CN111126842A - Work order classification method and device - Google Patents
Work order classification method and device Download PDFInfo
- Publication number
- CN111126842A CN111126842A CN201911346027.5A CN201911346027A CN111126842A CN 111126842 A CN111126842 A CN 111126842A CN 201911346027 A CN201911346027 A CN 201911346027A CN 111126842 A CN111126842 A CN 111126842A
- Authority
- CN
- China
- Prior art keywords
- work order
- classification
- svm
- order data
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a work order classification method and a work order classification device, wherein the work order classification method comprises the following steps: performing Chinese word segmentation on the work order data according to a pre-generated custom word bank and a non-use word bank so as to clean the work order data; and classifying the work order data by using the cleaned work order data and a pre-generated SVM work order classification model. The work order classification method provided by the invention can automatically classify the new work orders, reduce manual operation, avoid misjudgment and improve processing efficiency.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to the technical field of customer service data analysis in the financial industry, and particularly relates to a work order classification method and device.
Background
The bank call center work order is an important source of data for accepting customer complaints, knowing customer requirements and analyzing decisions. The bank business products are various in types, the user experience requirements are continuously improved, when bank customer service personnel deal with customer complaints, the classification of the work order needs to be manually judged according to analysis such as customer complaint reasons, problem description, business handling channels and the like, basic information of the work order is filled, the efficiency of handling one work order is low, the customer waiting time is long, the experience is poor, and complaint upgrading is easily caused. Meanwhile, the problems of inaccurate analysis and judgment, inconsistent type correspondence and the like of customer service personnel often occur due to the various business classifications of banks and the various reasons for customer complaints.
Disclosure of Invention
Aiming at the problems in the prior art, the work order classification method and the work order classification device provided by the invention analyze the historical data of the work order data by a multi-classification method in machine learning, and create a model for automatically classifying problems, and the model can automatically classify the service of a new work order, thereby reducing manual operation, avoiding misjudgment and improving the processing efficiency.
In order to solve the technical problems, the invention provides the following technical scheme:
in a first aspect, the present invention provides a work order classification method, including:
performing Chinese word segmentation on the work order data according to a pre-generated custom word bank and a non-use word bank so as to clean the work order data;
and classifying the work order data by using the cleaned work order data and a pre-generated SVM work order classification model.
Preferably, the step of generating the SVM work order classification model comprises:
performing text attribute conversion on the cleaned work order data by using a word segmentation tool to generate a feature vector corresponding to the work order data;
reducing the dimension of the feature vector by using a linear judgment analysis method;
and training an initial SVM work order classification model according to the feature vector after dimension reduction by using an SVM method so as to generate the SVM work order classification model.
Preferably, the step of generating the custom thesaurus and deactivating the thesaurus comprises:
generating the user-defined word stock and the stop word stock according to the work order data use scene;
the deactivation word bank is used for shielding ambiguity of common words.
Preferably, generating the SVM work order classification model further comprises:
dividing the types of the work order data to generate a classification result; the classification result is used for training the initial SVM worksheet classification model;
the classification result comprises: service complaints, credit problems, status anomalies, approvals, suspicious transactions, authentication, marketing-related, reconciliation services, and raise recommendations.
In a second aspect, the present invention provides a work order sorting apparatus, comprising:
the work order cleaning unit is used for performing Chinese word segmentation on the work order data according to a pre-generated custom word bank and a stop word bank so as to clean the work order data;
and the work order classification unit is used for classifying the work order data by using the cleaned work order data and a pre-generated SVM work order classification model.
Preferably, the work order sorting apparatus further comprises: the model generation unit is used for generating the SVM work order classification model and comprises the following steps:
the vector generation module is used for performing text attribute conversion on the cleaned work order data by using a word segmentation tool so as to generate a feature vector corresponding to the work order data;
the vector dimension reduction module is used for reducing the dimension of the characteristic vector by utilizing a linear judgment analysis method;
and the model generation module is used for training an initial SVM work order classification model according to the feature vector after dimensionality reduction by utilizing an SVM method so as to generate the SVM work order classification model.
Preferably, the work order cleaning unit includes:
the word bank generating module is used for generating the user-defined word bank and the stop word bank according to the work order data use scene;
the deactivation word bank is used for shielding ambiguity of common words.
Preferably, the model generation unit further includes:
the classification result generation module is used for dividing the types of the work order data to generate a classification result; the classification result is used for training the initial SVM worksheet classification model;
the classification result comprises: service complaints, credit problems, status anomalies, approvals, suspicious transactions, authentication, marketing-related, reconciliation services, and raise recommendations.
In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the work order classification method when executing the program.
In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the work order classification method.
As can be seen from the above description, the work order classification method and apparatus provided in the embodiments of the present invention firstly summarize key information of customer problems based on problem analysis of customer complaints, and perform cleaning, text attribute conversion, feature selection, and feature dimension reduction on these data by a machine learning method, so as to create a model, thereby realizing problem (work order) classification. In conclusion, the method provided by the invention can rapidly recommend the service classification to the new work order according to the complaint content of the user, shorten the work order acceptance time, improve the customer experience and avoid the complaint upgrade of the customer. The problems that the processing flow is long and historical data cannot be referred to are solved.
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 first flowchart illustrating a work order classification method according to an embodiment of the present disclosure;
FIG. 2 is a second flowchart illustrating a work order classification method according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating the process 300 of the work order classification method according to an embodiment of the invention;
FIG. 4 is a third schematic flow chart illustrating a work order classification method according to an embodiment of the present disclosure;
FIG. 5 is a flowchart illustrating the process steps 400 of the work order classification method according to an embodiment of the invention;
FIG. 6 is a fourth flowchart illustrating a work order classification method according to an embodiment of the present disclosure;
FIG. 7 is a flow chart illustrating a work order classification method according to an embodiment of the present invention;
FIG. 8 is a diagram illustrating the concept of a work order classification method according to an embodiment of the present invention;
FIG. 9 is a first schematic structural diagram of a work order sorting apparatus according to an embodiment of the present invention;
FIG. 10 is a second schematic structural view of a work order sorting apparatus according to an embodiment of the present invention;
FIG. 11 is a schematic diagram of a work order cleaning unit according to an embodiment of the present invention;
FIG. 12 is a schematic diagram of a model generating unit in an embodiment of the present invention;
fig. 13 is a schematic structural diagram of an electronic device in an embodiment of the 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 derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a specific implementation manner of a work order classification method, and referring to fig. 1, the method specifically includes the following contents:
step 100: and performing Chinese word segmentation on the work order data according to a pre-generated custom word bank and a stop word bank so as to clean the work order data.
Specifically, historical complaint problem data are obtained from a background system, then a word segmentation word bank conforming to a work order service scene is formulated, a model uses a Jieba to perform general Chinese word segmentation, but definition of a user-defined word bank is needed under some scenes, the Jieba can refer to the user-defined word bank, and word segmentation contents in the user-defined word bank can be searched firstly during word segmentation.
Step 200: and classifying the work order data by using the cleaned work order data and a pre-generated SVM work order classification model.
As can be seen from the above description, the work order classification method provided in the embodiment of the present invention firstly summarizes key information of customer problems based on problem analysis of customer complaints, and performs cleaning, text attribute conversion, feature selection, and feature dimension reduction on the data by a machine learning method, so as to create a model, thereby realizing classification of problems (work orders). In conclusion, the method provided by the invention can rapidly recommend the service classification to the new work order according to the complaint content of the user, shorten the work order acceptance time, improve the customer experience and avoid the complaint upgrade of the customer. The problems that the processing flow is long and historical data cannot be referred to are solved.
In one embodiment, referring to fig. 2, the work order classification method further includes:
step 300: and generating the SVM work order classification model.
In one embodiment, referring to FIG. 3, step 300 comprises:
step 301: and performing text attribute conversion on the cleaned work order data by using a word segmentation tool to generate a feature vector corresponding to the work order data.
Specifically, step 301 performs text attribute conversion, and converts the text into Word vectors using Word2vec, forming a Word vector matrix.
Step 302: and reducing the dimension of the feature vector by using a linear judgment analysis method.
Specifically, LDA is used for data dimension reduction, and a final feature vector is obtained. LDA (Linear DiscriniantAanlysis) linear judgment analysis is a classical algorithm of pattern recognition, and the basic idea is to search a vector which enables a Fisher criterion to reach a maximum value as an optimal projection direction, so that a projected sample can reach maximum accumulated dispersion and latest dispersion in class, and the projected sample has optimal separability. The method is a supervised linear dimension reduction method, so that data points after dimension reduction are distinguished as easily as possible.
Step 303: and training an initial SVM work order classification model according to the feature vector after dimension reduction by using an SVM method so as to generate the SVM work order classification model.
The SVM is a two-classifier, and there are two methods, direct and indirect, for multi-classification using SVM. The direct method is to modify an objective function, solve and combine parameters of a plurality of classification surfaces into an optimization problem, and realize multi-classification by solving the optimization problem. The indirect method mainly implements a multi-classification structure by combining a plurality of two classifiers, and a one-to-many (one-to-one-rest) method and a one-to-one (one-to-one) method are common.
In an embodiment, referring to fig. 4, the work order classification method further includes:
step 400: and generating a self-defined word bank and a stop word bank.
In one embodiment, referring to fig. 5, step 400 specifically includes:
step 401: and generating the user-defined word stock and the stop word stock according to the work order data use scene. The deactivation word bank is used for shielding ambiguity of common words.
It can be understood that disabling the thesaurus is also a necessary step in performing word segmentation processing, and the influence of many common words on semantic understanding can be shielded by the step in performing data cleaning.
In an embodiment, referring to fig. 6, before step 300, the method further includes:
step 500: dividing the types of the work order data to generate a classification result; and the classification result is used for training the initial SVM work order classification model.
The classification result comprises: service complaints, credit problems, status anomalies, approvals, suspicious transactions, authentication, marketing-related, reconciliation services, and raise recommendations.
Specifically, types such as service complaints, credit problems, status abnormalities, approvals, suspicious transactions, authentication, marketing-related, reconciliation services, raised recommendations, etc. are subdivided according to banking.
As can be seen from the above description, the work order classification method provided in the embodiment of the present invention firstly summarizes key information of customer problems based on problem analysis of customer complaints, and performs cleaning, text attribute conversion, feature selection, and feature dimension reduction on the data by a machine learning method, so as to create a model, thereby realizing classification of problems (work orders). In conclusion, the method provided by the invention can rapidly recommend the service classification to the new work order according to the complaint content of the user, shorten the work order acceptance time, improve the customer experience and avoid the complaint upgrade of the customer. The problems that the processing flow is long and historical data cannot be referred to are solved.
To further illustrate the present solution, the present invention provides a specific application example of the work order classification method, and the specific application example specifically includes the following contents, see fig. 7 and 8.
S0: and generating the user-defined word stock and the stop word stock according to the work order data use scene.
Specifically, a word segmentation word bank conforming to the work order service scene is formulated: the method is characterized in that a Jieba library is used for carrying out general Chinese word segmentation, but definition of a user-defined word library is required under some scenes, the Jieba segmentation can refer to the user-defined word library, and segmentation contents in the user-defined word library are searched firstly during word segmentation. Making a stop word bank: the method is characterized in that a word library is not used, and the method is used for solving the problem that the influence of a plurality of common words on semantic understanding can be shielded when the data is cleaned. The basic principle of the jieba library word segmentation is as follows: analyzing the association probability between the Chinese characters by utilizing a Chinese word bank; analyzing the association probability of the Chinese word group; and analyzing according to the phrases customized by the user.
S1: and dividing the types of the work order data to generate a classification result.
It is to be understood that the classification results are used to train the initial SVM worksheet classification model; depending on the banking business, types such as service complaints, credit problems, status anomalies, approvals, suspicious transactions, authentication, marketing-related, reconciliation services, raise suggestions, etc. are subdivided. Meanwhile, historical data needs to be summarized, types of the data are divided, and the data are summarized into the subdivided types to be used as labeling data for subsequent training.
S2: and performing Chinese word segmentation on the work order data according to a pre-generated custom word bank and a stop word bank so as to clean the work order data.
Specifically, a word segmentation tool is adopted to perform word segmentation processing on the data. According to the self-defined word segmentation word bank and stop word bank, some words irrelevant to semantic understanding are removed, including punctuation marks, common mood words and the like
S3: and performing text attribute conversion on the cleaned work order data by using a word segmentation tool to generate a feature vector corresponding to the work order data.
Specifically, text attribute conversion is performed, and in this embodiment, a word2vec model in a Gensim library is used to convert a text into a word vector, so as to form a word vector matrix. It will be appreciated that the word vectors are originally encoded using one-hot, which has the disadvantage of resulting in a very large feature space. The basic idea of Word2vec is to represent each Word in a natural language as an end vector of uniform meaning and uniform dimension. The training of the model, which is in effect a neural network with a hidden layer, takes as its input a vocabulary vector, and when a training sample is seen, for each word in the sample, sets the corresponding occurrence in the vocabulary to 1, otherwise to 0. The output is also a vocabulary vector. There are two training modes for this Model, CBOW (Continuous Bag-of-Words Model) and Skip-gram (Continuous Skip-gram Model). CBOW predicts the core words with the surrounding words, and Skip-gram predicts the surrounding words with the core words. The COBW mode is selected for the specific application example.
Then, feature selection is carried out, a variance selection method is used for calculating variance values of all feature attributes, the feature attributes with the largest influence are selected as a feature attribute list of a finally constructed model according to a set threshold value, a worksheet code exists in worksheet data, the creation time, the issuance time, the name of a client, a contact telephone, an evidence type, an evidence number, a complainer, a related branch, a related department, a business channel, a worksheet content, a complaint reason, a business type and the like exist in the worksheet data, and the related branch, the related department, the business channel, the complaint reason, an incoming call area, the worksheet content, the worksheet type and the customer satisfaction degree are selected as final feature items.
S4: and reducing the dimension of the feature vector by using a linear judgment analysis method.
And (5) using LDA to reduce the dimension of the data to obtain a final feature vector. LDA (Linear DiscriniantAanlysis) linear judgment analysis is a classical algorithm of pattern recognition, and the basic idea is to search a vector which enables a Fisher criterion to reach a maximum value as an optimal projection direction, so that a projected sample can reach maximum accumulated dispersion and latest dispersion in class, and the projected sample has optimal separability. The method is a supervised linear dimension reduction method, so that data points after dimension reduction are distinguished as easily as possible.
S5: and training an initial SVM work order classification model according to the feature vector after dimension reduction by using an SVM method so as to generate the SVM work order classification model.
The SVM is a two-classifier, and two methods, namely a direct method and an indirect method, can be used for multi-classification by using the SVM. The direct method is to modify an objective function, solve and combine parameters of a plurality of classification surfaces into an optimization problem, and realize multi-classification by solving the optimization problem. The indirect method mainly implements a multi-classification structure by combining a plurality of two classifiers, and a one-to-many (one-to-one-rest) method and a one-to-one (one-to-one) method are common. The specific application example uses a one-to-many method in the sklern package.
S6: and classifying the work order data by using the cleaned work order data and a pre-generated SVM work order classification model.
And after the model training is finished, recommending the service classification of the complaint problem newly proposed by the user by using the created SVM work order classification model. The method helps business personnel to automatically select business classification, reduces work order processing time and improves work efficiency.
As can be seen from the above description, the work order classification method provided in the embodiment of the present invention firstly summarizes key information of customer problems based on problem analysis of customer complaints, and performs cleaning, text attribute conversion, feature selection, and feature dimension reduction on the data by a machine learning method, so as to create a model, thereby realizing classification of problems (work orders). In conclusion, the method provided by the invention can rapidly recommend the service classification to the new work order according to the complaint content of the user, shorten the work order acceptance time, improve the customer experience and avoid the complaint upgrade of the customer. The problems that the processing flow is long and historical data cannot be referred to are solved.
Based on the same inventive concept, the embodiment of the present application further provides a work order sorting apparatus, which can be used to implement the method described in the above embodiment, such as the following embodiments. Because the principle of the work order classification device for solving the problems is similar to the work order classification method, the implementation of the work order classification device can be implemented by referring to the work order classification method, and repeated parts are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
The embodiment of the present invention provides a specific implementation manner of a work order classification device capable of implementing a work order classification method, and referring to fig. 9, the work order classification device specifically includes the following contents:
the work order cleaning unit 10 is used for performing Chinese word segmentation on the work order data according to a pre-generated custom word bank and a stop word bank so as to clean the work order data;
and the work order classification unit 20 is configured to classify the work order data by using the cleaned work order data and a pre-generated SVM work order classification model.
Preferably, referring to fig. 10, the work order sorting apparatus further includes: the model generating unit 30 is configured to generate the SVM work order classification model, and includes:
the vector generation module 301 is configured to perform text attribute conversion on the cleaned work order data by using a word segmentation tool to generate a feature vector corresponding to the work order data;
a vector dimension reduction module 302, configured to perform dimension reduction on the feature vector by using a linear judgment analysis method;
and the model generation module 303 is configured to train an initial SVM work order classification model according to the feature vector after the dimension reduction by using an SVM method, so as to generate the SVM work order classification model.
Preferably, referring to fig. 11, the work order cleaning unit 10 includes:
a word bank generating module 101, configured to generate the custom word bank and the deactivated word bank according to the work order data usage scenario;
the deactivation word bank is used for shielding ambiguity of common words.
Preferably, referring to fig. 12, the model generation unit 30 further includes:
a classification result generation module 304, configured to divide the types of the work order data to generate a classification result; the classification result is used for training the initial SVM worksheet classification model;
the classification result comprises: service complaints, credit problems, status anomalies, approvals, suspicious transactions, authentication, marketing-related, reconciliation services, and raise recommendations.
As can be seen from the above description, the work order classification apparatus provided in the embodiment of the present invention firstly summarizes key information of customer problems based on problem analysis of customer complaints, and performs cleaning, text attribute conversion, feature selection, and feature dimension reduction on the data by a machine learning method, so as to create a model, thereby realizing classification of problems (work orders). In conclusion, the method provided by the invention can rapidly recommend the service classification to the new work order according to the complaint content of the user, shorten the work order acceptance time, improve the customer experience and avoid the complaint upgrade of the customer. The problems that the processing flow is long and historical data cannot be referred to are solved.
An embodiment of the present application further provides a specific implementation manner of an electronic device, which is capable of implementing all steps in the work order classification method in the foregoing embodiment, and referring to fig. 13, the electronic device specifically includes the following contents:
a processor (processor)1201, a memory (memory)1202, a communication interface 1203, and a bus 1204;
the processor 1201, the memory 1202 and the communication interface 1203 complete communication with each other through the bus 1204; the communication interface 1203 is configured to implement information transmission between related devices, such as a server-side device, a classification device, and a client device.
The processor 1201 is configured to call the computer program in the memory 1202, and the processor executes the computer program to implement all the steps in the work order classification method in the above embodiments, for example, the processor executes the computer program to implement the following steps:
step 100: and performing Chinese word segmentation on the work order data according to a pre-generated custom word bank and a stop word bank so as to clean the work order data.
Step 200: and classifying the work order data by using the cleaned work order data and a pre-generated SVM work order classification model.
As can be seen from the above description, in the electronic device in the embodiment of the present application, first, key information of a customer problem is summarized based on problem analysis of customer complaints, and the data is cleaned, text attribute conversion, feature selection, and feature dimension reduction by a machine learning method, so as to create a model, thereby classifying the problem (work order). In conclusion, the method provided by the invention can rapidly recommend the service classification to the new work order according to the complaint content of the user, shorten the work order acceptance time, improve the customer experience and avoid the complaint upgrade of the customer. The problems that the processing flow is long and historical data cannot be referred to are solved.
An embodiment of the present application further provides a computer-readable storage medium capable of implementing all the steps in the work order classification method in the foregoing embodiment, where the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, implements all the steps in the work order classification method in the foregoing embodiment, for example, when the processor executes the computer program, the processor implements the following steps:
step 100: and performing Chinese word segmentation on the work order data according to a pre-generated custom word bank and a stop word bank so as to clean the work order data.
Step 200: and classifying the work order data by using the cleaned work order data and a pre-generated SVM work order classification model.
As can be seen from the above description, the computer-readable storage medium in the embodiment of the present application firstly summarizes key information of a customer problem based on problem analysis of customer complaints, and performs cleaning, text attribute conversion, feature selection, and feature dimension reduction on the data by a machine learning method, so as to create a model, thereby classifying the problem (work order). In conclusion, the method provided by the invention can rapidly recommend the service classification to the new work order according to the complaint content of the user, shorten the work order acceptance time, improve the customer experience and avoid the complaint upgrade of the customer. The problems that the processing flow is long and historical data cannot be referred to are solved.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Although the present application provides method steps as in an embodiment or a flowchart, more or fewer steps may be included based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or client product executes, it may execute sequentially or in parallel (e.g., in the context of parallel processors or multi-threaded processing) according to the embodiments or methods shown in the figures.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A work order classification method, comprising:
performing Chinese word segmentation on the work order data according to a pre-generated custom word bank and a non-use word bank so as to clean the work order data;
and classifying the work order data by using the cleaned work order data and a pre-generated SVM work order classification model.
2. The work order classification method of claim 1, wherein the step of generating the SVM work order classification model comprises:
performing text attribute conversion on the cleaned work order data by using a word segmentation tool to generate a feature vector corresponding to the work order data;
reducing the dimension of the feature vector by using a linear judgment analysis method;
and training an initial SVM work order classification model according to the feature vector after dimension reduction by using an SVM method so as to generate the SVM work order classification model.
3. The work order classification method of claim 1, wherein the steps of generating a custom thesaurus and deactivating the thesaurus comprise:
generating the user-defined word stock and the stop word stock according to the work order data use scene;
the deactivation word bank is used for shielding ambiguity of common words.
4. The work order classification method of claim 2, wherein generating the SVM work order classification model further comprises:
dividing the types of the work order data to generate a classification result; the classification result is used for training the initial SVM worksheet classification model;
the classification result comprises: service complaints, credit problems, status anomalies, approvals, suspicious transactions, authentication, marketing-related, reconciliation services, and raise recommendations.
5. A work order sorting apparatus, comprising:
the work order cleaning unit is used for performing Chinese word segmentation on the work order data according to a pre-generated custom word bank and a stop word bank so as to clean the work order data;
and the work order classification unit is used for classifying the work order data by using the cleaned work order data and a pre-generated SVM work order classification model.
6. The work order sorting apparatus of claim 5, further comprising: the model generation unit is used for generating the SVM work order classification model and comprises the following steps:
the vector generation module is used for performing text attribute conversion on the cleaned work order data by using a word segmentation tool so as to generate a feature vector corresponding to the work order data;
the vector dimension reduction module is used for reducing the dimension of the characteristic vector by utilizing a linear judgment analysis method;
and the model generation module is used for training an initial SVM work order classification model according to the feature vector after dimensionality reduction by utilizing an SVM method so as to generate the SVM work order classification model.
7. The work order sorting apparatus of claim 5, wherein the work order cleaning unit comprises:
the word bank generating module is used for generating the user-defined word bank and the stop word bank according to the work order data use scene;
the deactivation word bank is used for shielding ambiguity of common words.
8. The work order classification apparatus of claim 6, wherein the model generation unit further comprises:
the classification result generation module is used for dividing the types of the work order data to generate a classification result; the classification result is used for training the initial SVM worksheet classification model;
the classification result comprises: service complaints, credit problems, status anomalies, approvals, suspicious transactions, authentication, marketing-related, reconciliation services, and raise recommendations.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the work order classification method according to any one of claims 1 to 4 are performed when the program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the work order classification method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911346027.5A CN111126842A (en) | 2019-12-24 | 2019-12-24 | Work order classification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911346027.5A CN111126842A (en) | 2019-12-24 | 2019-12-24 | Work order classification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111126842A true CN111126842A (en) | 2020-05-08 |
Family
ID=70501844
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911346027.5A Pending CN111126842A (en) | 2019-12-24 | 2019-12-24 | Work order classification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126842A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657627A (en) * | 2021-08-17 | 2021-11-16 | 国网江苏省电力有限公司信息通信分公司 | Defect list generation method and system in power communication network |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760493A (en) * | 2016-02-18 | 2016-07-13 | 国网江苏省电力公司电力科学研究院 | Automatic work order classification method for electricity marketing service hot spot 95598 |
| CN107292292A (en) * | 2017-07-20 | 2017-10-24 | 浙江好络维医疗技术有限公司 | A kind of QRS complex sorting technique based on SVMs |
| CN108897798A (en) * | 2018-06-12 | 2018-11-27 | 广东电网有限责任公司 | Electricity consumption customer service work order classification method, device and electronic equipment |
| CN109389418A (en) * | 2018-08-17 | 2019-02-26 | 国家电网有限公司客户服务中心 | Electric service client's demand recognition methods based on LDA model |
| CN109492091A (en) * | 2018-09-28 | 2019-03-19 | 科大国创软件股份有限公司 | A kind of complaint work order intelligent method for classifying based on convolutional neural networks |
| CN109857864A (en) * | 2019-01-07 | 2019-06-07 | 平安科技（深圳）有限公司 | Text sentiment classification method, device, computer equipment and storage medium |
-
2019
- 2019-12-24 CN CN201911346027.5A patent/CN111126842A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760493A (en) * | 2016-02-18 | 2016-07-13 | 国网江苏省电力公司电力科学研究院 | Automatic work order classification method for electricity marketing service hot spot 95598 |
| CN107292292A (en) * | 2017-07-20 | 2017-10-24 | 浙江好络维医疗技术有限公司 | A kind of QRS complex sorting technique based on SVMs |
| CN108897798A (en) * | 2018-06-12 | 2018-11-27 | 广东电网有限责任公司 | Electricity consumption customer service work order classification method, device and electronic equipment |
| CN109389418A (en) * | 2018-08-17 | 2019-02-26 | 国家电网有限公司客户服务中心 | Electric service client's demand recognition methods based on LDA model |
| CN109492091A (en) * | 2018-09-28 | 2019-03-19 | 科大国创软件股份有限公司 | A kind of complaint work order intelligent method for classifying based on convolutional neural networks |
| CN109857864A (en) * | 2019-01-07 | 2019-06-07 | 平安科技（深圳）有限公司 | Text sentiment classification method, device, computer equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657627A (en) * | 2021-08-17 | 2021-11-16 | 国网江苏省电力有限公司信息通信分公司 | Defect list generation method and system in power communication network |
| CN113657627B (en) * | 2021-08-17 | 2024-01-12 | 国网江苏省电力有限公司信息通信分公司 | Defect list generation method and system in power communication network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111859960B (en) | Semantic matching method, device, computer equipment and medium based on knowledge distillation | |
| US20190325324A1 (en) | Automated ontology development | |
| CN107797982B (en) | Method, device and equipment for recognizing text type | |
| US11138978B2 (en) | Topic mining based on interactionally defined activity sequences | |
| US9904927B2 (en) | Funnel analysis | |
| US20200342016A1 (en) | Systems and methods for coverage analysis of textual queries | |
| US20230139628A1 (en) | Supporting automation of customer service | |
| CN112732911A (en) | Semantic recognition-based conversational recommendation method, device, equipment and storage medium | |
| US20100223099A1 (en) | Method and apparatus for a multi-dimensional offer optimization (mdoo) | |
| CN110046806B (en) | Method and device for customer service order and computing equipment | |
| CN106445915A (en) | New word discovery method and device | |
| CN110046648B (en) | Method and device for classifying business based on at least one business classification model | |
| CN112418320B (en) | Enterprise association relation identification method, device and storage medium | |
| US20230237276A1 (en) | System and Method for Incremental Estimation of Interlocutor Intents and Goals in Turn-Based Electronic Conversational Flow | |
| CN111190967B (en) | User multidimensional data processing method and device and electronic equipment | |
| CN113051380A (en) | Information generation method and device, electronic equipment and storage medium | |
| JP7287699B2 (en) | Information provision method and device using learning model through machine learning | |
| KR20190070044A (en) | Device and method for binarization computation of convolution neural network | |
| CN111190973A (en) | Method, device, equipment and storage medium for classifying statement forms | |
| CN111126842A (en) | Work order classification method and device | |
| CN111126038B (en) | Information acquisition model generation method and device and information acquisition method and device | |
| KR102217084B1 (en) | Hybrid recommendation system and method | |
| CN116662546A (en) | Complaint text labeling method, device, equipment and medium | |
| WO2022246162A1 (en) | Content generation using target content derived modeling and unsupervised language modeling | |
| US20220067623A1 (en) | Evaluate demand and project go-to-market resources |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |