CN112907305A - Customer full-period management system based on big data analysis - Google Patents
Customer full-period management system based on big data analysis Download PDFInfo
- Publication number
- CN112907305A CN112907305A CN202110396676.7A CN202110396676A CN112907305A CN 112907305 A CN112907305 A CN 112907305A CN 202110396676 A CN202110396676 A CN 202110396676A CN 112907305 A CN112907305 A CN 112907305A
- Authority
- CN
- China
- Prior art keywords
- customer
- event
- module
- client
- activity event
- 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.)
- Granted
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a customer full-period management system based on big data analysis, which relates to the technical field of customer management and solves the technical problem that the existing scheme can not fully utilize customer resources and can not realize accurate service; the product information module is arranged, and the product information module is used for acquiring product information, so that the accuracy and comprehensiveness of the product information are ensured, detailed reference can be provided for customers, and data support is provided for the event decision module; the invention is provided with a client portrait module, which realizes the accurate portrayal of the client portrait through transaction behavior data, ensures the accuracy of the client portrait and provides data support for an event decision module; the event decision module is arranged, and the activity event parameters are obtained by combining the product information, the client portrait, the client label and the error reverse propagation neural network model, so that the accuracy and the reasonability of the activity event parameters are ensured, and the smooth execution of the activity event parameters is facilitated.
Description
Technical Field
The invention belongs to the field of customer management systems, relates to a big data technology, and particularly relates to a customer full-period management system based on big data analysis.
Background
When the current customer relationship is managed, the customer resources are redundant, and when the customer resources are distributed to a certain marketing person and a customer order cannot be generated, the customer resources cannot be disclosed to other marketing persons, so that the waste of the customer resources is caused, and the fair competition of the customer during marketing is influenced; at present, most of client management systems only have the information data query management function of clients, and are simple and crude in function, complex in operation and low in intelligence degree.
The invention patent with publication number CN111754242A provides a client management system based on a cloud platform, which comprises a management client and a cloud platform, wherein the management client is connected with the cloud platform through a wireless communication terminal, a registration login module, an exploitation client module and a service client module are arranged in the management client, and the registration login module is used for performing registration by a worker of the management client.
According to the scheme, the intelligent optimization recommendation module, the screening function unit and the client development recommendation unit lamp are arranged, so that the effects of facilitating use, maintenance and development of clients by workers are achieved; at that time, the above scheme is too simple to manage the customer resources, and the customer resources cannot be fully utilized; therefore, the above solution still needs further improvement.
Disclosure of Invention
In order to solve the problems existing in the scheme, the invention provides a customer full-period management system based on big data analysis.
The purpose of the invention can be realized by the following technical scheme: the customer full-period management system based on big data analysis comprises a processor, a data center module, a product information module, a customer portrait module, an event decision module, an event execution module, an event feedback module and a data storage module;
the data center module acquires and stores transaction behavior data of the customer through an information interaction channel and respectively sends the transaction behavior data to the customer image module and the data storage module;
the client portrait module acquires a client portrait according to the transaction behavior data of the client, generates a client label and simultaneously sends the client portrait and the client label to the event decision module;
the event decision module generates activity event parameters based on the product information, the customer representation, and the customer label, including:
acquiring historical parameters of the activity event through a data storage module; the activity event historical parameters comprise activity event parameters and corresponding product information, customer figures and customer labels, and the activity time historical parameters are completed activity event parameter records;
carrying out principal component analysis on historical parameters of the activity event by a principal component analysis method to obtain a plurality of groups of event parameter analysis sequences;
sequentially setting numbers for an executor of the activity event, an execution object of the activity event, the execution time of the activity event, an execution channel of the activity event and the execution content of the activity event in the activity event parameters, sequentially combining the numbers to generate an activity event parameter sequence, and establishing a parameter training set according to the activity event parameter sequence and a corresponding event parameter analysis sequence;
establishing an error reverse propagation neural network model; the error reverse propagation neural network model at least comprises a hidden layer;
dividing the parameter training set into a training set, a test set and a check set according to a set proportion;
training, testing and verifying the error reverse propagation neural network through a training set, a testing set and a verifying set, and marking the trained error reverse propagation neural network as an event parameter prediction model;
marking the product information, the customer portrait and the customer label received by the event decision module as input data;
inputting input data into an event parameter prediction model to obtain predicted activity event parameters and marking the predicted activity event parameters as standard event parameters;
and respectively sending the standard event parameters to the event execution module and the data storage module.
