CN109949103B - Data processing method and device and electronic equipment - Google Patents
Data processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN109949103B CN109949103B CN201910252933.2A CN201910252933A CN109949103B CN 109949103 B CN109949103 B CN 109949103B CN 201910252933 A CN201910252933 A CN 201910252933A CN 109949103 B CN109949103 B CN 109949103B
- Authority
- CN
- China
- Prior art keywords
- data
- target user
- evaluation
- user
- customer service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The application discloses a data processing method, a data processing device and electronic equipment, wherein the method comprises the following steps: after the customer service system outputs second data aiming at first data input by a target user, monitoring whether feedback data input by the target user is received or not, wherein the feedback data is used for describing the satisfaction degree of the target user on the second data; and if the feedback data input by the target user is not received, generating evaluation data of the target user, wherein the evaluation data is used for simulating the feedback data. Therefore, the evaluation data capable of simulating the feedback data can be generated for the user when the user does not have the feedback data, and the service evaluation can be obtained in the customer service system.
Description
Technical Field
The present application relates to the field of intelligent customer service technologies, and in particular, to a data processing method and apparatus, and an electronic device.
Background
Intelligent customer service systems are increasingly used in various service areas. In an intelligent customer service system, statistical analysis needs to be performed on the evaluation of a user, so that the service condition of the user is known, and corresponding adjustment is further made, such as adjustment of a service mode or form of the user.
Currently, the evaluation of the intelligent customer service system by the user is usually active feedback information which is actively input by the user after the service is ended.
Disclosure of Invention
In view of the above, the present application provides a data processing method, including:
after the customer service system outputs second data aiming at first data input by a target user, monitoring whether feedback data input by the target user is received or not, wherein the feedback data is used for describing the satisfaction degree of the target user on the second data;
and if the feedback data input by the target user is not received, generating evaluation data of the target user, wherein the evaluation data is used for simulating the feedback data.
Preferably, the method for generating the evaluation data of the target user includes:
collecting user action data of the target user;
and processing the user action data to obtain the evaluation data of the target user.
Preferably, the method for processing the user motion data to obtain the evaluation data of the target user includes:
processing the user action data by using a classification model to obtain evaluation data of the target user;
wherein the classification model is generated by:
obtaining historical action data of at least one evaluated service in the customer service system and historical evaluation data corresponding to the historical action data;
and performing model training on the historical action data and the historical evaluation data by using a classification algorithm to obtain a classification model.
The above method, preferably, further comprises:
obtaining user portrait information of the target user;
wherein after generating the ratings data for the target user, the method further comprises:
and modifying the evaluation data of the target user by using the user portrait information to obtain modified evaluation data.
The above method, preferably, further comprises:
obtaining an output parameter when the customer service system outputs the second data;
wherein after generating the ratings data for the target user, the method further comprises:
and modifying the evaluation data of the target user by using the output parameters to obtain modified evaluation data.
The above method, preferably, further comprises:
obtaining product behavior data of the target user on a target product;
wherein after generating the ratings data for the target user, the method further comprises:
and modifying the evaluation data of the target user by using the product behavior data to obtain the modified evaluation data.
The above method, preferably, further comprises:
and optimizing the classification model based on the user action data of the target user and the evaluation data of the target user.
The above method, preferably, further comprises:
and generating an overall evaluation result of the customer service system based on the evaluation data of the target user and the historical evaluation data.
The present application also provides a data processing apparatus, including:
the data monitoring unit is used for monitoring whether feedback data input by a target user is received or not after a customer service system outputs second data aiming at first data input by the target user, wherein the feedback data are used for describing the satisfaction degree of the target user on the second data;
and the evaluation generation unit is used for generating the evaluation data of the target user if the feedback data input by the target user is not received, wherein the evaluation data is used for simulating the feedback data.
The present application further provides an electronic device, including:
the customer service interaction equipment is used for receiving first data input by a target user and outputting second data aiming at the first data;
and the evaluation processing equipment is used for monitoring whether feedback data input by the target user is received or not, the feedback data are used for describing the satisfaction degree of the target user on the second data, and if the feedback data input by the target user are not received, the evaluation data of the target user are generated and used for simulating the feedback data.
According to the technical scheme, after the customer service system outputs the second data aiming at the first data input by the target user, whether the feedback data which are input by the target user and describe the satisfaction degree of the target user on the second data are received or not is monitored, so that if the feedback data are not received, the evaluation data of the target user are generated, and the feedback data of the target user are simulated by the evaluation data. Therefore, the evaluation data capable of simulating the feedback data can be generated for the user when the user does not have the feedback data, and the service evaluation can be obtained in the customer service system.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a data processing method provided in a possible implementation manner of an embodiment of the present application;
fig. 2 is a partial flowchart of a data processing method provided in a possible implementation manner of an embodiment of the present application;
FIG. 3 is a diagram illustrating an example of an application of an embodiment of the present application;
fig. 4 is a schematic structural diagram of a data processing apparatus according to a possible implementation manner of the embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device provided in a possible implementation manner of an embodiment of the present application;
fig. 6 is another exemplary diagram of an application of the embodiment of the present application.
Detailed Description
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.
Fig. 1 is a flowchart of a data processing method provided in one possible implementation manner in an embodiment of the present application, where the method is applied to a device such as a customer service server where an intelligent customer service system is located.
In this embodiment, the method may specifically include the following steps:
step 101: after the customer service system outputs the second data for the first data input by the target user, whether feedback data input by the target user is received or not is monitored, and if not, step 102 is executed.
The first data may be data input by the target user through operations such as consulting and the like when the customer service system provides the customer service for the target user once, for example, the first data of asking about delivery time or the first data of performing after-sale compensation consultation and the like. And the second data refers to reply data of the customer service system aiming at the first data after the target user inputs the first data into the customer service system, such as replying the second data of the delivery time or the second data of the indemnity standard, and the like.
In this embodiment, after the customer service system replies the second data to the first data, it is monitored whether the target user inputs feedback data, where the feedback data can describe the satisfaction degree of the target user with respect to the second data, that is, in this embodiment, it is monitored whether the target user feeds back corresponding satisfaction degree evaluation data to the second data replied by the customer service system, for example, the very satisfactory or unsatisfactory satisfaction degree option evaluation data is selected and input through a control, or the very favorite character content evaluation data is input through a keyboard in a customized manner, and so on.
It should be noted that, in this embodiment, after the customer service system outputs the second data, the action of monitoring whether the feedback data is received may be started, and if the monitoring action continues until the condition is satisfied, the feedback data input by the target user is still not received, then it is considered that the feedback data input by the target user is not received, and at this time, step 102 is executed.
For example, in this embodiment, after the monitoring action is started, monitoring is performed for a certain duration, and if no feedback data input by the target user is received and continues to a preset duration threshold, for example, the target user does not input feedback data to the service even after the duration exceeds 12 hours, then step 102 is performed;
for another example, in this embodiment, after the monitoring action is started, monitoring is continued, and if the target user has started entering the next service (different from the current service), and still does not receive the feedback data input by the target user, at this time, step 102 is executed.
Step 102: and generating evaluation data of the target user.
The evaluation data in the embodiment is used for simulating feedback data, and the feedback data of the target user is simulated when it is monitored that the target user does not input the feedback data into the customer service system, so as to generate the evaluation data of the target user for subsequent data analysis.
It should be noted that the evaluation data generated in this embodiment may specifically be represented in a text description manner, for example, by text contents such as rich reply contents, fast reply speed, or inaccurate contents, with respect to at least one evaluation criterion, such as reply speed, reply accuracy, or whether the user is busy, or the evaluation data may also be represented in a level or star level, specifically may be represented in a numerical value, or in a character, or in an expression package, or the like. For example, a higher numerical value may characterize a higher rating satisfaction, character a may characterize a higher rating satisfaction than character c, a smiling face expression package may characterize a higher rating satisfaction than a flat mouth expression package, or 5 stars may characterize a higher rating satisfaction than 1 star, and so on.
It can be seen from the foregoing solutions that, in the data processing method provided in the embodiment of the present application, after the customer service system outputs the second data for the first data input by the target user, by monitoring whether the feedback data describing the satisfaction degree of the target user for the second data input by the target user is received, if the feedback data is not received, the evaluation data of the target user is generated, and the feedback data of the target user is simulated by using the evaluation data. Therefore, in the embodiment, evaluation data capable of simulating the feedback data of the user can be generated for the user when the user does not have the feedback data, so that the service evaluation can be obtained in the customer service system.
In one implementation, the step 102 may be specifically implemented by the following manner when generating the evaluation data of the target user, as shown in fig. 2:
step 201: user action data of a target user is collected.
Wherein, the user action data can be understood as: the consultation behavior operation data of the target user in the customer service system comprises various input action data, such as operations of character input, image input or expression package input, and specifically comprises data of input content, input duration and the like, wherein the input content can be understood as various contents, such as one or more of characters, images and expression packages, input by the target user in the customer service system, and the input duration can be understood as: the time length used by the target user when inputting the above input contents, for example, the time length used by the target user when the target user asks the customer service system for the product function, and then after the customer service system answers the function manual of the target user product, the target user asks or answers again after answering the function manual replied by the customer service system.
It should be noted that, in this embodiment, the user action data refers to user action data of the target user and the customer service system in the current service, as shown in fig. 3, the target user may log in the intelligent customer service system through a mobile phone and perform a corresponding action. The user action data refers to user action data involved in a current service for which feedback data input by a target user is not received, and is distinguished from historical action data with feedback data or other historical action data without feedback data.
It can be seen that each time the target user inputs, i.e. one action, there may be one or more actions of the target user in one consultation service in the customer service system, and these actions constitute one or more user action data of the target user. It should be noted that the user action data may be data related to the consulting content input by the target user in the customer service system, and may also include feedback data input by the target user in the customer service system, and in this embodiment, under the condition that the feedback data of the target user is not received, the user action data acquired in step 201 is data related to the consulting content input by the target user in the customer service system, such as action data of a function of asking about a product.
Step 202: and processing the user action data to obtain the evaluation data of the target user.
Specifically, in this embodiment, the user motion data may be processed in the following manner:
and processing the user action data by using the classification model to obtain the evaluation data of the target user.
The classification model can be modeled by using classification algorithms such as decision trees, logistic regression, naive Bayes, neural networks, Support Vector Machine (SVM) (support Vector machine), K-nearest neighbor KNN (K-nearest neighbor) and the like.
Specifically, the classification model can be implemented in the following manner when being constructed:
firstly, historical action data of at least one evaluated service in a customer service system and historical evaluation data corresponding to the historical action data are obtained, and then model training is carried out on the historical action data and the historical evaluation data by using a classification algorithm to obtain a classification model.
Wherein, the evaluated service can be understood as: the various completed services recorded by the customer service system already have the services of feedback data input or simulated by the user, and the evaluated services correspond to: the historical action data and the historical evaluation data corresponding to the historical action data, for example, interaction data between the user and the customer service system, evaluation data of the user on the customer service, and the like. The evaluated service may include a historical evaluated service of the target user, or may include a historical evaluated service of another user, and accordingly, the historical motion data includes historical motion data of the target user, or may include historical motion data of another user, and the historical evaluation data includes historical evaluation data of the target user, or may include historical evaluation data of another user.
Accordingly, in the present embodiment, after obtaining the historical motion data and the historical evaluation data of the evaluated service, the data are used as input sample data of a classification algorithm, such as SVM or KNN, and model training is performed, so as to construct a classifier, i.e., a classification model. And then, inputting the collected user action data of the target user into a classification model for processing, thereby obtaining the evaluation data of the target user.
Based on the above implementation, the classification model may also be optimized based on the user motion data of the target user and the generated evaluation data, for example, the user motion data of the target user and the generated evaluation data are used as historical data to be added to model construction or training of the classification model, so as to optimize the classification model, and thus, the accuracy of the evaluation data can be improved when the evaluation data is generated again by using the classification model in the following.
In addition, in this embodiment, the overall evaluation data of the customer service system may be generated based on the evaluation data of the target user and the historical evaluation data. For example, in the embodiment, the overall service condition of the customer service system is evaluated based on the evaluation data of the target user and other users on the customer service system, such as that the customer service system operates normally as a whole, the customer service replies generally slowly, or replies that most of the customer service replies inaccurately.
In practical applications, after the evaluation data of the target user is generated, the evaluation data may be modified to make the evaluation data closer to the evaluation intention of the target user, for example, the modified evaluation data may be obtained by modifying the generated evaluation data of the target user by obtaining one or more of user portrait information of the target user, output parameters when the customer service system outputs the second data, product behavior data of the target user on the target product, and the like. The details are as follows:
in one implementation, after obtaining the user portrait information of the target user, the generated evaluation data of the target user may be modified by using the user portrait information, so as to obtain modified evaluation data.
The user profile information can represent characteristics of the target user, including one or more of character characteristics, behavior characteristics and the like, for example, the target user is a person with violent or critical emotion or belonging to habit-tolerant treatment, and the like.
In the embodiment, the generated evaluation data is corrected based on the user portrait information, so that the evaluation data is closer to the evaluation habit or the evaluation behavior of the target user, and the accuracy of the generated evaluation data is improved.
For example, in the current interaction between the target user and the customer service system, the target user shows a wide and good character of treating the object, which indicates that the evaluation of the target user on the customer service system may be wide and fair, and at this time, the currently generated evaluation data may be corrected, for example, the satisfaction degree value represented in the evaluation data is improved.
For another example, the target user shows a harsh action style in the historical interaction, which indicates that the target user may have a harsh evaluation on the customer service system, and at this time, the currently generated evaluation data may be modified, such as reducing the satisfaction value represented in the evaluation data.
In an implementation manner, in this embodiment, after obtaining the output parameter when the customer service system outputs the second data, the evaluation data of the target user may be modified by using the output parameter to obtain the modified evaluation data.
The output parameter may represent a state in which the customer service system replies to the target user, such as a reply speed of the customer service system after the target user asks a question, a state parameter in which the target user asks the same question again after the customer service system replies to the target user, or asks the same question again for a different question.
In the embodiment, the generated evaluation data is corrected based on the output parameters of the customer service system, so that the condition of malicious evaluation formed by the personality of the user or automatic favorable evaluation of the system is avoided, and the accuracy of the generated evaluation data is improved.
For example, when the target user asks a question of the target user in the interaction with the customer service system, the customer service system replies within 1 second, which indicates that the customer service system provides a quick and efficient service for the target user, and at this time, the generated evaluation data can be corrected based on the reply speed, such as improvement of a satisfaction value represented in the evaluation data.
For another example, when the target user asks the target user in the interaction with the customer service system, the customer service system replies within 1 second only, and the other times all need more than 5 seconds to reply the target user, which indicates that the service provided by the customer service system for the target user is slow, and at this time, the generated evaluation data can be corrected based on the reply speed, for example, the satisfaction value represented in the evaluation data is reduced.
In an implementation manner, in this embodiment, after obtaining the product behavior data of the target product from the target user, the evaluation data of the target user may be modified by using the product behavior data to obtain modified evaluation data.
The product behavior data may be understood as the satisfaction degree of the target user with the target product consulted by the customer service system or the target product provided by the customer service system based on the service provided by the customer service system after the customer service system provides the service for the target user, such as the target user purchasing the target product again (satisfaction), the target user browsing the target product (possibly satisfaction), the target user returning the order of the target product or stopping payment (dissatisfaction), and the like.
In the embodiment, the generated evaluation data is corrected based on the product behavior data of the target product by the target user, so that the evaluation data is closer to the evaluation intention of the target user on the customer service system, and the accuracy of the generated evaluation data is improved.
For example, after the target user finishes interacting with the customer service system, the target user returns to the product page of the target product and places an order again, which indicates that the target user is satisfied with the service corresponding to the target product, and at this time, the generated evaluation data may be corrected based on the behavior data of the placed order, such as increasing the satisfaction value represented in the evaluation data.
Fig. 4 is a schematic structural diagram of a data processing apparatus provided in a possible implementation manner in an embodiment of the present application, where the data processing apparatus is suitable for a device such as a service server where a service system is located.
In this embodiment, the apparatus may specifically include the following structure:
the data monitoring unit 401 is configured to monitor whether feedback data input by the target user is received after the customer service system outputs second data for the first input by the target user.
The feedback data is used for describing the satisfaction degree of the target user on the second data.
An evaluation generating unit 402, configured to generate evaluation data of the target user if feedback data input by the target user is not received.
Wherein the evaluation data is used to simulate feedback data of the target user.
In one implementation, the evaluation generation unit 402 may generate the evaluation data by:
and acquiring user action data of a target user, and then processing the user action data to obtain evaluation data of the target user.
Specifically, the evaluation generating unit 402 may obtain historical motion data of at least one evaluated service in the customer service system and historical evaluation data corresponding to the historical motion data in advance, and perform model training on the historical motion data and the historical evaluation data by using a classification algorithm to obtain a classification model.
Accordingly, when the evaluation generating unit 402 processes the user motion data to obtain the evaluation data of the target user, the user motion data may be specifically processed by using the classification model obtained by the above training to obtain the evaluation data of the target user.
Further, after obtaining the evaluation data, the evaluation generating unit 402 may optimize the above classification model based on the user motion data of the target user and the evaluation data of the target user to improve the accuracy of the subsequent evaluation.
It can be seen from the foregoing solution that, in the data processing apparatus provided in the embodiment of the present application, after the customer service system outputs the second data for the first data input by the target user, by monitoring whether the feedback data describing the satisfaction degree of the target user for the second data input by the target user is received, if the feedback data is not received, the evaluation data of the target user is generated, and the feedback data of the target user is simulated by using the evaluation data. Therefore, in the embodiment, evaluation data capable of simulating the feedback data of the user can be generated for the user when the user does not have the feedback data, so that the service evaluation can be obtained in the customer service system.
Further, after obtaining the evaluation data, the evaluation generation unit 402 may modify the evaluation data of the target user by obtaining one or more of user portrait information of the target user, an output parameter when the customer service system outputs the second data, product behavior data of the target user on the target product, and the like, to obtain modified evaluation data.
Further, after obtaining the evaluation data, the evaluation generation unit 402 may generate the overall evaluation result of the customer service system based on the evaluation data of the target user and the historical evaluation data.
It should be noted that, for the specific implementation of each unit of the data processing apparatus in this embodiment, reference may be made to the corresponding content in the foregoing, and details are not described here.
Referring to fig. 5, a schematic structural diagram of an electronic device provided in a possible implementation manner of the embodiment of the present application is shown, where the electronic device may be a device such as a service server where a service system is located.
In this embodiment, the electronic device may specifically include the following structure:
the customer service interaction device 501 is configured to receive first data input by a target user, and output second data for the first data.
As shown in fig. 5, the customer service interaction device 501 has an input device and an output device, and the target user inputs first data through the input device, and the electronic device outputs second data for the target user through the output device, so as to implement customer service interaction with the target user.
The evaluation processing device 502 is configured to monitor whether feedback data input by the target user is received, where the feedback data is used to describe satisfaction of the target user on the second data, and if the feedback data input by the target user is not received, generate evaluation data of the target user, where the evaluation data is used to simulate the feedback data.
The evaluation processor device 502 may be implemented by a processor, and may monitor whether the input device finishes inputting the feedback data to the target user, and if not, generate evaluation data capable of simulating the feedback data.
In addition, the electronic device may further include a memory for storing the evaluation data, the first data, the second data, various historical service data, and the like.
In one implementation, the evaluation processing device 502 may generate the evaluation data by:
and acquiring user action data of a target user, and then processing the user action data to obtain evaluation data of the target user.
Specifically, the evaluation processing device 502 may obtain historical motion data of at least one evaluated service in the customer service system and historical evaluation data corresponding to the historical motion data in advance, and perform model training on the historical motion data and the historical evaluation data by using a classification algorithm to obtain a classification model.
Accordingly, when the evaluation processing device 502 processes the user motion data to obtain the evaluation data of the target user, the user motion data may be specifically processed by using the classification model obtained by the above training to obtain the evaluation data of the target user.
Further, after obtaining the evaluation data, the evaluation processing device 502 may optimize the above classification model based on the user action data of the target user and the evaluation data of the target user to improve the accuracy of the subsequent evaluation.
It can be seen from the foregoing solution that, in the electronic device provided in the embodiment of the present application, after the customer service system outputs the second data for the first data input by the target user, whether the feedback data describing the satisfaction degree of the target user for the second data input by the target user is received or not is monitored, so that if the feedback data is not received, the evaluation data of the target user is generated, and the feedback data of the target user is simulated by using the evaluation data. Therefore, in the embodiment, evaluation data capable of simulating the feedback data of the user can be generated for the user when the user does not have the feedback data, so that the service evaluation can be obtained in the customer service system.
Further, after obtaining the evaluation data, the evaluation processing device 502 may modify the evaluation data of the target user by obtaining one or more of user portrait information of the target user, an output parameter when the customer service system outputs the second data, product behavior data of the target user on the target product, and the like, to obtain modified evaluation data.
In addition, after obtaining the evaluation data, the evaluation processing device 502 may generate an overall evaluation result of the customer service system based on the evaluation data of the target user and the historical evaluation data.
It should be noted that, for the specific implementation of each structure of the electronic device in the present embodiment, reference may be made to the corresponding content in the foregoing, and details are not described here.
The following describes the technical solution in this embodiment by taking an intelligent customer service system as an example:
first, in the present embodiment, a primary Service (Service) in the smart customer Service system is defined as S, a user Action (Action) is defined as a, a user Action (Behavior) is defined as B, and a user Evaluation (Evaluation) is defined as E, so that:
s is the set of B, { B1, B2, B3, ·, Bn }, B is the set of a, { a1, a2, A3, ·, An };
the content item is a text content text, a feedback content feedback, an intention content intent, and an evaluation content E, and the content item is a star level star, a tag, and a comment.
In this embodiment, a user evaluation (E) is estimated for a user behavior (B) for which no user evaluation is made by a user behavior (B) including a user evaluation (E).
Wherein, the core main points of this embodiment are:
1. and acquiring user action A and user evaluation data E by embedding points in the intelligent customer service system. Each input by the user is denoted as Ai and the evaluation made by the user is recorded as Ei.
2. The classifier is constructed using the user data with the user rating E as input sample data for a classification algorithm (e.g., SVM, KNN, etc.).
3. And deducing the user data without the user evaluation E by using the trained classifier, wherein the deduced result is the user evaluation E of the service.
4. After the user evaluation is inferred, the service data are aggregated to obtain a data set D { S1., Sn }, wherein Si { B1., Be }, Be ═ a 1., Ae }. And carrying out appropriate statistical analysis on the data set D to obtain the overall user evaluation of the intelligent customer service system. Such as rating star, etc.
Therefore, in the embodiment, a supervised learning mode is adopted, so that the data coverage of user evaluation is improved, the evaluation of other users is deduced according to the user behavior of the known user evaluation, and the purpose of analyzing the intelligent customer service through the user evaluation is achieved.
In addition, full-automatic processing is realized in the embodiment, manual evaluation is replaced by a machine, and the time for manual reading/marking is saved, so that the time cost and the labor cost are reduced. And the data coverage is strong, and through the intelligent inference mode, all data can be marked with user evaluation labels, so that the size of a data set used for analysis is enlarged, the quality of a data analysis set is improved, and the reliability of an analysis result is improved.
Meanwhile, the inferred evaluation result in the embodiment can reflect the real user intention. Therefore, subjective influence carried by artificial analysis is avoided, and meanwhile, compared with a mode of giving a default value, the method is closer to the actual situation, and distortion risk generated in the data recovery process is greatly reduced.
Specifically, as shown in the data trend in fig. 6, the intelligent customer service system in this embodiment may include the following processing flows:
firstly, relevant data (behavior data and evaluation data) are obtained by embedding points in an intelligent customer service system;
then, for data with user evaluation as a training sample, generating a classification model (algorithms such as decision tree, logistic regression, naive Bayes, neural network and the like can be used) corresponding to the user evaluation;
for data without user evaluation, executing the classification model to generate predicted user evaluation;
finally, the user's assessment (trueness, inference) data is integrated for statistical analysis.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A method of data processing, comprising:
after the customer service system outputs second data aiming at first data input by a target user, monitoring whether feedback data input by the target user is received or not, wherein the feedback data is used for describing the satisfaction degree of the target user on the second data;
if feedback data input by the target user are not received, generating evaluation data of the target user, wherein the evaluation data are used for simulating the feedback data;
summarizing the evaluation data and the feedback data, and performing statistical analysis to obtain the overall user evaluation of the customer service system;
further comprising:
obtaining user portrait information of the target user;
wherein after generating the ratings data for the target user, the method further comprises:
modifying the evaluation data of the target user by using the user portrait information to obtain modified evaluation data; or the like, or, alternatively,
obtaining product behavior data of the target user on a target product;
wherein after generating the ratings data for the target user, the method further comprises:
and modifying the evaluation data of the target user by using the product behavior data to obtain the modified evaluation data.
2. The method of claim 1, generating ratings data for the target user, comprising:
collecting user action data of the target user;
and processing the user action data to obtain the evaluation data of the target user.
3. The method according to claim 2, wherein the processing the user action data to obtain the evaluation data of the target user specifically comprises:
processing the user action data by using a classification model to obtain evaluation data of the target user;
wherein the classification model is generated by:
obtaining historical action data of at least one evaluated service in the customer service system and historical evaluation data corresponding to the historical action data;
and performing model training on the historical action data and the historical evaluation data by using a classification algorithm to obtain a classification model.
4. The method of claim 1 or 2, further comprising:
obtaining an output parameter when the customer service system outputs the second data;
wherein after generating the ratings data for the target user, the method further comprises:
and modifying the evaluation data of the target user by using the output parameters to obtain modified evaluation data.
5. The method of claim 3, further comprising:
and optimizing the classification model based on the user action data of the target user and the evaluation data of the target user.
6. The method of claim 3, further comprising:
and generating an overall evaluation result of the customer service system based on the evaluation data of the target user and the historical evaluation data.
7. A data processing apparatus comprising:
the data monitoring unit is used for monitoring whether feedback data input by a target user is received or not after a customer service system outputs second data aiming at first data input by the target user, wherein the feedback data are used for describing the satisfaction degree of the target user on the second data;
the evaluation generation unit is used for generating evaluation data of the target user if feedback data input by the target user is not received, and the evaluation data is used for simulating the feedback data;
summarizing the evaluation data and the feedback data, and performing statistical analysis to obtain the overall user evaluation of the customer service system;
further comprising:
obtaining user portrait information of the target user;
modifying the evaluation data of the target user by utilizing the user portrait information to obtain modified evaluation data; or the like, or, alternatively,
obtaining product behavior data of the target user on a target product;
and modifying the evaluation data of the target user by using the product behavior data to obtain the modified evaluation data.
8. An electronic device, comprising:
the customer service interaction equipment is used for receiving first data input by a target user and outputting second data aiming at the first data;
the evaluation processing equipment is used for monitoring whether feedback data input by the target user is received or not, the feedback data are used for describing the satisfaction degree of the target user on the second data, if the feedback data input by the target user are not received, evaluation data of the target user are generated, and the evaluation data are used for simulating the feedback data;
summarizing the evaluation data and the feedback data, and performing statistical analysis to obtain the overall user evaluation of the customer service system;
further comprising:
obtaining user portrait information of the target user;
modifying the evaluation data of the target user by utilizing the user portrait information to obtain modified evaluation data; or the like, or, alternatively,
obtaining product behavior data of the target user on a target product;
and modifying the evaluation data of the target user by using the product behavior data to obtain the modified evaluation data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910252933.2A CN109949103B (en) | 2019-03-29 | 2019-03-29 | Data processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910252933.2A CN109949103B (en) | 2019-03-29 | 2019-03-29 | Data processing method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109949103A CN109949103A (en) | 2019-06-28 |
| CN109949103B true CN109949103B (en) | 2021-10-22 |
Family
ID=67013112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910252933.2A Active CN109949103B (en) | 2019-03-29 | 2019-03-29 | Data processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109949103B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110929005A (en) * | 2019-10-18 | 2020-03-27 | 平安科技（深圳）有限公司 | Emotion analysis-based task follow-up method, device, equipment and storage medium |
| CN111046162A (en) * | 2019-12-23 | 2020-04-21 | 联想(北京)有限公司 | Information processing method and device and electronic equipment |
| CN111210232A (en) * | 2019-12-31 | 2020-05-29 | 联想(北京)有限公司 | Data processing method and device and electronic equipment |
| CN111881268A (en) * | 2020-05-25 | 2020-11-03 | 重庆兆光科技股份有限公司 | Consulting robot evaluation method, system and equipment based on user behavior sequence |
| CN112527978A (en) * | 2020-11-10 | 2021-03-19 | 联想(北京)有限公司 | Conversation processing method and equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081631A (en) * | 2009-11-30 | 2011-06-01 | 国际商业机器公司 | Answer support system and method |
| CN105808652A (en) * | 2016-02-26 | 2016-07-27 | 北京京东尚科信息技术有限公司 | Realization method and device of online customer services |
| CN107220353A (en) * | 2017-06-01 | 2017-09-29 | 深圳追科技有限公司 | A kind of intelligent customer service robot satisfaction automatic evaluation method and system |
| CN108074108A (en) * | 2017-11-02 | 2018-05-25 | 平安科技（深圳）有限公司 | A kind of display methods and its terminal of net recommendation |
| CN109241518A (en) * | 2017-07-11 | 2019-01-18 | 北京交通大学 | A kind of detection network navy method based on sentiment analysis |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103186555B (en) * | 2011-12-28 | 2016-05-11 | 腾讯科技（深圳）有限公司 | Evaluation information generates method and system |
| CN108133393A (en) * | 2017-12-28 | 2018-06-08 | 新智数字科技有限公司 | Data processing method and system |
| CN109409759B (en) * | 2018-11-06 | 2022-02-08 | 河南理工大学 | Data mining system and method based on coal mine safety training game |
-
2019
- 2019-03-29 CN CN201910252933.2A patent/CN109949103B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081631A (en) * | 2009-11-30 | 2011-06-01 | 国际商业机器公司 | Answer support system and method |
| CN105808652A (en) * | 2016-02-26 | 2016-07-27 | 北京京东尚科信息技术有限公司 | Realization method and device of online customer services |
| CN107220353A (en) * | 2017-06-01 | 2017-09-29 | 深圳追科技有限公司 | A kind of intelligent customer service robot satisfaction automatic evaluation method and system |
| CN109241518A (en) * | 2017-07-11 | 2019-01-18 | 北京交通大学 | A kind of detection network navy method based on sentiment analysis |
| CN108074108A (en) * | 2017-11-02 | 2018-05-25 | 平安科技（深圳）有限公司 | A kind of display methods and its terminal of net recommendation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109949103A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109949103B (en) | Data processing method and device and electronic equipment | |
| US11689663B2 (en) | Customer journey management | |
| US20210224832A1 (en) | Method and apparatus for predicting customer purchase intention, electronic device and medium | |
| CN108021934B (en) | Method and device for recognizing multiple elements | |
| CN109254669A (en) | A kind of expression picture input method, device, electronic equipment and system | |
| US20210035183A1 (en) | Method and system for a recommendation engine utilizing progressive labeling and user content enrichment | |
| CN108763251B (en) | Personalized recommendation method and device for nuclear product and electronic equipment | |
| CN109767290A (en) | Product method for pushing, device, computer equipment and storage medium | |
| CN111144906A (en) | Data processing method and device and electronic equipment | |
| CN110196805B (en) | Data processing method, data processing apparatus, storage medium, and electronic apparatus | |
| CN113157898A (en) | Method and device for recommending candidate questions, computer equipment and storage medium | |
| KR102152081B1 (en) | Valuation method based on deep-learning and apparatus thereof | |
| CN109241249B (en) | Method and device for determining burst problem | |
| CN112925924A (en) | Multimedia file recommendation method and device, electronic equipment and storage medium | |
| CN115713389A (en) | Financial product recommendation method and device | |
| Sutton et al. | A reinforcement learning and synthetic data approach to mobile notification management | |
| CN110163652B (en) | Guest-obtaining conversion rate estimation method and device and computer readable storage medium | |
| CN110020728B (en) | Service model reinforcement learning method and device | |
| JP6941590B2 (en) | Information processing equipment and information processing programs | |
| US20190288971A1 (en) | Method for Communication in a Communication Network | |
| CN117217852B (en) | Behavior recognition-based purchase willingness prediction method and device | |
| CN114005014B (en) | Model training and social interaction strategy optimization method | |
| US20230262160A1 (en) | Systems and methods for phishing monitoring | |
| CN115239068A (en) | Target task decision method and device, electronic equipment and storage medium | |
| CN117172876A (en) | Method and device for recommending articles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |