CN115409017A

CN115409017A - Customer service communication text mining method and system, electronic equipment and storage medium

Info

Publication number: CN115409017A
Application number: CN202211070682.4A
Authority: CN
Inventors: 轩琪
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2022-09-02
Filing date: 2022-09-02
Publication date: 2022-11-29

Abstract

The invention provides a customer service communication text mining method and system, electronic equipment and a storage medium, which can be applied to the fields of artificial intelligence, block chain, distribution, cloud computing, big data, internet of things, mobile interconnection, network security, chips and finance. The method comprises the following steps: extracting text information in the customer service communication; performing text data processing and text characteristic analysis on the text information; performing emotion classification analysis and theme mining on the text subjected to text data processing and text feature analysis to obtain a user attention point; according to the user concern, emotion polarity analysis is carried out, and a satisfaction index system is constructed to obtain user satisfaction; therefore, the method and the system can help commercial banks to more intuitively know the evaluation of the customers on the products released by the banks and the service provided by the banks, can further know the demands and the preferences of the customers, and can further reflect the main focus of the customers when the customers communicate with customer service staff.

Description

Customer service communication text mining method and system, electronic equipment and storage medium

Technical Field

The invention belongs to the technical field of data analysis, and particularly relates to a method and a system for mining a customer service communication text, electronic equipment and a storage medium.

Background

At present, a customer service system of a commercial bank mainly uses character communication, voice dialing and video to realize the communication of telephone and video between customer service and a client; language information included in the communication between the client and the commercial bank can be mined.

In the prior art, manual processing judgment is adopted mostly, or systematic processing is not carried out on text information exchanged by customer service, so that the prior art is not perfect and comprehensive enough, and can not deeply mine the emotional tendency of customers and the satisfaction degree of releasing products or services for commercial banks.

Disclosure of Invention

In view of this, the present invention provides a method and a system for mining a text of a customer service communication, an electronic device, and a storage medium, which are used to help a commercial bank to more intuitively understand the evaluation of a customer on the product release and service provision of the bank.

The application discloses a first aspect of a customer service communication text mining method, which comprises the following steps:

extracting text information in the customer service communication;

performing text data processing and text characteristic analysis on the text information;

performing emotion classification analysis and theme mining on the text subjected to the text data processing and the text feature analysis to obtain a user concern;

and analyzing emotion polarity according to the user concern, and constructing a satisfaction index system to obtain the user satisfaction.

Optionally, in the method for mining a customer service communication text, the extracting text information in the customer service communication includes:

and converting the audio information exchanged between the customer service and the customer into text information.

Optionally, in the method for mining a customer service communication text, performing text data processing and text feature analysis on the text information includes:

performing data cleaning and word segmentation on the text information;

extracting high-frequency characteristic words of the text information after data cleaning and word segmentation, and analyzing main factors influencing emotion polarity.

Optionally, in the method for mining a customer service communication text, after performing data cleaning and word segmentation on the text information, the method further includes:

and performing visual display on the processed text information through the word frequency cloud picture and the semantic network.

Optionally, in the method for mining a customer service communication text, performing emotion classification analysis and topic mining on the text subjected to the text data processing and the text feature analysis to obtain a user focus point includes:

classifying and evaluating the emotional tendency of the text after the text data processing and the text feature analysis are carried out based on an emotional dictionary method;

and mining the theme in the customer service communication text by using an LDA model according to the classification and evaluation results to obtain the user attention point.

Optionally, in the method for mining the customer service communication text, emotion polarity analysis is performed according to the user concern, and a satisfaction index system is constructed to obtain the user satisfaction, where the method includes:

matching emotion short sentences according to the parts of speech corresponding to the user concern points;

calculating the sentiment value of the short sentence by adopting a sentiment dictionary method for the sentiment short sentence;

selecting feature words with important attributes according to the result of the high-frequency words;

clustering the word vectors of the feature words, and determining a satisfaction index of customer service communication;

and determining the weight of the customer satisfaction index according to the emotion short sentence occupation ratios and short sentence emotion values corresponding to different indexes, and analyzing and calculating the satisfaction condition to obtain the user satisfaction.

The second aspect of the present application discloses a customer service communication text mining system, including:

the extraction module is used for extracting the text information in the customer service communication;

the processing and analyzing module is used for performing text data processing and text characteristic analysis on the text information;

the emotion analysis module is used for carrying out emotion classification analysis on the text subjected to the text data processing and the text characteristic analysis to obtain an analysis result;

the theme mining module is used for continuing theme mining according to the analysis result to obtain a user concern;

and the satisfaction degree module is used for carrying out emotion polarity analysis according to the user concern points and constructing a satisfaction degree index system to obtain the user satisfaction degree.

Optionally, in the above system for text mining of customer service communication, when the extracting module is used to extract text information in customer service communication, the extracting module is specifically configured to:

A third aspect of the present application discloses an electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of customer interaction text mining as recited in any of the first aspects of the present application.

A fourth aspect of the present application discloses a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the customer service interaction text mining method according to any one of the first aspects of the present application.

According to the technical scheme, the method for mining the customer service communication text, provided by the invention, comprises the following steps: extracting text information in the customer service communication; performing text data processing and text characteristic analysis on the text information; performing emotion classification analysis and theme mining on the text subjected to text data processing and text feature analysis to obtain a user concern; according to the user concern, emotion polarity analysis is carried out, and a satisfaction index system is constructed to obtain user satisfaction; therefore, the method can help the commercial bank to more intuitively know the evaluation of the customer on the product release and service provision of the bank, can more deeply know the demand and the preference of the customer, and can further reflect the mainstream focus of the customer when the customer communicates with customer service staff, so that the product and the service are perfected and improved according to the evaluation of the customer, and the method has advantages in market competition.

Drawings

In order to more clearly illustrate 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, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a flowchart of a method for mining a customer service communication text according to an embodiment of the present invention;

FIG. 2 is a flowchart of another method for text mining for customer service interaction according to an embodiment of the present invention;

FIG. 3 is a flow chart of another method for mining customer service interaction text provided by an embodiment of the invention;

FIG. 4 is a flow chart of another method for mining customer service interaction text provided by an embodiment of the invention;

FIG. 5 is a flow chart of another method for mining customer service interaction text provided by an embodiment of the invention;

FIG. 6 is a flow chart of another method for mining customer service interaction text provided by an embodiment of the present invention;

FIG. 7 is a schematic diagram of a customer service interaction text mining system according to an embodiment of the present invention;

fig. 8 is a schematic diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.

In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.

The embodiment of the application provides a customer service communication text mining method, which is used for solving the problems that in the prior art, manual processing judgment is performed, or systematic processing is not performed on text information of customer service communication, the text mining method is not complete and comprehensive enough, and the emotional tendency of a customer and the satisfaction degree of pushing out products or services for a commercial bank cannot be deeply mined.

Referring to fig. 1, the customer service communication text mining method includes:

s101, extracting text information in the customer service communication.

It should be noted that the text to be exchanged may be extracted from the information input by the client.

For example, the customer and the customer service communicate with each other through voice, and the voice can be converted into text information. The communication between the client and the customer service is performed by text communication, and the communication text can be used as the text information.

That is to say, the text information may be unstructured text information, and certainly, the text information is also excluded as structured text information, which is not described herein any more, and is within the protection scope of the present application depending on the actual situation.

Specifically, the collecting text information of a customer service system of a commercial bank includes: the text information is extracted from the audio and video information for realizing telephone and video communication between the customer service and the client by using the pure text information of character communication and voice dialing and video.

And S102, performing text data processing and text characteristic analysis on the text information.

It should be noted that the text data processing may be processing such as analysis and filtering, and certainly is not limited to the example here, and the specific process of the text data processing is not described herein any more, and may be determined according to the actual situation, and all of them are within the protection scope of the present application.

The text feature analysis may be high-frequency vocabulary, emotion polarity analysis, and the like, and is not limited to the examples herein, and the specific process of the text feature analysis is not described herein any more, and may be determined according to the actual situation, all of which are within the scope of the present application.

And S103, performing emotion classification analysis and theme mining on the text subjected to text data processing and text feature analysis to obtain the user attention point.

The emotion classification analysis can be used for determining the emotion type of the corresponding text, for example, the emotion type of the text can be positive such as happy and happy, and the emotion type of the text can also be negative such as negative and impatient.

The specific process of emotion classification analysis is not described in detail here, and is determined according to the actual situation, and all of them are within the scope of protection of the present application.

Topic mining is a form of data mining, and a specific topic mining process is not described herein any more, and is within the scope of the present application depending on the actual situation.

Text mining is a process of extracting potentially important patterns or knowledge of interest to a user from unstructured text information, which can be viewed as an extension of data mining or knowledge discovery in databases. The text information is mined mainly based on mathematical statistics and computational linguistics as theory, and a computer finds out the rules of some characters and the relation between the characters and semantics and grammar. Text mining relates to a plurality of subject areas, such as information retrieval, text analysis, information extraction and the like.

And S104, performing emotion polarity analysis according to the user concern, and constructing a satisfaction index system to obtain the user satisfaction.

The step can be used for determining the satisfaction degree of the service or the satisfaction degree of the user to the attention point.

It should be noted that the user may have different points of interest, or may have only one point of interest, and when the user has different points of interest, the satisfaction degrees of the different points of interest may be determined respectively.

Specifically, the relationship between the emotion polarity and the satisfaction can be established in the satisfaction index system, that is, the corresponding satisfaction can be determined according to the emotion polarity.

Sentiment analysis is the process of studying text with sentimental colors, including effective recognition of article opinions, classification of positive and negative emotional tendencies, and the like. In the current rapid development period of the internet, sentiment analysis is commonly used for researching public opinion, online shopping evaluation, film watching feeling and the like.

Namely, the content of customer service communication is converted into text information, and the key points of the customer paying attention when communicating with the customer service of the commercial bank and the satisfaction degree of the commercial bank for delivering the service can be analyzed by using the text mining technology and the emotion analysis theory.

In the embodiment, text information in the customer service communication is extracted; performing text data processing and text characteristic analysis on the text information; performing emotion classification analysis and theme mining on the text subjected to text data processing and text feature analysis to obtain a user attention point; according to the user concern, emotion polarity analysis is carried out, and a satisfaction index system is constructed to obtain user satisfaction; therefore, the method can help the commercial bank to more intuitively know the evaluation of the customer on the product release and service provision of the bank, can more deeply know the demand and the preference of the customer, and can further reflect the mainstream focus of the customer when the customer communicates with customer service staff, so that the product and the service are perfected and improved according to the evaluation of the customer, and the method has advantages in market competition.

In practical application, referring to fig. 2, step S101, extracting text information in the customer service communication includes:

s201, converting the audio information communicated between the customer service and the customer into text information.

That is to say, the audio information is converted into the text information by using a conversion technology, and the specific conversion process is not described herein any more, and is within the protection scope of the present application depending on the actual situation.

In practical applications, referring to fig. 3, step S102, performing text data processing and text feature analysis on the text information includes:

s301, data cleaning and word segmentation are carried out on the text information.

Specifically, text information which does not meet the conditions can be cleaned, and noise is avoided.

The method can adopt a semantic analysis mode to segment the words of the text information so as to avoid the trouble caused by overlong data.

Specifically, data cleaning (including text de-duplication and cleaning punctuations and expression numbers), chinese word segmentation, word stop removal and the like are performed on the text information.

S302, extracting high-frequency characteristic words of the text information after data cleaning and word segmentation, and analyzing main factors influencing emotion polarity.

And if the occurrence frequency of the words in the text information is higher than the threshold value, taking the words as high-frequency characteristic words. Of course, words with little meaning, such as the word help, can be washed away when data are washed, and the words are not repeated one by one here, and can be determined according to actual conditions, and are all in the protection range of the application.

And after the high-frequency characteristic words are obtained, analyzing the high-frequency characteristic words to obtain main factors influencing the emotional machine type.

Specifically, TF-IDF of the customer service communication text is calculated, a word vector space is firstly constructed, words in the text are converted into word frequency matrixes, the occurrence frequency of each word is calculated, all text keywords in a word bag are obtained, the word frequency matrixes are counted into TF-IDF values through class calling, and important feature words in the customer service communication are obtained.

The XGboost model is adopted to calculate the characteristics, importance scores are obtained through feature _ attributes, characteristic selection is carried out according to the scores, and the selected words are used as words comprehensively expressing the customer service communication attribute characteristics; and then visually displaying through a decision tree.

In practical applications, referring to fig. 4, after the step S301, performing data cleansing and word segmentation on the text information, the method further includes:

s401, performing visual display on the processed text information through a word frequency cloud picture and a semantic network.

Specifically, the word segmentation effect is shown by drawing a word frequency cloud picture, and the words concerned in the customer service communication can be clearly shown by analysis.

The semantic network expresses the knowledge structure through a network format, and the relation among high-frequency words in the text of customer service communication can be visually displayed by drawing the semantic network.

Specifically, the text data processing mainly comprises data preprocessing, word frequency analysis and semantic network. The text feature visualization system mainly comprises TF-IDF word frequency visualization analysis and decision tree-based feature word importance analysis. And carrying out preprocessing such as cleaning, word segmentation and the like on the acquired customer service communication text data.

Then, feature extraction is carried out, high-frequency words are displayed through a word frequency cloud picture, and the relation among the high-frequency words is described through a semantic network; extracting important characteristic words of the product through TF-IDF, and analyzing the importance degree of the characteristic words through a CART decision tree.

In practical application, referring to fig. 5, step S103, performing emotion classification analysis and topic mining on the text after text data processing and text feature analysis to obtain a user focus, includes:

s501, classifying and evaluating the emotion tendencies of the text after text data processing and text feature analysis based on an emotion dictionary method.

And carrying out emotion classification on the preprocessed customer service text by an emotion dictionary based method.

And S502, mining the theme in the customer service communication text by using an LDA model to the classification and evaluation results to obtain the user focus.

And mining the theme of the uniform text through an LDA theme model, and extracting the positive and negative theme words to obtain the user attention point.

Specifically, firstly, emotion classification is carried out on the preprocessed customer service communication texts by adopting an emotion dictionary-based method. And then mining, displaying and contrastively analyzing the topics of the positive and negative comments by adopting an LDA topic model.

In practical application, referring to fig. 6, step S104, according to the user attention point, performing emotion polarity analysis, and constructing a satisfaction index system to obtain user satisfaction, including:

and S601, matching the emotion short sentence according to the part of speech corresponding to the user concern point.

And S602, calculating the sentiment value of the short sentence by adopting a sentiment dictionary method for the sentiment short sentence.

And S603, selecting the feature words with the important attributes according to the result of the high-frequency words.

S604, clustering the word vectors of the feature words, and determining the satisfaction index of customer service communication.

S605, determining the weight of the evaluation customer satisfaction index according to the emotion short sentence ratio and the short sentence emotion value corresponding to different indexes, and analyzing and calculating the satisfaction condition to obtain the user satisfaction.

And calculating short sentence emotion scores through emotion word pairing, constructing a satisfaction index system based on K-mean clustering, further determining satisfaction index weight, and calculating and analyzing the satisfaction of the client.

That is, a phrase is first constructed by matching emotion words, and a phrase emotion score is calculated based on the emotion dictionary. And then vectorizing through the feature words, clustering, and taking the attribute obtained by clustering as an index for evaluating the satisfaction degree of the user. And then, expanding the characteristic words of each attribute category, classifying the short sentences according to the categories to which the characteristic words of the emotion short sentences belong, and further researching the emotion polarity distribution characteristics of the clients on different attributes to obtain the user satisfaction.

Another embodiment of the application provides a customer service communication text mining system.

Referring to fig. 7, a customer service interaction text mining system includes:

and the extraction module 101 is used for extracting the text information in the customer service communication.

And the processing and analyzing module 102 is used for performing text data processing and text feature analysis on the text information.

The process analysis module 102 includes: the system comprises a data preprocessing module, a TF-IDF word frequency visualization analysis module and a characteristic word analysis module of a decision tree.

A data preprocessing module: and performing data cleaning on the text information (including text duplication removal and cleaning punctuation marks and expression numbers), chinese word segmentation, stop word removal and the like.

A data preprocessing module: the word segmentation effect is shown by drawing a word frequency cloud picture, and words concerned in customer service communication can be clearly shown by analysis. The semantic network expresses the knowledge structure through a network format, and the relation among high-frequency words in the text of customer service communication can be visually displayed by drawing the semantic network.

TF-IDF word frequency visualization analysis module: the method comprises the steps of calculating TF-IDF of a customer service communication text, firstly constructing a word vector space, converting words in the text into a word frequency matrix, calculating the occurrence frequency of each word, then obtaining all text keywords in a word bag, and counting the word frequency matrix into TF-IDF values through class calling, so that important characteristic words in customer service communication are obtained.

A characteristic word analysis module of the decision tree: the XGboost model is adopted to calculate the characteristics, importance scores are obtained through feature _ attributes, characteristic selection is carried out according to the scores, the selected words are used as words comprehensively expressing the customer service communication attribute characteristics, and visual display is carried out through a decision tree.

And the emotion analysis module 103 is used for performing emotion classification analysis on the text subjected to the text data processing and the text feature analysis to obtain an analysis result.

Specifically, emotion classification is carried out on the preprocessed customer service text through a method based on an emotion dictionary.

And the theme mining module 104 is used for continuing theme mining according to the analysis result to obtain the user attention point.

Specifically, the topics of the text can be mined through an LDA topic model, and positive and negative topic words are extracted, so that the user focus is obtained.

And the satisfaction degree module 105 is used for performing emotion polarity analysis according to the user attention points and constructing a satisfaction degree index system to obtain the user satisfaction degree.

Specifically, short sentence emotion scores are calculated through emotion word pairing, a satisfaction index system is constructed based on K-mean clustering, and then satisfaction index weight is determined, and satisfaction of customers is calculated and analyzed to obtain user satisfaction.

For details of the working process and principle of each module, reference is made to the customer service communication text mining method provided in the above embodiment, and details are not repeated here one by one, and all of them are within the protection scope of the present application.

In this embodiment, the extraction module 101 extracts text information in the customer service communication; the processing and analyzing module 102 performs text data processing and text feature analysis on the text information; the emotion analysis module 103 performs emotion classification analysis on the text subjected to text data processing and text feature analysis to obtain an analysis result; the topic mining module 104 continues topic mining according to the analysis result to obtain the user focus; the satisfaction degree module 105 analyzes emotion polarity according to the user concern points, and constructs a satisfaction degree index system to obtain user satisfaction degree; therefore, the method can help the commercial bank to more intuitively know the evaluation of the customer on the product release and service provision of the bank, can further know the demand and the preference of the customer, and can further reflect the mainstream focus of the customer when the customer communicates with customer service staff, so that the product and the service are improved according to the evaluation of the customer, and the method is advantageous in market competition.

Another embodiment of the present application provides a storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the customer service interaction text mining method as in any one of the above embodiments.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

Another embodiment of the present invention provides an electronic device, as shown in fig. 8, including:

one or more processors 601.

A storage device 602 having one or more programs stored thereon.

The one or more programs, when executed by the one or more processors 601, cause the one or more processors 601 to implement a method of customer interaction text mining as in any of the above embodiments.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

While several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and the technical features disclosed in the present disclosure (but not limited to) having similar functions are replaced with each other to form the technical solution.

It should be noted that the customer service communication text mining method and system, the electronic device, and the storage medium provided by the invention can be used in the fields of artificial intelligence, block chaining, distributed, cloud computing, big data, internet of things, mobile internet, network security, chip, virtual reality, augmented reality, holography, quantum computing, quantum communication, quantum measurement, digital twinning, and finance. The foregoing is merely an example, and does not limit the application fields of the method and system for mining a customer service communication text, the electronic device, and the storage medium provided by the present invention.

Features described in the embodiments in the present specification may be replaced with or combined with each other, and the same and similar portions among the embodiments may be referred to each other, and each embodiment is described with emphasis on differences from other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

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 invention.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. 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 invention. Thus, the present invention 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

1. A customer service communication text mining method is characterized by comprising the following steps:

extracting text information in the customer service communication;

performing text data processing and text feature analysis on the text information;

2. The method of claim 1, wherein extracting text information in the customer service communication comprises:

3. The method of claim 1, wherein performing text data processing and text feature analysis on the text message comprises:

performing data cleaning and word segmentation on the text information;

4. The method of claim 1, further comprising, after data cleansing and word segmentation of the text message:

5. The method as claimed in claim 1, wherein the step of performing sentiment classification analysis and topic mining on the text subjected to the text data processing and the text feature analysis to obtain the user interest point comprises:

and mining the theme in the customer service communication text by using an LDA model to obtain the user attention point for the classification and evaluation result.

6. The method for mining the customer service communication text according to claim 1, wherein emotion polarity analysis is performed according to the user attention point, and a satisfaction index system is constructed to obtain user satisfaction, comprising:

7. A customer service interaction text mining system, comprising:

the extraction module is used for extracting text information in the customer service communication;

8. The system of claim 7, wherein the extraction module, when extracting text information in the customer service communication, is specifically configured to:

9. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the customer interaction text mining method of any of claims 1-6.

10. A storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of customer interaction text mining according to any of claims 1-6.