CN113033941A

CN113033941A - Customer complaint case distribution method, apparatus, device and storage medium

Info

Publication number: CN113033941A
Application number: CN202011539058.5A
Authority: CN
Inventors: 周梅
Original assignee: Ping An Puhui Enterprise Management Co Ltd
Current assignee: Ping An Puhui Enterprise Management Co Ltd
Priority date: 2020-12-23
Filing date: 2020-12-23
Publication date: 2021-06-25

Abstract

The invention relates to the field of research and development management and discloses a customer complaint case distribution method, a device, equipment and a storage medium. The method comprises the following steps: receiving a case allocation request, and acquiring a target customer complaint case corresponding to the case allocation request; acquiring case information and a target user associated with a target customer complaint case, and calculating the case score of the customer complaint case according to the case information; obtaining customer complaint service information related to a preset customer complaint mechanism, and calculating the service grade of the customer complaint mechanism according to the customer complaint information; and determining a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service grade, and distributing the similar customer complaint case to a target case handler for processing according to a preset case distribution rule. The technical problems that the customer complaint processing efficiency is low and the customer satisfaction is low due to the fact that the case characteristics cannot be automatically identified are solved.

Description

Customer complaint case distribution method, apparatus, device and storage medium

Technical Field

The invention relates to the field of big data, in particular to a customer complaint case distribution method, a customer complaint case distribution device, customer complaint case distribution equipment and a storage medium.

Background

With the increasing quality of life, the demand of people for products or services is also increasing, and users (such as consumers) often choose to feed back to suppliers in the face of various adverse situations or questions. For example, the customer may feed back relevant questions to customer service personnel through the customer complaint system of the supplier.

At present, a common method for customer complaint problem handling is that when a user feeds back a problem to a customer service staff through a customer complaint system, the customer service staff can establish a corresponding work order according to different customer complaint problems, then assign the work order to a corresponding service processing staff for handling, after the service processing staff finishes handling the work order, the work order is returned to a customer service node, and the customer service staff feeds back the result of the customer complaint work order to the user. However, in the existing customer complaint problem handling manner, customer service staff need to search for case characteristics across multiple systems, and further assign a work order to a corresponding business handler, so that the customer service staff cannot quickly handle complaint cases, and service experience of users is seriously affected.

Disclosure of Invention

The invention mainly aims to solve the technical problems of low customer complaint processing efficiency and low customer satisfaction caused by the fact that case characteristics cannot be automatically identified.

The invention provides a customer complaint case distribution method, which comprises the following steps:

receiving a case allocation request, and acquiring a target customer complaint case corresponding to the case allocation request;

acquiring case information and a target user associated with the target customer complaint case, and calculating the case score of the customer complaint case according to the case information;

obtaining customer complaint service information associated with a preset customer complaint mechanism, and calculating the service grade of the customer complaint mechanism according to the customer complaint information;

and determining a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service grade, and distributing the customer complaint case to the target customer complaint mechanism.

Optionally, in a first implementation manner of the first aspect of the present invention, before the receiving a case allocation request and acquiring a target customer complaint case corresponding to the case allocation request, the method further includes:

obtaining customer complaint data, wherein the customer complaint data is a customer complaint record of a target user;

judging whether the customer complaint data is text data or not;

if the customer complaint data is voice data, carrying out voice-to-text processing on the customer complaint data to obtain text data corresponding to the customer complaint data;

and performing data cleaning on the text data to obtain target user data, wherein the target user data carries a main key corresponding to the target user.

Optionally, in a second implementation manner of the first aspect of the present invention, after receiving the case allocation request and acquiring the target customer complaint case corresponding to the case allocation request, the method further includes:

acquiring text information of a target customer complaint case, preprocessing the text information, and vectorizing the preprocessed text information to acquire vector information corresponding to the target customer complaint case;

similarity matching is carried out on the vector information and vector information corresponding to each customer complaint case in a preset database, and soft cosine similarity information of the target customer complaint case and each customer complaint case in the database is obtained;

and extracting cosine similarity information meeting preset conditions, and taking the customer complaint cases in the database corresponding to the cosine similarity information meeting the preset conditions as similar cases.

Optionally, in a third implementation manner of the first aspect of the present invention, the performing data cleansing on the text data to obtain target user data includes:

configuring a data cleaning rule file, wherein the data cleaning rule file comprises at least one data cleaning rule, and the data cleaning rule comprises a data table name, a data cleaning rule pseudo code and a rule serial number;

generating a data cleaning code according to the data cleaning rule file;

executing the data cleaning code, and labeling the text data;

and analyzing the label, and cleaning the text data according to an analysis result to obtain target user data.

Optionally, in a fourth implementation manner of the first aspect of the present invention, the receiving a case allocation request and acquiring a target customer complaint case corresponding to the case allocation request includes:

receiving a case allocation request, and acquiring a historical customer complaint record of the target user according to a main key corresponding to the target user;

extracting the characteristics of the historical customer complaint data of the target user through a preset characteristic extraction algorithm to generate characteristic words of the historical customer complaint data;

matching the feature words with labels in a preset label library to obtain labels matched with the target users;

performing multi-dimensional description on the target user based on the label and a preset label description model to generate a customer complaint portrait of the user;

and acquiring a target customer complaint case corresponding to the case distribution request based on the customer complaint portrait of the user.

Optionally, in a fifth implementation manner of the first aspect of the present invention, the determining, according to the case score and the service level, a target customer complaint mechanism corresponding to the customer complaint case, and allocating the customer complaint case to the target customer complaint mechanism includes:

inquiring a preset classification table, acquiring a service grade matched with the case score, and taking a preset customer complaint mechanism corresponding to the service grade as a target customer complaint mechanism;

and distributing the customer complaint case to a corresponding case handler in the target customer complaint mechanism according to a preset rule, and recording a case handling flow.

A second aspect of the present invention provides a customer complaint case distribution device including:

the system comprises a first acquisition module, a first response module and a second response module, wherein the first acquisition module is used for receiving a case distribution request and acquiring a target customer complaint case corresponding to the case distribution request;

the first calculation module is used for acquiring case information and a target user which are associated with the target customer complaint case, and calculating the case score of the customer complaint case according to the case information;

the second calculation module is used for acquiring customer complaint service information associated with a preset customer complaint mechanism and calculating the service grade of the customer complaint mechanism according to the customer complaint information;

and the allocation module is used for determining a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service grade, and allocating the customer complaint case to the target customer complaint mechanism.

Optionally, in a first implementation manner of the second aspect of the present invention, the customer complaint case distribution apparatus includes:

the second acquisition module is used for acquiring customer complaint data, wherein the customer complaint data is a customer complaint record of a target user;

the judging module is used for judging whether the customer complaint data is text data;

the processing module is used for carrying out voice-to-text processing on the customer complaint data when the customer complaint data is voice data to obtain text data corresponding to the customer complaint data;

and the data cleaning module is used for performing data cleaning on the text data to obtain target user data, wherein the target user data carries the main key corresponding to the target user.

Optionally, in a second implementation manner of the second aspect of the present invention, the customer complaint case distribution apparatus includes:

the third acquisition module is used for acquiring the text information of the target customer complaint case, preprocessing the text information, and vectorizing the preprocessed text information to acquire vector information corresponding to the target customer complaint case;

the matching module is used for carrying out similarity matching on the vector information and the vector information corresponding to each customer complaint case in a preset database to obtain the soft cosine similarity information of the target customer complaint case and each customer complaint case in the database;

and the extraction module is used for extracting the cosine similarity information meeting the preset conditions, and taking the customer complaint case in the database corresponding to the cosine similarity information meeting the preset conditions as a similar case.

Optionally, in a third implementation manner of the second aspect of the present invention, the data cleansing module is specifically configured to:

generating a data cleaning code according to the data cleaning rule file;

executing the data cleaning code, and labeling the text data;

Optionally, in a fourth implementation manner of the second aspect of the present invention, the first obtaining module is specifically configured to:

Optionally, in a fifth implementation manner of the second aspect of the present invention, the allocating module includes:

the query unit is used for querying a preset classification table, acquiring a service grade matched with the case score, and taking a preset customer complaint mechanism corresponding to the service grade as a target customer complaint mechanism;

and the distribution unit is used for distributing the customer complaint case to a corresponding case handler in the target customer complaint mechanism according to a preset rule and recording a case handling process.

A third aspect of the present invention provides customer complaint case distribution apparatus comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;

the at least one processor calls the instructions in the memory to cause the customer complaint case distribution equipment to execute the customer complaint case distribution method.

A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to execute the customer complaint case distribution method described above.

In the technical scheme provided by the invention, a target customer complaint case corresponding to a case distribution request is obtained by receiving the case distribution request; acquiring case information and a target user associated with a target customer complaint case, and calculating the case score of the customer complaint case according to the case information; obtaining customer complaint service information related to a preset customer complaint mechanism, and calculating the service grade of the customer complaint mechanism according to the customer complaint information; and determining a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service grade, and distributing the similar customer complaint case to a target case handler for processing according to a preset case distribution rule. The technical problems that the customer complaint processing efficiency is low and the customer satisfaction is low due to the fact that the case characteristics cannot be automatically identified are solved.

Drawings

FIG. 1 is a schematic diagram of a first embodiment of a case allocation method for customer complaints according to the present invention;

FIG. 2 is a schematic diagram of a case distribution method according to a second embodiment of the present invention;

FIG. 3 is a schematic diagram of a third embodiment of the case distribution method for customer complaints of the present invention;

FIG. 4 is a diagram of a fourth embodiment of the case distribution method for customer complaints of the present invention;

FIG. 5 is a schematic diagram of a fifth embodiment of the case distribution method of customer complaints of the present invention;

FIG. 6 is a schematic view of a first embodiment of the customer complaint case distribution apparatus of the present invention;

FIG. 7 is a schematic view of a second embodiment of the case distribution device of the present invention;

FIG. 8 is a schematic view of an embodiment of the customer complaint case distribution apparatus of the present invention.

Detailed Description

The embodiment of the invention provides a customer complaint case distribution method, a device, equipment and a storage medium, wherein in the technical scheme of the invention, a case distribution request is received firstly, and a target customer complaint case corresponding to the case distribution request is obtained; acquiring case information and a target user associated with a target customer complaint case, and calculating the case score of the customer complaint case according to the case information; obtaining customer complaint service information related to a preset customer complaint mechanism, and calculating the service grade of the customer complaint mechanism according to the customer complaint information; and determining a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service grade, and distributing the similar customer complaint case to a target case handler for processing according to a preset case distribution rule. The technical problems that the customer complaint processing efficiency is low and the customer satisfaction is low due to the fact that the case characteristics cannot be automatically identified are solved.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For convenience of understanding, a specific flow of the embodiment of the present invention is described below, and referring to fig. 1, a first embodiment of a customer complaint case distribution method in the embodiment of the present invention includes:

101. receiving a case allocation request, and acquiring a target customer complaint case corresponding to the case allocation request;

in this embodiment, a server receives a case allocation request, where a triggering form of the case allocation request in this embodiment is not limited, for example, a user clicks an "allocation" key at a terminal to trigger the case allocation request, the terminal sends the case allocation request to the server, and when the server receives the case allocation request, the server obtains a case to be allocated in the case allocation request, where the number of cases to be allocated in this embodiment may be one or multiple cases.

It should be noted that the customer complaint case corresponding to the received case allocation request in this embodiment may not only be preset according to the allocation rule, but also be obtained by the server in real time from a preset customer complaint database corresponding to the customer complaint handling mechanism when the case allocation request is received.

Namely, when the server receives a case allocation request, the server queries a preset customer complaint database, wherein the preset customer complaint database is a database preset on a preset customer complaint processing mechanism, and customer complaint cases of different users are recorded in the preset customer complaint database; the server acquires the case with the overdue mark in the preset case database and the overdue time of the case; the server is used for calling the case with overdue time exceeding first preset time, and the case with overdue time exceeding the first preset time is used as the case corresponding to the case distribution request, wherein the first preset time refers to a preset overdue time critical value of the customer, and can be set according to specific scenes, for example, the first preset time can be set to be 3 days. The case allocation is automatically carried out according to the case information and the relevance in front of the customer, the case handler is automatically identified, the case handling process is recorded, the customer complaint can be timely and effectively handled, and the customer satisfaction is improved.

102. Acquiring case information and a target user associated with a target customer complaint case, and calculating the case score of the customer complaint case according to the case information;

in this embodiment, the server obtains case information associated with the customer complaint case, where the case information includes, but is not limited to, the grades (high-value users, medium-value users, and low-value users) of customers corresponding to the customer complaint case, the number of complaints, the time left after handling of the complaints, and the credit score of the customers, and the server scores the customer complaints according to the grades (high-value users, medium-value users, and low-value users) of the customers, the number of complaints, the time left after handling of the complaints, and the credit score of the customers, and in this embodiment, the case scoring for determining the customer complaints may be implemented in different manners, for example,

the server presets a calculation formula, wherein the preset calculation formula is related to case information, namely, the calculation formula can be a function of client application information, a borrowing mechanism, a borrowing GPS address, an identity card address, a mortgage location address, a service attribution city and client credit rating, and the server inputs the application information, the borrowing mechanism, the borrowing GPS address, the identity card address, the mortgage location address, the service attribution city and the client credit rating into the preset calculation formula to obtain the case of the client complaint and perform case rating. In this embodiment, the server calculates the score of the customer complaint case according to the case information of the customer complaint case, so that different information is taken into consideration when the customer complaint case is distributed.

103. Obtaining customer complaint service information related to a preset customer complaint mechanism, and calculating the service grade of the customer complaint mechanism according to the customer complaint information;

in this embodiment, the server obtains customer complaint information associated with a preset customer complaint mechanism, where the preset customer complaint mechanism refers to a mechanism for customer complaint handling, and the server calculates the service level of the preset customer complaint mechanism according to the customer complaint information. The server acquires customer complaint service information associated with a preset customer complaint mechanism, wherein the customer complaint service information comprises but is not limited to customer complaint processing efficiency, customer complaint success rate and other information of the preset customer complaint mechanism, and queries a preset service score table, wherein the preset service score table refers to service information and a score mapping table preset in the server, the server acquires a limit score matched with the customer complaint severity grade, acquires an efficiency score matched with the customer complaint processing efficiency, and acquires a quality score matched with the customer complaint success rate; and then, the server performs weighted calculation on the limit score, the efficiency score and the quality score to obtain the service level of the preset customer complaint mechanism.

104. And determining a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service grade, and distributing the customer complaint case to the target customer complaint mechanism.

In this embodiment, according to the case score and the service level, a target customer complaint handling mechanism corresponding to the customer complaint case is determined, and the customer complaint case is assigned to the customer complaint handling mechanism.

The server inquires a preset classification table, wherein the preset classification table is a preset customer complaint case score and customer complaint mechanism grade corresponding table, the server acquires a service grade matched with the case score, and a preset customer complaint mechanism corresponding to the service grade is used as a target customer complaint mechanism; when the number of the target customer complaint mechanisms is not less than two, that is, when a plurality of the current customer complaint mechanisms meet the case distribution condition, the server needs to select one of the target customer complaint mechanisms to distribute the case, in this embodiment, the customer complaint case is distributed to the target customer complaint mechanism with the highest customer complaint processing efficiency, so as to realize the rapid processing of the customer complaint case.

In this embodiment, when the server receives the case allocation request, the server scores the customer complaint case according to the customer complaint case information, then the server obtains the service information of the preset customer complaint mechanism, and calculates the service level of the preset customer complaint mechanism according to the customer complaint service information, and the server determines the target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service level to allocate the customer complaint case, so that the server considers different influence factors when performing the customer complaint case evaluation, and the allocation of the customer complaint case is more reasonable.

In the embodiment of the invention, a target customer complaint case corresponding to a case distribution request is obtained by receiving the case distribution request; acquiring case information and a target user associated with a target customer complaint case, and calculating the case score of the customer complaint case according to the case information; obtaining customer complaint service information related to a preset customer complaint mechanism, and calculating the service grade of the customer complaint mechanism according to the customer complaint information; and determining a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service grade, and distributing the similar customer complaint case to a target case handler for processing according to a preset case distribution rule. The technical problems that the customer complaint processing efficiency is low and the customer satisfaction is low due to the fact that the case characteristics cannot be automatically identified are solved.

Referring to fig. 2, a second embodiment of the customer complaint case distribution method according to the embodiment of the present invention includes:

201. customer complaint data is obtained, wherein the customer complaint data is a customer complaint record of a target user;

in this embodiment, the customer complaint data refers to complaint data obtained during real-time communication between the user in the designated APP and customer service staff in the APP, and includes, but is not limited to, complaint related data such as personal information of the user, specific events, and processing results given by the customer service staff to the user, where the complaint data is a consultation complaint data related to a specific service. Specifically, it may include, but is not limited to: financial product data previously purchased by the user, and the like.

202. Judging whether the customer complaint data is text data or not;

in this embodiment, the present invention is a method for distributing customer complaints to text data, so before analyzing and identifying the collected complaint data, the data type of the complaint data is determined first. The data type may be text data or voice data.

203. When the customer complaint data is voice data, carrying out voice-to-text processing on the customer complaint data to obtain text data corresponding to the customer complaint data;

in this embodiment, a speech recognition algorithm may be used to perform voice-to-text processing on each piece of original audio data, so as to obtain text data corresponding to each piece of inquiry data.

Speech recognition is a cross discipline. In the last two decades, speech recognition technology has advanced significantly, starting to move from the laboratory to the market. It is expected that voice recognition technology will enter various fields such as industry, home appliances, communications, automotive electronics, medical care, home services, consumer electronics, etc. within the next 10 years. The application of speech recognition dictation machines in some fields is rated by the U.S. news community as one of ten major computer developments in 1997. Many experts consider the speech recognition technology to be one of the ten important technological development technologies in the information technology field between 2000 and 2010. The fields to which speech recognition technology relates include: signal processing, pattern recognition, probability and information theory, sound and hearing mechanisms, artificial intelligence, and the like.

204. Performing data cleaning on the text data to obtain target user data, wherein the target user data carries a main key corresponding to a target user;

in this embodiment, the process of Data cleansing (Data cleansing) to review and verify Data is intended to delete duplicate information, correct existing errors, and provide Data consistency.

Data cleansing also looks by name to "wash out" dirty, meaning the last procedure to find and correct recognizable errors in a data file, including checking data consistency, handling invalid and missing values, etc. Because the data in the data warehouse is a collection of data oriented to a certain subject, the data is extracted from a plurality of business systems and contains historical data, so that the condition that some data are wrong data and some data conflict with each other is avoided, and the wrong or conflicting data are obviously unwanted and are called as 'dirty data'. We need to "wash" dirty data according to certain rules, which is data washing. The task of data cleaning is to filter the data which do not meet the requirements, and the filtered result is sent to a business administration department to confirm whether the data are filtered or corrected by a business unit and then extracted. The data which is not qualified is mainly three categories of incomplete data, error data and repeated data. Data cleaning is different from questionnaire examination, and data cleaning after entry is generally completed by a computer instead of a human.

In this embodiment, different service scenarios may need to be subjected to data cleansing, such as: a certain shopping establishment needs to carry out data cleaning on transaction data, and a user can send a data cleaning request to the data cleaning device through the shopping establishment or other clients. Some data cleansing key information may be included in the data cleansing request, such as: if data cleaning is to be performed on certain transaction data, the data cleaning request may include information such as a transaction serial number, an order number, user names of both parties of the transaction, and the like of the transaction. The data cleansing request may also include requirements for data cleansing, such as: and (5) cleaning out what data are. The data cleansing request may also correspond to a data cleansing scenario such as: a commission return business data cleansing scenario, an order data cleansing scenario, etc. The data cleansing request in the embodiment of the present specification may include an offline data cleansing request, and the offline data cleansing may implement cleansing of a large data volume, for example: and cleaning the transaction data of the past month to obtain the transaction data meeting the commission returning condition.

205. Receiving a case allocation request, and acquiring a target customer complaint case corresponding to the case allocation request;

206. acquiring text information of a target customer complaint case, preprocessing the text information, and vectorizing the preprocessed text information to acquire vector information corresponding to the target customer complaint case;

in this embodiment, the text needs to be segmented first because the word is the smallest meaningful language component that can be moved independently. When the words are divided, the single characters, punctuation marks and word groups are firstly separated by using jieba or other word dividing tools, and then the language words and other nonsense words are filtered out by contrasting the disabled word list. The description of each target complaint case is in text form, as described above, in order to enable the target complaint case to be used for model calculation, the target complaint case needs to be converted into vector form, and after the cases are vectorized, each case is converted into vector form. Each dimension of the vector represents the frequency with which the word appears in the case text in the lexicon V.

207. Similarity matching is carried out on the vector information and vector information corresponding to each customer complaint case in a preset database, and soft cosine similarity information of the target customer complaint case and each customer complaint case in the database is obtained;

in this embodiment, new customer complaint cases a are sequentially traversed with cases in the database, the case traversed each time is replaced with b, and the calculation formula is as follows:

where sij is sim (fi, fj), where fi denotes the word vector for the ith word and fj denotes the word vector for the jth word. ai represents the frequency with which the ith word appears in document a, and bi represents the frequency with which the jth word appears in document b. The soft cosine value calculated according to the formula can represent the similarity value of two documents, and the size of the similarity value is between 0 and 1.

208. Extracting cosine similarity information meeting preset conditions, and taking customer complaints in a database corresponding to the cosine similarity information meeting the preset conditions as similar cases;

in this embodiment, after the soft cosine similarity value is calculated for the target customer complaint case and each customer complaint case of the database, the customer complaint handler and the handling result of the most similar case may be selected as the recommended customer complaint handler and the handling result of the target customer complaint case, and on the other hand, appropriate customer complaint handlers may be recommended and matched according to the customer complaint handlers and the handling results of the plurality of recommended customer complaint cases as the recommendation results.

209. Acquiring case information and a target user associated with a target customer complaint case, and calculating the case score of the customer complaint case according to the case information;

210. obtaining customer complaint service information related to a preset customer complaint mechanism, and calculating the service grade of the customer complaint mechanism according to the customer complaint information;

211. and determining a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service grade, and distributing the customer complaint case to the target customer complaint mechanism.

The steps 205-208 in this embodiment are similar to the steps 101-104 in the first embodiment, and are not described herein again.

Referring to fig. 3, a third embodiment of the customer complaint case distribution method according to the embodiment of the present invention includes:

301. customer complaint data is obtained;

302. judging whether the customer complaint data is text data or not;

303. when the customer complaint data is voice data, carrying out voice-to-text processing on the customer complaint data to obtain text data corresponding to the customer complaint data;

304. configuring a data cleaning rule file, wherein the data cleaning rule file comprises at least one data cleaning rule, and the data cleaning rule comprises a data table name, a data cleaning rule pseudo code and a rule serial number;

in this embodiment, the data cleansing rule file includes: rule _ id is the rule flow number; table _ name is the name of the data table, i.e. the name of the data table to which the rule belongs; the bit _ offset is a rule serial number which is a binary offset and is used for marking data; a rule _ code is a data cleansing rule pseudo code; description, Chinese description of data cleaning rule; op _ level, the processing level of dirty data; is _ active is whether the rule is in effect.

It should be noted that each data cleansing rule is provided with a table _ name field, for example, when the table _ name is r _ gmv _ alipay, it indicates that the data cleansing rule is applied to a data table with a table name of r _ gmv _ alipay; meanwhile, each data cleaning rule is also provided with a rule sequence number bit _ offset field, and for each table _ name, such as r _ gmv _ alipay, the rule sequence numbers of the corresponding data cleaning rules are arranged in sequence and are not repeated. But the rule sequence number of the data cleaning rule of different data table names does not need to be changed. The data cleaning rule file only needs to be filled in once, and then can be updated conveniently.

305. Generating a data cleaning code according to the data cleaning rule file;

in this embodiment, for each data table, according to the data table name thereof, a data cleaning rule with the same data table name may be found in the data cleaning rule file, specifically, each data cleaning rule includes a field of the data table name table _ name to which the rule belongs, and for each data table, according to the table name table _ name of the data table, a data cleaning rule including the table _ name is searched in the data cleaning rule file, and all data cleaning rules applicable to the data table in the data cleaning rule file are found.

And then generating a data cleaning code for separating dirty data according to the data cleaning rules and the field information of the data table. The generation of the data cleaning code is automatically generated by adopting an automatic cleaning code generation tool developed by a shell programming language, and a series of conversion and combination are carried out on the content in the data cleaning rule file to generate the code which accords with the grammar of a distributed computing mechanism.

Specifically, the method for automatically generating the cleaning code of the invention comprises the following steps:

1) and reading the data cleaning rule corresponding to the data table name from the data cleaning rule file to generate a temporary file. Firstly, reading a data cleaning rule file into a memory, searching a table name matched with a data table to be cleaned at this time from the opened data cleaning rule file by using a grep (native operating system) tool, storing the found data cleaning rule into a temporary file for subsequent use, wherein the current effective data cleaning rule is a data cleaning rule.

2) And reading a first data cleaning rule of the temporary file, taking a data cleaning rule pseudo code in the data cleaning rule as a condition part for condition judgment, and generating a cleaning code aiming at the data cleaning rule. Reading the temporary file into a memory, reading a first data cleaning rule from the opened temporary file, assigning to a variable, putting the variable into a condition judgment statement, wherein the condition part of the condition judgment statement is a data cleaning rule pseudo code, and the execution part is to label the data to be cleaned after the judgment.

3) Traversing all the data cleaning rules in the temporary file, generating corresponding cleaning codes for each data cleaning rule, and combining the cleaning codes into a complete cleaning code of the data table. And traversing the rest rules, executing the operation of the step 2) on each rule, merging all codes and combining the codes into a complete cleaning code.

306. Executing data washing codes and labeling text data;

in this embodiment, submitting the data cleaning code to a distributed computing mechanism for operation to obtain cleaned data, where each piece of data is labeled, specifically includes the steps of: (1) reading data to be cleaned, setting an initial label for the data to be cleaned, and matching the data cleaning rules applicable to the data table one by one; (2) when the data to be cleaned triggers a data cleaning rule, the label value is increased by 2^ bit _ offset; (3) traversing all data cleaning rules applicable to the data table; (4) reading the next piece of data, repeating the steps (1) to (3), traversing each piece of data to be cleaned, and labeling each piece of data to be cleaned.

It should be noted that the default value of the initial tag of the data to be cleaned is 0, when the data cleaning rules applicable to the data table are matched one by one, each time a data cleaning rule is triggered, the tag value is increased by 2^ bit _ offset, otherwise, the tag value is not changed, that is, if any data cleaning rule is not triggered, the tag value is always 0.

307. Analyzing the label, and cleaning the text data according to the analysis result to obtain target user data;

in this embodiment, the dirty data is cleaned by cutting the dirty data from the original data table and transferring the cut dirty data to a special dirty data table, where each piece of dirty data in the special dirty data table indicates a rule sequence number of a data cleaning rule triggered by the dirty data table. Because the serial number of the data cleaning rule triggered by each piece of dirty data is known, the quantity of the dirty data cleaned by each rule can be obtained by summarizing the data cleaning rules by using an SQL language.

308. Receiving a case allocation request, and acquiring a target customer complaint case corresponding to the case allocation request;

309. acquiring case information and a target user associated with a target customer complaint case, and calculating the case score of the customer complaint case according to the case information;

310. obtaining customer complaint service information related to a preset customer complaint mechanism, and calculating the service grade of the customer complaint mechanism according to the customer complaint information;

311. and determining a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service grade, and distributing the customer complaint case to the target customer complaint mechanism.

The steps 301-302 in this embodiment are similar to the steps 201-203 in the second embodiment, and 308-311 is similar to the steps 101-104 in the first embodiment, which will not be described herein again.

Referring to fig. 4, a fourth embodiment of the customer complaint case distribution method according to the embodiment of the present invention includes:

401. receiving a case allocation request, and acquiring historical customer complaint records of a target user according to a main key corresponding to the target user;

in this embodiment, the historical customer appeal data includes historical customer appeal data of the target user in the specified APP and customer service staff in the APP, where the related historical customer appeal data is consultation customer appeal data related to financial product business purchased by the customer. Specifically, it may include, but is not limited to: the financial product types purchased by the users before, the borrowing institutions of the clients, the borrowing GPS address, the ID card address, the address of the collateral, the business attribution city and the like.

The transaction data related to the historical complaints can be obtained by inquiring the historical consultation records stored in the database of the transaction data. Alternatively, they may be obtained by other routes. For example, the user actively provides; for example, the general customer account information of the customer is automatically identified according to the incoming call number, and the identity of the customer is more accurately identified in the process of voice communication with the customer; firstly, judging whether the client appears as a main applicant in a client system or not according to the incoming call number of the client; and secondly judging whether the client is used as a related person and is used as a common contact, an emergency contact and the like of the applicant according to the incoming call number of the client.

In a practical scenario, the historical customer appeal data may also include other historical trading information that can reflect the trading habits of the user. In some possible implementation scenarios, other aspects of information may include, but are not limited to: and automatically matching the client information in an information list inquired by the system according to the description of the client, and accurately positioning the information of the client. And automatically analyzing information of case processing mechanisms and the like in sequence from multiple dimensions of a client borrowing mechanism, a borrowing GPS address, an ID card address, a mortgage location address, a business attribution city and the like according to the application information of the client. The method of acquiring the other historical customer information is not particularly limited. For example, the user actively provides; or through other channels, such as through trade industry blockchains, etc., to obtain the user's published historical information.

402. Extracting the characteristics of the historical customer complaint data of the target user through a preset characteristic extraction algorithm to generate characteristic words of the historical customer complaint data;

in this embodiment, the involved feature extraction algorithm may include, but is not limited to: the N-Gram algorithm. In a website or APP, a user may enter content that he wants to search in a search bar. Specifically, the text may be directly input, and the specific text may be a word, a phrase, or a combination thereof, or a sentence, or may be a keyword corresponding to the content by scanning the image and recognizing the content of the image. Specifically, the content of interest to the user is a keyword corresponding to a text input by the user, for example, the user inputs "a medicine for treating diabetes, which are others than metformin? For example, the keywords obtained are "diabetes", "diabetes treatment drug" and "metformin". For example, if the historical medical data is "drugs for diabetes treatment, which are in addition to metformin? Based on an N-Gram algorithm, extracting the characteristics of the Unigram, the Bigram, the Trigram and the like to obtain corresponding Unigram characteristics, Bigram characteristics, Trigram characteristics and the like; wherein each Unigram feature contains one word, each Bigram feature contains two words, and each Trigram feature contains three words. Based on this, the historical transaction characteristics that can be extracted after the above historical medical data is processed by the N-Gram algorithm may include, but are not limited to: sugar, urine, disease, treatment, second, first, second, guanidine, treatment, diabetes, treatment, medicament, metformin and the like.

403. Matching the feature words with the labels in a preset label library to obtain the labels matched with the target users;

in this embodiment, the feature words are used as keywords to be matched with the tags in the preset tag database, so as to obtain the tags corresponding to the target users. The tag information of the user can be the inherent attribute of the user, can also be the dynamic attribute of the user, and can also be the combination of the two, and different tag information can be obtained according to different service scenes. The inherent attributes comprise attributes of the user such as age, gender and occupation, and the dynamic attributes comprise attributes of historical behaviors purchased by the user and records viewed by browsing.

