Emotion-based customer service method and device, electronic equipment and storage medium

Abstract

The invention provides an emotion-based customer service method and device, electronic equipment and a storage medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring user input information and user identity information; determining the current emotion tendency of the user according to the user identity information; and determining reply information of the customer service staff according to the user input information and the current emotion tendency. The emotion tendency is obtained by analyzing the identity information of the user, the intention of the user can be accurately understood in combination with the input information of the user, the verbal skill meeting the emotion requirement of the user is output, and the problem that the understanding of customer service staff on the intention of the user deviates is solved.

Description

Background Art

[0002] Customer service refers to customer service work (accepting customer inquiries and helping customers answer questions), or the organization that undertakes customer service work. Traditional customer service solutions mainly rely on manual customer service to handle customer inquiries and questions, which can meet the basic needs of customers to a certain extent. However, with the increasing prosperity of business activities and the continuous growth of customer needs, the number of manual customer service staff is often unable to meet the growing service needs. This not only leads to slower customer service response speed and longer customer waiting time, but also may affect service quality due to excessive work pressure on customer service staff, thereby reducing customer satisfaction.

[0003] In the related technology, intelligent customer service is combined with manual customer service to provide services, thereby saving labor costs, increasing business processing volume, and meeting user needs. Although this intelligent-to-manual customer service solution optimizes the customer service process and improves the transfer efficiency to a certain extent, it still cannot overcome the inherent limitations of manual customer service, that is, manual customer service has a certain degree of subjectivity and inconsistency when dealing with complex problems, resulting in a deviation in the understanding of user intentions, increasing the workload of customer service, prolonging the customer's waiting time, and reducing service efficiency.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The present disclosure provides an emotion-based customer service method, device, electronic device, and storage medium, which at least to a certain extent overcome the problem of deviation in customer service's understanding of user intentions in related technologies.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to one aspect of the present disclosure, there is provided an emotion-based customer service method, including: obtaining user input information and user identity information; determining the user's current emotional tendency based on the user identity information; and determining customer service reply information based on the user input information and the current emotional tendency.

[0008] In some embodiments, determining the user's current emotional tendency based on the user identity information includes: determining the user's basic data based on the user identity information; determining the user's basic emotional tendency value within a historical unit time period based on the basic data; and determining the user's current emotional tendency based on a preset basic emotional tendency threshold and the basic emotional tendency value.

[0009] In some embodiments, determining the basic data of the user based on the user identity information includes: determining three behavioral dimensions of the user based on the user identity information, wherein the three behavioral dimensions include: behavior itself, behavior frequency, and behavior depth; and determining the three behavioral dimensions of the user as basic data.

[0010] In some embodiments, determining the basic emotional tendency value of the user within a historical unit time period based on the basic data includes: dividing the basic data according to a time window of preset length as a segmentation unit, and the basic data falling within each time window is a group of analysis data, and determining multiple groups of analysis data; taking each group of analysis data as a whole, extracting data features to form a feature vector, and identifying the emotion represented by the feature vector through a pre-trained emotion recognition model to obtain an emotion label; subdividing each dimension data of the group of analysis data according to time, identifying the emotion of each subdivided data through an emotion recognition model, and obtaining multiple subdivided emotion labels; for each dimension of the subdivided emotion label, determining the number of inconsistencies between two adjacent emotion labels according to the time order; determining the emotional tendency value of each group of analysis data in the dimension of the behavior itself according to the number of inconsistencies between two adjacent emotion labels in each dimension; and determining the basic emotional tendency value based on the emotional tendency value in the dimension of the behavior itself.

[0011] In some embodiments, determining the user's current emotional tendency based on a preset basic emotional tendency threshold and the basic emotional tendency value includes: if the user's emotional tendency value is less than the preset basic emotional tendency threshold, determining that the user's current emotional tendency is normal; if the user's emotional tendency value is greater than or equal to the preset basic emotional tendency threshold, determining that the user's current emotional tendency is abnormal.

[0012] In some embodiments, determining the customer service's reply information based on the user input information and the current emotional tendency includes: inputting a large language model based on the user input information and the current emotional tendency in combination with user preferences and product feature data, and outputting words that conform to the business scenario; and determining the words that conform to the business scenario as the customer service's reply information.

[0013] According to another aspect of the present disclosure, an emotion-based customer service device is also provided, including: an information acquisition module for acquiring user input information and user identity information; a current emotion tendency determination module for determining the user's current emotion tendency based on the user identity information; and a customer service reply module for determining the customer service's reply information based on the user input information and the current emotion tendency.

[0014] According to another aspect of the present disclosure, an electronic device is also provided, which includes: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned emotion-based customer service methods by executing the executable instructions.

[0015] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the emotion-based customer service method described above is implemented.

[0016] According to another aspect of the present disclosure, a computer program product is also provided, including a computer program, wherein when the computer program is executed by a processor, the computer program implements any one of the above-mentioned emotion-based customer service methods.

[0017] The emotion-based customer service method provided in the embodiments of the present disclosure obtains user input information and user identity information; determines the user's current emotional tendency based on the user identity information; and determines the customer service's reply information based on the user input information and the current emotional tendency. The present application obtains the emotional tendency by analyzing the user's identity information, and can accurately understand the user's intentions in combination with the user's input information, and outputs the words that meet the user's emotional needs, thereby solving the problem of deviation in the customer service's understanding of the user's intentions.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0020] Figure 1 A schematic diagram showing a structure of an emotion-based customer service system in an embodiment of the present disclosure;

[0021] Figure 2 A flow chart of an emotion-based customer service method in an embodiment of the present disclosure is shown;

[0022] Figure 3 A flowchart showing a specific example of an emotion-based customer service method in an embodiment of the present disclosure;

[0023] Figure 4 A flowchart showing another specific example of an emotion-based customer service method in an embodiment of the present disclosure;

[0024] Figure 5 A flowchart showing another specific example of an emotion-based customer service method in an embodiment of the present disclosure;

[0025] Figure 6 A flowchart showing another specific example of an emotion-based customer service method in an embodiment of the present disclosure;

[0026] Figure 7 A flowchart showing another specific example of an emotion-based customer service method in an embodiment of the present disclosure;

[0027] Figure 8 A schematic diagram of an emotion-based customer service device in an embodiment of the present disclosure is shown;

[0028] Fig. 9 A structural block diagram of a computer device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0029] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0030] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0031] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0032] Figure 1 FIG. 1 shows an exemplary application system architecture diagram to which the emotion-based customer service method in the embodiment of the present disclosure can be applied. Figure 1 As shown, the system architecture may include a terminal device 101 , a network 102 and a server 103 .

[0033] The network 102 is a medium for providing a communication link between the terminal device 101 and the server 103, and can be a wired network or a wireless network.

[0034] Optionally, the wireless network or wired network described above uses standard communication technology and / or protocol. The network is usually the Internet, but it can also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or any combination of a virtual private network). In some embodiments, the data exchanged through the network is represented by technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPSec) can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above data communication technologies.

[0035] The terminal device 101 can be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, smart speakers, smart watches, wearable devices, augmented reality devices, virtual reality devices, etc.

[0036] Optionally, the client of the application installed in different terminal devices 101 is the same, or the client of the same type of application based on different operating systems. Based on the different terminal platforms, the specific form of the client of the application can also be different, for example, the application client can be a mobile client, a PC client, etc.

[0037] The server 103 may be a server that provides various services, such as a background management server that provides support for the device operated by the user using the terminal device 101. The background management server may analyze and process the received request and other data, and feed back the processing results to the terminal device.

[0038] Optionally, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0039] In one example of the present disclosure, the server is used to obtain user input information and user identity information; determine the user's current emotional tendency based on the user identity information; and determine customer service response information based on the user input information and the current emotional tendency.

[0040] Those skilled in the art will know that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration, and any number of terminal devices, networks and servers may be provided according to actual needs, and the embodiments of the present disclosure do not limit this.

[0041] Figure 2 A flow chart of an emotion-based customer service method in an embodiment of the present disclosure is shown as follows: Figure 2 As shown, the emotion-based customer service method provided in the embodiment of the present disclosure includes the following steps:

[0042] S202, obtaining user input information and user identity information.

[0043] It should be noted that the user input information can be a user expressing his or her needs in a variety of ways. For example, the user input information can be obtained through the text input by the user, or through the voice, link, image, etc. input by the user. The user identity information can be various data or features that can uniquely identify or associate with a specific user. For example, the user name when the user logs in. It should be noted that obtaining the user input information and user identity information does not involve the leakage of personal privacy, because the execution subject is not the customer service, but the server of the business. When the user needs customer service, he or she will first log in, and the server can obtain the user's identity information at this time. For example, the user calls the customer service phone and enters the identity information. The identity information will be sent to the server for identity authentication, and the server can obtain the identity information at this time. When the identity authentication is passed, a customer service is assigned to it, and then a call connection is established between the user and the customer service. In the process of assigning customers and establishing a call connection between the user and the customer service, the server determines the customer service solution based on the identity information during the identity authentication through the method of this proposal. After the call connection between the user and the customer service is established, the server will push the solution to the customer service, thereby assisting the customer service to provide corresponding services.

[0044] S204: Determine the user's current emotional tendency based on the user's identity information.

[0045] It should be noted that the above current emotional tendency includes: abnormal emotion and normal emotion. If the user's current emotional tendency is abnormal emotion, it means that the user's emotional state is poor at this time and needs to improve the user's emotional state; if the user's current emotional tendency is normal emotion, it means that the user's emotional state is good at this time and can continue to maintain the emotional state.

[0046] S206, determining the customer service response information based on the user input information and the current emotional tendency.

[0047] It should be noted that the above reply information may be feedback information on the user's input information and current emotional tendency.

[0048] For example, based on the user input information, the preset questions in the question and answer library are accurately matched at the semantic level to accurately identify the user's consultation intention; based on the user's consultation intention and current emotional tendency, combined with user preferences and product feature data, personalized product recommendations are made among different user groups, or appropriate customer care is provided, to achieve more standardized and considerate customer service.

[0049] This application obtains emotional tendencies by analyzing the user's identity information, and combined with the user's input information, it can accurately understand the user's intentions and output words that meet the user's emotional needs, thus solving the problem of customer service's deviation in understanding user intentions.

[0050] In one embodiment of the present disclosure, Figure 3 As shown, the emotion-based customer service method provided in the embodiment of the present disclosure can determine the current emotional tendency of the user through the following steps, and can accurately predict the current emotional tendency of the user:

[0051] S302, determining basic data of the user according to the user identity information;

[0052] S304, determining the basic emotional tendency value of the user in a historical unit time period according to the basic data;

[0053] S306, determining the user's current emotional tendency according to a preset basic emotional tendency threshold and a basic emotional tendency value.

[0054] In one embodiment of the present disclosure, Figure 4 As shown, in the emotion-based customer service method provided in the embodiment of the present disclosure, determining the basic data of the user according to the user identity information includes the following steps:

[0055] S402, determining three behavior dimensions of the user according to the user identity information, wherein the three behavior dimensions include: behavior itself, behavior frequency, and behavior depth;

[0056] S404, determining the three behavioral dimensions of the user as basic data.

[0057] Among them, behavior refers to all behaviors of users, such as payment behavior, query behavior, business handling behavior, etc. The data of the behavior dimension itself, that is, the data describing the behavior, such as payment behavior data (such as payment time, payment content, etc.), query behavior data (such as query time, query content, etc.), business usage data, etc. The data of the behavior frequency dimension, that is, the data describing the frequency of behavior, such as payment frequency, query frequency, business handling frequency, etc. The data of the behavior depth dimension, that is, the maximum degree of describing the behavior, such as the maximum payable value, the maximum traffic value in the current traffic service, etc.

[0058] In this application, the basic data refers to the data of three dimensions of user behavior, one dimension is the behavior itself, one dimension is the frequency of behavior, and one dimension is the depth of behavior. The basic data includes the user's current data and historical data, so the emotional tendency value obtained through the basic data can represent the user's overall emotion.

[0059] In one embodiment of the present disclosure, Figure 5 As shown, in the emotion-based customer service method provided in the embodiment of the present disclosure, determining the basic emotion tendency value of the user in a historical unit time period according to the basic data includes the following steps:

[0060] S502, taking a time window of a preset duration as a division unit, dividing the basic data according to the time window, the basic data falling into each time window is a group of analysis data, and determining a plurality of groups of analysis data.

[0061] For example, a time window of a preset length is used as a division unit, all basic data are divided according to the time window, and the basic data falling into each time window is a group of analysis data, thus obtaining multiple groups of analysis data.

[0062] S504, taking each group of analysis data as a whole, extracting data features to form a feature vector, identifying the emotion represented by the feature vector through a pre-trained emotion recognition model, and obtaining an emotion label.

[0063] For example, for each set of analysis data, the analysis data is taken as a whole, data features are extracted to form a feature vector, and the emotion represented by the feature vector is identified through a pre-trained emotion recognition model to obtain an emotion label.

[0064] S506, segmenting each dimension data of the group of analysis data according to time, identifying the emotion of each segmented data through an emotion recognition model, and obtaining a plurality of segmented emotion labels.

[0065] For example, each dimension data of the group of analysis data is segmented according to time, and the emotion of each segmented data is identified by the emotion recognition model to obtain multiple segmented emotion labels. For example, a group of data is data within a week. After segmenting by day, 7 groups of segmented data are obtained, and then 7 segmented emotion labels of each dimension are obtained, that is, 21 segmented emotion labels. In this way, an emotion data sequence is obtained. Each element in the emotion data sequence corresponds to a set of feature vectors, emotion labels, and segmented emotion label sets of a group of analysis data. Among them, the emotion recognition model can be constructed based on the existing emotion recognition principle through an artificial intelligence large model, such as, based on the ABC theory of psychologist Albert Ellis, the emotion recognition model is obtained through neural network training. Among them, the ABC theory characterizes that emotional reactions (Consequences, C) are not directly caused by events (Activating Events, A) themselves, but are caused by individuals' evaluations and beliefs (Beliefs, B) of events.

[0066] Based on the ABC theory, the construction of the emotion recognition model can be divided into the following steps: Data collection: Collect data sets containing different situations (A) and individuals' evaluations and beliefs (B) of these situations and corresponding emotional responses (C). Feature extraction: Preprocess the data set to extract features related to the situation (A), evaluation and belief (B), and emotional response (C). Neural network design: Select a suitable neural network architecture, such as convolutional neural network (CNN), recurrent neural network (RNN) or deep neural network (DNN). According to the characteristics of the data and task requirements, design the parameters of the neural network such as the number of layers, number of nodes, activation function, etc. Model training: Use the preprocessed data set to train the neural network so that it can learn the mapping relationship from situation (A) and evaluation and belief (B) to emotional response (C). During the training process, use appropriate loss functions and optimization algorithms to evaluate the performance of the model, and adjust the network parameters to minimize the loss. Model evaluation and optimization: Use the test data set to evaluate the trained model and check its emotion recognition accuracy in different situations. Optimize the model based on the evaluation results, such as adjusting the network structure and adding data enhancement technology.

[0067] S508: For each dimension of the segmented emotion tags, determine the number of inconsistencies between two adjacent emotion tags according to the time sequence.

[0068] For example, for each dimension, the segmented emotion labels are sorted by time from the earliest time to the present time, and the number of inconsistencies between two adjacent emotion labels is determined.

[0069] S510, determining the emotional tendency value of each group of analysis data in the dimension of the behavior itself according to the number of inconsistencies between two adjacent emotional labels in each dimension.

[0070] For example, in one example of the present disclosure, the emotional tendency value of each set of analysis data in the behavior dimension is calculated by the following formula (1):

[0071]

[0072] Among them, i is the group identifier of the analysis data, J is the total number of segmented emotion labels, is the number of inconsistencies between two adjacent emotion labels in the behavior dimension of the i-th group of analysis data, is the number of inconsistencies between two adjacent emotion labels in the behavior frequency dimension of the i-th group of analysis data, is the number of inconsistencies between two adjacent emotion labels in the behavioral depth dimension of the i-th group of analysis data, The number of segmented sentiment labels that are different from the sentiment label in the analyzed data for the i-th group.

[0073] S512, determining a basic emotional tendency value according to the emotional tendency value in the dimension of the behavior itself.

[0074] In one example of the present disclosure, the basic emotional tendency value is calculated by the following formula (2):

[0075]

[0076] Where I is the total number of analyzed data sets, sim k,k-1 is the similarity between the feature vector of the kth group of analysis data and the feature vector of the k-1th group of analysis data.

[0077] The basic emotion tendency value E reflects the user's behavior pattern in the emotional process. There is a close correlation between these behavioral data and the user's basic emotions. The higher E is, the more it indicates that the user is in a positive basic emotion (such as happiness), while the lower E is, the more it indicates that the user has encountered difficulties, lost interest, or is likely to be sad. Therefore, by analyzing the basic emotions and the number of times they change, we can more accurately understand the user's basic emotional state. In addition, the feature vector and the number of times it changes are the most direct and real-time data indicators in the emotion recognition system. Compared with other types of behavioral data, such as user self-reports or psychological test results, these data are more objective and reliable, and help to promptly discover and respond to user emotional fluctuations. Therefore, E can determine to a certain extent whether the user has a tendency to be negative, low attention or difficult.

[0078] In addition, E is a statistical value rather than a quantitative value. That is, based on the emotion labels obtained from the existing emotion theory, E is obtained by counting the cases where two emotion labels are consistent. i After that, based on the E i The value obtained.

[0079] Therefore, the innovative point of the emotional tendency disclosed in the present invention is not how to identify emotional labels, but how to obtain the user's emotional possibilities by processing the emotional labels, and then provide them with words that meet their emotional needs.

[0080] In one embodiment of the present disclosure, Figure 6 As shown, in the emotion-based customer service method provided in the embodiment of the present disclosure, determining the current emotion tendency of the user according to the preset basic emotion tendency threshold and the basic emotion tendency value includes:

[0081] S602: If the user's emotional tendency value is less than a preset basic emotional tendency threshold, it is determined that the user's current emotional tendency is normal.

[0082] For example, if the user's emotional tendency value is less than the basic emotional tendency threshold, it is determined that the user's current emotional tendency is normal, indicating that the user's emotional state is good at this time and can continue to maintain the emotional state.

[0083] S604: If the user's emotional tendency value is greater than or equal to a preset basic emotional tendency threshold, it is determined that the user's current emotional tendency is abnormal.

[0084] For example, if the user's emotional tendency value is not less than the basic emotional tendency threshold, the user's current emotional tendency is determined to be abnormal, indicating that the user's emotional state is poor at this time and needs to be improved.

[0085] This application divides the user's current emotional tendency into normal emotional state and abnormal emotional state. This division method effectively identifies the user's emotional state and provides useful auxiliary information for customer service.

[0086] In one embodiment of the present disclosure, Figure 7 As shown, in the emotion-based customer service method provided in the embodiment of the present disclosure, determining the customer service response information according to the user input information and the current emotional tendency includes:

[0087] S702, according to the user input information and current emotional tendency combined with user preferences and product feature data input into the big language model, output the words that meet the business scenario;

[0088] S704, determining the words that meet the business scenario as the customer service’s reply information.

[0089] In a specific example, the existing solution is used to accurately match the preset questions in the question and answer library from the semantic level to the user's text needs, and accurately identify the user's consultation intention. Based on the user's consultation intention and emotional tendency, combined with user preferences and product feature data, personalized product recommendations are made in different user groups, or appropriate customer care is provided to achieve more standardized and considerate services.

[0090] For example, user preferences can be added as prompts to the large language model, and combined with user portraits, preferred products and other features, speech that meets business scenarios can be generated, and the speech can be fed back to users through artificial intelligence and other technologies, thus realizing intelligent customer service. Compared with manual customer service, it can deliver more standardized marketing or communication speech, and provide customers with 24-hour customer service. At the same time, it can also reduce the cost of understanding customers for manual customer service and improve customer service satisfaction.

[0091] Based on the same inventive concept, the embodiment of the present disclosure also provides an emotion-based customer service device, as described in the following embodiment. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0092] Figure 8 A schematic diagram of an emotion-based customer service device in an embodiment of the present disclosure is shown. Figure 8 As shown, the device includes: an information acquisition module 81, a current emotional tendency determination module 82 and a customer service response module 83.

[0093] The information acquisition module 81 is used to acquire user input information and user identity information.

[0094] The current emotional tendency determination module 82 is used to determine the user's current emotional tendency based on the user's identity information.

[0095] The customer service response module 83 is used to determine the customer service response information based on the user input information and current emotional tendency.

[0096] In one example of the present disclosure, the above-mentioned current emotional tendency determination module 82 is also used to determine the user's basic data based on the user's identity information; determine the user's basic emotional tendency value within a historical unit time period based on the basic data; and determine the user's current emotional tendency based on a preset basic emotional tendency threshold and basic emotional tendency value.

[0097] In one example of the present disclosure, the current emotional tendency determination module 82 is also used to determine the three behavioral dimensions of the user based on the user identity information, wherein the three behavioral dimensions include: the behavior itself, the frequency of the behavior, and the depth of the behavior; and the three behavioral dimensions of the user are determined as basic data.

[0098] In one example of the present disclosure, the current emotion tendency determination module 82 is further used to divide the basic data according to the time window with a preset duration as a segmentation unit, and the basic data falling into each time window is a group of analysis data, thereby determining multiple groups of analysis data; taking each group of analysis data as a whole, extracting data features to form a feature vector, and identifying the emotion represented by the feature vector through a pre-trained emotion recognition model to obtain an emotion label; subdividing each dimension data of the group of analysis data according to time, identifying the emotion of each subdivided data through the emotion recognition model, and obtaining multiple subdivided emotion labels; for each dimension of the subdivided emotion label, determining the number of inconsistencies between two adjacent emotion labels according to the time sequence; determining the emotion tendency value of each group of analysis data in the dimension of the behavior itself according to the number of inconsistencies between two adjacent emotion labels in each dimension; and determining the basic emotion tendency value according to the emotion tendency value in the dimension of the behavior itself.

[0099] In one example of the present disclosure, the above-mentioned current emotional tendency determination module 82 is also used to determine that the user's current emotional tendency is normal if the user's emotional tendency value is less than a preset basic emotional tendency threshold; if the user's emotional tendency value is greater than or equal to the preset basic emotional tendency threshold, then determine that the user's current emotional tendency is abnormal.

[0100] In one example of the present disclosure, the customer service reply module 83 is also used to input a large language model based on user input information and current emotional tendencies combined with user preferences and product feature data to output words that conform to the business scenario; and determine the words that conform to the business scenario as the customer service's reply information.

[0101] It should be noted that the above information acquisition module 81, current emotion tendency determination module 82 and customer service response module 83 correspond to S202 to S206 in the method embodiment, and the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above method embodiment. It should be noted that the above modules as part of the device can be executed in a computer system such as a set of computer executable instructions.

[0102] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0103] Refer to the following Fig. 9 The electronic device 900 according to this embodiment of the present disclosure is described. Fig. 9The electronic device 900 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0104] like Fig. 9 As shown, the electronic device 900 is in the form of a general computing device. The components of the electronic device 900 may include but are not limited to: at least one processing unit 910, at least one storage unit 920, and a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910).

[0105] The storage unit stores program codes, which can be executed by the processing unit 910, so that the processing unit 910 executes the steps described in the above “Exemplary Method” section of this specification according to various exemplary embodiments of the present disclosure.

[0106] For example, the processing unit 910 can execute the following steps of the above method embodiment: obtain user input information and user identity information; determine the user's current emotional tendency based on the user identity information; determine the customer service's reply information based on the user input information and the current emotional tendency.

[0107] For example, the processing unit 910 can execute the following steps of the above method embodiment: determine the user's basic data based on the user identity information; determine the user's basic emotional tendency value within a historical unit time period based on the basic data; determine the user's current emotional tendency based on a preset basic emotional tendency threshold and basic emotional tendency value.

[0108] For example, the processing unit 910 can execute the following steps of the above method embodiment: determine the three behavioral dimensions of the user based on the user identity information, where the three behavioral dimensions include: the behavior itself, the behavior frequency, and the behavior depth; and determine the three behavioral dimensions of the user as basic data.

[0109] For example, the processing unit 910 can execute the following steps of the above-mentioned method embodiment: based on a time window of preset length as a segmentation unit, the basic data is divided according to the time window, the basic data falling into each time window is a group of analysis data, and multiple groups of analysis data are determined; each group of analysis data is taken as a whole, the data features are extracted to form a feature vector, and the emotion represented by the feature vector is identified by a pre-trained emotion recognition model to obtain an emotion label; each dimension data of the group of analysis data is subdivided according to time, the emotion of each subdivided data is identified by the emotion recognition model, and multiple subdivided emotion labels are obtained; for the subdivided emotion labels of each dimension, the number of inconsistencies between two adjacent emotion labels is determined according to the time sequence; according to the number of inconsistencies between two adjacent emotion labels in each dimension, the emotion tendency value of each group of analysis data in the dimension of the behavior itself is determined; according to the emotion tendency value in the dimension of the behavior itself, the basic emotion tendency value is determined.

[0110] For example, the processing unit 910 can execute the following steps of the above method embodiment: if the user's emotional tendency value is less than the preset basic emotional tendency threshold, the user's current emotional tendency is determined to be normal; if the user's emotional tendency value is greater than or equal to the preset basic emotional tendency threshold, the user's current emotional tendency is determined to be abnormal.

[0111] For example, the processing unit 910 can execute the following steps of the above method embodiment: input a large language model based on user input information and current emotional tendencies combined with user preferences and product feature data, and output words that meet the business scenario; determine the words that meet the business scenario as the customer service's reply information.

[0112] The storage unit 920 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 9201 and / or a cache storage unit 9202 , and may further include a read-only storage unit (ROM) 9203 .

[0113] The storage unit 920 may also include a program / utility 9204 having a set (at least one) of program modules 9205, such program modules 9205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0114] Bus 930 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0115] The electronic device 900 may also communicate with one or more external devices 940 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 900, and / or may communicate with any device that enables the electronic device 900 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 950. Furthermore, the electronic device 900 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 960. As shown, the network adapter 960 communicates with other modules of the electronic device 900 via a bus 930. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0116] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0117] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer program product, which includes: a computer program, which implements the above-mentioned emotion-based customer service method when executed by a processor.

[0118] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the above method of the present disclosure is stored thereon. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above “Exemplary Method” section of this specification.

[0119] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0120] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0121] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0122] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0123] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0124] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0125] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0126] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. An emotion-based customer service method, characterized in that: include: Obtain user input information and user identity information; Determining the current emotional tendency of the user according to the user identity information; Determine customer service response information based on the user input information and the current emotional tendency.

2. The emotion-based customer service method according to claim 1, characterized in that: Determining the current emotional tendency of the user according to the user identity information includes: Determining basic data of the user according to the user identity information; Determining the basic emotional tendency value of the user in a historical unit time period according to the basic data; The user's current emotional tendency is determined according to a preset basic emotional tendency threshold and the basic emotional tendency value.

3. The emotion-based customer service method according to claim 2, characterized in that: Determining the basic data of the user according to the user identity information includes: Determine three behavior dimensions of the user according to the user identity information, wherein the three behavior dimensions include: behavior itself, behavior frequency, and behavior depth; The three behavioral dimensions of the user are determined as basic data.

4. The emotion-based customer service method according to claim 3, characterized in that: Determining the basic emotional tendency value of the user in a historical unit time period according to the basic data includes: According to a time window of a preset duration as a division unit, the basic data is divided according to the time window, the basic data falling within each time window is a group of analysis data, and multiple groups of analysis data are determined; Taking each set of analysis data as a whole, extracting data features to form a feature vector, identifying the emotion represented by the feature vector through a pre-trained emotion recognition model, and obtaining an emotion label; Each dimension of the group of analysis data is segmented according to time, and the emotion of each segmented data is identified through the emotion recognition model to obtain multiple segmented emotion labels; For each dimension of segmented emotion labels, determine the number of inconsistencies between two adjacent emotion labels based on the time sequence; According to the number of inconsistencies between two adjacent emotional labels in each dimension, the emotional tendency value of each set of analysis data in the dimension of the behavior itself is determined; The basic emotional tendency value is determined according to the emotional tendency value on the dimension of the behavior itself.

5. The emotion-based customer service method according to claim 2, characterized in that: The determining the current emotional tendency of the user according to the preset basic emotional tendency threshold and the basic emotional tendency value comprises: If the user's emotional tendency value is less than the preset basic emotional tendency threshold, determining that the user's current emotional tendency is normal; If the user's emotional tendency value is greater than or equal to a preset basic emotional tendency threshold, it is determined that the user's current emotional tendency is abnormal.

6. The emotion-based customer service method according to claim 1, characterized in that: Determining customer service response information according to the user input information and the current emotional tendency includes: According to the user input information and the current emotional tendency combined with the user preferences and product feature data, a large language model is input to output the words that meet the business scenario; The words that match the business scenario are determined as the customer service's reply information.

7. An emotion-based customer service device, characterized in that: include: An information acquisition module is used to obtain user input information and user identity information; A current emotional tendency determination module, used to determine the current emotional tendency of the user according to the user identity information; The customer service response module is used to determine the customer service response information based on the user input information and the current emotional tendency.

8. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the emotion-based customer service method described in any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the emotion-based customer service method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising: A computer program or instruction, characterized in that when the computer program or instruction is executed by a processor, it implements the emotion-based customer service method described in any one of claims 1 to 6.

Images