction; if the data type of the user interaction data is audio, the user interaction method is voice interaction, and the customer service interaction method is also voice interaction.

[0046] Step S105: Match the associated video segment and the associated evaluation data according to the associated live broadcast information and the associated evaluation information, and perform an interactive expression of artificial intelligence according to the customer service interaction method.

[0047] In an embodiment of the present invention, according to the key interaction information, the customer service interaction information is matched from a plurality of preset standard interaction information, then according to the associated live broadcast information, the corresponding associated video segment is matched, and according to the associated evaluation information, the corresponding associated evaluation data is matched. Furthermore, according to the customer service interaction method, an interactive expression of artificial intelligence of the customer service interaction information, the associated video segment and the associated evaluation data is performed on the user.

[0048] It can be understood that the multiple standard interaction information is information preset for standardizing responses to different user needs.

[0049] It can be understood that if the customer service interaction method is text interaction, both the customer service interaction information and the associated evaluation information in the associated evaluation data are interactively displayed in text; if the customer service interaction method is voice interaction, both the customer service interaction information and the associated evaluation information in the associated evaluation data are interactively expressed in audio.

[0050] Specifically, Figure 5 The flowchart of the interactive expression of artificial intelligence in the method provided by the embodiment of the present invention is shown.

[0051] Among them, in another preferred embodiment provided by the present invention, the matching of the associated video segment and the associated evaluation data according to the associated live broadcast information and the associated evaluation information, and performing an interactive expression of artificial intelligence according to the customer service interaction method specifically includes the following steps: Step S1051: Match the customer service interaction information according to the key interaction information.

[0052] Step S1052: Match the associated video segment and the associated evaluation data according to the associated live broadcast information and the associated evaluation information.

[0053] Step S1053: Perform a corresponding interactive expression of artificial intelligence on the customer service interaction information, the associated video segment and the associated evaluation data according to the customer service interaction method.

[0054] Further, Figure 6 The application architecture diagram of the customer service interaction system based on artificial intelligence provided by the embodiments of the present invention is shown.

[0055] Specifically, in another preferred embodiment provided by the present invention, a customer service interaction system based on artificial intelligence includes: An interaction data recognition module 101, configured to receive user interaction data, recognize the user interaction data, determine a target consultation product, and obtain multiple live video segments and multiple product evaluation data of the target consultation product.

[0056] In the embodiments of the present invention, when the user has an interaction request, the interaction data recognition module 101 creates an interaction operation interface, receives user interaction data in the interaction operation interface, then performs target recognition on the content of the user interaction data to determine the target consultation product, and obtains the internal product number of the target consultation product in the online mall. Furthermore, according to the internal product number, multiple live video segments and multiple product evaluation data of the target consultation product are obtained.

[0057] A text information extraction module 102, configured to extract multiple live text information from multiple live video segments, and extract multiple evaluation text information from multiple product evaluation data.

[0058] In the embodiments of the present invention, the text information extraction module 102 extracts multiple live segment audio from multiple live video segments, then performs content recognition on the multiple live segment audio and converts it into text to obtain multiple corresponding live text information, and extracts multiple evaluation text information from multiple product evaluation data.

[0059] Specifically, Figure 7 The structural block diagram of the text information extraction module 102 in the system provided by the embodiments of the present invention is shown.

[0060] Wherein, in another preferred embodiment provided by the present invention, the text information extraction module 102 specifically includes: An audio extraction unit 1021, configured to extract multiple live segment audio from multiple live video segments.

[0061] An audio conversion unit 1022, configured to perform content recognition and text conversion on multiple live segment audio to generate multiple corresponding live text information.

[0062] A text extraction unit 1023, configured to extract multiple evaluation text information from multiple product evaluation data.

[0063] Further, the customer service interaction system based on artificial intelligence further includes: The association comparison and selection module 103 is configured to extract key interaction information from the user interaction data, perform an association comparison on the multiple live text information and the multiple evaluation text information, and select the associated live information and the associated evaluation information.

[0064] In an embodiment of the present invention, the association comparison and selection module 103 extracts key interaction information from the user interaction data, and then performs an association analysis on the multiple live text information and the multiple evaluation text information according to multiple keywords in the key interaction information, calculates multiple mutual association values, and then compares and arranges the multiple mutual association values from largest to smallest, records the comparison and arrangement data, and further selects the associated live information ranked first from the multiple live text information and selects the associated evaluation information ranked first from the multiple evaluation text information. Specifically, the calculation formula for the multiple mutual association values is as follows: ; Wherein, represents the key interaction information, which is composed of keywords, is the th keyword, is the th live text information or evaluation text information, is the mutual association value between the key interaction information and the th live text information or evaluation text information, represents the number of occurrences of the th keyword in the th live text information or evaluation text information, is the number of texts with the th keyword among all the live text information and evaluation text information, and are respectively a preset first mediation constant and a second mediation constant, is the th live text information or evaluation text information's text length, is the average text length of all the live text information and evaluation text information.

[0065] Specifically, Figure 8 shows the structural block diagram of the association comparison and selection module 103 in the system provided by the embodiment of the present invention.

[0066] Wherein, in another preferred embodiment provided by the present invention, the association comparison and selection module 103 specifically includes: The information extraction unit 1031 is configured to extract key interaction information from the user interaction data.

[0067] The association analysis unit 1032 is configured to perform association analysis on the multiple live text information and the multiple evaluation text information according to the key interaction information, and calculate multiple mutual association values.

[0068] The comparison and arrangement unit 1033 is configured to compare and arrange the multiple mutual association values, and record the comparison and arrangement data.

[0069] The information selection unit 1034 is configured to select associated live information from the multiple live text information and select associated evaluation information from the multiple evaluation text information according to the comparison and arrangement data.

[0070] Furthermore, the customer service interaction system based on artificial intelligence further includes: The interaction mode determination module 104 is configured to determine the customer service interaction mode according to the user interaction data.

[0071] In an embodiment of the present invention, the interaction mode determination module 104 determines the user interaction mode by identifying the data type of the user interaction data, and then determines the same customer service interaction mode according to the user interaction mode. Specifically, if the data type of the user interaction data is text, the user interaction mode is text interaction, and the customer service interaction mode is also text interaction; if the data type of the user interaction data is audio, the user interaction mode is voice interaction, and the customer service interaction mode is also voice interaction.

[0072] The intelligent interaction expression module 105 is configured to match associated video segments and associated evaluation data according to the associated live information and the associated evaluation information, and perform artificial intelligence interaction expression according to the customer service interaction mode.

[0073] In an embodiment of the present invention, the intelligent interaction expression module 105 matches the customer service interaction information from a plurality of preset standard interaction information according to the key interaction information, then matches the corresponding associated video segments according to the associated live information, and matches the corresponding associated evaluation data according to the associated evaluation information, and then performs artificial intelligence interaction expression of the customer service interaction information, the associated video segments and the associated evaluation data to the user according to the customer service interaction mode.

[0074] Specifically, Figure 9 FIG. shows the structural block diagram of the intelligent interaction expression module 105 in the system provided by the embodiment of the present invention.

[0075] Wherein, in another preferred embodiment provided by the present invention, the intelligent interaction expression module 105 specifically includes: The information matching unit 1051 is configured to match the customer service interaction information according to the key interaction information.

[0076] An associated matching unit 1052 is configured to match an associated video segment and associated evaluation data according to the associated live broadcast information and the associated evaluation information.

[0077] An interactive expression unit 1053 is configured to perform corresponding artificial intelligence interactive expressions on the customer service interaction information, the associated video segment, and the associated evaluation data according to the customer service interaction mode.

[0078] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are sequentially shown according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential either, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0079] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0080] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

Claims

1. A customer service interaction method based on artificial intelligence, characterized in that, The method specifically includes the following steps: Receive user interaction data, identify the user interaction data, determine the target consultation product, and obtain multiple live video segments and multiple product evaluation data of the target consultation product; Extract multiple live text information from multiple live video segments, and extract multiple evaluation text information from multiple product evaluation data; Extract key interaction information from the user interaction data, conduct an associated comparison on multiple live text information and multiple evaluation text information, and select associated live information and associated evaluation information; Determine the customer service interaction method according to the user interaction data; Match the associated video segments and associated evaluation data according to the associated live information and the associated evaluation information, and perform artificial intelligence interaction expression according to the customer service interaction method.

2. The customer service interaction method based on artificial intelligence according to claim 1, wherein, The step of receiving user interaction data, identifying the user interaction data, determining the target consultation product, and obtaining multiple live video segments and multiple product evaluation data of the target consultation product specifically includes the following steps: Create an interaction operation interface to receive user interaction data; Identify the user interaction data to determine the target consultation product; Obtain the internal product number of the target consultation product; According to the internal product number, obtain multiple live video segments and multiple product evaluation data of the target consultation product.

3. The customer service interaction method based on artificial intelligence according to claim 1, wherein The step of extracting multiple live text information from multiple live video segments and extracting multiple evaluation text information from multiple product evaluation data specifically includes the following steps: Extract multiple live segment audios from multiple live video segments; Conduct content recognition and text conversion on multiple live segment audios to generate multiple corresponding live text information; Extract multiple evaluation text information from multiple product evaluation data.

4. The customer service interaction method based on artificial intelligence according to claim 1, wherein The step of extracting key interaction information from the user interaction data, conducting an associated comparison on multiple live text information and multiple evaluation text information, and selecting associated live information and associated evaluation information specifically includes the following steps: Extract key interaction information from the user interaction data; Conduct an associated analysis on multiple live text information and multiple evaluation text information according to the key interaction information, and calculate multiple mutual association values; Compare and arrange multiple mutual association values, and record the comparison and arrangement data; According to the comparison and arrangement data, select associated live information from multiple live text information, and select associated evaluation information from multiple evaluation text information.

5. The customer service interaction method based on artificial intelligence according to claim 4, wherein The calculation formula for multiple mutual association values is: ； Among them, represents key interaction information, which consists of keywords, is the th keyword, is the th live text information or evaluation text information, is the correlation value between the key interaction information and the th live text information or evaluation text information, represents the presence quantity of the th keyword in the th live text information or evaluation text information, is the text quantity with the th keyword in all live text information and evaluation text information, and are respectively the preset first mediation constant and second mediation constant, is the text length of the th live text information or evaluation text information, is the average text length of all live text information and evaluation text information.

6. The customer service interaction method based on artificial intelligence according to claim 1, wherein The step of matching the associated video segments and associated evaluation data according to the associated live information and the associated evaluation information, and performing artificial intelligence interaction expression according to the customer service interaction method specifically includes the following steps: Match customer service interaction information according to the key interaction information; Match the associated video segments and associated evaluation data according to the associated live information and the associated evaluation information; According to the customer service interaction method, perform corresponding artificial intelligence interaction expressions on the customer service interaction information, the associated video segments, and the associated evaluation data.

7. An artificial intelligence-based customer service interaction system, characterized in that, The system includes an interaction data recognition module, a text information extraction module, an associated comparison and selection module, an interaction method determination module, and an intelligent interaction expression module, where: The interaction data recognition module is used to receive user interaction data, recognize the user interaction data, determine the target consultation product, and obtain multiple live video segments and multiple product evaluation data of the target consultation product; The text information extraction module is used to extract multiple live text information from multiple live video segments, and extract multiple evaluation text information from multiple product evaluation data; The associated comparison and selection module is used to extract key interaction information from the user interaction data, perform an associated comparison on multiple live text information and multiple evaluation text information, and select associated live information and associated evaluation information; The interaction method determination module is used to determine the customer service interaction method according to the user interaction data; The intelligent interaction expression module is used to match the associated video segments and the associated evaluation data according to the associated live information and the associated evaluation information, and perform corresponding artificial intelligence interaction expressions according to the customer service interaction method.

8. The customer service interaction system based on artificial intelligence according to claim 7, characterized in that, The text information extraction module specifically includes: An audio extraction unit, used to extract multiple live segment audios from multiple live video segments; An audio conversion unit, used to perform content recognition and text conversion on multiple live segment audios to generate multiple corresponding live text information; A text extraction unit, used to extract multiple evaluation text information from multiple product evaluation data.

9. The customer service interaction system based on artificial intelligence according to claim 7, wherein The associated comparison and selection module specifically includes: An information extraction unit, used to extract key interaction information from the user interaction data; An associated analysis unit, used to perform an associated analysis on multiple live text information and multiple evaluation text information according to the key interaction information, and calculate multiple mutual association values; A comparison and arrangement unit, used to compare and arrange multiple mutual association values, and record the comparison and arrangement data; An information selection unit, used to select associated live information from multiple live text information and select associated evaluation information from multiple evaluation text information according to the comparison and arrangement data.

10. The customer service interaction system based on artificial intelligence according to claim 7, characterized in that, The intelligent interaction expression module specifically includes: An information matching unit, used to match customer service interaction information according to the key interaction information; An associated matching unit, used to match associated video segments and associated evaluation data according to the associated live information and the associated evaluation information; An interaction expression unit, used to perform corresponding artificial intelligence interaction expressions on the customer service interaction information, the associated video segments, and the associated evaluation data according to the customer service interaction method.

Images