Preferably, the event execution module is configured to execute the standard event parameter and generate a feedback result, where the feedback result includes an execution state and an execution time; and the event feedback module integrates according to the feedback result to generate the transaction behavior data of the customer.
Preferably, the event parameter analysis sequences comprise key factors, key weights and corresponding activity event parameters, the key factors correspond to the key weights one by one, the key weights are all larger than or equal to a weight threshold, the weight threshold is larger than 0.5, and the key factors are obtained from product information, customer figures and customer labels through a principal component analysis method.
Preferably, the product information module is used for editing product information; the product information includes a product name, a product category, a product income, a product period, a product risk, a product amount, and a product transaction channel.
Preferably, the activity event parameters include an executive person of the activity event, an executive object of the activity event, an executive time of the activity event, an executive channel of the activity event and executive contents of the activity event; the execution channel comprises a mobile phone bank, an online bank, a network counter, a telephone, a short message and a WeChat.
Preferably, the customer representation includes customer product preferences, customer channel preferences, customer risk preferences, customer marketing responses, customer economic strength, and customer interest preferences; the customer label includes a product term, a customer birthday, a customer account age, and a customer grade.
Preferably, the obtaining of the customer rating specifically includes the following steps:
acquiring the service handling times of a client in a set period and marking the service handling times as SYC; the set period comprises one month, three months, six months and twelve months;
obtaining the overdue times of the loan of the client, and marking the overdue times of the loan as DYC; extracting the residential address of the user through the reserved identity card image of the client, calculating the distance between the residential address and the business hall, and marking the distance as JL;
when the service transaction times SYC of the client meet the SYC<When the system is L1, the credit evaluation is not carried out on the client, when SYC is more than or equal to L1, the credit evaluation is carried out on the client, and the client is subjected to the credit evaluation through a formula
Obtaining a reputation evaluation coefficient YXPX of a customer; wherein L1 is a threshold value of service transaction times, L1 is an integer greater than 0, α 1 and α 2 are proportionality coefficients, and both α 1 and α 2 are real numbers greater than 0;
when the reputation evaluation coefficient YXPX is greater than or equal to the reputation evaluation coefficient threshold value, judging that the corresponding customer is a target customer; the reputation evaluation coefficient threshold is obtained through simulation of a large amount of data;
integrating the screened target customers to obtain a target customer base;
acquiring a grade division model through a data storage module;
acquiring transaction behavior data corresponding to a target client in a target client library and marking the transaction behavior data as input data;
inputting input data into a grade division model to obtain an output result, and marking the output result as a customer grade after data reverse normalization.
Preferably, the obtaining of the ranking model specifically includes the following steps:
acquiring an original client library through a data storage module; the original customer base comprises customer grades and transaction behavior data of original customers, wherein the original customers refer to the customers with the customer grades set; the customer rating is an integer greater than or equal to 1 and less than or equal to 20;
dividing transaction behavior data in an original customer base and corresponding customer grades into a training set, a test set and a check set according to a set proportion through a processor; the set ratio comprises 2:1:1, 3:1:1 and 4:3: 1;
constructing a fusion model; the fusion model is constructed by combining at least two of a support vector machine, a deep convolutional neural network and an RBF neural network with a fusion mode, wherein the fusion mode comprises a linear weighting fusion method, a cross fusion method, a waterfall fusion method, a feature fusion method and a prediction fusion method;
training, testing and checking the fusion model after the training set, the testing set and the checking set are subjected to data normalization, and marking the trained fusion model as a grade division model;
and sending the grading model to a data storage module for storage through the processor.
Preferably, the information interaction channel comprises a short message platform, a counter system, an ATM system, a WeChat bank and an online bank; the transaction behavior data comprises a product name, a product type, transaction time, a transaction amount, a product period, product risks, a transaction channel and customer information of transaction, the customer information comprises a customer name, a customer birthday and a customer account age, and the transaction channel comprises an ATM system, a WeChat bank, an online bank and a counter system.
Preferably, the processor is respectively in communication connection with the data center module, the product information module, the client portrait module, the event decision module, the event execution module, the event feedback module and the data storage module; the data center module is respectively in communication connection with the product information module and the client portrait module, the event feedback module is respectively in communication connection with the data storage module and the event execution module, and the event decision module is respectively in communication connection with the event execution module and the client portrait module.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention sets up the product information module, this arrangement is used for editing the product information; the product information module is used for editing product names, product types, product benefits, product periods, product risks, product limits and product transaction channels to generate complete product information, so that the accuracy and comprehensiveness of the product information are guaranteed, detailed references can be provided for customers, and data support is provided for the event decision module;
2. the invention is provided with a customer portrait module, which acquires customer portraits according to the transaction behavior data of customers and generates customer labels; the client portrait module realizes the accurate portrayal of the client portrait through the transaction behavior data, ensures the accuracy of the client portrait and provides data support for the event decision module;
3. the invention is provided with an event decision module, which generates activity event parameters according to product information, a customer portrait and a customer label; the event decision module acquires the activity event parameters through the combination of product information, customer figures, customer labels and an error reverse propagation neural network model, the whole process is automatically completed, the accuracy and the reasonability of the activity event parameters are guaranteed, and the smooth execution of the activity event parameters is facilitated.
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 described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic diagram of the principle of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a customer full-period management system based on big data analysis includes a processor, a data center module, a product information module, a customer portrait module, an event decision module, an event execution module, an event feedback module, and a data storage module;
the data center module acquires and stores transaction behavior data of the customer through an information interaction channel and respectively sends the transaction behavior data to the customer image module and the data storage module;
the client portrait module acquires a client portrait according to the transaction behavior data of the client, generates a client label and simultaneously sends the client portrait and the client label to the event decision module;
the event decision module generates activity event parameters based on the product information, the customer representation, and the customer tag, including:
acquiring historical parameters of the activity event through a data storage module; the activity event history parameters comprise activity event parameters and corresponding product information, customer figures and customer labels, and the activity time history parameters are completed activity event parameter records;
carrying out principal component analysis on historical parameters of the activity event by a principal component analysis method to obtain a plurality of groups of event parameter analysis sequences;
sequentially setting numbers for an executor of the activity event, an execution object of the activity event, the execution time of the activity event, an execution channel of the activity event and the execution content of the activity event in the activity event parameters, sequentially combining the numbers to generate an activity event parameter sequence, and establishing a parameter training set according to the activity event parameter sequence and a corresponding event parameter analysis sequence;
establishing an error reverse propagation neural network model; the error reverse propagation neural network model at least comprises a hidden layer;
dividing the parameter training set into a training set, a test set and a check set according to a set proportion;
training, testing and verifying the error reverse propagation neural network through a training set, a testing set and a verifying set, and marking the trained error reverse propagation neural network as an event parameter prediction model;
marking the product information, the customer portrait and the customer label received by the event decision module as input data;
inputting input data into an event parameter prediction model to obtain predicted activity event parameters and marking the predicted activity event parameters as standard event parameters;
and respectively sending the standard event parameters to the event execution module and the data storage module.
Further, the event execution module is used for executing the standard event parameters and generating a feedback result, wherein the feedback result comprises an execution state and an execution time; and the event feedback module integrates according to the feedback result to generate the transaction behavior data of the customer.
Further, the event parameter analysis sequences comprise key factors, key weights and corresponding activity event parameters, the key factors correspond to the key weights one by one, the key weights are all larger than or equal to a weight threshold value, the weight threshold value is larger than 0.5, and the key factors are obtained from the product information, the customer portrait and the customer label through a principal component analysis method.
Further, the product information module is used for editing product information; the product information includes a product name, a product category, a product income, a product period, a product risk, a product amount, and a product transaction channel.
Further, the activity event parameters comprise an executive person of the activity event, an executive object of the activity event, an executive time of the activity event, an executive channel of the activity event and executive content of the activity event; the execution channels comprise mobile phone banks, online banks, network counters, telephones, short messages and WeChat.
Further, the customer representation includes customer product preferences, customer channel preferences, customer risk preferences, customer marketing responses, customer economic strength, and customer interest preferences; the customer label includes a product term, a customer birthday, a customer account age, and a customer grade.
