WO2020000875A1

WO2020000875A1 - Data processing method and electronic device

Info

Publication number: WO2020000875A1
Application number: PCT/CN2018/116169
Authority: WO
Inventors: 缪庆亮; 胡长建; 李杨
Original assignee: 联想(北京)有限公司
Priority date: 2018-06-28
Filing date: 2018-11-19
Publication date: 2020-01-02
Also published as: CN108876407B; CN108876407A

Abstract

Disclosed are a data processing method and an electronic device. The method comprises: acquiring user information of a first user when problem information sent by the first user is received; determining a first user tag cluster according to the user information of the first user; determining the first user tag cluster as a user tag cluster of the first user; and responding to the problem information sent by the first user according to parameters on the technical level of the first user tag cluster. By means of the solution, according to user information of a different user, a different user tag cluster corresponding to the user is determined so that the problem raised by each user is responded to according to parameters on the technical level corresponding to the user tag cluster of each user, and the targeted solution is achieved according to different professional levels of different users.

Description

Data processing method and electronic equipment

Technical field

The invention relates to the field of processing, in particular to a data processing method and an electronic device.

Background technique

In the customer service system, users enter the questions they want to ask through the customer service system, and the customer service answers according to the questions raised by the user.

However, due to the different technical levels of different users or the knowledge of product use, for customer service staff, some users' questions are easier to answer and some users have more complex questions; for users, the technical level is low or Users with less knowledge about product use need more detailed answers from customer service staff, while users with higher technical level or more knowledge about product use do not need more explanation from customer service staff.

In order to provide different users with targeted questions and answers, it is necessary to evaluate the technical level of different users.

Summary of the invention

In view of this, the present invention provides a data processing method and an electronic device to solve the problems raised by different users in the prior art and cannot provide targeted answers. The specific solutions are as follows:

A data processing method includes:

When the problem information sent by the first user is received, obtaining the user information of the first user;

Determining a first user tag cluster according to the user information of the first user, and determining the first user tag cluster as a user tag cluster of the first user;

Reply to the question information sent by the first user according to the technical level parameter of the first user tag cluster.

Further, determining the first user tag cluster according to the user information of the first user includes:

Find a user relationship graph, the user relationship graph includes: no less than two users and similarity between each two users;

When the first user is included in the user relationship graph, a first user label cluster of the first user is determined according to a user label cluster of an initial user in the user relationship graph.

Determine the similarity ranking of the first user and the first number of user tag clusters according to the user information of the first user;

The first user tag cluster is determined according to the similarity.

Further, determining the first user tag cluster of the first user according to the user tag cluster of the initial user in the user relationship graph includes:

Determining an initial user from no less than two users in the user relationship graph, and setting a user tag cluster for the initial user;

According to the similarity between each two users in the user relationship graph and an iterative function, a user tag cluster of other users except the initial user in the user relationship graph is determined.

Further, determining the initial user from no less than two users in the user relationship diagram includes:

Setting a problem cluster for the problem information sent by each of the two or more users in the user relationship graph;

Determine the proportion of the number of people in each question cluster, where the proportion of the number of people in the question cluster is: the number of users corresponding to the questions under each question cluster and the questions The ratio of the number of corresponding users;

Determining the initial number of users corresponding to each problem cluster according to the proportion of the number of people in each problem cluster;

An initial user is determined according to the number of initial users corresponding to each question cluster.

Further, it also includes:

Receiving the question information sent by the first user, and determining whether other question information is received within the first time interval when the question information is received;

When other question information is received within the first time interval of receiving the question information, the question information is combined with other question information.

An electronic device includes a processor and a memory, wherein:

The memory is configured to store a user tag cluster and a technical level parameter corresponding to the user tag cluster;

The processor is configured to obtain user information of the first user when receiving the question information sent by the first user, determine a first user tag cluster according to the user information of the first user, and group the first user The tag cluster is determined as the user tag cluster of the first user, and the question information sent by the first user is returned according to the technical level parameter of the first user tag cluster.

Further, the determining, by the processor according to the user information of the first user, a first user tag cluster includes:

The processor searches for a user relationship graph, and the user relationship graph includes: no less than two users and a similarity between each two users, and when the user relationship graph includes the first user, according to the The user tag cluster of the initial user in the user relationship graph determines the first user tag cluster of the first user.

The processor determines the similarity ranking of the first user and the first number of user tag clusters according to the user information of the first user, and determines the first user tag cluster according to the similarity.

Further, the determining, by the processor according to the user tag cluster of the initial user in the user relationship graph, the first user tag cluster of the first user includes:

The processor determines an initial user from no less than two users in the user relationship diagram, sets a user tag cluster for the initial user, and according to the similarity between every two users in the user relationship diagram And an iterative function to determine a user tag cluster of other users in the user relationship graph other than the initial user among the two or more users.

As can be seen from the above technical solution, the data processing method and electronic device disclosed in this application, when receiving the question information sent by the first user, obtain the user information of the first user, and determine the first user according to the user information of the first user Tag clustering, determines the first user tag cluster as the user tag cluster of the first user, and responds to the question information sent by the first user according to the technical level parameters of the first user tag cluster. This solution determines different user tag clusters corresponding to the user according to the user information of different users, thereby achieving the reply to the questions raised by the technical level parameters corresponding to the user tag clusters of each user, and achieving the realization according to different users. Different professional levels for targeted answers.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly explain the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without paying creative labor.

FIG. 1 is a flowchart of a data processing method disclosed by an embodiment of the present invention;

2 is a flowchart of a data processing method disclosed by an embodiment of the present invention;

3 is a flowchart of a data processing method disclosed by an embodiment of the present invention;

4 is a flowchart of a data processing method disclosed by an embodiment of the present invention;

5 is a flowchart of a data processing method disclosed by an embodiment of the present invention;

FIG. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

detailed description

In the following, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. It is apparent, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted to avoid unnecessarily obscuring the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the present disclosure. As used herein, the terms "including", "comprising", and the like indicate the presence of stated features, steps, operations, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted to have meanings consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

Where expressions such as "at least one of A, B, C, etc." are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "having A, B, and C "A system of at least one of" shall include, but is not limited to, a system with A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc. ). Where expressions such as "at least one of A, B, or C" are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "having A, B, or C "A system of at least one of" shall include, but is not limited to, a system with A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc. ).

Some block diagrams and / or flowcharts are shown in the drawings. It should be understood that some blocks or combinations of block diagrams and / or flowcharts may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing device, so that when executed by the processor, these instructions may be created to implement the functions illustrated in the block diagrams and / or flowcharts / Operating device. The techniques of this disclosure may be implemented in the form of hardware and / or software (including firmware, microcode, etc.). In addition, the techniques of this disclosure may take the form of a computer program product on a computer-readable storage medium storing instructions, which computer program product may be used by or in conjunction with an instruction execution system.

The invention discloses a data processing method. The flowchart is shown in FIG. 1 and includes:

Step S11: When the problem information sent by the first user is received, the user information of the first user is acquired;

In a customer service system or a webpage or forum, when a user asks a question, the user asking the question can be logged in. When the user sends a question, the user's user information can be obtained from the account that the user logs in to.

The user information may be personal information filled in by the user when registering or supplementing the logged-in account, and may also be information such as questions or speeches previously issued by the account in which the user is logged in.

For example: In the customer service system, the user sends a question to the customer service. Before the user sends the problem, the user can first log in to the account, after logging in, send the problem to the customer service, and then the customer service system obtains the user's user from the account. Information, such as: age, how long the product has been used, the number of products used, questions the user has asked, etc.

Step S12: Determine a first user tag cluster according to the user information of the first user, and determine the first user tag cluster as a user tag cluster of the first user;

In the embodiment of the present invention, multiple user tag clusters can be set in advance, different user tag clusters correspond to different technical level parameters, and the user's technical level in the corresponding user tag cluster is represented by different technical level parameters.

For example: three user tag clusters are set in advance, which are the first user tag cluster, the second user tag cluster, and the third user tag cluster. The first user tag cluster corresponds to a high level of technology, and the technical level parameters can be 1; in the technical level corresponding to the second user tag cluster, the technical level parameter may be 2; the third user tag cluster corresponds to a low technical level, and the technical level parameter may be 3.

Determining the first user tag cluster according to the user information of the first user may be specifically: comprehensively evaluating the user tag cluster of the user according to the multiple user information corresponding to the first user.

For example, the product the user consulted is an electronic product, the user is 30 years old, and the user has been using the electronic product for 3 years, and the user has asked professional questions that are more professional. Since young people have a better understanding of electronic products, and have been using the electronic products for 3 years, the questions they have asked are also more professional. Then, it can be determined from this that the user tag to which the user belongs is clustered as the first user tag. Clustering, high technical level;

If the product the user consults is an electronic product, the user is 65 years old, and the user has used the electronic product for 3 months. Since the elderly know less about the electronic product and use the electronic product for a shorter time, this can be It is determined that the user tag cluster to which the user belongs is a third user tag cluster, and the technical level is low.

In the data processing method disclosed in this embodiment, the user tag cluster of the user may also be determined by other methods, which is not specifically limited herein.

Step S13: Reply to the question information sent by the first user according to the technical level parameters of the first user tag clustering.

Since different user tag clusters correspond to different technical level parameters, the technical level of users belonging to the corresponding user tag cluster can be determined according to different technical level parameters. Then, according to the different technical levels of different users, they respond to their suggestions. The problem.

Different technical level parameters correspond to different ways of answering questions. For example, for users with low technical level, when replying to their questions, use simple language, minimize professional terms, and reply longer; for high technical level Users can use more specialized terminology when replying to their questions, and the reply content is mainly short.

In the data processing method disclosed in this embodiment, when the problem information sent by the first user is received, the user information of the first user is acquired, the first user tag cluster is determined according to the first user user information, and the first user tags are clustered. The class is determined as the user tag cluster of the first user, and the question information sent by the first user is returned according to the technical level parameters of the first user tag cluster. This solution determines different user tag clusters corresponding to the user according to the user information of different users, thereby achieving the reply to the questions raised by the technical level parameters corresponding to the user tag clusters of each user, and achieving the realization according to different users. Different professional levels for targeted answers.

This embodiment discloses a data processing method. The flowchart is shown in FIG. 2 and includes:

Step S21: When the problem information sent by the first user is received, the user information of the first user is acquired;

Step S22. Finding a user relationship graph, the user relationship graph includes: no less than two users and similarity between each two users;

A user relationship graph is stored in advance, and the user relationship graph includes: no less than two users, and a similarity between each two users.

Specifically, constructing a user relationship graph requires first extracting user features and calculating feature values, and then constructing a user and feature matrix.

Extracting user features can be specifically: extracting predefined user features and question features, as shown in Table 1 user feature description and Table 2 user question feature description:

Table 1

用户特征名称User Feature Name	特征值Eigenvalues	特征说明Feature description
用户年龄User age	整数值Integer value	根据用户注册时填的信息估算出年龄Estimate the age based on the information provided when the user registered
用户使用手机数Number of mobile phones used by users	整数值Integer value	用户购买手机的次数Number of times a user bought a phone
用户使用手机时间跨度User use phone time span	整数值Integer value	用户第一次购买手机到问问题的时间间隔Time interval between the user's first purchase of the mobile phone and the question

Table 2

用户问题特征名称User Issue Feature Name	特征值Eigenvalues	特征说明Feature description
用户问题中专业词频率Frequency of professional words in user questions	整数值Integer value	用户历史问题中专业词汇出现的频率Frequency of professional vocabulary in user history issues
用户问题的代表性Representation of user questions	整数值Integer value	用户问题所在聚类的样本数Number of samples in the cluster where the user problem is located
用户问题答案详细程度User question answer level of detail	整数值Integer value	用户问题对应答案的字符数Number of characters for answer to user question
用户问题数User Questions	整数值Integer value	用户历史问题数量Number of user history issues
用户对话时间User conversation time	整数值Integer value	用户对话平均耗时User conversations take an average of time
用户交互轮数User interaction rounds	整数值Integer value	用户与客服人员交互的轮数Number of rounds of user interaction with customer service staff

Among them, Table 1 includes: the name, feature value, and feature description of the user ’s characteristics. For example, when the question sent by the user in the customer service system is a consultation for a mobile phone, and the user ’s characteristic is the user ’s age, it is based on the user ’s registration. The information is the estimated age; when the user is specifically the number of mobile phones used by the user, it is determined based on the number of times the user has purchased the mobile phone; the user characteristic is the time span of the user ’s mobile phone, which is based on the user ’s first purchase of the mobile phone to the current question The time interval is determined.

Table 2 includes: the name, feature value, and feature description of the user ’s question feature. For example, when the question sent by the user in the customer service system is a consultation for a mobile phone, the feature of the user question is the professional word frequency in the user question, which is based on The frequency of professional vocabulary in user history questions is determined; the user question feature is the representativeness of the user question, which is determined based on the number of samples in the cluster where the user question is located; the user question feature is the detail level of the user question answer, which is based on the user The number of characters for the answer to the question is determined; the feature of the user question is the number of user questions, which is determined based on the number of historical user questions; the feature of the user question is the user's dialogue time, which is based on the average of the user's historical question dialogue in the customer service system It takes time to determine; the user problem is characterized by the number of user interaction rounds, which is determined according to the number of user interactions with the customer service in the historical problems in the customer service system.

A user and feature matrix M is constructed, each row of the matrix represents a user, each column of the matrix represents a one-dimensional feature, and then each column is normalized.

Assume that the user relationship graph G is fully linked:

User relationship graph G is composed of user U and user similarity, where G's nodes are users and edges are similarity between users. Define a node V _i = <U _i , Q _i >, where V _i is the first i nodes, the _U-i for the user information portion of the V _i, Q _i V _i as part of the user problems, the edges between nodes represent similarity node. The calculation method of the similarity between the nodes V _i = <U _i , Q _i > and V _j = <U _j , Q _j > is as follows:

sim (V _i , V _j ) = αsim (u _i , U _j ) + (1-α) sim (Q _i , Q _j ) Formula (1)

Among them, U _i , U _j , Q _i , and Q _j in the formulae (1), (2), and (3) are normalized characteristic values, and δ and γ are constants.

After the above steps, the user relationship graph can be constructed.

Step S23: When the first user is included in the user relationship graph, determine the first user label cluster of the first user according to the user label cluster of the initial user in the user relationship graph;

When the users in the user relationship graph constructed in the above steps include the first user, that is, the user who sent the question information, directly determine the first user of the first user according to the user tag cluster of the initial user in the user relationship graph. Label clustering.

Specifically, an initial user is determined from not less than two users in the user relationship graph, a user tag cluster is set for the initial user, and the user relationship is determined based on the similarity between each two users in the user relationship graph and the iterative function. In the figure, the user tag cluster of other users except the initial user among two users is clustered.

When the user tag clusters of all users in the user relationship graph have been determined, then the user tag cluster to which the first user belongs in the user relationship graph has also been determined.

Further, determining the user tag clustering of users other than the initial user among the two or more users in the user relationship graph according to the similarity between each two users in the user relationship graph and the iterative function may be specifically:

Let n * n matrix M be the edge weight matrix of the user relationship graph G. The element m _ij in the matrix represents the similarity of the nodes r _i and r _j . Then, each row vector of M is normalized to obtain the matrix M ′. Each element in M ′ is calculated by formula (4), so that the sum of terms in each row vector of M ′ is 1.

The category information vector is set for the nodes in the graph, and the small category vector for the initial label category node setter is: v = (0, ..., 1 _t , ..., 0) _n .

Take n = 2 as an example:

For a labeled node, let its class vector be v = (0, ..., 1 _t , ..., 0) _n , the t-th dimension of the vector is 1, and the remaining latitudes are 0. In step k + 1, the class vector v of each class node r is rewritten as v _{k + 1} = M′v _k .

During the class diffusion process, after the class vector of each node is updated iteratively, the class vector of the node with the initial labeled category will be restored to the initial set vector to make it consistent with the labeled category. For other unlabeled nodes, when After the i-th iteration, calculate the cosine similarity sim (v _i , v _{i + 1} ) of the two class vectors before and after the iteration of the node, and record the impact of the i-th iteration on the node as impact (v _i ) = 1-sim (v _i , v _{i + 1} ).

Use the average influence degree of all nodes after the i-th iteration average_impact (i) as the criterion of whether the class diffusion is balanced:

If the average influence degree of the node after the i-th iteration is less than a certain threshold, it is considered that the diffusion has reached equilibrium, and the class diffusion process of the iteration is terminated.

When the diffusion reaches equilibrium, the category information vector v = (p (c ₁ ), p (c ₂ ), ..., p (c _n )) _n of each node r in the graph is taken as the largest of the relation category vectors. The category corresponding to the dimension is the category of the relationship pair, and type (v) = argmaxp (c _i ).

Among them, different categories are different levels of technology.

Step S24: Reply to the question information sent by the first user according to the technical level parameters of the first user tag clustering.

This embodiment discloses a data processing method. A flowchart of the method is shown in FIG. 3 and includes:

Step S31: When the question information sent by the first user is received, the user information of the first user is obtained;

Step S32. Find a user relationship graph. The user relationship graph includes: no less than two users and the similarity between each two users;

Step S33. When the first user is included in the user relationship diagram, issue clusters are set for the problem information sent by each of the two or more users in the user relationship diagram.

Step S34: Determine the proportion of the number of people in each question cluster, where the proportion of the number of people in the question cluster is: the number of users corresponding to the questions under each question cluster and all the questions under all question clusters The ratio of the number of corresponding users;

Step S35: Determine the initial number of users corresponding to each question cluster according to the proportion of the number of people in each question cluster;

Step S36: Determine an initial user according to the number of initial users corresponding to each question cluster, and set a user tag cluster for the initial user;

Set up question clusters for all questions raised by all users in the user relationship graph, and each question cluster corresponds to no less than one question.

For example: set 5 problem clusters, the first problem cluster includes 100 questions, the second problem cluster includes 300 questions, the third problem cluster includes 200 questions, and the fourth problem cluster There are 400 questions under the category, and 500 questions under the fifth question cluster.

Under each problem cluster, one question corresponds to one user. Then, 100 questions under the first problem cluster correspond to 100 users, that is, 100 users have asked questions that belong to the first problem cluster; The 300 questions under the second question cluster correspond to 300 users, that is, 300 users have raised questions that belong to the second question cluster.

Determine the proportion of the number of people in each question cluster, that is, the ratio of the number of users corresponding to the questions under each question cluster and the number of users corresponding to all the questions under all question clusters, where all questions are asked The number of users corresponding to all the questions in the cluster, that is, a total of 1500 questions in 5 question clusters, corresponding to 1500 users, then the proportion of the number of people in the first question cluster is: 100/1500, which is 1 / 15; the proportion of the number of people in the second question cluster is: 300/1500, which is 3/15; the proportion of the number of people in the third question cluster: 200/1500, which is 2/15; the fourth question The proportion of the number of people in the cluster is: 400/1500, which is 4/15; the proportion of the number of people in the fifth problem cluster is: 500/1500, which is 5/15.

Determine the number of initial users corresponding to each question cluster according to the proportion of the number of people in each question cluster, that is, the proportion of the number of people in the first question cluster is 1/15. Then, among all the initial users, The number of users extracted from the first problem cluster accounts for 1/15 of the total number of initial users. That is, if there are 15 initial users in total, then a user is selected as the initial user from the first problem cluster. Three users are selected as initial users in the second problem cluster, two users are selected as initial users in the third problem cluster, and four users are selected as initial users in the fourth problem cluster. Five users are selected as the initial users in this problem cluster. That is, the number of initial users extracted in each problem cluster is related to the proportion of the number of people in the problem cluster to the number of people in all problem clusters, and is directly proportional.

Step S37: Determine user tag clusters of users other than the initial user among not less than two users in the user relationship graph according to the similarity between each two users in the user relationship graph and the iterative function;

Step S38: Reply to the question information sent by the first user according to the technical level parameter of the first user tag cluster corresponding to the first user.

This embodiment discloses a data processing method. The flowchart is shown in FIG. 4 and includes:

Step S41: When the problem information sent by the first user is received, the user information of the first user is acquired;

Step S42: Determine the similarity ranking of the first user and the first number of user tag clusters according to the user information of the first user;

Step S43: Determine the first user tag cluster according to the similarity, and determine the first user tag cluster as the user tag cluster of the first user;

A first number of user tag clusters are set in advance, and the first number of user tag clusters are set according to user characteristics.

When the question information sent by the first user is received, the similarity ranking of the first user and the first number of user tag clusters is determined according to the user information of the first user.

That is, the user characteristics of the first user are determined according to the user information of the first user, the similarity between the user characteristics of the first user and each user tag cluster in the plurality of user tag clusters is determined, and the multiple similarities are ranked to determine The similarity between the user characteristics of the first user and each of the user tag clusters in the multiple user tag clusters, selecting the user tag cluster with the highest similarity, and determining the user tag cluster as the first user tag cluster, That is, the user tag clustering of the first user.

For example: 5 user tag clusters are set in advance. When the user characteristics of the first user are similar to the 5 user tag clusters, the behavior is ranked as follows: C user tag clustering → D user tag clustering → A user tag clustering → E user tag clustering → B user tag clustering, then, among the user features with the highest similarity to the first user, the C user tag clustering, the lowest similarity is the B user tag clustering, and the C user tag clustering It is set as the first user tag cluster, that is, the C user tag cluster is determined as the user tag cluster of the first user.

Further, it is also possible to directly select the user tag cluster with the highest similarity to the user characteristics of the first user, and determine it as the user tag cluster of the first user, without ranking the similarities.

Further, the interval is fixed, and the user tag cluster is reset according to the user characteristics of all users. That is, when the number of users who ask questions increases, the user base in the user tag cluster increases. The user characteristics of all users determine the new user tag cluster.

Step S44: Reply to the question information sent by the first user according to the technical level parameters of the first user tag clustering.

In the data processing method disclosed in this embodiment, when the problem information sent by the first user is received, the user information of the first user is acquired, the first user tag cluster is determined according to the user information of the first user, and the first user tags are clustered. The class is determined as the user tag cluster of the first user, and the question information sent by the first user is returned according to the technical level parameters of the first user tag cluster. This solution determines different user tag clusters corresponding to the user according to the user information of different users, thereby achieving the reply to the questions raised by the technical level parameters corresponding to the user tag clusters of each user, and achieving the realization according to different users. Different professional levels for targeted answers.

This embodiment discloses a data processing method. The flowchart is shown in FIG. 5 and includes:

Step S51: When receiving the question information sent by the first user, determine whether other question information is received within the first time interval when the question information is received;

Step S52: When other problem information is received within the first time interval of receiving the problem information, the problem information is combined with other problem information;

When receiving the question information sent by the first user, it is first determined whether other question information is received within the first time interval in which the question information is received, where the first time interval may be: the moment when the question information is received If the first predetermined time period before and the second predetermined time period after the time when the problem information is received, if other problem information is also received within the first time interval, the problem information is merged with other problem information, so that the problem can be unified. The user does not need to reply multiple times, or when the user divides a question into multiple questions, it will not cause the problem to be unclear.

Further, it may be: filtering out information that the length of the question information sent by the user is less than the first threshold, such as greetings, greetings, and other information, such as Hi, Hello, and the like.

Step S53: Acquire user information of the first user.

Step S54: Determine the first user tag cluster according to the user information of the first user, and determine the first user tag cluster as the user tag cluster of the first user;

Step S55: Reply to the combined question information sent by the first user according to the technical level parameters of the first user tag clustering.

In the data processing method disclosed in this embodiment, when the problem information sent by the first user is received, the user information of the first user is acquired, the first user tag cluster is determined according to the first user user information, and the first user tags are clustered The class is determined as the user tag cluster of the first user, and the question information sent by the first user is returned according to the technical level parameters of the first user tag cluster. This solution determines different user tag clusters corresponding to the user according to the user information of different users, thereby achieving the reply to the questions raised by the technical level parameters corresponding to the user tag clusters of each user, and achieving the realization according to different users. Different professional levels for targeted answers.

This embodiment discloses an electronic device. The structure diagram is shown in FIG. 6 and includes:

The processor 61 and the memory 62.

The memory 62 is configured to store user tag clusters and technical level parameters corresponding to the user tag clusters.

The processor 61 is configured to obtain user information of the first user when receiving the question information sent by the first user, determine the first user tag cluster according to the user information of the first user, and determine the first user tag cluster as the first The user tag clustering of a user responds to the question information sent by the first user according to the technical level parameters of the first user tag clustering.

The processor 61 determining the first user tag cluster according to the user information of the first user includes:

The processor is used to find the user relationship graph. The user relationship graph includes: no less than two users and the similarity between each two users. When the user relationship graph includes the first user, according to the user label of the initial user in the user relationship graph The clustering determines a first user tag cluster of the first user.

A user relationship graph is stored in advance, and the user relationship graph is: no less than two users, and the similarity between each two users.

Table 1

Table 2

Assume that the user relationship graph G is fully linked:

After the above steps, the user relationship graph can be constructed.

Take n = 2 as an example:

Among them, different categories are different levels of technology.

The processor 61 determines the initial user from no less than two users in the user relationship diagram, including:

The processor is configured to set a problem cluster for the problem information sent by each of the users in the user relationship graph, and determine the proportion of the number of people in each problem cluster, of which the number of people in the problem cluster The ratio is: the ratio of the number of users corresponding to the questions under each question cluster to the number of users corresponding to all the questions under all question clusters, and each question cluster is determined according to the proportion of the number of people in each question cluster The number of initial users corresponding to the class is determined according to the number of initial users corresponding to each problem cluster.

The processor 61 is further configured to receive the question information sent by the first user, and determine whether other question information is received within the first time interval during which the question information is received. For other problem information, merge the problem information with other problem information.

The electronic device disclosed in this embodiment includes a memory and a processor. The processor is configured to obtain the user information of the first user when the problem information sent by the first user is received, and determine the first user tag group according to the user information of the first user. Class, determining the first user tag cluster as the user tag cluster of the first user, and replying to the question information sent by the first user according to the technical level parameters of the first user tag cluster. This solution determines different user tag clusters corresponding to the user according to the user information of different users, thereby achieving the reply to the questions raised by the technical level parameters corresponding to the user tag clusters of each user, and achieving the realization according to different users. Different professional levels for targeted answers.

According to an embodiment of the present invention, the processor 61 may include, for example, a general-purpose microprocessor, an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), and so on. The processor 61 may also include on-board memory for caching purposes. The memory 62 may be, for example, a non-volatile computer-readable storage medium, and specific examples include, but are not limited to: a magnetic storage device such as a magnetic tape or a hard disk (HDD); an optical storage device such as a compact disc (CD-ROM); a memory such as Random Access Memory (RAM) or Flash; etc.

The embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same and similar parts between the embodiments, refer to each other. As for the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant part may refer to the description of the method.

Professionals may further realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the hardware and software, Interchangeability. In the above description, the composition and steps of each example have been described generally in terms of functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

The steps of the method or algorithm described in connection with the embodiments disclosed herein may be directly implemented by hardware, a software module executed by a processor, or a combination of the two. Software modules can be placed in random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or in technical fields Any other form of storage medium is known.

The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention will not be limited to the embodiments shown herein, but shall conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

A data processing method, comprising:

When the problem information sent by the first user is received, obtaining the user information of the first user;

Determining a first user tag cluster according to the user information of the first user, and determining the first user tag cluster as a user tag cluster of the first user;

Reply to the question information sent by the first user according to the technical level parameter of the first user tag cluster.
The method according to claim 1, wherein determining the first user tag cluster according to the user information of the first user comprises:

Find a user relationship graph, the user relationship graph includes: no less than two users and similarity between each two users;

When the first user is included in the user relationship graph, a first user label cluster of the first user is determined according to a user label cluster of an initial user in the user relationship graph.
The method according to claim 1, wherein determining the first user tag cluster according to the user information of the first user comprises:

Determine the similarity ranking of the first user and the first number of user tag clusters according to the user information of the first user;

The first user tag cluster is determined according to the similarity.
The method according to claim 2, wherein the determining a first user tag cluster of the first user according to a user tag cluster of an initial user in the user relationship graph comprises:

Determining an initial user from no less than two users in the user relationship graph, and setting a user tag cluster for the initial user;

According to the similarity between each two users in the user relationship graph and an iterative function, a user tag cluster of other users except the initial user in the user relationship graph is determined.
The method according to claim 4, wherein the determining an initial user from no less than two users in the user relationship graph comprises:

Setting a problem cluster for the problem information sent by each of the two or more users in the user relationship graph;

Determine the proportion of the number of people in each question cluster, where the proportion of the number of people in the question cluster is: the number of users corresponding to the questions under each question cluster and the questions The ratio of the number of corresponding users;

Determining the initial number of users corresponding to each problem cluster according to the proportion of the number of people in each problem cluster;

An initial user is determined according to the number of initial users corresponding to each question cluster.
The method according to claim 1, further comprising:

Receiving the question information sent by the first user, and determining whether other question information is received within the first time interval when the question information is received;

When other question information is received within the first time interval of receiving the question information, the question information is combined with other question information.
An electronic device, comprising: a processor and a memory, wherein:

The memory is configured to store a user tag cluster and a technical level parameter corresponding to the user tag cluster;

The processor is configured to obtain user information of the first user when receiving the question information sent by the first user, determine a first user tag cluster according to the user information of the first user, and group the first user The tag cluster is determined as the user tag cluster of the first user, and the question information sent by the first user is returned according to the technical level parameter of the first user tag cluster.
The electronic device according to claim 7, wherein the processor determining the first user tag cluster according to the user information of the first user comprises:

The processor searches for a user relationship graph, and the user relationship graph includes: no less than two users and a similarity between each two users, and when the user relationship graph includes the first user, according to the The user tag cluster of the initial user in the user relationship graph determines the first user tag cluster of the first user.
The electronic device according to claim 7, wherein the processor determining the first user tag cluster according to the user information of the first user comprises:

The processor determines the similarity ranking of the first user and the first number of user tag clusters according to the user information of the first user, and determines the first user tag cluster according to the similarity.
The electronic device according to claim 8, wherein the determining the first user tag cluster of the first user according to the user tag cluster of the initial user in the user relationship graph comprises:

The processor determines an initial user from no less than two users in the user relationship diagram, sets a user tag cluster for the initial user, and according to the similarity between every two users in the user relationship diagram And an iterative function to determine a user tag cluster of other users in the user relationship graph other than the initial user among the two or more users.