CN110866112A

CN110866112A - Response sequence determination method, server and terminal equipment

Info

Publication number: CN110866112A
Application number: CN201810923367.9A
Authority: CN
Inventors: 许涵斌; 靳玉康
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2018-08-14
Filing date: 2018-08-14
Publication date: 2020-03-06

Abstract

The application provides a response sequence determination method, a server and a terminal device, wherein the method comprises the following steps: acquiring emotion representation data of each user in a target user group; determining the emotion value of each user according to the emotion characterization data; and determining the response sequence of each user according to the emotion value of each user. By utilizing the technical scheme provided by the embodiment of the application, the problems that the existing sequential response easily causes customer complaints and the user experience is not high can be avoided, and the technical effect of effectively improving the user experience is achieved.

Description

Response sequence determination method, server and terminal equipment

Technical Field

The application belongs to the technical field of internet, and particularly relates to a response sequence determination method, a server and a terminal device.

Background

With the continuous development of internet technology, more and more people carry out operations such as shopping, learning, consultation and the like through a network platform. This makes it possible for the reception staff to have to communicate with a plurality of customers at the same time. Taking the e-commerce platform as an example, a merchant needs to receive a large number of customers by customer service, that is, the customer service needs to communicate with a plurality of customers simultaneously, some customers even need to receive dozens of or even hundreds of customers simultaneously, and at this time, as the customer service is too busy, the waiting time of some customers may be too long, so that the experience of the customers in the communication process is very bad, and the service public praise of the corresponding shop may be affected.

At present, the mode of customer service for customer service mainly includes: first come first served, randomly assigned services, etc. However, these reception methods have certain problems, which may lead to complaints from customers waiting too long or having low tolerance, and thus the user experience is not good.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The application aims to provide a response sequence determining method, a server and terminal equipment, which can effectively improve user experience.

The application provides a response sequence determination method, a server and a terminal device, which are realized as follows:

a response order determination method, the method comprising:

acquiring emotion representation data of each user in a target user group;

determining the emotion value of each user according to the emotion characterization data;

and determining the response sequence of each user according to the emotion value of each user.

A method of data processing, the method comprising:

obtaining a plurality of emotion representation data corresponding to a plurality of request clients;

determining a plurality of emotion values corresponding to the plurality of requesting clients according to the emotion characterization data;

determining a response order to the plurality of requesting clients according to the emotion values.

A display method, comprising:

providing a display interface;

and displaying conversation windows of the clients who reply to the plurality of waiting messages through the display interface, and displaying the response sequence of each client, wherein the response sequence is determined by the emotion value of each client.

A server comprising a processor and a memory for storing processor-executable instructions that when executed by the processor implement:

acquiring emotion representation data of a client waiting for information reply;

determining the emotion value of each client according to the emotion characterization data;

and determining the order of the customer service for information reply to the customers according to the emotion value of each customer.

A terminal device comprising a processor and a memory for storing processor-executable instructions that when executed by the processor implement:

providing a display interface;

A computer readable storage medium having stored thereon computer instructions which, when executed, implement the steps of the above-described method.

According to the response sequence determining method, the server and the terminal device, the emotion value of each user is determined through the emotion representation data of each user in the target user group, and the response sequence of each user is determined based on the emotion value of each user, so that the problems that customer complaints are easily caused and user experience is not high in the existing sequential response are solved, and the technical effect of effectively improving the user experience is achieved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

FIG. 1 is a flow chart of a method of one embodiment of a response order determination method provided herein;

FIG. 2 is a flow chart of a method of one embodiment of a display method provided herein;

FIG. 3 is a schematic illustration of a customer service response sequence determination provided herein;

FIG. 4 is a schematic diagram of the architecture of a server provided herein;

fig. 5 is a schematic block diagram of an embodiment of a response sequence determining apparatus provided in the present application.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Considering that different customers have different tolerances to the service waiting time, it is obviously not suitable if all customers assume the same emotional value to be handled and arranged. If the emotion value of a customer can be evaluated, for a customer with a low emotion value (i.e., relatively unsatisfied), services are prioritized relatively, and for a customer with a high emotion value (i.e., relatively more satisfied), services can be delayed, so that the probability of occurrence of customer complaints can be effectively reduced, and the user experience can be effectively improved.

Further, the historical behavior data of the client can reflect the tolerance of the client, considering that when the service of the client to the customer service is not full, the content of the sent message and the behavior of the sent message are changed to a certain extent. Specifically, if the content of the message currently sent by the client and the behavior of the sent message show the state of dissatisfaction of the client, the client can be preferentially taken over; if the content of the message currently sent by the client and the behavior of the sent message show a more satisfactory state of the client, some service providing can be delayed, and the client with lower satisfaction currently is prioritized.

That is, the emotional value of the client can be determined according to one or more of the historical behavior data of the client, the content of the current sent message and the behavior of the sent message, and the client is provided with services according to the emotional value, so that the complaint of the client is avoided. It is to be noted, however, that the historical behavior data, the content of the current sent message and the behavior of the sent message are also only an exemplary decision basis, and when it is actually implemented, the emotion value of the user may also be determined in combination with other data, such as: the occupation, gender, etc. of the customer can be taken into consideration for determining the emotional value of the user. Specifically, which data are used as the basis for determining the emotion value of the client is not limited in the application and can be selected according to actual needs.

Based on this, in this example, a response order determination method is provided, as shown in fig. 1, which may include the steps of:

step 101: acquiring emotion representation data of each user in a target user group;

the emotion characterization data is data that can determine an emotion value of the user, and for example, the emotion characterization data may include: historical behavioral data, content of a currently sent message, behavioral data of the currently sent message, and the like, and when actually implemented, the emotion characterization data may be one or more of the above listed data types, and other data, such as occupation, identity, and the like of the user, may be used as the data for determining the emotion value of the user.

Specifically, the historical behavior data may include, but is not limited to: the number of historical bad reviews given by the user, the number of historical good reviews given by the user, the number of 1-star service evaluations given by the user, the number of 2-star service evaluations given by the user, the number of 3-star service evaluations given by the user, the number of 4-star service evaluations given by the user, the number of 5-star service evaluations given by the user, the total number of service evaluations given by the user, the number of user returns, the number of user changes, and the like. The data can be used as historical behavior data of the user, and the tolerance of the user can be determined based on the behavior data of the user, wherein the higher the tolerance is, the higher the corresponding emotion value is, and the lower the tolerance is, the lower the corresponding emotion value is. For example, if a user gives a high percentage of 1-star service ratings, it may be determined that the user's tolerance is relatively low.

The above-mentioned act of sending a message may include, but is not limited to: the number of times of screen shaking used by the conversation, the number of times of using the forward expression used by the conversation, the number of times of using the neutral expression used by the conversation, the number of times of using the negative expression used by the conversation, the average interval duration of the last N times of message sending, the average message length of the last N times of message sending, the last responded time interval and the chat duration of the user and the like can also be determined based on the behaviors of the sent messages, for example, if the number of tables used for the forward expression is large (laugh, smile and the like), the current emotion value of the user can be reflected to be high, and if the number of the negative expression is large, the current emotion value of the user can be reflected to be low.

For example, the number of times that the user uses a screen for the current conversation, the number of times that the conversation uses a forward expression, the number of times that the conversation uses a neutral expression, the number of times that the conversation uses a negative expression, the average interval duration of the last N messages, the average message length of the last N messages, the last responded time interval and the chat duration of the user, and the like may be counted, and these data may be input as input data into a preset formula or model for calculating emotion values, in which the emotion value scores corresponding to different proportions of the forward expression in the expression, the emotion value scores corresponding to different proportions of the neutral expression in the expression, the emotion value scores corresponding to different message interval durations, the emotion value scores corresponding to different chat durations, and the like are recorded, and then a weight value may be set for these items, and finally accumulating the emotion value scores according to the weight values to obtain the emotion value based on the behavior of the message sent at this time. That is, by counting the number of the plurality of items preset, for example: the number of forward expressions sent, the number of times of screen shaking and the like are counted quantitatively, and then the data are input into a preset formula or a calculation model based on the counting result, so that the emotion value score based on the message sending behavior can be obtained. For example, the characterization data may be: vibrating the screen: 5 times, positive expression: 3, negative expression: 5, total expression: 12, etc., i.e., characterization data can be statistically derived in this fashion.

For example: a sentence is sent by the sender repeatedly at a fast rate, which may indicate that the user is in a hurry at this time, and the same sentence may be set to be sent repeatedly a plurality of times in a short time, corresponding to a lower emotion value.

However, the emotion value is obtained by setting the corresponding score and weight value for each item, and when the emotion value is actually obtained, other manners may also be adopted, for example, the score item is labeled based on the historical behavior data, and then the score model is trained to obtain the emotion value based on the behavior of the message sent this time. Specifically, which mode is adopted is not limited, and the selection can be performed according to actual needs in actual implementation.

The content of the currently sent message is text or voice content actually sent by the user, that is, content with semantics, and these text content may also express the current emotion of the user, for example: at this point, it can be considered that the user is now in a relatively urgent state, and the emotion value is relatively low, for example: how slow you reply to do nothing to do anything is not seen, which can be considered as a low emotional value. Therefore, the content of the message currently sent by the user can be analyzed to determine the current emotion value of the user.

In particular, determining the sentiment value may be based on semantic recognition for the content of the currently transmitted message. For example, the emotion in the message content can be determined by using a text emotion analysis method in NLP, so as to determine the emotion value of the real-time chat content of the user, specifically, the following steps can be adopted:

s1: preprocessing the chat content of the user to remove interference information and text formats in the chat content;

s2: performing word segmentation on the preprocessed chat content to obtain a plurality of word segments;

s3: generating a word feature vector for the multiple word segments by using word2vec and other methods to obtain multiple word feature vectors;

s4: generating a feature vector of corresponding chat content through the obtained plurality of word feature vectors;

s5: predicting the positive and negative emotion probabilities of each sentence of chat content through an svm classifier, and assuming that: p (n);

s6: using formulas

And calculating the emotion value of the latest chat content.

That is, the text content in the current chat can be divided into a plurality of segments, the segments are converted into word vectors, the feature vectors of corresponding sentences can be obtained based on the word vectors, the positive and negative emotion probabilities of the feature vectors of the sentences can be determined through a preset classifier, the emotion probabilities are used as the emotion values of the sentences or the words, and the emotion values of the current chat content can be obtained by averaging the emotion probabilities of the sentences or the words.

The svm classifier may be obtained by training based on a plurality of training samples, for example, a plurality of words may be obtained as training samples, then corresponding positive and negative emotion probabilities are labeled to the words, after the training samples are trained, a svm classifier for predicting positive and negative emotion probabilities of a sentence or a word may be obtained, and the determination of the positive and negative emotion probabilities of a target sentence or word may be achieved based on the classifier.

However, it should be noted that the specific data contents of the historical behavior data, the content of the current sent message, and the behavior data of the current sent message listed above are only some exemplary illustrations, and other data may be used as the historical behavior data, the content of the current sent message, and the behavior data of the current sent message when the implementation is practical, and the application is not limited thereto.

Step 102: determining the emotion value of each user according to the emotion characterization data;

if the emotion representation data has multiple data, a weight value can be set for each data, then emotion value scores corresponding to the various data are obtained through calculation respectively, and then the emotion value scores are accumulated according to the weight values corresponding to the various data to obtain a final emotion value. For example, if the mood characterizing data includes: the three data of historical behavior data, content of the currently sent message and behavior data of the currently sent message are used for determining the emotion value of each user according to the emotion characterization data, and the determination may include:

s1: calculating a first sentiment value score based on historical behavior data (a 1);

s2: calculating a second emotion value score (a2) based on the content of the currently transmitted message;

s3: calculating a third emotion value score based on the behavior data of the currently transmitted message (a 3);

s4: acquiring a first weight value (a) of a first emotion value score, a second weight value (b) of a second emotion value score and a third weight value (c) of a third emotion value score;

s5: and calculating the emotion value of each user according to the first emotion value score, the second emotion value score, the third emotion value score, the first weight value, the second weight value and the third weight value.

That is, the final mood value can be calculated as a × a1+ b × a2+ c × A3, where a + b + c is 1.

Specifically, the calculating of the second emotion value score based on the content of the currently transmitted message for S2 described above may include: removing interference data in the content of the current sending message; performing word segmentation on the content without the interference data to obtain a plurality of word vectors; calculating positive and negative emotion probabilities of all word vectors in the word vectors; and calculating to obtain a second emotion value score of the content of the current sent message according to the positive and negative emotion probabilities of each word vector. Namely, calculating the emotion probability of each participle after the participle, thereby determining the emotion value corresponding to the content of the current sent message.

Step 103: and determining the response sequence of each user according to the emotion value of each user.

The lower the mood value at the time of actual determination indicates a higher probability of complaints by the user, and the users are ranked relatively forward. This operation of determining the response sequence may be continuously judged in real time. After the emotion value is determined, the users may be inserted into the response queue in order of the emotion value from low to high, wherein the lower the emotion value is, the more front the response queue is, so that the users with low emotion value may be preferentially responded.

In order to enable a responder to simply and efficiently identify which users have low emotion values and which users have high emotion values, the users with low emotion values can be specially displayed, or the users are divided into different levels according to the sequence of the emotion values from low to high, and different display modes are given to the different levels, so that the responder can effectively determine which users are in urgent response.

That is, after the response order of each user is determined according to the emotion value of each user, the response level may be divided for each user according to the emotion value; and generating a response prompt corresponding to the response grade for each user according to the response grade.

Taking the response as an example of a reply message, the difference in emotion value may be displayed on the dialog window identifier, for example, for a user with a particularly low emotion value, a large red color may be displayed in his avatar position or his chat window identifier to indicate that the user needs to respond. Specifically, a preset response reminding list can be called, wherein response reminders corresponding to different response levels are recorded in the response reminding list; determining a response prompt corresponding to each user according to the response prompt list; and displaying the corresponding response prompt at the identification position of the dialog window of each user in the dialog interface according to the determined response prompt.

When actually implemented, the response reminder may include, but is not limited to, at least one of the following: color, flicker frequency, and dialog window arrangement order. That is, the emotional value of the user is indicated by color or blinking frequency or the like. For example, the user chat box is marked with different colors, and different flashing frequencies are used to prompt the urgency of the current user service. In one embodiment, an emotion value threshold may be set, and when the emotion of the user reaches the set threshold, a chat box may be popped up directly to prompt the customer service response sequence and priority.

Specifically, the response sequence determining method may be applied to a customer service system, and may also be applied to other aspects, for example: on-line question answering, on-line teaching, etc.

Taking the application in a customer service system as an example, the response sequence determining method may include:

s1: acquiring emotion representation data of a client waiting for information reply;

s2: determining the emotion value of each client according to the emotion characterization data;

s3: and determining the order of the customer service for information reply to the customers according to the emotion value of each customer.

In implementation, the client may trigger an operation of determining a response sequence every time a new message is sent, or may periodically rephoto all waiting users, and specifically, which manner is adopted may be selected according to actual needs, which is not limited in the present application.

For the customer service terminal, a display method is provided, as shown in fig. 2, which may include:

s201: providing a display interface;

s202: and displaying conversation windows of the clients who reply to the plurality of waiting messages through the display interface, and displaying the response sequence of each client, wherein the response sequence is determined by the emotion value of each client.

The customer service terminal may be a terminal device or software used for customer service operation. Specifically, the customer service terminal may be a terminal device such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart watch, or other wearable devices. Of course, the customer service terminal may also be software that can run in the above-mentioned terminal device. For example: and the mobile phone is applied to application software such as a Taobao, a Paobao or a browser.

In this application, a data processing method is further provided to determine a response sequence of a plurality of requesting clients, and specifically, the method may include the following steps:

step 1: obtaining a plurality of emotion representation data corresponding to a plurality of request clients;

step 2: determining a plurality of emotion values corresponding to the plurality of requesting clients according to the emotion characterization data;

and step 3: determining a response order to the plurality of requesting clients according to the emotion values.

That is, there may be a plurality of requesting clients, which may be terminal devices or software used by a user operation requesting a response. Specifically, the request client may be a terminal device such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart watch, or other wearable devices. Of course, the requesting client may also be software that can run in the terminal device. For example: and the mobile phone is applied to application software such as a Taobao, a Paobao or a browser. The user can request the customer service terminal to provide response service through the request client side, or after the user performs identity registration and authentication.

In order to take into account the emotions of a plurality of clients to prevent the clients from complaining about the service requests when a plurality of requesting clients make service requests, the emotion characterization data of each requesting client can be obtained, the emotion value of each requesting client is determined, and the response sequence is determined based on the determined emotion values, so that the possibility of the clients complaining about the service requests is reduced, and the user experience is improved.

In particular, the emotion characterization data may be obtained based on a message sent by the requesting client, and thus, the emotion characterization data may be obtained for whether the requesting client sent the message, and for what the message was sent. For example, whether the plurality of requesting clients send messages may be detected in real time; if a message requesting the client to send is detected, acquiring corresponding emotion representation data based on the message; if a message sent by a requesting client is not detected, the corresponding emotion characterization data is set as a default initial value. That is, a default initial value may be set for each requesting client, and if the requesting client does not send a message, default data may be obtained from the system as emotion characterization data thereof, and if the message is sent, corresponding emotion characterization data may be obtained based on behavior or content of the sent message, where the emotion characterization data may include content of the currently sent message.

For the content of a sent message, sometimes the message carries a picture element, for example: expressions in the expression package, expressions of the user's personal collection, pictures taken by the user or pictures stored in the user terminal, etc. may all be sent as messages by the user. Thus, the client may be requested to send a picture element in the message, based on which the emotion value of the user is determined.

Specifically, an emotion picture set may be preset, a plurality of pictures with emotion are collected in the emotion picture set as sample pictures, and an emotion value is labeled for each sample picture. Therefore, in actual implementation, the acquired picture elements can be compared with pictures in the preset emotion picture set to determine a picture sample similar to the picture elements. For example, the most similar picture sample may be selected as the matched picture sample, and then the emotion value of the picture sample may be used as the emotion value of the requesting client. Or matching to obtain a plurality of picture samples with similarity exceeding a preset threshold, then obtaining emotion values of the plurality of picture samples, carrying out weighted averaging on the emotion values, and taking the result obtained after weighted averaging as the emotion value of the request client. The specific method can be selected according to actual needs, and the application does not limit the method.

That is, the determining, in step 3, a plurality of emotion values corresponding to the plurality of requesting clients according to the emotion characterization data may include:

s1: acquiring a picture element of a request client in a current sending message aiming at the request client;

s2: searching a picture sample closest to the picture element in a preset emotion picture set;

s3: and determining the emotion value corresponding to the request client according to the emotion value of the picture sample.

In the above example, the picture element is taken as the emotion representation data for explanation, the picture element carried in the content of the message sent by each request client is taken as the emotion representation data, the emotion value of each request client is determined based on the emotion representation data, and the response sequence to the request client is determined according to the emotion value, so that the response to the request client is realized, and the user experience can be effectively improved.

The response sequence determination method is described below with reference to a specific embodiment, however, it should be noted that the specific embodiment is only for better describing the present application and is not to be construed as an undue limitation on the present application.

In this example, the customer service answering user inquiry is taken as an example for explanation, and as shown in fig. 3, the customer service response sequence determination diagram may include the following steps:

s1: whenever a new user asks for customer service, the user is added to the end of the default customer service queue and the chat behavior of the user is monitored.

S2: when a user inputs a sentence of chat content each time, historical behavior data, current chat behavior data and current chat content data of the user can be obtained, and then a current emotion value of the user is calculated based on the historical behavior data, the current chat behavior data and the current chat content data of the user.

S3: and inserting the users into corresponding positions of the customer service queue according to the calculated emotion values, so that all the users are sorted from high to low according to the emotion values, and the lower the emotion values are, the worse the emotion of the users is, the position of the users arranged at the front of the queue is shown.

S4: after the user response queue is updated, different prompts can be sent to corresponding customer service according to different emotion values of the user, for example, different colors can be used for marking a user chat box, different flashing frequencies can be used for prompting the emergency degree of the current user service, an emotion value threshold can be set, and when the threshold is reached, the customer service can be prompted in the modes of directly popping up the chat box and the like to prompt the customer service of the service order and priority of the user.

The emotion value may be calculated as follows, and specifically, may include:

1) and calculating a client historical emotion value, wherein the part of emotion value can be determined by historical data of service evaluation given by the user, and the historical data can be used for determining whether the user is a person with urgency or a person with peace. When the method is implemented, the positive probability and the negative probability of the historical emotion of the user can be evaluated by using the svm classifier, so that the emotion value of the user can be determined. Specifically, the emotion value Ehistory of the user based on the historical data can be determined by the characteristic values in the following table 1:

TABLE 1

2) And calculating the current emotion value of the user, wherein the current emotion value is used for evaluating the real-time chat emotion of the user.

Specifically, two parts may be included: a real-time chat behavior emotion value and a real-time chat content emotion value.

The real-time chat behavior emotion value can be determined by determining the positive probability and the negative probability of the current emotion of the user by using an svm classifier. Specifically, the emotion value of the real-time chat behavior of the user, namely, the action can be determined by the characteristic values in the following table 2:

TABLE 2

Characteristic value	Description of the invention
		PUZZ_NUM	The number of the vibration screens used by the chat user
POSITIVE_EMOYION_NUM	The chat user uses the number of forward expressions
		NORMAL_EMOYION_NUM	The chat user uses the neutral expression number
NEGATIVE_EMOYION_NUM	The chat user uses the negative expression number
		USER_SEND_RECENT_MSG_TIMEINTERVAL	Average time interval of last three times of message sending of user
USER_SEND_RECENT_MSG_LENGTH	Average message length of messages sent three times last by user
		USER_LAST_REPLY_TIMEINTERVAL	Last time user was answered
CHAT_TIME_LENGTH	Duration of user chat
		……..	……..

The real-time chat content emotion value can be calculated by using a text emotion analysis mode in NLP (NLP), and specifically can be calculated by adopting the following steps:

s6: using formulas

Calculating the emotion value of the latest chat content;

the emotion value calculation formula of the end user is Etotal α + ease β + Econtent γ, where α + β + γ is 1.

In the above example, the customer service is automatically guided to take over the corresponding customer by using the historical behaviors and the current chat behaviors of the customer and the current chat contents. The tolerance of the customer to the waiting time can be determined through the historical behavior of the customer, and if the tolerance is low, the customer is given priority to take treatment, and if the tolerance is high, the customer can take treatment later. Meanwhile, the current emotional state of the user can be determined according to the current chat content and the current chat behavior of the user, if the user is in an unsatisfied state, the user can be received preferentially, and if the current communication is satisfactory, the user can be received later. The order of customer service response users is determined through the behavior characteristics, and the customer service is reminded in real time, so that the quality of the customer service is improved, and the user experience is improved. Namely, the current emotion value of each user is determined according to the current state of each user, and the customer service reception sequence is adjusted in real time according to the emotion value of each user, so that the satisfaction degree of the users is improved.

The method provided by the embodiment of the application can be executed in a server side, a computer terminal or a similar operation device. Taking the example of the operation on the server side, fig. 4 is a hardware structure block diagram of the server side of the response order determination method according to the embodiment of the present invention. As shown in fig. 4, the server 10 may include one or more (only one shown) processors 102 (the processors 102 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission module 106 for communication functions. It will be understood by those skilled in the art that the structure shown in fig. 4 is only an illustration and is not intended to limit the structure of the electronic device. For example, the server 10 may also include more or fewer components than shown in FIG. 4, or have a different configuration than shown in FIG. 4.

The memory 104 may be used to store software programs and modules of application software, such as program instructions/modules corresponding to the response sequence determination method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implements the response sequence determination method of the application program. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory located remotely from processor 102, which may be connected to server 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission module 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission module 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

At a software level, as shown in fig. 5, the response sequence determining apparatus may include: an obtaining module 501, a first determining module 502, and a second determining module 503, wherein:

an obtaining module 501, configured to obtain emotion representation data of each user in a target user group;

a first determining module 502, configured to determine an emotion value of each user according to the emotion characterization data;

a second determining module 503, configured to determine a response sequence of each user according to the emotion value of each user.

In one embodiment, the first determining module 502 may specifically insert the users into the response queue in an order of a lower emotion value to a higher emotion value, wherein the lower emotion value is inserted into a position of the response queue that is further forward.

In one embodiment, the response order determining apparatus may further include: the dividing module is used for dividing response grades for the users according to the emotion values after determining the response sequence of the users according to the emotion values of the users; and the generating module is used for generating response prompts corresponding to the response grades for all the users according to the response grades.

In one embodiment, the generating module may include: the calling unit is used for calling a preset response reminding list, wherein response reminders corresponding to different response levels are recorded in the response reminding list; the determining unit is used for determining the response reminding corresponding to each user according to the response reminding list; and the display unit is used for displaying the corresponding response prompt at the identification position of the dialog window of each user in the dialog interface according to the determined response prompt.

In one embodiment, the response alert may include, but is not limited to, at least one of: color, flicker frequency, and dialog window arrangement order.

In one embodiment, the mood characterizing data may include, but is not limited to, at least one of: historical behavior data, content of a currently sent message, behavior data of a currently sent message.

In one embodiment, the emotion characterization data includes: determining the emotion value of each user according to the emotion characterization data under the conditions of the historical behavior data, the content of the current sent message and the behavior data of the current sent message, wherein the determining may include: calculating a first sentiment value score based on historical behavior data; calculating a second sentiment value score based on the content of the currently transmitted message; calculating a third sentiment value score based on the behavioral data of the currently transmitted message; acquiring a first weight value of the first emotion value score, a second weight value of the second emotion value score and a third weight value of the third emotion value score; and calculating the emotion value of each user according to the first emotion value score, the second emotion value score, the third emotion value score, the first weight value, the second weight value and the third weight value.

In one embodiment, calculating a second sentiment value score based on the content of the currently transmitted message may include: removing interference data in the content of the current sending message; performing word segmentation on the content without the interference data to obtain a plurality of word vectors; calculating positive and negative emotion probabilities of all word vectors in the word vectors; and calculating to obtain a second emotion value score of the content of the current sent message according to the positive and negative emotion probabilities of each word vector.

According to at least one embodiment of the present application, the emotion characterization data includes content of a currently transmitted message. The content of the message comprises emotion pictures, wherein the emotion pictures and picture subsets contained in the emotion picture set can be set based on a Hevner emotion ring; the Hevner emotion ring generally comprises a plurality of adjectives (such as 67 adjectives), all the adjectives are divided into a plurality of categories (such as eight categories), all the categories form a ring according to the mutual relations among the adjectives, and any ring and the adjacent rings in front of and behind the adjective have a progressive relation in emotion logic.

The application also provides a customer service response sequence determination device, which is located in the server and may include: the acquisition module is used for acquiring emotion representation data of the client waiting for information reply; the first determining module is used for determining the emotion value of each client according to the emotion representation data; and the second determining module is used for determining the order of the customer service for information reply to the customers according to the emotion value of each customer.

In one embodiment, the obtaining module may include: the detection unit is used for detecting whether the client waiting for the reply of the message sends a message or not; and the triggering unit is used for triggering the emotion characterization data to be acquired under the condition that the sending message is detected.

The present application further provides a display device, located in a terminal device, and may include: the providing module is used for providing a display interface; and the display module is used for displaying the conversation windows of the clients who reply to the plurality of waiting messages through the display interface and displaying the response sequence of each client, wherein the response sequence is determined by the emotion value of each client.

In one embodiment, the display module may specifically, but not limited to, display the response sequence of each client by one of the following ways: color, flicker frequency, and dialog window arrangement order.

Although the present application provides method steps as described in an embodiment or flowchart, additional or fewer steps may be included based on conventional or non-inventive efforts. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or client product executes, it may execute sequentially or in parallel (e.g., in the context of parallel processors or multi-threaded processing) according to the embodiments or methods shown in the figures.

The apparatuses or modules illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. The functionality of the modules may be implemented in the same one or more software and/or hardware implementations of the present application. Of course, a module that implements a certain function may be implemented by a plurality of sub-modules or sub-units in combination.

The methods, apparatus or modules described herein may be implemented in computer readable program code to a controller implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, Application Specific Integrated Circuits (ASICs), programmable logic controllers and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may therefore be considered as a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

Some of the modules in the apparatus described herein may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary hardware. Based on such understanding, the technical solutions of the present application may be embodied in the form of software products or in the implementation process of data migration, which essentially or partially contributes to the prior art. The computer software product may be stored in a storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, mobile terminal, server, or network device, etc.) to perform the methods described in the various embodiments or portions of the embodiments of the present application.

The embodiments in the present specification are described in a progressive manner, and the same or similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. All or portions of the present application are operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, mobile communication terminals, multiprocessor systems, microprocessor-based systems, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

While the present application has been described with examples, those of ordinary skill in the art will appreciate that there are numerous variations and permutations of the present application without departing from the spirit of the application, and it is intended that the appended claims encompass such variations and permutations without departing from the spirit of the application.

Claims

1. A response order determination method, the method comprising:

acquiring emotion representation data of each user in a target user group;

2. The method of claim 1, wherein determining the response order for each user based on the emotion value for each user comprises:

and inserting the users into the response queue according to the sequence of the emotion values from low to high, wherein the lower the emotion value is, the more front the response queue is.

3. The method of claim 1, wherein after determining the response order for each user based on the emotion value for each user, the method further comprises:

dividing response grades for all users according to the emotion values;

and generating a response prompt corresponding to the response grade for each user according to the response grade.

4. The method of claim 3, wherein generating a response prompt for each user with a corresponding response level according to the response level when the response is a reply message comprises:

calling a preset response reminding list, wherein response reminders corresponding to different response levels are recorded in the response reminding list;

determining a response prompt corresponding to each user according to the response prompt list;

and displaying the corresponding response prompt at the identification position of the dialog window of each user in the dialog interface according to the determined response prompt.

5. The method of claim 4, wherein the responsive alert comprises at least one of: color, flicker frequency, and dialog window arrangement order.

6. The method of claim 1, wherein the mood characterization data comprises at least one of: historical behavior data, content of a currently sent message, behavior data of a currently sent message.

7. The method of claim 6, wherein determining an emotion value for each user based on the emotion characterization data comprises:

calculating a first sentiment value score based on historical behavior data;

calculating a second sentiment value score based on the content of the currently transmitted message;

calculating a third sentiment value score based on the behavioral data of the currently transmitted message;

acquiring a first weight value of the first emotion value score, a second weight value of the second emotion value score and a third weight value of the third emotion value score;

and calculating the emotion value of each user according to the first emotion value score, the second emotion value score, the third emotion value score, the first weight value, the second weight value and the third weight value.

8. The method of claim 6, wherein calculating a second sentiment value score based on the content of the currently transmitted message comprises:

removing interference data in the content of the current sending message;

performing word segmentation on the content without the interference data to obtain a plurality of word vectors;

calculating positive and negative emotion probabilities of all word vectors in the word vectors;

and calculating to obtain a second emotion value score of the content of the current sent message according to the positive and negative emotion probabilities of each word vector.

9. A method of data processing, the method comprising:

10. The method of claim 9, wherein obtaining a plurality of emotion characterization data corresponding to a plurality of requesting clients comprises:

detecting whether the plurality of requesting clients send messages;

if a message requesting the client to send is detected, acquiring corresponding emotion representation data based on the message;

if a message sent by a requesting client is not detected, the corresponding emotion characterization data is set as a default initial value.

11. The method of claim 9, wherein the emotion characterization data comprises content of a currently transmitted message.

12. The method of claim 11, wherein determining a plurality of sentiment values corresponding to the plurality of requesting clients from the sentiment characterization data comprises:

acquiring a picture element of a request client in a current sending message aiming at the request client;

searching a picture sample closest to the picture element in a preset emotion picture set;

and determining the emotion value corresponding to the request client according to the emotion value of the picture sample.

13. A display method, comprising:

providing a display interface;

14. The method of claim 13, wherein displaying the order of responses from the clients comprises:

displaying the response sequence of each client by one of the following ways: color, flicker frequency, and dialog window arrangement order.

15. A server comprising a processor and a memory for storing processor-executable instructions that when executed by the processor implement:

acquiring emotion representation data of each user in a target user group;

16. The server according to claim 15, wherein determining the response sequence of each user according to the emotion value of each user comprises:

17. The server according to claim 15, wherein the processor, after determining the response sequence of each user according to the emotion value of each user, further comprises:

dividing response grades for all users according to the emotion values;

18. The server of claim 15, wherein the emotion characterization data comprises at least one of: historical behavior data, content of a currently sent message, behavior data of a currently sent message.

19. The server of claim 18, wherein the emotion characterization data comprises: under the conditions of historical behavior data, the content of the current sent message and the behavior data of the current sent message, determining the emotion value of each user according to the emotion characterization data, wherein the emotion value comprises the following steps:

calculating a first sentiment value score based on historical behavior data;

20. The server of claim 18, wherein calculating a second sentiment value score based on the content of the currently transmitted message comprises:

removing interference data in the content of the current sending message;

21. A server comprising a processor and a memory for storing processor-executable instructions that when executed by the processor implement:

22. A terminal device comprising a processor and a memory for storing processor-executable instructions that when executed by the processor implement:

providing a display interface;

23. A computer readable storage medium having stored thereon computer instructions which, when executed, implement the steps of the method of any one of claims 1 to 8.