Further, the obtaining of the customer level specifically includes the following steps:
acquiring the service handling times of a client in a set period and marking the service handling times as SYC; the set period includes one month, three months, six months and twelve months;
obtaining the overdue times of the loan of the client, and marking the overdue times of the loan as DYC; extracting the residential address of the user through the reserved identity card image of the client, calculating the distance between the residential address and the business hall, and marking the distance as JL;
when the service transaction times SYC of the client meet the SYC<When the system is L1, the credit evaluation is not carried out on the client, when SYC is more than or equal to L1, the credit evaluation is carried out on the client, and the client is subjected to the credit evaluation through a formula
Obtaining a reputation evaluation coefficient YXPX of a customer; wherein L1 is a threshold value of service transaction times, L1 is an integer greater than 0, α 1 and α 2 are proportionality coefficients, and both α 1 and α 2 are real numbers greater than 0;
when the reputation evaluation coefficient YXPX is greater than or equal to the reputation evaluation coefficient threshold value, judging that the corresponding customer is a target customer; the credit evaluation coefficient threshold is obtained through a large amount of data simulation;
integrating the screened target customers to obtain a target customer base;
acquiring a grade division model through a data storage module;
acquiring transaction behavior data corresponding to a target client in a target client library and marking the transaction behavior data as input data;
inputting input data into a grade division model to obtain an output result, and marking the output result as a customer grade after data reverse normalization.
Further, the obtaining of the grade division model specifically includes the following steps:
acquiring an original client library through a data storage module; the original customer base comprises customer grade and transaction behavior data of an original customer, wherein the original customer refers to a customer with a customer grade set; an integer having a customer rank of 1 or more and 20 or less;
dividing transaction behavior data in an original customer base and corresponding customer grades into a training set, a test set and a check set according to a set proportion through a processor; the set ratio comprises 2:1:1, 3:1:1 and 4:3: 1;
constructing a fusion model; the fusion model is constructed by combining at least two of a support vector machine, a deep convolutional neural network and an RBF neural network with a fusion mode, wherein the fusion mode comprises a linear weighting fusion method, a cross fusion method, a waterfall fusion method, a feature fusion method and a prediction fusion method;
training, testing and checking the fusion model after the training set, the testing set and the checking set are subjected to data normalization, and marking the trained fusion model as a grade division model;
and sending the grading model to a data storage module for storage through the processor.
Further, the information interaction channel comprises a short message platform, a counter system, an ATM system, a WeChat bank and an online bank; the transaction behavior data comprises the name of a product, the type of the product, transaction time, transaction amount, product period, product risk, transaction channel and customer information of a transaction, the customer information comprises customer name, customer birthday and customer account age, and the transaction channel comprises an ATM system, a WeChat bank, an online bank and a counter system.
Further, the processor is respectively in communication connection with the data center module, the product information module, the client portrait module, the event decision module, the event execution module, the event feedback module and the data storage module; the data center module is respectively in communication connection with the product information module and the client portrait module, the event feedback module is respectively in communication connection with the data storage module and the event execution module, and the event decision module is respectively in communication connection with the event execution module and the client portrait module.
The above formulas are all calculated by removing dimensions and taking numerical values thereof, the formula is a formula which is obtained by acquiring a large amount of data and performing software simulation to obtain the closest real situation, and the preset parameters and the preset threshold value in the formula are set by the technical personnel in the field according to the actual situation or obtained by simulating a large amount of data.
The working principle of the invention is as follows:
the data center module acquires and stores transaction behavior data of the customer through an information interaction channel and respectively sends the transaction behavior data to the customer image module and the data storage module;
the client portrait module acquires a client portrait according to the transaction behavior data of the client, generates a client label and simultaneously sends the client portrait and the client label to the event decision module;
acquiring the service handling times of a client in a set period and marking the service handling times as SYC; obtaining the overdue times of the loan of the client, and marking the overdue times of the loan as DYC; extracting the residential address of the user through the reserved identity card image of the client, calculating the distance between the residential address and the business hall, and marking the distance as JL; when the service transaction times SYC of the client meet the SYC < L1, the credit evaluation is not carried out on the client, and when the SYC is more than or equal to L1, the credit evaluation is carried out on the client to obtain the credit evaluation coefficient YXPX of the client; when the reputation evaluation coefficient YXPX is greater than or equal to the reputation evaluation coefficient threshold value, judging that the corresponding customer is a target customer; integrating the screened target customers to obtain a target customer base; acquiring a grade division model through a data storage module; acquiring transaction behavior data corresponding to a target client in a target client library and marking the transaction behavior data as input data; inputting input data into a grade division model to obtain an output result, and marking the output result as a client grade after data inverse normalization;
acquiring historical parameters of the activity event through a data storage module; carrying out principal component analysis on historical parameters of the activity event by a principal component analysis method to obtain a plurality of groups of event parameter analysis sequences; sequentially setting numbers for an executor of the activity event, an execution object of the activity event, the execution time of the activity event, an execution channel of the activity event and the execution content of the activity event in the activity event parameters, sequentially combining the numbers to generate an activity event parameter sequence, and establishing a parameter training set according to the activity event parameter sequence and a corresponding event parameter analysis sequence; establishing an error reverse propagation neural network model; the error reverse propagation neural network model at least comprises a hidden layer; dividing the parameter training set into a training set, a test set and a check set according to a set proportion; training, testing and verifying the error reverse propagation neural network through a training set, a testing set and a verifying set, and marking the trained error reverse propagation neural network as an event parameter prediction model; marking the product information, the customer portrait and the customer label received by the event decision module as input data; inputting input data into an event parameter prediction model to obtain predicted activity event parameters and marking the predicted activity event parameters as standard event parameters; and respectively sending the standard event parameters to the event execution module and the data storage module.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (9)
1. The customer full-period management system based on big data analysis is characterized by comprising a processor, a data center module, a product information module, a customer portrait module, an event decision module, an event execution module, an event feedback module and a data storage module;
the data center module acquires and stores transaction behavior data of the customer through an information interaction channel and respectively sends the transaction behavior data to the customer image module and the data storage module;
the client portrait module acquires a client portrait according to the transaction behavior data of the client, generates a client label and simultaneously sends the client portrait and the client label to the event decision module;
the event decision module generates activity event parameters based on the product information, the customer representation, and the customer label, including:
acquiring historical parameters of the activity event through a data storage module; the activity event historical parameters comprise activity event parameters and corresponding product information, customer figures and customer labels, and the activity time historical parameters are completed activity event parameter records;
carrying out principal component analysis on historical parameters of the activity event by a principal component analysis method to obtain a plurality of groups of event parameter analysis sequences;
sequentially setting numbers for an executor of the activity event, an execution object of the activity event, the execution time of the activity event, an execution channel of the activity event and the execution content of the activity event in the activity event parameters, sequentially combining the numbers to generate an activity event parameter sequence, and establishing a parameter training set according to the activity event parameter sequence and a corresponding event parameter analysis sequence;
establishing an error reverse propagation neural network model; the error reverse propagation neural network model at least comprises a hidden layer;
dividing the parameter training set into a training set, a test set and a check set according to a set proportion;
training, testing and verifying the error reverse propagation neural network through a training set, a testing set and a verifying set, and marking the trained error reverse propagation neural network as an event parameter prediction model;
marking the product information, the customer portrait and the customer label received by the event decision module as input data;
inputting input data into an event parameter prediction model to obtain predicted activity event parameters and marking the predicted activity event parameters as standard event parameters;
and respectively sending the standard event parameters to the event execution module and the data storage module.
2. The big data analysis-based customer full cycle management system according to claim 1, wherein the event execution module is configured to execute standard event parameters and generate feedback results, the feedback results comprising an execution status and an execution time; and the event feedback module integrates according to the feedback result to generate the transaction behavior data of the customer.
3. The customer full-period management system based on big data analysis according to claim 1, wherein the plurality of sets of event parameter analysis sequences comprise key factors, key weights and corresponding activity event parameters, the key factors and the key weights are in one-to-one correspondence, the key weights are all greater than or equal to a weight threshold, the weight threshold is greater than 0.5, and the key factors are obtained from product information, customer figures and customer labels through a principal component analysis method.
4. The big data analysis-based customer full cycle management system according to claim 1, wherein the product information module is configured to edit product information; the product information includes a product name, a product category, a product income, a product period, a product risk, a product amount, and a product transaction channel.
5. The big data analysis-based customer full-period management system according to claim 1, wherein the activity event parameters comprise an executive of the activity event, an executive object of the activity event, an execution time of the activity event, an execution channel of the activity event and an execution content of the activity event; the execution channel comprises a mobile phone bank, an online bank, a network counter, a telephone, a short message and a WeChat.
6. The big data analytics-based customer full cycle management system of claim 1, wherein the customer representation includes customer product preferences, customer channel preferences, customer risk preferences, customer marketing responses, customer economic strength, and customer interest preferences; the customer label includes a product term, a customer birthday, a customer account age, and a customer grade.
7. The big data analysis-based client full-period management system as claimed in claim 6, wherein the number of business transactions of a client in a set period is obtained and marked as SYC; the set period comprises one month, three months, six months and twelve months;
obtaining the overdue times of the loan of the client, and marking the overdue times of the loan as DYC; extracting the residential address of the user through the reserved identity card image of the client, calculating the distance between the residential address and the business hall, and marking the distance as JL;
when the service transaction times SYC of the client meet the SYC<When the system is L1, the credit evaluation is not carried out on the client, when SYC is more than or equal to L1, the credit evaluation is carried out on the client, and the client is subjected to the credit evaluation through a formula
Obtaining a reputation evaluation coefficient YXPX of a customer; wherein L1 is a threshold value of service transaction times, L1 is an integer greater than 0, α 1 and α 2 are proportionality coefficients, and both α 1 and α 2 are real numbers greater than 0;
when the reputation evaluation coefficient YXPX is greater than or equal to the reputation evaluation coefficient threshold value, judging that the corresponding customer is a target customer; the reputation evaluation coefficient threshold is obtained through simulation of a large amount of data;
integrating the screened target customers to obtain a target customer base;
acquiring a grade division model through a data storage module;
acquiring transaction behavior data corresponding to a target client in a target client library and marking the transaction behavior data as input data;
inputting input data into a grade division model to obtain an output result, and marking the output result as a customer grade after data reverse normalization.
8. The big data analysis-based customer full-cycle management system according to claim 7, wherein the obtaining of the ranking model specifically comprises the following steps:
acquiring an original client library through a data storage module; the original customer base comprises customer grades and transaction behavior data of original customers, wherein the original customers refer to the customers with the customer grades set; the customer rating is an integer greater than or equal to 1 and less than or equal to 20;
dividing transaction behavior data in an original customer base and corresponding customer grades into a training set, a test set and a check set according to a set proportion through a processor; the set ratio comprises 2:1:1, 3:1:1 and 4:3: 1;
constructing a fusion model; the fusion model is constructed by combining at least two of a support vector machine, a deep convolutional neural network and an RBF neural network with a fusion mode, wherein the fusion mode comprises a linear weighting fusion method, a cross fusion method, a waterfall fusion method, a feature fusion method and a prediction fusion method;
training, testing and checking the fusion model after the training set, the testing set and the checking set are subjected to data normalization, and marking the trained fusion model as a grade division model;
and sending the grading model to a data storage module for storage through the processor.
9. The customer full-period management system based on big data analysis as claimed in claim 1, wherein the information interaction channel comprises a short message platform, a counter system, an ATM system, a WeChat bank and an online bank; the transaction behavior data comprises a product name, a product type, transaction time, a transaction amount, a product period, product risks, a transaction channel and customer information of transaction, the customer information comprises a customer name, a customer birthday and a customer account age, and the transaction channel comprises an ATM system, a WeChat bank, an online bank and a counter system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110396676.7A CN112907305B (en) | 2021-04-13 | 2021-04-13 | Customer full-period management system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110396676.7A CN112907305B (en) | 2021-04-13 | 2021-04-13 | Customer full-period management system based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112907305A true CN112907305A (en) | 2021-06-04 |
| CN112907305B CN112907305B (en) | 2021-11-23 |
Family
ID=76110610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110396676.7A Active CN112907305B (en) | 2021-04-13 | 2021-04-13 | Customer full-period management system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112907305B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113246421A (en) * | 2021-07-07 | 2021-08-13 | 广州中和互联网技术有限公司 | Big data-based injection molding industry data processing system and method |
| CN113379529A (en) * | 2021-06-07 | 2021-09-10 | 广发银行股份有限公司 | Collaborative decision engine application framework |
| CN113556318A (en) * | 2021-06-07 | 2021-10-26 | 广州康辰科技有限公司 | E-commerce verification method based on cloud security |
| CN113822715A (en) * | 2021-09-23 | 2021-12-21 | 安徽数据堂科技有限公司 | Data acquisition, training and processing integrated platform analysis method |
| CN115487589A (en) * | 2022-11-08 | 2022-12-20 | 湖南富海环保科技有限公司 | Automatic filtration control management system for water plant filter tank |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170316438A1 (en) * | 2016-04-29 | 2017-11-02 | Genesys Telecommunications Laboratories, Inc. | Customer experience analytics |
| CN110009432A (en) * | 2019-04-15 | 2019-07-12 | 武汉理工大学 | A kind of personal consumption behavior prediction technique |
| CN110555714A (en) * | 2018-06-04 | 2019-12-10 | 百度在线网络技术（北京）有限公司 | method and apparatus for outputting information |
| CN112464094A (en) * | 2020-11-30 | 2021-03-09 | 泰康保险集团股份有限公司 | Information recommendation method and device, electronic equipment and storage medium |
-
2021
- 2021-04-13 CN CN202110396676.7A patent/CN112907305B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170316438A1 (en) * | 2016-04-29 | 2017-11-02 | Genesys Telecommunications Laboratories, Inc. | Customer experience analytics |
| CN110555714A (en) * | 2018-06-04 | 2019-12-10 | 百度在线网络技术（北京）有限公司 | method and apparatus for outputting information |
| CN110009432A (en) * | 2019-04-15 | 2019-07-12 | 武汉理工大学 | A kind of personal consumption behavior prediction technique |
| CN112464094A (en) * | 2020-11-30 | 2021-03-09 | 泰康保险集团股份有限公司 | Information recommendation method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 刘承水 等: "基于价值的客户序位评价应用研究", 《管理科学》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113379529A (en) * | 2021-06-07 | 2021-09-10 | 广发银行股份有限公司 | Collaborative decision engine application framework |
| CN113556318A (en) * | 2021-06-07 | 2021-10-26 | 广州康辰科技有限公司 | E-commerce verification method based on cloud security |
| CN113556318B (en) * | 2021-06-07 | 2023-07-07 | 广西叫酒网络科技有限公司 | Electronic commerce verification method based on cloud security |
| CN113246421A (en) * | 2021-07-07 | 2021-08-13 | 广州中和互联网技术有限公司 | Big data-based injection molding industry data processing system and method |
| CN113246421B (en) * | 2021-07-07 | 2021-10-08 | 广州中和互联网技术有限公司 | Big data-based injection molding industry data processing system and method |
| CN113822715A (en) * | 2021-09-23 | 2021-12-21 | 安徽数据堂科技有限公司 | Data acquisition, training and processing integrated platform analysis method |
| CN115487589A (en) * | 2022-11-08 | 2022-12-20 | 湖南富海环保科技有限公司 | Automatic filtration control management system for water plant filter tank |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112907305B (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112907305B (en) | Customer full-period management system based on big data analysis | |
| CN110111198A (en) | User's financial risks predictor method, device, electronic equipment and readable medium | |
| CN110417721A (en) | Safety risk estimating method, device, equipment and computer readable storage medium | |
| CN110163683B (en) | Value user key index determination method, advertisement delivery method and device | |
| Tong et al. | The research of customer loyalty improvement in telecom industry based on NPS data mining | |
| CN107808346A (en) | A kind of appraisal procedure and apparatus for evaluating of potential target object | |
| CN109492863A (en) | The automatic generation method and device of financial document | |
| CN107977855B (en) | Method and device for managing user information | |
| Onar et al. | A fuzzy rule based inference system for early debt collection | |
| CN115619270A (en) | Data asset management method, device, computer equipment and storage medium | |
| CN110610415B (en) | Method and device for updating model | |
| Keeney | Modeling values for telecommunications management | |
| CN112381440A (en) | Evaluation method, device, processor and evaluation system for power operator environment | |
| Sardana | Measuring business performance: A conceptual framework with focus on improvement | |
| CN116645134A (en) | Method, device, equipment and medium for recommending credit card in stages | |
| CN107844874A (en) | Enterprise operation problem analysis system and its method | |
| CN110706122A (en) | Method, device and readable medium for improving social security agent efficiency based on big data analysis | |
| CN110263249A (en) | A kind of telecommunications Precision Marketing Method and system based on multi-objective optimization algorithm and user's internet information | |
| CN112651433B (en) | Abnormal behavior analysis method for privileged account | |
| CN114565450A (en) | Overdue common debt-based collection strategy determination method and related equipment | |
| Handayani et al. | The Effect of The Use Of Information Technology and Implementation of Internal Controls on The Quality of Accounting Information | |
| Hartwich et al. | Setting research priorities: an example from agriculture using the analytic hierarchy process | |
| CN108564380B (en) | Telecommunication user classification method based on iterative decision tree | |
| Dan et al. | An incident prioritization algorithm based on BDIM | |
| CN115994766B (en) | Outbound system for automatically positioning target crowd |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |