CN115049423A - Client portrait generation method, device, equipment and storage medium - Google Patents

Client portrait generation method, device, equipment and storage medium Download PDF

Info

Publication number
CN115049423A
CN115049423A CN202210585685.5A CN202210585685A CN115049423A CN 115049423 A CN115049423 A CN 115049423A CN 202210585685 A CN202210585685 A CN 202210585685A CN 115049423 A CN115049423 A CN 115049423A
Authority
CN
China
Prior art keywords
data
customer
client
bank
processed
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210585685.5A
Other languages
Chinese (zh)
Inventor
辜伟鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Bank Co Ltd
Original Assignee
Ping An Bank Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Bank Co Ltd filed Critical Ping An Bank Co Ltd
Priority to CN202210585685.5A priority Critical patent/CN115049423A/en
Publication of CN115049423A publication Critical patent/CN115049423A/en
Pending legal-status Critical Current

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462—Approximate or statistical queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • 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
    • 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
    • G06Q40/02—Banking, e.g. interest calculation or account maintenance
    • 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
    • G06Q40/06—Asset management; Financial planning or analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Technology Law (AREA)
  • Game Theory and Decision Science (AREA)
  • Computational Linguistics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Human Resources & Organizations (AREA)
  • Operations Research (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the field of artificial intelligence, and discloses a method, a device, equipment and a storage medium for generating a client portrait, which are used for improving the accuracy of generating the client portrait. The client representation generation method comprises the following steps: collecting business card data of a bank client to be processed to obtain business card data, and performing data extraction on the business card data to obtain content data and browsing data; standardizing the content data to obtain attribute data, and generating a customer attribute label corresponding to a bank customer to be processed according to the attribute data; the bank client to be processed carries out personal information authentication and carries out normalization processing on the browsing data to obtain access data; inputting the access data into a client portrait processing model for user tag calculation to obtain a client access tag; and determining a customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label. In addition, the invention also relates to a block chain technology, and the client access label can be stored in the block chain node.

Description

Client portrait generation method, device, equipment and storage medium
Technical Field
The invention relates to the field of artificial intelligence, in particular to a method, a device, equipment and a storage medium for generating a client portrait.
Background
With the change of the mode of one-way output to customers by banks in the past, customers have become the center of marketing mode. Under the marketing mode that the customer is leading, who can master customer's demand more fast, the customization accords with the marketing mode of customer action, just can win the favor of more customers. Therefore, the bank introduces the customer portrait to make predictions for the customer, and brings personalized marketing to the customer.
In the existing scheme, a client is labeled through big data analysis, the label characteristics comprise region, age, gender, occupation, preference, source and the like, the label characteristics are combined together, the requirement of the client is understood to a certain extent, and the label characteristics play a role in refined client operation, but the precision of the existing scheme is low.
Disclosure of Invention
The invention provides a client portrait generation method, a client portrait generation device, client portrait generation equipment and a storage medium, which are used for improving the accuracy of client portrait generation.
A first aspect of the present invention provides a client representation generation method, comprising: collecting business card data of a bank client to be processed from a preset bank application program to obtain the business card data corresponding to the bank client to be processed, and extracting the data of the business card data to obtain content data and browsing data corresponding to the business card data; standardizing the content data to obtain attribute data corresponding to the content data, and generating a customer attribute label corresponding to the bank customer to be processed according to the attribute data corresponding to the content data; performing personal information authentication on the bank client to be processed and performing normalization processing on the browsing data to obtain access data corresponding to the browsing data; inputting the access data into a preset customer portrait processing model for user label calculation to obtain a customer access label corresponding to the bank customer to be processed; and determining a customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label.
Optionally, in a first implementation manner of the first aspect of the present invention, the acquiring business card data of a bank client to be processed from a preset bank application program to obtain business card data corresponding to the bank client to be processed, and performing data extraction on the business card data to obtain content data and browsing data corresponding to the business card data includes: acquiring business card data corresponding to a bank client to be processed from a preset bank application program, and preprocessing the business card data to obtain standard data corresponding to the business card data; performing identification extraction on the standard data to obtain a data identification corresponding to the standard data; and carrying out data classification on the standard data according to the data identification corresponding to the standard data to obtain content data and browsing data corresponding to the business card data.
