Intelligent customer service response method and device, equipment and storage medium

Abstract

The embodiment of the invention provides an intelligent customer service response method and device, equipment and a storage medium, and relates to the technical field of vehicle diagnosis, and the method comprises the steps: receiving a consultation question sent by a response terminal, and judging whether the consultation question has a preset answer or not; if the preset answer exists, sending the preset answer to the response terminal; if the preset answer does not exist, sending the consultation question to a manual terminal; and receiving a target answer sent by the manual terminal, sending the target answer to the response terminal, and providing the target answer to a user by the response terminal. By judging whether the consultation question has the preset answer, the service efficiency can be improved, the labor cost is reduced, and the user satisfaction is improved; and receiving the target answer sent by the manual terminal, so that the question of the user can be accurately and comprehensively answered, the service quality is improved, and the question answering range of the service terminal can be updated and expanded through the participation of the manual terminal.

Description

Technical Field

[0001] The present application relates to the field of vehicle diagnosis technology, and in particular to intelligent customer service response methods, devices, equipment and storage media. Background Art

[0002] With the continuous development of the automobile industry, the role of automobile diagnosis has become increasingly prominent. Whether in the field of research and development, production or after-sales, automobile diagnosis is an indispensable function. In today's highly digitalized automobile industry, vehicle diagnostic software is increasingly important as a bridge connecting car owners, maintenance technicians and automobile manufacturers. With the continuous advancement of automobile technology, vehicle systems are becoming increasingly complex, and the number of electronic control units, sensors and actuators involved has increased sharply, making the fault diagnosis and troubleshooting process cumbersome and challenging. Therefore, building an efficient, convenient and knowledgeable Q&A platform that centrally manages and displays common questions is of great significance for improving customer service quality, accelerating fault resolution and reducing operating costs. However, the current common Q&A database in the field of vehicle diagnosis mainly exists: paid third-party intelligent robot customer service platform, the platform provides common Q&A database management, but the service is for a wide range of general fields, the semantics of the vehicle diagnosis field, industry-specific vocabulary and other resources are limited, the scope of answers is relatively limited, and the response efficiency is not high.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide an intelligent customer service response method, device, equipment and storage medium, aiming to solve the technical problems of narrow intelligent customer service response range and low efficiency in vehicle diagnosis.

[0005] To achieve the above objectives, the present application proposes an intelligent customer service response method, wherein the method is applied to a service terminal, and the method comprises:

[0006] Receive the consulting question sent by the answering terminal, and determine whether there is a preset answer to the consulting question; if there is a preset answer, send the preset answer to the answering terminal; if there is no preset answer, send the consulting question to the manual terminal;

[0007] The target answer sent by the manual terminal is received, and the target answer is sent to the response terminal, and the response terminal provides the target answer to the consulting user.

[0008] In one embodiment, the step of receiving the consulting question sent by the answering terminal and determining whether there is a preset answer to the consulting question includes:

[0009] Preprocessing and word segmenting the consulting questions by using a text preprocessing algorithm;

[0010] Extracting keyword features from the consulting question using a keyword extraction algorithm to obtain characteristic keywords of the consulting question;

[0011] Performing a latent semantic analysis on the characteristic keywords by using a latent semantic analysis algorithm to obtain latent keywords corresponding to the characteristic keywords;

[0012] A keyword matching algorithm is used to determine whether there are preset questions corresponding to the characteristic keywords and potential keywords in the preset question and answer library. If there are corresponding preset questions, the answers corresponding to the preset questions are determined to be the preset answers.

[0013] In one embodiment, the method further comprises:

[0014] Analyze and count the target answers and the corresponding consulting questions to obtain the number of times the consulting questions appear;

[0015] If the number of times the consulting question appears is greater than a preset threshold, the consulting question and the target answer are written into a preset question and answer library to obtain a target question and answer library.

[0016] In one embodiment, the step of writing the consulting question and the target answer into a preset question and answer library to obtain the target question and answer library includes:

[0017] Perform keyword feature extraction on the consulting question to obtain feature keywords of the consulting question;

[0018] Classify the consulting questions according to the characteristic keywords and generate question classification results;

[0019] The consulting question and the target answer are written into a preset question and answer library according to the question classification result to obtain a target question and answer library.

[0020] In one embodiment, the intelligent customer service response method is applied to a response terminal, and the method includes:

[0021] Receive the consulting question input by the consulting user, and send the consulting question to the service terminal, and the service terminal determines whether there is a preset answer to the consulting question; if there is a preset answer, the service terminal sends the preset answer to the answering terminal; if there is no preset answer, the service terminal sends the consulting question to the manual terminal;

[0022] Receive the preset answer / target answer sent by the service terminal, and provide the preset answer / target answer to the consulting user.

[0023] In one embodiment, the intelligent customer service response method is applied to a manual terminal, and the method includes:

[0024] Receiving a consultation question sent by a service terminal, the consultation question is received by the answering terminal and then sent to the service terminal, and the service terminal determines that there is no preset answer;

[0025] The target answer to the consulting question is obtained through manual service, and the target answer is sent to the service terminal, which sends the target answer to the response terminal, and the response terminal provides the target answer to the consulting user.

[0026] In one embodiment, the method further comprises:

[0027] The consulting questions and corresponding target answers are set and entered into a preset question and answer library through manual service, and the preset question and answer library is updated to obtain a target question and answer library.

[0028] In addition, to achieve the above purpose, the present application also proposes an intelligent customer service response device, the intelligent customer service response device comprising:

[0029] A question receiving module is used to receive the consulting question sent by the answering terminal and determine whether there is a preset answer to the consulting question; if there is a preset answer, the preset answer is sent to the answering terminal; if there is no preset answer, the consulting question is sent to the manual terminal;

[0030] The answer receiving module is used to receive the target answer sent by the manual terminal, send the target answer to the answering terminal, and the answering terminal provides the target answer to the user.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes an intelligent customer service response device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the intelligent customer service response method as described above.

[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the intelligent customer service response method described above are implemented.

[0033] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the intelligent customer service response method described above.

[0034] One or more technical solutions proposed in this application have at least the following technical effects:

[0035] The embodiments of the present application provide an intelligent customer service answering method, device, equipment and storage medium, which receives the consulting question sent by the answering terminal and determines whether the consulting question has a preset answer; if there is a preset answer, the preset answer is sent to the answering terminal; if there is no preset answer, the consulting question is sent to the manual terminal; the target answer sent by the manual terminal is received, and the target answer is sent to the answering terminal, and the answering terminal provides the target answer to the user. By determining whether there is a preset answer to the consulting question, service efficiency can be improved, labor costs can be reduced, and user satisfaction can be improved; receiving the target answer sent by the manual terminal can accurately and comprehensively answer the user's questions, improve service quality, and the participation of the manual terminal can update and broaden the scope of question answers of the service terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0038] Figure 1 A flowchart of the first embodiment of the intelligent customer service response method of this application is provided;

[0039] Figure 2 A flowchart of the fifth embodiment of the intelligent customer service response method of this application is provided;

[0040] Figure 3 A schematic diagram of an interface of a specific scenario-based response terminal provided in an embodiment of the intelligent customer service response method of the present application;

[0041] Figure 4 A schematic diagram of a service evaluation interface in a scenario-specific response terminal interface provided in an embodiment of the intelligent customer service response method of this application;

[0042] Figure 5 A flowchart of the sixth embodiment of the intelligent customer service response method of this application is provided;

[0043] Figure 6 This is a schematic diagram of the module structure of the intelligent customer service response device according to an embodiment of the present application;

[0044] Figure 7 This is a schematic diagram of the device structure of the hardware operating environment involved in the intelligent customer service response method in the embodiment of the present application.

[0045] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0047] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0048] The main solutions of the embodiments of this application are:

[0049] Applied to the service terminal: receiving the consulting question sent by the answering terminal, and determining whether there is a preset answer to the consulting question; if there is a preset answer, the preset answer is sent to the answering terminal; if there is no preset answer, the consulting question is sent to the manual terminal; receiving the target answer sent by the manual terminal, sending the target answer to the answering terminal, and the answering terminal provides the target answer to the user. Applied to the answering terminal: receiving the consulting question input by the consulting user, and sending the consulting question to the service terminal, and the service terminal determines whether there is a preset answer to the consulting question; if there is a preset answer, the service terminal sends the preset answer to the answering terminal; if there is no preset answer, the service terminal sends the consulting question to the manual terminal; receiving the preset answer / target answer sent by the service terminal, and providing the preset answer / target answer to the consulting user. Applied to manual terminals: receiving consulting questions sent by service terminals, the consulting questions are received by the answering terminal and then sent to the service terminal, and the service terminal obtains the answers after judging that there are no preset answers; obtaining the target answers to the consulting questions through manual service, sending the target answers to the service terminal, and the service terminal sending the target answers to the answering terminal, and then the answering terminal provides the target answers to the consulting user.

[0050] In today's highly digitalized automotive industry, vehicle diagnostic software is becoming increasingly important as a bridge between car owners, maintenance technicians and automakers. With the continuous advancement of automotive technology, vehicle systems are becoming increasingly complex, and the number of electronic control units, sensors and actuators involved has increased dramatically, making the fault diagnosis and troubleshooting process cumbersome and challenging. Therefore, building an efficient, convenient and knowledgeable Q&A platform that centrally manages and displays common questions is of great significance for improving customer service quality, accelerating troubleshooting and reducing operating costs. However, the current FAQ question and answer library mainly exists: paid third-party intelligent robot customer service platform, the platform provides FAQ library management, but the service is for a wide range of general fields, and the semantics and industry-specific vocabulary resources in the field of vehicle diagnosis are limited, the scope of answers is relatively limited, and the response efficiency is not high.

[0051] This application can improve service efficiency, reduce labor costs, and improve user satisfaction by judging whether there is a preset answer to the consultation question; receiving the target answer sent by the artificial terminal can accurately and comprehensively answer the user's question, improve service quality, and through the participation of the artificial terminal, the scope of question answering of the service terminal can be updated and broadened.

[0052] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, an intelligent customer service response device, etc. The following takes the intelligent customer service response device as an example to illustrate this embodiment and the following embodiments.

[0053] Based on this, the present application embodiment provides an intelligent customer service response method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the intelligent customer service response method of the present application.

[0054] In this embodiment, the intelligent customer service response method is applied to a service terminal, including steps S10 to S20:

[0055] Step S10, receiving the consulting question sent by the answering terminal, and determining whether there is a preset answer to the consulting question; if there is a preset answer, sending the preset answer to the answering terminal; if there is no preset answer, sending the consulting question to the manual terminal.

[0056] It should be noted that the service terminal is used to receive the consulting questions sent by the answering terminal, and determine whether the consulting questions have a preset answer in the preset question and answer library; if the preset answer exists, the preset answer is sent to the answering terminal; if the preset answer does not exist, the consulting question is sent to the manual terminal; at the same time, the service end can receive the target answer sent by the manual terminal and send the target answer to the answering terminal. The service end can also update the preset question and answer library according to the target answer to obtain the target question and answer library.

[0057] More specifically, the service terminal has a preset question and answer library, which can be constructed based on historical consulting data or manually written; the question and answer library stores diagnostic questions and answers to diagnostic questions, that is, solutions to the diagnostic problems that arise, and the diagnostic questions are classified in the question and answer library, and the problem classification includes but is not limited to pre-sales questions, after-sales questions, fault code problems, diagnostic software operation problems, etc.; the preset question and answer library adds keyword tags to the preset questions, which are used to search for matching consulting questions to see if they are preset questions.

[0058] In addition, it should be noted that the answering terminal is used to receive consulting questions from consulting users and send the consulting questions to the service terminal; receive preset answers / target answers sent by the service terminal, and provide the preset answers / target answers to the consulting users.

[0059] In addition, it should be noted that the consulting questions refer to questions related to vehicle diagnosis input by the consulting user through the answering terminal, such as pre-sales questions, after-sales questions, fault code questions, diagnostic software operation questions, etc.

[0060] In addition, it should be noted that the preset answers refer to answers stored in a preset question and answer library. The preset question and answer library can be constructed based on consulting data of historical vehicle diagnostic problems, or can be manually written.

[0061] Specifically, the consulting questions sent by the answering terminal are received, the consulting questions are preprocessed, and then keyword feature extraction is performed to extract feature keywords, and then latent semantic analysis is performed on the feature keywords to obtain potential keywords. A keyword matching algorithm is used to determine whether there are preset questions corresponding to the feature keywords and potential keywords in the preset question and answer library. If there are corresponding preset questions, the answer corresponding to the preset question is determined to be the preset answer; if there are no corresponding preset questions, the consulting question is sent to the manual terminal.

[0062] Step S20, receiving the target answer sent by the manual terminal, sending the target answer to the answering terminal, and the answering terminal providing the target answer to the consulting user.

[0063] It should be noted that the artificial terminal is used to receive consultation questions determined to have no preset answers, obtain the target answers to the consultation questions through artificial services, and is used to process questions that cannot be automatically answered by the preset Q&A library.

[0064] Specifically, the consulting user inputs a consultation question through the response terminal. The response terminal sends the consultation question to the service terminal. The service terminal determines whether there is a preset answer to the consultation question in the preset Q&A library. If there is no preset answer, the service terminal sends the consultation question to the artificial terminal. The artificial terminal obtains the target answer through artificial services, sends the target answer to the service terminal. The service terminal receives the target answer and sends the target answer to the response terminal, and the response terminal provides the target answer to the consulting user.

[0065] Based on the first embodiment, the second embodiment of the present application is proposed. The difference between the second embodiment of the present application and the first embodiment is as follows:

[0066] In this embodiment, the steps of receiving the consultation question sent by the response terminal and determining whether there is a preset answer to the consultation question include steps S11 to S14:

[0067] Step S11, preprocess and segment the consultation question through a text preprocessing algorithm.

[0068] It should be noted that the text preprocessing algorithm includes processing such as data cleaning, text normalization, and word segmentation. Data cleaning refers to operations such as removing irrelevant characters, removing stop words, and processing noisy data. Removing irrelevant characters includes removing characters such as HTML tags, special symbols, and emojis; stop words in removing stop words refer to those words with high frequency of occurrence but little help for text understanding, such as words like "de", "le", "zai", etc.; processing noisy data includes processing data such as spelling mistakes, abbreviations, and repeated texts. Text normalization includes processing such as case conversion, lemma reduction, and stemming. Word segmentation refers to that for languages such as Chinese without natural space separation, word segmentation processing needs to be carried out to split the sentence into a sequence of words or phrases. The word segmentation algorithm includes rule-based word segmentation, statistics-based word segmentation, and hybrid word segmentation methods.

[0069] Specifically, preprocessing and segmenting the consultation question through the text preprocessing algorithm is beneficial to saving storage space and improving subsequent processing efficiency.

[0070] Step S12, extract the keyword features of the consultation question through a keyword extraction algorithm to obtain the characteristic keywords of the consultation question.

[0071] It should be noted that the keyword extraction algorithm can automatically extract key words or phrases from the question text, which are essential for understanding the core content and intent of the question. Some common keyword extraction algorithms include TF-IDF algorithm, TextRank algorithm, LDA (Latent Direction Allocation) topic model, KeyBert and other algorithms combined with pre-trained models.

[0072] Specifically, in this embodiment, the TF-IDF algorithm is used to calculate the TF-IDF value of each word in the consulting question, and the characteristic keywords of the consulting question are determined according to the TF-IDF value. The larger the TF-IDF value of the word, the higher its importance. The more important the word is, the more likely it is to be used as a characteristic keyword.

[0073] Step S13, performing latent semantic analysis on the characteristic keywords by using a latent semantic analysis algorithm to obtain latent keywords corresponding to the characteristic keywords.

[0074] It should be noted that the latent semantic analysis algorithm is mainly used for topic analysis of texts, and is characterized in that the semantic relationship between texts and words based on topics is discovered through matrix decomposition, and the latent semantic relationship between texts and words is discovered through matrix decomposition, and the problem of polysemy and monosemy of multiple words can be solved to a certain extent. Understandably, when using the keyword extraction algorithm to extract keywords, the extracted keywords may not be able to express the characteristics of the consulting questions well, so the latent semantic analysis algorithm is required to perform feature mapping on the keywords to obtain potential keywords. The latent semantic analysis algorithm mainly includes: text preprocessing, constructing a document matrix, singular value decomposition or non-negative matrix decomposition, identifying potential keywords or topics, and post-processing and interpretation.

[0075] Specifically, in one embodiment of the present application, the consulting questions are first preprocessed by word segmentation and stop word removal, and then the preprocessed consulting questions are represented by a document matrix to represent a text collection. The document matrix is ​​then subjected to singular value decomposition to obtain a singular matrix of the document matrix. By observing the singular matrix, words that are highly correlated with specific latent topics are found. These words can be regarded as potential keywords related to the consulting questions and these topics. Finally, the singular matrix is ​​post-processed, such as cluster analysis, topic modeling, etc., to further explain and refine the latent semantic structure. According to specific needs, appropriate algorithms and parameters can be selected to optimize the results and improve the accuracy and relevance of potential keywords.

[0076] Step S14, using a keyword matching algorithm to determine whether there are preset questions corresponding to the characteristic keywords and potential keywords in the preset question and answer library, if there are corresponding preset questions, then determine that the answer corresponding to the preset question is the preset answer.

[0077] It should be noted that the keyword matching algorithm is to identify elements that match specific keywords or keyword sets from given text data. These keywords can be search terms entered by users, predefined tags, category names, or any identifiers used to index, retrieve or classify text data. The keyword matching algorithm mainly includes several steps such as text preprocessing, index construction, matching logic and result processing.

[0078] Specifically, in one embodiment of the present application, the extracted feature keywords and potential keywords are first subjected to text preprocessing; then the preprocessed keywords are indexed and constructed, and the index can be a simple word list, a hash table, or a more complex inverted index, which maps each keyword to a text location or a document list containing the keyword; then the keywords are logically matched with the keywords of preset questions in a preset question and answer library, and the matching logic can be a simple exact match based on string comparison, or a fuzzy match based on edit distance (such as Levenshtein edit distance), or a more complex semantic-based match, such as using word embedding to calculate the similarity between words for semantic matching; finally, after the matching is completed, the results need to be sorted, deduplicated, etc., so that the most relevant or useful information is presented to the user, and the sorting can be based on a variety of factors such as matching degree, frequency of occurrence, importance score, etc.

[0079] Specifically, the present application may also use a semantic similarity algorithm to determine whether there are preset questions corresponding to the feature keywords and potential keywords in the preset question and answer library. If there are corresponding preset questions, the answers corresponding to the preset questions are determined to be preset answers. Among them, the semantic similarity algorithm refers to a method of measuring the degree of similarity between two or more texts at the semantic level. This similarity is calculated based on the deep meaning and relationship of the words, phrases and sentences in the text, rather than just based on the surface character or vocabulary matching of the text. The semantic similarity algorithm includes steps such as text preprocessing, feature extraction, vector representation and similarity calculation.

[0080] The present application receives consulting questions sent by the answering terminal through the service terminal, and determines whether there are preset answers to the consulting questions. If there are preset answers, the preset answers are sent to the answering terminal, and the problems of the consulting users can be effectively solved through the preset question and answer library, providing an effective solution for the vehicle diagnosis; if there are no preset answers, the consulting questions are sent to the manual terminal, and effective answers to the consulting questions can be provided through manual service, and the consulting questions and target answers can also be accumulated in the question and answer library.

[0081] Based on the second embodiment, a third embodiment of the present application is proposed. The difference between the third embodiment of the present application and the second embodiment is that:

[0082] In this embodiment, the method further includes steps S30 to S40:

[0083] Step S30, analyzing and counting the target answer and the corresponding consulting question to obtain the number of times the consulting question appears.

[0084] Specifically, consulting questions without preset answers are stored through the service terminal, and then for each consulting question, a counter is maintained to record the number of times it appears. Whenever the same question appears again, the counter of the question is increased. All recorded consulting questions and their counters are traversed regularly (for example, daily, weekly or monthly), and the consulting questions are analyzed and counted to obtain the number of times the consulting questions appear.

[0085] Step S40: If the number of occurrences of the consulting question is greater than a preset threshold, the consulting question and the target answer are written into a preset question and answer library to obtain a target question and answer library.

[0086] It should be noted that the preset threshold is used to determine whether the frequency of asking the consulting question is high. If the number of times the consulting question appears is greater than the preset threshold, the frequency of asking the consulting question is high; if the number of times the consulting question appears is less than or equal to the preset threshold, the frequency of asking the consulting question is low. The preset threshold can be set according to actual needs and application scenarios, for example, it can be set to 10, 50 or higher.

[0087] In addition, it should be noted that the target question and answer database refers to the question and answer database after the query questions of consulting customers are collected and entered and the query and answer database is updated.

[0088] Specifically, a preset threshold is set, and the number of times a consulting question appears is compared with the preset threshold. If the number of times a consulting question appears is greater than the preset threshold, the consulting question and its corresponding target answer are written into the preset question and answer library, and the update of the question and answer library is completed to obtain the target question and answer library. This step may include adding new question and answer pairs to the database, or updating the number of occurrences of existing question and answer pairs. For example, if the question and answer library already contains the question but the answer is different, further processing may be required, such as merging the answers or retaining the latest answer.

[0089] This application analyzes and counts the target answer and the corresponding consulting question to obtain the number of times the consulting question appears; if the number of times the consulting question appears is greater than a preset threshold, the consulting question and the target answer are written into a preset question and answer library to obtain a target question and answer library. Updating the preset question and answer library according to the target answer can accumulate professional vocabulary in the vehicle diagnosis industry, and at the same time, accumulating consulting questions and corresponding answers in the question and answer library is conducive to subsequent data applications.

[0090] Based on the third embodiment, a fourth embodiment of the present application is proposed. The difference between the fourth embodiment of the present application and the third embodiment is that:

[0091] In this embodiment, the step of writing the consulting question and the target answer into a preset question and answer database to obtain the target question and answer database includes steps S41 to S43:

[0092] Step S41, extracting keyword features of the consulting question to obtain feature keywords of the consulting question.

[0093] Step S42, classifying the consulting questions according to the characteristic keywords to generate question classification results.

[0094] Step S43, writing the consulting question and the target answer into a preset question and answer library according to the question classification result to obtain a target question and answer library.

[0095] It should be noted that the problem result classification refers to the classification of consulting questions based on characteristic keywords. Problem classification includes but is not limited to pre-sales questions, after-sales questions, fault code questions, diagnostic software operation questions, etc.

[0096] Specifically, characteristic keywords of the consulting question are extracted through a keyword extraction algorithm to obtain the characteristic keywords of the consulting question; the consulting question is classified according to the characteristic keywords and the keywords of the question classification in the question and answer library to generate a question classification result; according to the question classification result, the consulting question and the target answer are written into a preset question and answer library to obtain a target question and answer library.

[0097] Reference Figure 2 , Figure 2 This is a flow chart of the fifth embodiment of the intelligent customer service response method of the present application.

[0098] Based on the fourth embodiment, a fifth embodiment of the present application is proposed. The difference between the fifth embodiment of the present application and the fourth embodiment is that:

[0099] In this embodiment, the intelligent customer service response method is applied to the response terminal, including steps S50 to S60:

[0100] Step S50, receiving the consulting question input by the consulting user, and sending the consulting question to the service terminal, and the service terminal determines whether there is a preset answer to the consulting question; if there is a preset answer, the service terminal sends the preset answer to the answering terminal; if there is no preset answer, the service terminal sends the consulting question to the manual terminal.

[0101] Specifically, the consulting user inputs the consulting question through the interface of the answering terminal, for example, through the web page, application interface, telephone voice system, etc. of the answering terminal. The answering terminal captures the consulting question input by the user and stores it as data to be processed; the consulting question is then sent to the service terminal through the network or other communication methods. The service terminal can be a server, a cloud platform or any system that can process requests and return responses; after receiving the consulting question, the service terminal first queries its preset question and answer library to see whether there is a preset answer that matches the question. If there is a preset answer, the service terminal sends the preset answer to the answering terminal, and provides the preset answer to the user through the interface of the answering terminal; if there is no preset answer, the service terminal sends the consulting question to the manual terminal, and the manual terminal provides the target answer to the consulting question.

[0102] For easier understanding, please refer to Figure 3 , Figure 3 This is a schematic diagram of the interface of the answering terminal for a specific implementation scenario of this application. When the consulting user opens the consulting page, the answering service will be automatically triggered, and a consulting welcome message will appear on the answering page, such as "Hello, I am your technical service consultant, and I am happy to serve you." After the user enters the consulting question, the interface of the answering terminal gives the corresponding answer. After the last reply from the answering terminal has passed an interval time period, such as an interval of one minute, two minutes, or five minutes, if the consulting user does not reply again, it can be determined that the user has completed the consultation. There is a service evaluation button at the bottom of the interface, and the user can evaluate the service of this consultation based on the relevance, feasibility, timeliness, etc. of the answer. Please refer to Figure 4 , Figure 4 This is a schematic diagram of a service evaluation interface in an answering terminal interface for a specific implementation scenario of the present application. The service evaluation includes a score and whether the answer is helpful.

[0103] Step S60, receiving the preset answer / target answer sent by the service terminal, and providing the preset answer / target answer to the consulting user.

[0104] Specifically, the preset answer / target answer sent by the service terminal is received, and the preset answer / target answer is provided to the consulting user through the interface of the answering terminal.

[0105] Reference Figure 5 , the figure is a flow chart of the sixth embodiment of the intelligent customer service response method of the present application.

[0106] Based on the fifth embodiment, a sixth embodiment of the present application is proposed. The difference between the sixth embodiment of the present application and the fifth embodiment is that:

[0107] In this embodiment, the intelligent customer service response method is applied to a manual terminal, including steps S70 to S80:

[0108] Step S70, receiving the consulting question sent by the service terminal, the consulting question is received by the answering terminal and then sent to the service terminal, and the service terminal determines that there is no preset answer.

[0109] Step S80, obtaining the target answer to the consulting question through manual service, sending the target answer to the service terminal, the service terminal sending the target answer to the response terminal, and then the response terminal providing the target answer to the consulting user.

[0110] It should be noted that manual service refers to the answering of technical support questions manually. Manual technical support includes but is not limited to customer service, on-site technical support engineers, diagnostic engineers, product managers, branch distributors (channels), etc. Manual service inputs the target answer corresponding to the consultation question through the manual terminal.

[0111] Specifically, a consulting question sent by a service terminal is received, and the consulting question is sent to the service terminal after being received by the answering terminal, and the service terminal obtains the answer after determining that there is no preset answer; a technical support personnel through manual service inputs a target answer to the consulting question, and sends the target answer to the service terminal, and the service terminal sends the target answer to the answering terminal, and then the answering terminal provides the target answer to the consulting user.

[0112] Based on the sixth embodiment, a seventh embodiment of the present application is proposed. The difference between the seventh embodiment of the present application and the sixth embodiment is that:

[0113] In this embodiment, the method further includes step S90:

[0114] Step S90: The consulting question and the corresponding target answer are set and entered into a preset question and answer database through manual service, and the preset question and answer database is updated to obtain a target question and answer database.

[0115] Specifically, the present application can also directly allow the technical support personnel of manual service to enter the consulting questions and corresponding target answers into the preset question and answer library through the manual terminal according to the specific actual situation, update the preset question and answer library, obtain the target question and answer library, realize semi-automatic data accumulation of the question and answer library, and improve the quality and scope of intelligent customer service responses.

[0116] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the intelligent customer service response method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0117] This application also provides an intelligent customer service answering device, please refer to Figure 6, the intelligent customer service response device comprises:

[0118] The question receiving module 601 is used to receive the consulting question sent by the answering terminal and determine whether there is a preset answer to the consulting question; if there is a preset answer, the preset answer is sent to the answering terminal; if there is no preset answer, the consulting question is sent to the manual terminal;

[0119] The answer receiving module 602 is used to receive the target answer sent by the manual terminal, send the target answer to the answering terminal, and the answering terminal provides the target answer to the user.

[0120] The intelligent customer service response device provided by the present application adopts the intelligent customer service response method in the above embodiment, which can solve the technical problems of narrow intelligent customer service response range and low efficiency in vehicle diagnosis. Compared with the prior art, the beneficial effects of the intelligent customer service response device provided by the present application are the same as the beneficial effects of the intelligent customer service response method provided by the above embodiment, and the other technical features in the intelligent customer service response device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0121] The present application provides an intelligent customer service response device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the intelligent customer service response method in the above-mentioned embodiment one.

[0122] Reference below Figure 7 , which shows a schematic diagram of the structure of an intelligent customer service response device suitable for implementing the embodiment of the present application. The intelligent customer service response device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Multimedia Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The intelligent customer service answering device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0123] like Figure 7As shown, the intelligent customer service answering device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read On ly Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the intelligent customer service answering device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the intelligent customer service answering device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows an intelligent customer service answering device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0124] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0125] The intelligent customer service response device provided by this application adopts the intelligent customer service response method in the above embodiment, which can solve the technical problems of narrow intelligent customer service response range and low efficiency in vehicle diagnosis. Compared with the prior art, the beneficial effects of the intelligent customer service response device provided by this application are the same as the beneficial effects of the intelligent customer service response method provided by the above embodiment, and the other technical features in the intelligent customer service response device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0126] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0127] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0128] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the intelligent customer service response method in the above-mentioned embodiment.

[0129] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read On ly Memory), an erasable programmable read-only memory (EPROM: Erasable Programmab le Read On ly Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read On ly Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0130] The computer-readable storage medium may be included in the intelligent customer service answering device; or it may exist independently without being assembled into the intelligent customer service answering device.

[0131] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the intelligent customer service answering device, the intelligent customer service answering device: receives the consulting question sent by the answering terminal, and determines whether there is a preset answer to the consulting question; if there is a preset answer, sends the preset answer to the answering terminal; if there is no preset answer, sends the consulting question to the manual terminal; receives the target answer sent by the manual terminal, sends the target answer to the answering terminal, and the answering terminal provides the target answer to the consulting user.

[0132] The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0133] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0134] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0135] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned intelligent customer service response method, and can solve the technical problems of narrow intelligent customer service response range and low efficiency in vehicle diagnosis. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the intelligent customer service response method provided by the above-mentioned embodiment, and will not be repeated here.

[0136] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned intelligent customer service response method when executed by a processor.

[0137] The computer program product provided by this application can solve the technical problems of narrow response range and low efficiency of intelligent customer service in vehicle diagnosis. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the intelligent customer service response method provided by the above embodiment, which will not be repeated here.

[0138] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An intelligent customer service response method, characterized in that: The intelligent customer service response method is applied to a service terminal, and the method includes: Receive the consulting question sent by the answering terminal, and determine whether there is a preset answer to the consulting question; if there is a preset answer, send the preset answer to the answering terminal; if there is no preset answer, send the consulting question to the manual terminal; The target answer sent by the manual terminal is received, and the target answer is sent to the response terminal, and the response terminal provides the target answer to the consulting user.

2. The method according to claim 1, characterized in that The step of receiving the consultation question sent by the answering terminal and determining whether there is a preset answer to the consultation question includes: Preprocessing and word segmenting the consulting questions by using a text preprocessing algorithm; Extracting keyword features from the consulting question using a keyword extraction algorithm to obtain characteristic keywords of the consulting question; Performing a latent semantic analysis on the characteristic keywords by using a latent semantic analysis algorithm to obtain latent keywords corresponding to the characteristic keywords; A keyword matching algorithm is used to determine whether there are preset questions corresponding to the characteristic keywords and potential keywords in the preset question and answer library. If there are corresponding preset questions, the answers corresponding to the preset questions are determined to be the preset answers.

3. The method according to claim 1, characterized in that The method further comprises: Analyze and count the target answers and the corresponding consulting questions to obtain the number of times the consulting questions appear; If the number of times the consulting question appears is greater than a preset threshold, the consulting question and the target answer are written into a preset question and answer library to obtain a target question and answer library.

4. The method according to claim 3, characterized in that The step of writing the consulting question and the target answer into a preset question and answer library to obtain the target question and answer library comprises: Perform keyword feature extraction on the consulting question to obtain feature keywords of the consulting question; Classify the consulting questions according to the characteristic keywords and generate question classification results; The consulting question and the target answer are written into a preset question and answer library according to the question classification result to obtain a target question and answer library.

5. An intelligent customer service response method, characterized in that: The intelligent customer service response method is applied to a response terminal, and the method includes: Receive the consulting question input by the consulting user, and send the consulting question to the service terminal, and the service terminal determines whether there is a preset answer to the consulting question; if there is a preset answer, the service terminal sends the preset answer to the answering terminal; if there is no preset answer, the service terminal sends the consulting question to the manual terminal; Receive the preset answer / target answer sent by the service terminal, and provide the preset answer / target answer to the consulting user.

6. An intelligent customer service response method, characterized in that: The intelligent customer service response method is applied to a manual terminal, and the method includes: Receiving a consultation question sent by a service terminal, the consultation question is received by the answering terminal and then sent to the service terminal, and the service terminal determines that there is no preset answer; The target answer to the consulting question is obtained through manual service, and the target answer is sent to the service terminal, which sends the target answer to the response terminal, and the response terminal provides the target answer to the consulting user.

7. The method according to claim 6, characterized in that The method further comprises: The consulting questions and corresponding target answers are set and entered into a preset question and answer library through manual service, and the preset question and answer library is updated to obtain a target question and answer library.

8. An intelligent customer service response device, characterized in that: The device comprises: The question receiving module is used to receive the consulting question sent by the answering terminal and determine whether there is a preset answer to the consulting question; if there is a preset answer, the preset answer is sent to the answering terminal; if there is no preset answer, the consulting question is sent to the manual terminal; The answer receiving module is used to receive the target answer sent by the manual terminal, send the target answer to the answering terminal, and the answering terminal provides the target answer to the user.

9. An intelligent customer service answering device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the intelligent customer service response method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the intelligent customer service response method as described in any one of claims 1 to 7 are implemented.

Images