404. Performing multi-dimensional description on a target user based on a label and a preset label description model to generate a customer complaint portrait of the user;

in this embodiment, the user portrait is an effective tool for outlining the target user and associating the user appeal with the design direction. In the actual operation process, the attributes, behaviors and expectations of the user are often related to the shallowest apparent and life-close words. In this embodiment, the user representation is composed of a plurality of acquired tag information, the plurality of acquired tag information are composed into a text vector, and the composed text vector is used as the user representation of the user. The user complaint portrait in the embodiment refers to a portrait of a user with a data set of user-related complaint information and personal associated data fused, for example, after a user telephone is accessed, the user account information of the user, which is popular, is automatically identified according to an incoming call number, and the identity of the user is more accurately identified in the process of voice communication with the user; firstly, judging whether the client appears as a main applicant in a client system or not according to the incoming call number of the client; and secondly judging whether the client is used as a related person and is used as a common contact, an emergency contact and the like of the applicant according to the incoming call number of the client. In the initial dialogue, the client information is automatically matched in an information list inquired by the system according to the description of the client, the information of the client is accurately positioned, and the case processing mechanism is automatically analyzed in sequence from a plurality of dimensions of a client borrowing mechanism, a borrowing GPS address, an ID card address, a mortgage location address, a service attribution city and the like according to the application information of the client.

405. Acquiring a target customer complaint case corresponding to the case distribution request based on the customer complaint portrait of the user;

in the embodiment, the complaint case corresponding to the case allocation request is obtained according to the complaint portrait of the user, for example, after a telephone of a client is accessed, the customer account information of the client in the favor is automatically identified according to the incoming call number, and the identity of the client is more accurately identified in the process of voice communication with the client; firstly, judging whether the client appears as a main applicant in a client system or not according to the incoming call number of the client; and secondly judging whether the client is used as a related person and is used as a common contact, an emergency contact and the like of the applicant according to the incoming call number of the client. In the initial dialogue, the client information is automatically matched in an information list inquired by the system according to the description of the client, the information of the client is accurately positioned, and the case processing mechanism is automatically analyzed in sequence from a plurality of dimensions of a client borrowing mechanism, a borrowing GPS address, an ID card address, a mortgage location address, a service attribution city and the like according to the application information of the client. It should be noted that the customer complaint case corresponding to the received case allocation request in this embodiment may not only be set in advance according to the corresponding allocation rule, but also be obtained in real time by the server from a preset customer complaint database corresponding to the customer complaint handling mechanism when the case allocation request is received.

406. Acquiring case information and a target user associated with a target customer complaint case, and calculating the case score of the customer complaint case according to the case information;

407. obtaining customer complaint service information related to a preset customer complaint mechanism, and calculating the service grade of the customer complaint mechanism according to the customer complaint information;

408. and determining a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service grade, and distributing the customer complaint case to the target customer complaint mechanism.

The steps 406-408 in the present embodiment are similar to the steps 102-104 in the first embodiment, and are not described herein again.

Referring to fig. 5, a fifth embodiment of the customer complaint case distribution method according to the embodiment of the present invention includes:

501. receiving a case allocation request, and acquiring a target customer complaint case corresponding to the case allocation request;

502. acquiring case information and a target user associated with a target customer complaint case, and calculating the case score of the customer complaint case according to the case information;

503. obtaining customer complaint service information related to a preset customer complaint mechanism, and calculating the service grade of the customer complaint mechanism according to the customer complaint information;

504. inquiring a preset classification table, acquiring a service grade matched with the case score, and taking a preset customer complaint mechanism corresponding to the service grade as a target customer complaint mechanism;

in this embodiment, a server queries a preset classification table, where the preset classification table refers to a preset customer complaint case score and customer complaint organization grade correspondence table, and the server obtains a service grade matched with the case score and takes a preset customer complaint organization corresponding to the service grade as a target customer complaint organization; when the number of the target customer complaint mechanisms is not less than two, that is, when a plurality of the current customer complaint mechanisms meet the case distribution condition, the server needs to select one of the target customer complaint mechanisms to distribute the case, in this embodiment, the customer complaint case is distributed to the target customer complaint mechanism with the highest customer complaint processing efficiency, so as to realize the rapid processing of the customer complaint case.

In this embodiment, when the server receives a customer complaint case allocation request, the server scores the customer complaint cases according to the customer complaint case information, then the server obtains service information of a preset customer complaint mechanism and calculates a service level of the preset customer complaint mechanism according to the customer complaint service information, and the server determines a target customer complaint mechanism corresponding to the customer complaint case according to the case scoring and the service level to allocate the customer complaint cases, so that the server considers different influence factors when performing the customer complaint case allocation, and the customer complaint case allocation is more reasonable.

505. And distributing the case to corresponding case handlers in the target customer complaint mechanism according to a preset rule, and recording the case processing flow.

In the embodiment, under each mechanism, a handler is identified according to a certain custom rule, a case is allocated to the handler for processing, and a case processing flow is recorded. For example, the same customer complains and distributes to the same processor under the same organization for processing; distributing case handlers according to the type of the complaint service and the complaint level; case handlers are automatically assigned under the level according to the priority and the weight. In practical application, case allocation is automatically carried out according to the case information and the relevance between the cases and the clients, case handlers are automatically identified, and case processing procedures are recorded.

The steps 501-603 in this embodiment are similar to the steps 101-103 in the first embodiment, and are not described herein again.

With reference to fig. 6, the customer complaint case distribution method in the embodiment of the present invention is described above, and a first embodiment of the customer complaint case distribution device in the embodiment of the present invention includes:

a first obtaining module 601, configured to receive a case allocation request, and obtain a target customer complaint case corresponding to the case allocation request;

a first calculating module 602, configured to obtain case information and a target user associated with the target customer complaint case, and calculate a case score of the customer complaint case according to the case information;

a second calculating module 603, configured to obtain customer complaint service information associated with a preset customer complaint organization, and calculate a service level of the customer complaint organization according to the customer complaint information;

and the allocating module 604 is configured to determine a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service level, and allocate the customer complaint case to the target customer complaint mechanism.

Referring to fig. 7, a customer complaint case distribution device according to a second embodiment of the present invention specifically includes:

In this embodiment, the customer complaint case distribution device includes:

a second obtaining module 605, configured to obtain customer complaint data, where the customer complaint data is a customer complaint record of a target user;

a judging module 606, configured to judge whether the customer complaint data is text data;

a processing module 607, configured to perform voice-to-text processing on the customer complaint data when the customer complaint data is voice data, to obtain text data corresponding to the customer complaint data;

a data cleaning module 608, configured to perform data cleaning on the text data to obtain target user data, where the target user data carries a primary key corresponding to the target user.

In this embodiment, the customer complaint case distribution device includes:

a third obtaining module 609, configured to obtain text information of a target customer complaint case, pre-process the text information, and vectorize the pre-processed text information to obtain vector information corresponding to the target customer complaint case;

a matching module 610, configured to perform similarity matching on the vector information and vector information corresponding to each customer complaint case in a preset database, so as to obtain soft cosine similarity information between the target customer complaint case and each customer complaint case in the database;

the extracting module 611 is configured to extract cosine similarity information meeting a preset condition, and use a customer complaint case in the database corresponding to the cosine similarity information meeting the preset condition as a similar case.

In this embodiment, the data cleaning module 608 is specifically configured to:

generating a data cleaning code according to the data cleaning rule file;

executing the data cleaning code, and labeling the text data;

In this embodiment, the first obtaining module 601 is specifically configured to:

In this embodiment, the allocating module 604 includes:

a query unit 6041, configured to query a preset classification table, obtain a service level matched with the case score, and use a preset customer complaint mechanism corresponding to the service level as a target customer complaint mechanism;

and the allocating unit 6042 is configured to allocate the customer complaint case to a corresponding case handler in the target customer complaint institution according to a preset rule, and record a case handling flow.

Fig. 6 and 7 describe the customer complaint case distribution device in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the customer complaint case distribution device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

Fig. 8 is a schematic structural diagram of a customer complaint case distribution apparatus 800 according to an embodiment of the present invention, where the customer complaint case distribution apparatus 800 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 810 (e.g., one or more processors) and a memory 820, and one or more storage media 830 (e.g., one or more mass storage devices) storing an application 833 or data 832. Memory 820 and storage medium 830 may be, among other things, transient or persistent storage. The program stored on the storage medium 830 may include one or more modules (not shown), each of which may include a series of instruction operations for the customer complaint case distribution apparatus 800. Still further, the processor 810 may be configured to communicate with the storage medium 830, and execute a series of instruction operations in the storage medium 830 on the customer case distribution apparatus 800 to implement the steps of the customer case distribution method provided by the above-mentioned method embodiments.

The customer complaint distribution apparatus 800 may also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input-output interfaces 860, and/or one or more operating systems 831, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the customer complaint case distribution apparatus configuration shown in FIG. 8 does not constitute a limitation of the customer complaint case distribution apparatus provided herein, and may include more or less components than shown, or some components in combination, or a different arrangement of components.

The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, or a volatile computer-readable storage medium, having stored therein instructions, which, when executed on a computer, cause the computer to perform the steps of the above customer complaint case allocation method.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A customer complaint case distribution method is characterized by comprising the following steps:

and determining a target customer complaint mechanism corresponding to the customer complaint case according to the case score and the service grade, and distributing the customer complaint case to the target customer complaint handling personnel according to a preset rule.

2. The customer complaint case distribution method according to claim 1, further comprising, before the receiving a case distribution request and acquiring a target customer complaint case corresponding to the case distribution request:

judging whether the customer complaint data is text data or not;

3. The customer complaint case distribution method according to claim 1, further comprising, after the receiving a case distribution request and acquiring a target customer complaint case corresponding to the case distribution request:

4. The customer complaint case distribution method of claim 2, wherein the data cleansing of the text data to obtain target user data comprises:

generating a data cleaning code according to the data cleaning rule file;

executing the data cleaning code, and labeling the text data;

5. The customer complaint case distribution method of claim 1, wherein the receiving a case distribution request and obtaining a target customer complaint case corresponding to the case distribution request comprises:

6. The customer complaint case distribution method of claim 1, wherein the determining a target customer complaint organization corresponding to the customer complaint case according to the case score and the service level, and distributing the customer complaint case to the target customer complaint organization comprises:

7. A customer complaint case distribution device characterized by comprising:

8. The customer complaint case distribution device as claimed in claim 7, characterized in that it comprises:

9. The customer complaint case distribution device of claim 7, wherein the first obtaining module is specifically configured to:

10. A customer complaint case distribution apparatus, characterized by comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;

the at least one processor invoking the instructions in the memory to cause the customer complaint case distribution apparatus to perform the steps of the customer complaint case distribution method of any of claims 1-6.

11. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when being executed by a processor, carries out the steps of the customer complaint case distribution method of any one of claims 1-6.