Optionally, in a second implementation manner of the first aspect of the present invention, before the collecting business card data of a bank customer to be processed from a preset bank application, the customer representation generating method further includes: acquiring operation history data of a bank client to be processed; inputting the operation historical data into a preset training model for model training to obtain a sample probability value corresponding to the training model, wherein the training model comprises a plurality of neural networks; performing statistical analysis on the operation historical data to obtain an analysis result, generating a behavior tag matrix according to the analysis result, and determining a target value according to the behavior tag matrix; determining a sample loss value according to the sample probability value and the target value, and judging whether the sample loss value is smaller than a preset loss threshold value; and if the sample loss value is smaller than a preset loss threshold value, taking the training model as a customer portrait processing model.
Optionally, in a third implementation manner of the first aspect of the present invention, the inputting the operation history data into a preset training model for model training to obtain a sample probability value corresponding to the training model includes: setting input weights between an input layer and a hidden layer in the training model based on the operation history data, and setting output weights between the operation history data and the hidden layer and the output layer in the training model; computing a hidden vector for the training model based on the operation history data and the input weights; inputting the hidden vector into the hidden layer for feature extraction based on the output weight to obtain a feature vector; and inputting the feature vector into the output layer for probability operation to obtain a sample probability value.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the standardizing the content data to obtain attribute data corresponding to the content data, and generating a customer attribute tag corresponding to the bank customer to be processed according to the attribute data corresponding to the content data includes: performing stability analysis on the content data to obtain stability data, and taking the stability data as attribute data to obtain attribute data corresponding to the content data; and extracting the attribute label in the attribute data, and taking the attribute label as a customer attribute label corresponding to the bank customer to be processed.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the performing personal information authentication on the bank customer to be processed and performing normalization processing on the browsing data to obtain access data corresponding to the browsing data includes: performing personal information authentication on the bank client to be processed to obtain an authentication result, wherein the authentication result comprises authentication passing and authentication failure; if the authentication result is that the authentication is passed, calling a preset normalization function to carry out normalization operation on the browsing data to obtain access data corresponding to the browsing data.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the determining, according to the customer attribute tag and the customer access tag, a customer portrait corresponding to the bank customer to be processed includes: performing label clustering on the customer attribute labels and the customer access labels through a preset clustering algorithm to obtain label clustering results; and determining the customer portrait of the bank customer to be processed according to the label clustering result.
A second aspect of the present invention provides a client representation generating apparatus comprising: the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring business card data of a bank client to be processed from a preset bank application program to obtain the business card data corresponding to the bank client to be processed, and extracting the data of the business card data to obtain content data and browsing data corresponding to the business card data; the processing module is used for carrying out standardization processing on the content data to obtain attribute data corresponding to the content data and generating a customer attribute label corresponding to the bank customer to be processed according to the attribute data corresponding to the content data; the normalization module is used for authenticating personal information of the bank client to be processed and normalizing the browsing data to obtain access data corresponding to the browsing data; the calculation module is used for inputting the access data into a preset customer portrait processing model to perform user label calculation to obtain a customer access label corresponding to the bank customer to be processed; and the generating module is used for determining the customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label.
Optionally, in a first implementation manner of the second aspect of the present invention, the acquisition module is specifically configured to: acquiring business card data corresponding to a bank client to be processed from a preset bank application program, and preprocessing the business card data to obtain standard data corresponding to the business card data; performing identification extraction on the standard data to obtain a data identification corresponding to the standard data; and carrying out data classification on the standard data according to the data identification corresponding to the standard data to obtain content data and browsing data corresponding to the business card data.
