An intelligent interaction method and system for a distributed multi-modal online customer service

Abstract

The present invention relates to the technical field of retrieval feedback calculation, and more specifically, to an intelligent interaction method and system for distributed multi-modal online customer service. The solution includes setting up an infrastructure layer to complete the construction of the infrastructure; after obtaining data in the infrastructure layer, performing online knowledge base management; on the basis of the online knowledge base management, setting up course information management; performing time statistics on all historical Q&A information; according to the time statistics results, quickly retrieving answers according to the questions raised by client users; and performing detailed dashboard display. This solution reduces the dependence on human customer service through automated processing and reduces labor costs.

Description

Technical Field

[0001] The present invention relates to the technical field of retrieval feedback calculation, and more specifically, to an intelligent interaction method and system for distributed multi-modal online customer service. Background Art

[0002] The retrieval and question-answering functions of the customer service system are the bridges for modern enterprises to communicate with customers. Their importance lies not only in improving customer satisfaction, but also in helping enterprises reduce costs and improve efficiency. The retrieval and question-answering system can quickly find the answers to questions from a large amount of data and provide instant feedback to customers. The automated question-answering system reduces the waiting time of customers and improves customer satisfaction. By automatically processing common questions, the dependence on human customer service is reduced, thus reducing the labor cost.

[0003] Before the technology of the present invention, the existing traditional customer service systems mainly rely on retrieval technology, with limited ability to understand the semantics of questions raised by users and generate responses. They can only answer according to fixed rules, and their interaction methods are single, making it difficult to meet the complex and diverse question-asking needs of users. In addition, the construction of their knowledge bases mainly relies on manually writing question-and-answer pairs one by one, consuming a large amount of time and effort and making the construction of the knowledge base cumbersome. Summary of the Invention

[0004] In view of the above problems, the present invention proposes an intelligent interaction method and system for distributed multi-modal online customer service, which reduces the dependence on human customer service through automated processing and reduces the labor cost.

[0005] According to the first aspect of the embodiments of the present invention, an intelligent interaction method for distributed multi-modal online customer service is provided.

[0006] In one or more embodiments, preferably, the intelligent interaction method for distributed multi-modal online customer service includes:

[0007] Set up the infrastructure layer to complete the construction of the infrastructure;

[0008] After obtaining data in the infrastructure layer, perform online knowledge base management;

[0009] On the basis of online knowledge base management, set up course information management;

[0010] Perform time statistics on all historical question-and-answer information;

[0011] According to the time statistics results, perform fast answer retrieval according to the questions raised by the client users;

[0012] Perform detailed dashboard display.

[0013] In one or more embodiments, preferably, the infrastructure layer is set up to complete the construction of the infrastructure, specifically including:

[0014] Set up a large model server and an application server;

[0015] Set up a K8S containerization platform;

[0016] Set up a MySQL database;

[0017] Set up a low-code platform.

[0018] In one or more embodiments, preferably, after obtaining data in the infrastructure layer, online knowledge base management is performed, specifically including:

[0019] Set up knowledge base management to include functions such as new creation, viewing, searching, taking offline, and clearing;

[0020] Under the new creation function, click the Create QA button, a pop-up window will appear, enter the question and answer fields, and click OK to save;

[0021] Under the viewing function, click the View Details button, a pop-up window will appear, and the pop-up window will display field information such as question ID and data source, which cannot be edited;

[0022] Under the search function, enter conditions in the question description and date box, click the search button, and the system will query according to the conditions, and the query results will be displayed on the page;

[0023] Under the clearing function, click the clear button to clear the search conditions in the condition input box; under the taking offline function, click the take offline button, a pop-up window will appear, confirm whether to take offline, click OK, and the data will enter the pending review interface.

[0024] In one or more embodiments, preferably, based on the online knowledge base management, course information management is set up, specifically including:

[0025] The page includes functions such as new creation, deletion, editing, and searching;

[0026] The new creation function requires filling in the course id and course name;

[0027] Click the edit button in the operation column to enter the edit interface and modify the original course information;

[0028] Click the delete button to perform a delete operation on this data;

[0029] The page supports fuzzy search according to the course name.

[0030] In one or more embodiments, preferably, time statistics are performed on all historical Q&A information, specifically including:

[0031] Set the statistical classification to monthly statistics, quarterly statistics, and annual statistics;

[0032] Conduct statistics based on fuzzy search of followed users and the number of export times;

[0033] Each statistic includes fields such as the total number of questions and answers, effective rate, like rate, and failure rate.

[0034] In one or more embodiments, preferably, according to the time statistical results, perform a quick answer retrieval according to the questions raised by client users, specifically including:

[0035] Set the vocabulary management page to include functions such as querying by sensitive word type, fuzzy query by sensitive word, new creation, editing, and deletion;

[0036] Query by sensitive word type to form a first number;

[0037] Perform a fuzzy query by sensitive word to form a second number;

[0038] Obtain the questions raised by client users, perform vocabulary extraction, and determine whether there are sensitive words;

[0039] If there are sensitive words, use the first calculation formula to calculate the feedback number of the currently most matching sensitive word;

[0040] Feedback the pre-set feedback answer according to the feedback number of the currently most matching sensitive word;

[0041] Obtain all the matching words currently, and obtain the time grouping where the current word is located. The time minute is pre-set, and the time grouping is one of monthly statistics, quarterly statistics, and annual statistics;

[0042] Perform effectiveness calculation using the second calculation formula based on the fuzzy search and the number of export times;

[0043] Obtain the corresponding optimal feedback list under the current knowledge base and course using the large model based on all the matching words currently;

[0044] When the effectiveness does not exceed the preset value, calculate the comprehensive index using the third calculation formula based on the optimal feedback list and the fields of the total number of answers, effective rate, like rate, and failure rate corresponding to the answers in the optimal feedback list;

[0045] When the effectiveness exceeds the preset value, incorporate the associated feedback of the answers associated with this retrieval in the exported data into the optimal feedback list;

[0046] And calculate the comprehensive index using the third calculation formula based on the fields of the total number of answers, effective rate, like rate, and failure rate;

[0047] Take the result of the comprehensive index as the first feedback result, and when the effectiveness exceeds the preset value, take the answer with the highest comprehensive index among the answers related to this retrieval in the exported data as the second feedback result;

[0048] The first calculation formula is:

[0049] B = k1×S1 + k2×S2

[0050] Where B is the feedback number of the currently most matching sensitive word, k1 is the first preset coefficient, k2 is the second preset coefficient, S1 is the first number, and S2 is the second number;

[0051] The second calculation formula is:

[0052] Y = D / M

[0053] Where Y is the effectiveness, D is the export times, and M is the fuzzy search;

[0054] The third calculation formula is:

[0055] ZZ = DZ×xl×(1 - sb) 3 ×(1 + dianz)

[0056] Where ZZ is the comprehensive index, DZ is the total number of answers, xl is the effective rate, dianz is the like rate, and sb is the failure rate.

[0057] In one or more embodiments, preferably, the detailed dashboard display specifically includes:

[0058] Set four attention modules, namely: followed user selection, data statistics, line chart, and data report;

[0059] The followed user selection is to be able to select to view all data or the data under a certain followed user;

[0060] Set the data statistics to include the total number of questions and answers, the total number of questions, the number of visits, the total number of likes and dislikes, the effective rate, the like rate, and the failure rate;

[0061] Stat the number of questions and answers per day in the past 5 days and make a line chart of the number of questions;

[0062] Stat the quantity and proportion of all likes and dislikes as a data report.

[0063] According to the second aspect of the embodiments of the present invention, there is provided an intelligent interaction system for distributed multi-modal online customer service.

[0064] In one or more embodiments, preferably, the intelligent interaction system for distributed multi-modal online customer service includes:

[0065] An infrastructure setting module, configured to set up the infrastructure layer and complete the construction of the infrastructure;

[0066] A knowledge base management module, configured to perform online knowledge base management after obtaining data at the infrastructure layer;

[0067] A course management module, configured to set up course information management based on the online knowledge base management;

[0068] A time statistics module, configured to perform time statistics on all historical Q&A information;

[0069] An intelligent recommendation module, configured to perform a quick answer retrieval according to the time statistics result and in accordance with the questions raised by the client users;

[0070] A dashboard display module, configured to perform a detailed dashboard display.

[0071] According to a third aspect of an embodiment of the present invention, there is provided a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described in any one of the first aspects of the embodiments of the present invention is implemented.

[0072] According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device, including a memory and a processor, where the memory is configured to store one or more computer program instructions, and wherein the one or more computer program instructions are executed by the processor to implement the method described in any one of the first aspects of the embodiments of the present invention.

[0073] The technical solution provided by the embodiments of the present invention may include the following beneficial effects:

[0074] In the solution of the present invention, an automated detection Q&A interaction system is provided, which reduces the labor cost.

[0075] In the solution of the present invention, according to the time statistics result, a quick answer retrieval is performed in accordance with the questions raised by the client users, so as to achieve a quick Q&A interaction.

[0076] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention may be realized and obtained by the structures specifically pointed out in the written specification, claims, and drawings.

[0077] Next, through the drawings and embodiments, the technical solution of the present invention will be further described in detail. Description of the Drawings

[0078] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those skilled in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0079] Figure 1 It is a flowchart of an intelligent interaction method for a distributed multi-modal online customer service according to an embodiment of the present invention.

[0080] Figure 2 It is a flowchart of setting up the infrastructure layer in an intelligent interaction method for a distributed multi-modal online customer service according to an embodiment of the present invention to complete the construction of the infrastructure.

[0081] Figure 3 It is a flowchart of performing online knowledge base management after obtaining data in the infrastructure layer in an intelligent interaction method for a distributed multi-modal online customer service according to an embodiment of the present invention.

[0082] Figure 4 It is a flowchart of setting up course information management based on the online knowledge base management in an intelligent interaction method for a distributed multi-modal online customer service according to an embodiment of the present invention.

[0083] Figure 5 It is a flowchart of performing time statistics on all historical Q&A information in an intelligent interaction method for a distributed multi-modal online customer service according to an embodiment of the present invention.

[0084] Figure 6 It is a flowchart of quickly retrieving answers according to the time statistics results and the questions raised by the client users in an intelligent interaction method for a distributed multi-modal online customer service according to an embodiment of the present invention.

[0085] Figure 7 It is a flowchart of performing detailed dashboard display in an intelligent interaction method for a distributed multi-modal online customer service according to an embodiment of the present invention.

[0086] Figure 8 It is a structural diagram of a distributed multi-modal online customer service intelligent interaction system according to an embodiment of the present invention.

[0087] Figure 9 It is a structural diagram of an electronic device according to an embodiment of the present invention. Detailed implementation manners

[0088] In some of the processes described in the specification, claims, and above-mentioned drawings of the present invention, there are multiple operations that occur in a specific order. However, it should be clearly understood that these operations can be performed not in the order in which they appear herein or in parallel. The operation numbers such as 101, 102, etc. are only used to distinguish different operations, and the numbers themselves do not represent any execution order. Additionally, these processes can include more or fewer operations, and these operations can be executed sequentially or in parallel. It should be noted that the descriptions such as "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are different types.

[0089] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0090] The retrieval and question-and-answer functions of the customer service system are the bridges for modern enterprises to communicate with customers. Their importance is not only reflected in improving customer satisfaction but also in helping enterprises reduce costs and improve efficiency. The retrieval and question-and-answer system can quickly find the answers to questions from a large amount of data and provide instant feedback to customers. The automated question-and-answer system reduces the waiting time of customers and improves customer satisfaction. By automatically processing common questions, the dependence on human customer service is reduced, thereby reducing labor costs.

[0091] Before the technology of the present invention, the existing traditional customer service systems mainly rely on retrieval technology, with limited capabilities in semantic understanding and response generation for the questions raised by users. They can only answer according to fixed rules, and their interaction methods are single, making it difficult to meet the complex and diverse question needs of users. In addition, the construction of their knowledge bases mainly relies on manually writing question-and-answer pairs one by one, consuming a large amount of time and energy, and making the construction of the knowledge base cumbersome.

[0092] In the embodiments of the present invention, an intelligent interaction method and system for a distributed multi-modal online customer service are provided. This solution reduces the dependence on human customer service through automation and reduces labor costs.

[0093] According to the first aspect of the embodiments of the present invention, an intelligent interaction method for a distributed multi-modal online customer service is provided.

[0094] Figure 1 It is a flowchart of an intelligent interaction method for a distributed multi-modal online customer service according to an embodiment of the present invention.

[0095] In one or more embodiments, preferably, the intelligent interaction method of the distributed multi-modal online customer service includes:

[0096] S101. Set up the infrastructure layer and complete the construction of the infrastructure;

[0097] S102. After obtaining data in the infrastructure layer, perform online knowledge base management;

[0098] S103. Based on the online knowledge base management, set up course information management;

[0099] S104. Perform time statistics on all historical Q&A information;

[0100] S105. According to the time statistics results, perform fast answer retrieval according to the questions raised by the client users;

[0101] S106. Perform detailed dashboard display.

[0102] In the embodiments of the present invention, by automatically processing common problems, the dependence on human customer service is reduced, thereby reducing the labor cost; in addition, the automated system can handle the consultations of multiple customers simultaneously, improving the efficiency of problem handling. In addition, it should be noted that the multi-modal online customer service can import ASR text (subtitle information).

[0103] Figure 2 It is a flowchart of setting up the infrastructure layer and completing the construction of the infrastructure in the intelligent interaction method of the distributed multi-modal online customer service according to an embodiment of the present invention.

[0104] As Figure 2 shown, in one or more embodiments, preferably, the setting up the infrastructure layer and completing the construction of the infrastructure specifically includes:

[0105] S201. Set up a large model server and an application server;

[0106] S202. Set up a K8S containerization platform;

[0107] S203. Set up a MySQL database;

[0108] S204. Set up a low-code platform.

[0109] In the embodiment of the present invention, the infrastructure layer is the foundation of the system, providing the operating environment and support for other layers. It includes hardware, operating systems, network infrastructure, storage systems, etc. At this layer, the main concerns are the reliability, scalability, security, and performance of the system. The design decisions of the infrastructure layer will directly affect the overall stability and availability of the system. In this architecture, we use basic technologies such as large model servers, application servers, operating systems, large model middleware services, low-code platforms, MySQL databases, k8s, and docker.

[0110] Figure 3 It is a flowchart for online knowledge base management after obtaining data at the infrastructure layer in an intelligent interaction method of a distributed multi-modal online customer service according to an embodiment of the present invention.

[0111] As Figure 3 shown, in one or more embodiments, preferably, after obtaining data at the infrastructure layer, performing online knowledge base management specifically includes:

[0112] S301. Set that the knowledge base management includes functions of new creation, viewing, searching, offline, and clearing;

[0113] S302. Under the new creation function, click the Create QA button, a pop-up window will appear, enter the question and answer fields, and click OK to save;

[0114] S303. Under the viewing function, click the View Details button, a pop-up window will jump out, and the pop-up window will display field information such as question ID and data source, which cannot be edited;

[0115] S304. Under the searching function, enter conditions in the question description and date box, click the Search button, and the system will query according to the conditions, and the query results will be displayed on the page;

[0116] S305. Under the clearing function, click the Clear button to clear the search conditions in the condition input box; under the offline function, click the Offline button, a pop-up window will appear, whether to confirm offline, click OK, and the data will enter the pending review interface.

[0117] In the embodiments of the present invention, for the knowledge base required for answering, unified management can be performed in the background. The knowledge base is divided into an FAQ library and a knowledge base. FAQ library management - published page, the page mainly includes functions such as new creation, viewing, searching, offline, and clearing; click the Create QA button, a pop-up window will appear, enter the question and answer fields, and click OK to save; click the View Details button, a pop-up window will pop up, and the pop-up window displays field information such as question ID and data source, which cannot be edited; enter conditions in the question description and date box, click the Search button, the system will query according to the conditions, and the page will display the query results; click the Clear button to clear the search conditions in the condition input box; click the Offline button, a pop-up window will appear, asking whether to confirm offline, click OK, and the data will enter the pending review interface; Knowledge base - FAQ library management - pending review page, the page includes functions such as viewing, publishing, and deleting; click the View button to enter the viewing page, and the page displays fields such as question ID, question description, and reviewer, supporting modification functions. Click the Publish button, a pop-up window will appear, and the content of the pop-up window shows whether to publish. Click OK to publish to the published page. The Publish button on the viewing page has the same function as this button. Click the Delete button, a pop-up window will appear, and the content of the pop-up window shows whether to delete. Click OK to delete the data.

[0118] Figure 4 Based on the online knowledge base management in an intelligent interaction method of a distributed multi-modal online customer service in an embodiment of the present invention, a flowchart for setting course information management is provided.

[0119] As Figure 4 shown, in one or more embodiments, preferably, based on the online knowledge base management, course information management is set up, specifically including:

[0120] S401. The page includes functions such as new creation, deletion, editing, and searching;

[0121] S402. For the new creation function, the course ID and course name need to be filled in;

[0122] S403. Click the Edit button in the operation column to enter the editing interface and modify the original course information;

[0123] S404. Click the Delete button to perform a deletion operation on the data;

[0124] S405. The page supports fuzzy search according to the course name.

[0125] In the embodiment of the present invention, for the background management system - course information management, the page includes functions such as new creation, deletion, editing, and search. The page supports fuzzy search according to the course name; for the new creation function, the course ID and course name need to be filled in, and the concerned users are selected from the dropdown list (the data source is the concerned user management). Click the edit button in the operation column to enter the edit interface, where the original course information can be modified; click the delete button to perform the deletion operation on this data.

[0126] Figure 5 It is a flowchart for time statistics of all historical Q&A information in an intelligent interaction method of a distributed multi-modal online customer service according to an embodiment of the present invention.

[0127] As Figure 5 shown, in one or more embodiments, preferably, the time statistics of all historical Q&A information specifically include:

[0128] S501. Set the statistical classifications as monthly statistics, quarterly statistics, and annual statistics;

[0129] S502. Conduct statistics according to the fuzzy search by concerned users and the export times;

[0130] S503. Each statistic includes fields such as the total number of Q&A, effective rate, like rate, and failure rate.

[0131] In the embodiment of the present invention, the statistics include monthly statistics, quarterly statistics, and annual statistics. For this statistics, fuzzy search and export can be performed according to the concerned users. Each statistic includes fields such as the total number of Q&A, effective rate, like rate, and failure rate. The statistical time fields are statistically calculated by month, quarter, and year respectively.

[0132] Figure 6 It is a flowchart for quickly retrieving answers according to the questions raised by the client users according to the time statistical results in an intelligent interaction method of a distributed multi-modal online customer service according to an embodiment of the present invention.

[0133] As Figure 6 shown, in one or more embodiments, preferably, the quick answer retrieval according to the time statistical results and the questions raised by the client users specifically includes:

[0134] S601. Set that the vocabulary management page includes functions such as query by sensitive word type, fuzzy query by sensitive word, new creation, editing, and deletion;

[0135] S602. Query by sensitive word type to form the first number;

[0136] S603. Fuzzy query by sensitive word to form the second number;

[0137] S604. Obtain the questions raised by the client users, perform lexical extraction, and determine whether there are sensitive words;

[0138] S605. If there are sensitive words, calculate the currently most matching sensitive word feedback number using the first calculation formula;

[0139] S606. According to the currently most matching sensitive word feedback number, feedback the pre-set feedback answer;

[0140] S607. Obtain all the matching words currently, obtain the time grouping where the current word is located, the time minute is pre-set, and the time grouping is one of monthly statistics, quarterly statistics, and annual statistics;

[0141] S608. Perform effectiveness calculation using the second calculation formula according to the fuzzy search and the export times;

[0142] S609. Obtain the corresponding optimal feedback list under the current knowledge base and course using the large model according to all the matching words currently;

[0143] S6010. When the effectiveness does not exceed the preset value, calculate the comprehensive index using the third calculation formula according to the optimal feedback list and the answer total number, effective rate, like rate, and failure rate fields corresponding to the optimal feedback list answers;

[0144] S6011. When the effectiveness exceeds the preset value, incorporate the associated feedback of the answers associated with this retrieval in the exported data into the optimal feedback list;

[0145] S6012. And calculate the comprehensive index using the third calculation formula according to the answer total number, effective rate, like rate, and failure rate fields;

[0146] S6013. Use the result of the comprehensive index as the first feedback result, and when the effectiveness exceeds the preset value, use the one with the highest comprehensive index among the answers associated with this retrieval in the exported data as the second feedback result;

[0147] The first calculation formula is:

[0148] B = k1×S1 + k2×S2

[0149] Where, B is the currently most matching sensitive word feedback number, k1 is the first preset coefficient, k2 is the second preset coefficient, S1 is the first number, and S2 is the second number;

[0150] The second calculation formula is:

[0151] Y = D / M

[0152] Where, Y is the effectiveness, D is the export times, and M is the fuzzy search;

[0153] The third calculation formula is as follows:

[0154] ZZ = DZ × xl × (1 - sb) 3 × (1 + dianz)

[0155] Where ZZ is the comprehensive index, DZ is the total number of answers, xl is the effective rate, dianz is the like rate, and sb is the failure rate.

[0156] In the embodiment of the present invention, the vocabulary management page includes functions of querying by sensitive word type, fuzzy query by sensitive word, new creation, editing, and deletion; querying by sensitive word type; fuzzy query by sensitive word; new creation: select the sensitive word type from the drop-down list, enter the sensitive word and status; editing: click the edit button in the operation column to enter the editing interface, where the original vocabulary information can be modified; deletion: click the delete button to delete the data. For the questions missing in the knowledge base, they can be temporarily supplemented in Business Management - Backstage Management - Automatic Reply Management. When answering questions, it will first screen whether the question is in the automatic reply management. Query logic: obtain the question raised by the client user; search for the corpus in the automatic reply management according to the question; obtain the standard answer to the question according to the corpus.

[0157] Figure 7 It is a flowchart for detailed dashboard display in an intelligent interaction method of a distributed multi-modal online customer service according to an embodiment of the present invention.

[0158] As Figure 7 shown, in one or more embodiments, preferably, the detailed dashboard display specifically includes:

[0159] S701. Set four attention modules, namely: selected followed user, data statistics, line chart, and data report;

[0160] S702. Use the option to view all data or data under a certain followed user as the selected followed user;

[0161] S703. Set the data statistics to include the total number of questions and answers, the total number of questions, the number of visits, the total number of likes and dislikes, the effective rate, the like rate, and the failure rate;

[0162] S704. Statistically generate a line chart of the number of questions and answers per day in the past 5 days;

[0163] S705. Statistically generate a data report on the quantity and proportion of all likes and dislikes.

[0164] In the embodiments of the present invention, to facilitate the manager to view system data, a dashboard function is provided. This page is divided into four modules, namely, selected followed users, data statistics, line chart, and data report. Selected followed users: You can choose to view all data or the data under a certain followed user. Data statistics: It includes the total number of questions and answers, the total number of questions, the number of visits, the total number of likes & dislikes, the efficiency rate, the like rate, and the failure rate. Line chart: It statistics the number of questions and answers per day in the past 5 days. Data report: It statistics the quantity and proportion of all likes & dislikes.

[0165] According to the second aspect of the embodiments of the present invention, there is provided an intelligent interaction system for distributed multi-modal online customer service.

[0166] Figure 8 It is a structural diagram of an intelligent interaction system for distributed multi-modal online customer service according to an embodiment of the present invention.

[0167] In one or more embodiments, preferably, the intelligent interaction system for distributed multi-modal online customer service includes:

[0168] An infrastructure setting module 801, which is used to set the infrastructure layer and complete the construction of the infrastructure;

[0169] A knowledge base management module 802, which is used to perform online knowledge base management after obtaining data in the infrastructure layer;

[0170] A course management module 803, which is used to set course information management based on the online knowledge base management;

[0171] A time statistics module 804, which is used to perform time statistics on all historical question and answer information;

[0172] An intelligent recommendation module 805, which is used to quickly retrieve answers according to the time statistics results and the questions raised by the client users;

[0173] A dashboard display module 806, which is used to perform detailed dashboard display.

[0174] In the embodiments of the present invention, through a series of modular designs, a system suitable for different structures is realized. This system can achieve closed-loop, reliable, and efficient execution through collection, analysis, and control.

[0175] According to the third aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the methods described in any one of the first aspects of the embodiments of the present invention are implemented.

[0176] According to the fourth aspect of the embodiments of the present invention, there is provided an electronic device. Figure 9It is a structural diagram of an electronic device in an embodiment of the present invention. Figure 9 The illustrated electronic device is an intelligent interaction device for a general distributed multi-modal online customer service. The electronic device can be a device such as a smart phone or a tablet computer. As shown, the electronic device 900 includes a processor 901 and a memory 902. Among them, the processor 901 is electrically connected to the memory 902. The processor 901 is the control center of the terminal 900, connecting various parts of the entire terminal through various interfaces and lines, and by running or calling computer programs stored in the memory 902, as well as calling data stored in the memory 902, it executes various functions of the terminal and processes data, thereby monitoring the terminal as a whole.

[0177] In this embodiment, the processor 901 in the electronic device 900 will load instructions corresponding to the processes of one or more computer programs into the memory 902 according to the following steps, and the processor 901 will run the computer programs stored in the memory 902 to implement various functions: set up the infrastructure layer to complete the construction of the infrastructure; after obtaining data in the infrastructure layer, perform online knowledge base management; on the basis of online knowledge base management, set up course information management; perform time statistics on all historical question-and-answer information; according to the time statistics results, perform a quick answer retrieval according to the questions raised by the client users; perform a detailed dashboard display.

[0178] The memory 902 can be used to store computer programs and data. The computer programs stored in the memory 902 contain instructions that can be executed in the processor. The computer programs can form various functional modules. The processor 901 executes various functional applications and data processing by calling the computer programs stored in the memory 902.

[0179] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0180] In the solution of the present invention, an automated detection question-and-answer interaction system is provided, which reduces labor costs.

[0181] In the solution of the present invention, according to the time statistics results, a quick answer retrieval is performed according to the questions raised by the client users to achieve quick question-and-answer interaction.

[0182] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0183] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general purpose computers, special purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0184] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0185] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0186] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent interaction method for a distributed multi-modal online customer service, characterized in that, The method includes: Setting up the infrastructure layer to complete the construction of the infrastructure; After obtaining data in the infrastructure layer, performing online knowledge base management; Based on the online knowledge base management, setting up course information management; Performing time statistics on all historical Q&A information; According to the time statistics results, performing fast answer retrieval according to the questions raised by client users; Performing detailed dashboard display; Among them, the performing time statistics on all historical Q&A information specifically includes: Setting statistical classifications as monthly statistics, quarterly statistics, and annual statistics; Performing statistics according to the fuzzy search and export times of the users being concerned; Each statistic includes fields such as the total number of Q&A, effective rate, like rate, and failure rate; Among them, the performing fast answer retrieval according to the questions raised by client users according to the time statistics results specifically includes: Setting up a vocabulary management page to include functions such as querying by sensitive word type, fuzzy query by sensitive word, new creation, editing, and deletion; Querying by sensitive word type to form a first number; Performing a fuzzy query by sensitive word to form a second number; Obtaining the questions raised by client users, performing vocabulary extraction, and determining whether there are sensitive words; If there are sensitive words, calculating the feedback number of the currently most matching sensitive word using the first calculation formula; Feedbacking the pre-set feedback answer according to the feedback number of the currently most matching sensitive word; Obtaining all the currently matching vocabulary, obtaining the time grouping where the current vocabulary is located, and the time grouping is pre-set, and the time grouping is one of monthly statistics, quarterly statistics, and annual statistics; Performing effectiveness calculation using the second calculation formula according to the fuzzy search and the export times; Obtaining the corresponding optimal feedback list under the current knowledge base and courses using the large model according to all the currently matching vocabulary; When the effectiveness does not exceed the preset value, calculating the comprehensive index using the third calculation formula according to the optimal feedback list and the fields of the total number of answers, effective rate, like rate, and failure rate corresponding to the answers in the optimal feedback list; When the effectiveness exceeds the preset value, incorporating the associated feedback of the answers associated with this retrieval in the exported data into the optimal feedback list; And calculating the comprehensive index using the third calculation formula according to the fields of the total number of answers, effective rate, like rate, and failure rate; Taking the result of the comprehensive index as the first feedback result, and when the effectiveness exceeds the preset value, taking the one with the highest comprehensive index among the answers associated with this retrieval in the exported data as the second feedback result; The first calculation formula is: B = k1×S1 + k2×S2 Among them, B is the feedback number of the currently most matching sensitive word, k1 is the first preset coefficient, k2 is the second preset coefficient, S1 is the first number, and S2 is the second number; The second calculation formula is: Y = D / M Among them, Y is the effectiveness, D is the export times, and M is the fuzzy search; The third calculation formula is: ZZ = DZ × xl × (1 - sb) 3 × (1 + dianz) Among them, ZZ is the comprehensive index, DZ is the total number of answers, xl is the effective rate, dianz is the like rate, and sb is the failure rate.

2. The intelligent interaction method of a distributed multi-modal online customer service according to claim 1, wherein, The setting up the infrastructure layer to complete the construction of the infrastructure specifically includes: Setting up a large model server and an application server; Setting up a K8S containerization platform; Set up the MySQL database; Set up the low-code platform.

3. An intelligent interaction method for a distributed multi-modal online customer service according to claim 1, characterized in that, After obtaining data at the infrastructure layer, perform online knowledge base management, specifically including: Set up the knowledge base management to include functions such as new creation, viewing, searching, taking offline, and clearing; Under the new creation function, click the Create QA button, a pop-up window will appear, enter the question and answer fields, and click OK to save; Under the viewing function, click the View Details button, a pop-up window will pop up, and the pop-up window will display field information such as question ID and data source, which cannot be edited; Under the search function, enter conditions in the question description and date box, click the search button, and the system will query according to the conditions, and the query results will be displayed on the page; Under the clearing function, click the clear button to clear the search conditions in the condition input box; under the taking offline function, click the take offline button, a pop-up window will appear, whether to confirm taking offline, click OK, and the data will enter the pending review interface.

4. An intelligent interaction method for a distributed multi-modal online customer service according to claim 1, characterized in that Based on the above online knowledge base management, set up course information management, specifically including: The page includes functions such as new creation, deletion, editing, and searching; For the new creation function, the course id and course name need to be filled in; Click the edit button in the operation column to enter the edit interface and modify the original course information; Click the delete button to perform a delete operation on this data; The page supports fuzzy search according to the course name.

5. The intelligent interaction method of a distributed multi-modal online customer service according to claim 1, characterized in that, Perform a detailed dashboard display, specifically including: Set up four attention modules, namely: selected by the followed user, data statistics, line chart, and data report; The option to view all data or data under a certain followed user is used as the selection by the followed user; Set up data statistics to include the total number of Q&A times, total number of questions, page views, total number of likes and dislikes, effective rate, like rate, and failure rate; Statistical line chart of the number of Q&A times and questions per day in the past 5 days; Statistical data report of the quantity and proportion of all likes and dislikes.

6. An intelligent interaction system for a distributed multi-modal online customer service, characterized in that, This system is used to implement the method described in any one of claims 1-5. This system includes: An infrastructure setting module for setting up the infrastructure layer and completing the construction of the infrastructure; A knowledge base management module for performing online knowledge base management after obtaining data at the infrastructure layer; A course management module for setting up course information management based on the online knowledge base management; A time statistics module for performing time statistics on all historical Q&A information; An intelligent recommendation module for quickly retrieving answers according to the time statistics results and the questions raised by the client user; A dashboard display module for performing a detailed dashboard display.

7. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, The computer program instructions, when executed by a processor, implement the method described in any one of claims 1-5.

8. An electronic device, comprising a memory and a processor, characterized in that The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in any one of claims 1-5.

Images