Optionally, in a second implementation manner of the second aspect of the present invention, the client representation generating apparatus further includes a training module, where the training module includes: the acquisition unit is used for acquiring operation history data of a bank client to be processed; the input unit is used for inputting the operation historical data into a preset training model for model training to obtain a sample probability value corresponding to the training model, wherein the training model comprises a plurality of neural networks; the analysis unit is used for carrying out statistical analysis on the operation historical data to obtain an analysis result, generating a behavior tag matrix according to the analysis result and determining a target value according to the behavior tag matrix; determining a sample loss value according to the sample probability value and the target value, and judging whether the sample loss value is smaller than a preset loss threshold value; and if the sample loss value is smaller than a preset loss threshold value, taking the training model as a customer portrait processing model.
Optionally, in a third implementation manner of the second aspect of the present invention, the input unit is specifically configured to: setting input weights between an input layer and a hidden layer in the training model based on the operation history data, and setting output weights between the operation history data and the hidden layer and the output layer in the training model; computing a hidden vector for the training model based on the operation history data and the input weights; inputting the hidden vector into the hidden layer for feature extraction based on the output weight to obtain a feature vector; and inputting the feature vector into the output layer for probability operation to obtain a sample probability value.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the processing module is specifically configured to: performing stability analysis on the content data to obtain stability data, and taking the stability data as attribute data to obtain attribute data corresponding to the content data; and extracting the attribute label in the attribute data, and taking the attribute label as a customer attribute label corresponding to the bank customer to be processed.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the normalization module is specifically configured to: performing personal information authentication on the bank client to be processed to obtain an authentication result, wherein the authentication result comprises authentication passing and authentication failure; if the authentication result is that the authentication is passed, calling a preset normalization function to carry out normalization operation on the browsing data to obtain access data corresponding to the browsing data.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the generating module is specifically configured to: performing label clustering on the customer attribute labels and the customer access labels through a preset clustering algorithm to obtain label clustering results; and determining the customer portrait of the bank customer to be processed according to the label clustering result.
A third aspect of the present invention provides a client representation generating apparatus comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the client representation generating device to perform the client representation generating method described above.
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 above-described client representation generation method.
In the technical scheme provided by the invention, business card data of a bank client to be processed is collected to obtain the business card data, and the data extraction is carried out on the business card data to obtain content data and browsing data; standardizing the content data to obtain attribute data, and generating a customer attribute label corresponding to a bank customer to be processed according to the attribute data; the bank client to be processed carries out personal information authentication and carries out normalization processing on the browsing data to obtain access data; inputting the access data into a client portrait processing model for user tag calculation to obtain a client access tag; and determining a customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label. The invention can analyze the access data of the client and update the client portrait and the preference from multiple dimensions by tracking the bank client clues in real time, thereby improving the accuracy of generating the client portrait.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for generating a client representation in accordance with the present invention;
FIG. 2 is a schematic diagram of another embodiment of a client representation generation method in accordance with the present invention;
FIG. 3 is a schematic diagram of an embodiment of a client representation generation apparatus in accordance with the present invention;
FIG. 4 is a schematic diagram of another embodiment of a client representation generation apparatus in accordance with the present invention;
FIG. 5 is a schematic diagram of an embodiment of a client representation generating apparatus in an embodiment of the invention.
Detailed Description
The embodiment of the invention provides a client portrait generation method, a client portrait generation device, client portrait generation equipment and a storage medium, which are used for improving the accuracy of client portrait generation. 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 ease of understanding, a detailed flow of an embodiment of the present invention is described below, with reference to fig. 1, a first embodiment of a client representation generation method in an embodiment of the present invention includes:
101. acquiring business card data of a bank client to be processed from a preset bank application program to obtain the business card data corresponding to the bank client to be processed, and extracting the data of the business card data to obtain content data and browsing data corresponding to the business card data;
it should be noted that the bank client to be processed is a bank client that needs to construct a client figure; the business card data is original data stored in a preset database, wherein the preset database is used for storing content data and browsing data of bank customers; the content data is relatively stable data such as region, age, gender, occupation, preference, source and other basic demographic attributes, and customer member grade, loan deposit, financial investment and the like in a bank; the browsing data includes browsing time, browsing content name, viewing and forwarding times, browsing duration, interpersonal track, reading track, sharing amount, order amount and order amount of the client in the bank application program.
It is to be understood that the executing subject of the present invention may be a client representation generating device, a terminal or a server, and is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject. The embodiment of the invention can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.
102. Standardizing the content data to obtain attribute data corresponding to the content data, and generating a client attribute label corresponding to a bank client to be processed according to the attribute data corresponding to the content data;
specifically, the server performs standardization processing on the content data, and the obtained attribute data corresponding to the content data is attribute data corresponding to the content data selected from relatively stable content data. The server carries out standardization processing on the content data, and aims to obtain attribute data corresponding to the content data, and the server generates a client attribute label corresponding to a bank client to be processed according to the attribute data corresponding to the content data.
103. The bank client to be processed carries out personal information authentication and carries out normalization processing on the browsing data to obtain access data corresponding to the browsing data;
the server normalizes the browsing data to obtain the access data, namely normalizes the browsing data through a preset normalization processing formula to obtain the access data. The server combines big data to carry out personal information authentication (namely KYC authentication), analyzes client browsing, investment preference and the like to generate product recommendation strategies, a finance manager can develop accurate marketing clients and automatic visitor classification through clues to comprehensively know the preference of the clients to contents and products, analyzes client behaviors and investment preference through accessing KYC identification and wealth diagnosis, automatically generates product recommendation strategies, forms an all-round recommendation strategy of the clients, and helps the manager corresponding to the clients to comprehensively know the preference of the clients to the contents and the products.
104. Inputting the access data into a preset customer portrait processing model to perform user label calculation to obtain a customer access label corresponding to a bank customer to be processed;
specifically, the server generates a client access label through the client portrait processing model according to the access data, the client access label is an input layer for inputting the access data into the client portrait processing model to obtain output data, the server processes the output data and the hidden layer to obtain characteristic data, and finally the characteristic data is processed through the client portrait processing model to obtain a client access label corresponding to the bank client to be processed.
105. And determining a customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label.
Specifically, the server determines a client portrait of the bank client to be processed according to the client attribute tag and the client access tag, and inputs the client attribute tag and the client access tag into a preset user portrait algorithm to generate the user portrait, so as to obtain the client portrait of the bank client to be processed, wherein the preset user portrait algorithm is a user portrait sample preset by the user.
Further, the server stores the client access tag in a blockchain database, which is not limited herein.
In the embodiment of the invention, business card data of a bank client to be processed is collected to obtain the business card data, and the data extraction is carried out on the business card data to obtain content data and browsing data; standardizing the content data to obtain attribute data, and generating a customer attribute label corresponding to a bank customer to be processed according to the attribute data; the bank client to be processed carries out personal information authentication and carries out normalization processing on the browsing data to obtain access data; inputting the access data into a client portrait processing model for user tag calculation to obtain a client access tag; and determining a customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label. The invention can analyze the access data of the client and update the client portrait and the preference from multiple dimensions by tracking the bank client clues in real time, thereby improving the accuracy of generating the client portrait.
Referring to FIG. 2, a second embodiment of a method for generating a client representation according to the present invention comprises:
201. acquiring business card data of a bank client to be processed from a preset bank application program to obtain the business card data corresponding to the bank client to be processed, and extracting the data of the business card data to obtain content data and browsing data corresponding to the business card data;
specifically, the server acquires business card data corresponding to a bank client to be processed from a preset bank application program, and preprocesses the business card data to obtain standard data corresponding to the business card data; the server extracts the standard data to obtain a data identifier corresponding to the standard data; and the server classifies the standard data according to the data identification corresponding to the standard data to obtain the content data and the browsing data corresponding to the business card data. Specifically, the server extracts the business card data to obtain the content data and the browsing data, and the business card data is directly extracted based on a preset data acquisition tool to obtain the content data and the browsing data. The business card data comprises user names, personal introduction, talent exhibition, growth centers, names, post information and the like.
Specifically, the server acquires operation history data of a bank client to be processed; the server inputs the operation historical data into a preset training model for model training to obtain a sample probability value corresponding to the training model, wherein the training model comprises a plurality of neural networks; the server carries out statistical analysis on the operation historical data to obtain an analysis result, generates a behavior tag matrix according to the analysis result, and determines a target value according to the behavior tag matrix; the server determines a sample loss value according to the sample probability value and the target value and judges whether the sample loss value is smaller than a preset loss threshold value; and if the sample loss value is smaller than a preset loss threshold value, the server takes the training model as a client portrait processing model.
Specifically, the server collects information through a preset AI (Artificial Intelligence) business card and records browsing, forwarding, consulting and other information of the bank client in real time, the operation history data are the internet behavior data, bank outlet behavior data and the like of the bank client to be processed in a bank application program within a preset time interval, the preset time interval can be generated by bank client image generation equipment, and the server is preset according to actual requirements; the plurality of neural networks are composed of an input layer, a hidden layer and an output layer, wherein the input layer, the hidden layer and the output layer are composed of a plurality of neuron nodes. The server obtains operation history data of the bank client to be processed, and searches the operation history data corresponding to the bank client to be processed in a preset database according to the identity. When the sample loss value is greater than the preset loss threshold value, the server indicates that the accuracy of the training model is low, and at this time, the training model needs to be trained. Therefore, the input weight and the output weight need to be adjusted according to the sample loss value. The server adjusts the input weight and the output weight according to the sample loss value to find a weight adjustment value corresponding to the sample loss value in a preset mapping relation table, the preset mapping relation table comprises a corresponding relation between the sample loss value and the weight adjustment value, the corresponding relation between the sample loss value and the weight adjustment value can be preset by a user according to actual conditions, and the input weight and the output weight are adjusted according to the weight adjustment value. After the input weight and the output weight are adjusted, the server needs to return to the step of determining the hidden vector of the training model through a preset activation function according to the operation historical data and the input weight until the sample loss value is smaller than a preset loss threshold value. And when the sample loss value is smaller than the preset loss threshold value, the server shows that the accuracy of the training model is higher, and the training model after training is used as a client portrait processing model.
Specifically, the server sets an input weight between an input layer and a hidden layer in the training model based on the operation history data, and sets an output weight between the hidden layer and an output layer in the operation history data and the training model; the server calculates a hidden vector of the training model based on the operation historical data and the input weight; the server inputs the hidden vector into a hidden layer for feature extraction based on the output weight to obtain a feature vector; and the server inputs the feature vectors into the output layer for probability operation to obtain a sample probability value. It should be noted that the input weight is a connection weight value between an input layer neuron and a hidden layer neuron of the training model; the output weight is a connection weight value between a hidden layer neuron and an output layer neuron of the training model; the preset activation function is a Sigmoid function. The server determines the hidden vector of the training model through the preset activation function according to the operation history data and the input weight, and the hidden vector can be represented as follows: the server determines the feature vector of the training model according to the hidden vector and the output weight through a preset activation function as follows: and the server determines a sample loss value according to the sample probability value, namely, inputting the sample probability value into a preset sample loss value calculation script to obtain the sample loss value, wherein the preset sample loss value calculation script is a calculation script preset by a user. It should be noted that the preset loss threshold is a value preset by the user, and is used to determine whether the accuracy of the neural network model meets the user requirement. And the server performs statistical analysis on the operation historical data to obtain an analysis result, and analyzes the behavior data such as customer value, purchasing power, channel activity, loss possibility and the like to obtain an analysis result. The server determines a sample loss value according to the sample probability value and the target value, and calculates the sample loss value according to the sample probability value and the target value through a preset loss function calculation formula, wherein the preset loss function calculation formula is as follows:
202. performing stability analysis on the content data to obtain stability data, and taking the stability data as attribute data to obtain attribute data corresponding to the content data;
specifically, the server performs standardization processing on the content data, and the obtained attribute data corresponding to the content data is attribute data corresponding to the content data selected from relatively stable content data. The server carries out standardization processing on the content data, and aims to obtain attribute data corresponding to the content data, and the server generates a client attribute label corresponding to a bank client to be processed according to the attribute data corresponding to the content data.
203. And extracting the attribute tags in the attribute data, and taking the attribute tags as client attribute tags corresponding to the bank clients to be processed.
Specifically, the server performs stability analysis on the content data to obtain stability data, wherein the stability data is attribute data corresponding to the content data, and the server obtains the attribute data corresponding to the content data by using the stability data as the attribute data; and the server extracts the attribute tags in the attribute data, and takes the attribute tags as client attribute tags corresponding to the bank clients to be processed.
204. The bank client to be processed carries out personal information authentication and carries out normalization processing on the browsing data to obtain access data corresponding to the browsing data;
specifically, the server authenticates personal information of the bank client to be processed to obtain an authentication result, wherein the authentication result comprises authentication passing and authentication failure; and if the authentication result is that the authentication is passed, the server calls a preset normalization function to carry out normalization operation on the browsing data, and access data corresponding to the browsing data are obtained. Specifically, if the authentication result is that the authentication is passed, the server does not perform portrait generation on the hard goods client to be processed, and automatically generates a product recommendation strategy by accessing KYC identification and wealth diagnosis, analyzing client behaviors and investment preferences.
205. Inputting the access data into a preset customer portrait processing model to perform user label calculation to obtain a customer access label corresponding to a bank customer to be processed;
specifically, the server generates a client access label through the client portrait processing model according to the access data, the client access label is an input layer for inputting the access data into the client portrait processing model to obtain output data, the server processes the output data and the hidden layer to obtain characteristic data, and finally the characteristic data is processed through the client portrait processing model to obtain a client access label corresponding to the bank client to be processed.
206. And determining a customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label.
Specifically, the server performs label clustering on the client attribute label and the client access label through a preset clustering algorithm to obtain a label clustering result; and the server determines the client portrait of the bank client to be processed according to the label clustering result. It should be noted that the preset clustering algorithm is a fuzzy clustering algorithm, and the like. And the server performs label clustering on the client attribute label and the client access label through a preset clustering algorithm to obtain a label clustering result, namely performs label clustering on the client attribute label and the client access label through a fuzzy clustering algorithm to obtain a label clustering result. And the server determines the client portrait of the bank client to be processed as a statistical label clustering result according to the label clustering result, and determines the client portrait of the bank client to be processed according to the statistical result.
Further, the server stores the client access tag in a blockchain database, which is not limited herein.
In the embodiment of the invention, business card data of bank customers to be processed are collected to obtain the business card data, and the data extraction is carried out on the business card data to obtain content data and browsing data; standardizing the content data to obtain attribute data, and generating a customer attribute label corresponding to a bank customer to be processed according to the attribute data; authenticating personal information of bank clients to be processed and carrying out normalization processing on browsing data to obtain access data; inputting the access data into a client portrait processing model for user tag calculation to obtain a client access tag; and determining a customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label. The invention can analyze the access data of the client and update the client portrait and the preference from multiple dimensions by tracking the bank client clues in real time, thereby improving the accuracy of generating the client portrait.
With reference to fig. 3, the client representation generating method in the embodiment of the present invention is described above, and a client representation generating apparatus in the embodiment of the present invention is described below, where a first embodiment of the client representation generating apparatus in the embodiment of the present invention includes:
the acquisition module 301 is configured to acquire business card data of a bank client to be processed from a preset bank application program, obtain business card data corresponding to the bank client to be processed, perform data extraction on the business card data, and obtain content data and browsing data corresponding to the business card data;
the processing module 302 is configured to perform standardization processing on the content data to obtain attribute data corresponding to the content data, and generate a customer attribute tag corresponding to the bank customer to be processed according to the attribute data corresponding to the content data;
the normalization module 303 is configured to perform personal information authentication on the bank client to be processed and perform normalization processing on the browsing data to obtain access data corresponding to the browsing data;
a calculation module 304, configured to input the access data into a preset customer portrait processing model for user tag calculation, so as to obtain a customer access tag corresponding to the bank customer to be processed;
and a generating module 305, configured to determine a customer portrait corresponding to the bank customer to be processed according to the customer attribute tag and the customer access tag.
Further, the server stores the client access tag in a blockchain database, which is not limited herein.
In the embodiment of the invention, business card data of a bank client to be processed is collected to obtain the business card data, and the data extraction is carried out on the business card data to obtain content data and browsing data; standardizing the content data to obtain attribute data, and generating a customer attribute label corresponding to a bank customer to be processed according to the attribute data; authenticating personal information of bank clients to be processed and carrying out normalization processing on browsing data to obtain access data; inputting the access data into a client portrait processing model for user tag calculation to obtain a client access tag; and determining a customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label. The invention can analyze the access data of the client and update the client portrait and the preference from multiple dimensions by tracking the bank client clues in real time, thereby improving the accuracy of generating the client portrait.
Referring to FIG. 4, a second embodiment of a client representation generation apparatus according to the present invention comprises:
the acquisition module 301 is configured to acquire business card data of a bank client to be processed from a preset bank application program, obtain business card data corresponding to the bank client to be processed, perform data extraction on the business card data, and obtain content data and browsing data corresponding to the business card data;
the processing module 302 is configured to perform standardization processing on the content data to obtain attribute data corresponding to the content data, and generate a customer attribute tag corresponding to the bank customer to be processed according to the attribute data corresponding to the content data;
the normalization module 303 is configured to perform personal information authentication on the bank client to be processed and perform normalization processing on the browsing data to obtain access data corresponding to the browsing data;
a calculation module 304, configured to input the access data into a preset customer portrait processing model for user tag calculation, so as to obtain a customer access tag corresponding to the bank customer to be processed;
and a generating module 305, configured to determine a customer portrait corresponding to the bank customer to be processed according to the customer attribute tag and the customer access tag.
Optionally, the acquisition module 301 is specifically configured to:
acquiring business card data corresponding to a bank client to be processed from a preset bank application program, and preprocessing the business card data to obtain standard data corresponding to the business card data; performing identification extraction on the standard data to obtain a data identification corresponding to the standard data; and performing data classification on the standard data according to the data identification corresponding to the standard data to obtain content data and browsing data corresponding to the business card data.
Optionally, the client representation generating apparatus further comprises a training module 306, wherein the training module 306 comprises:
an obtaining unit 3061, configured to obtain operation history data of the bank customer to be processed;
an input unit 3062, configured to input the operation history data into a preset training model for model training, so as to obtain a sample probability value corresponding to the training model, where the training model includes a plurality of neural networks;
an analysis unit 3063, configured to perform statistical analysis on the operation history data to obtain an analysis result, generate a behavior tag matrix according to the analysis result, and determine a target value according to the behavior tag matrix; determining a sample loss value according to the sample probability value and the target value, and judging whether the sample loss value is smaller than a preset loss threshold value or not; and if the sample loss value is smaller than a preset loss threshold value, taking the training model as a customer portrait processing model.
Optionally, the input unit 3061 is specifically configured to:
setting input weights between an input layer and a hidden layer in the training model based on the operation history data, and setting output weights between the operation history data and the hidden layer and the output layer in the training model; computing a hidden vector for the training model based on the operation history data and the input weights; inputting the hidden vector into the hidden layer for feature extraction based on the output weight to obtain a feature vector; and inputting the feature vector into the output layer for probability operation to obtain a sample probability value.
Optionally, the processing module 302 is specifically configured to:
performing stability analysis on the content data to obtain stability data, and taking the stability data as attribute data to obtain attribute data corresponding to the content data; and extracting the attribute label in the attribute data, and taking the attribute label as a customer attribute label corresponding to the bank customer to be processed.
Optionally, the normalization module 303 is specifically configured to:
performing personal information authentication on the bank client to be processed to obtain an authentication result, wherein the authentication result comprises authentication passing and authentication failure; if the authentication result is that the authentication is passed, calling a preset normalization function to carry out normalization operation on the browsing data to obtain access data corresponding to the browsing data.
Optionally, the generating module 305 is specifically configured to:
performing label clustering on the customer attribute labels and the customer access labels through a preset clustering algorithm to obtain label clustering results; and determining the customer portrait of the bank customer to be processed according to the label clustering result.
Further, the server stores the client access tag in a blockchain database, which is not limited herein.
In the embodiment of the invention, business card data of a bank client to be processed is collected to obtain the business card data, and the data extraction is carried out on the business card data to obtain content data and browsing data; standardizing the content data to obtain attribute data, and generating a customer attribute label corresponding to a bank customer to be processed according to the attribute data; the bank client to be processed carries out personal information authentication and carries out normalization processing on the browsing data to obtain access data; inputting the access data into a client portrait processing model for user tag calculation to obtain a client access tag; and determining a customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label. The invention can analyze the access data of the client and update the client portrait and the preference from multiple dimensions by tracking the bank client clues in real time, thereby improving the accuracy of generating the client portrait.
Fig. 3 and 4 describe the client representation generating apparatus in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the client representation generating apparatus in the embodiment of the present invention is described in detail from the perspective of hardware processing.
FIG. 5 is a schematic diagram of a client representation generating apparatus 500, which may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, one or more storage media 530 (e.g., one or more mass storage devices) for storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on storage medium 530 may include one or more modules (not shown), each of which may include a sequence of instruction operations for client representation generation apparatus 500. Still further, processor 510 may be configured to communicate with storage medium 530 to execute a series of instruction operations in storage medium 530 on client representation generating device 500.
Client representation generating device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the configuration of client representation generating device illustrated in FIG. 5 does not constitute a limitation of client representation generating devices and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components.
The present invention also provides a client representation generating device comprising a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to carry out the steps of the client representation generating method in the embodiments described above.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, which may also be 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 client representation generation method.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
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 is clear to 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 (10)

1. A client representation generation method, comprising:
collecting business card data of a bank client to be processed from a preset bank application program to obtain the business card data corresponding to the bank client to be processed, and extracting the data of the business card data to obtain content data and browsing data corresponding to the business card data;
standardizing the content data to obtain attribute data corresponding to the content data, and generating a customer attribute label corresponding to the bank customer to be processed according to the attribute data corresponding to the content data;
performing personal information authentication on the bank client to be processed and performing normalization processing on the browsing data to obtain access data corresponding to the browsing data;
inputting the access data into a preset customer portrait processing model for user label calculation to obtain a customer access label corresponding to the bank customer to be processed;
and determining a customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label.
2. The customer figure generation method of claim 1, wherein the collecting business card data of the bank customer to be processed from a preset bank application program to obtain the business card data corresponding to the bank customer to be processed, and performing data extraction on the business card data to obtain content data and browsing data corresponding to the business card data comprises:
acquiring business card data corresponding to a bank client to be processed from a preset bank application program, and preprocessing the business card data to obtain standard data corresponding to the business card data;
performing identification extraction on the standard data to obtain a data identification corresponding to the standard data;
and performing data classification on the standard data according to the data identification corresponding to the standard data to obtain content data and browsing data corresponding to the business card data.
3. A customer representation generation method as claimed in claim 1, wherein prior to said collecting of bank customer's business card data to be processed from a pre-set banking application, said customer representation generation method further comprises:
acquiring operation history data of a bank client to be processed;
inputting the operation historical data into a preset training model for model training to obtain a sample probability value corresponding to the training model, wherein the training model comprises a plurality of neural networks;
performing statistical analysis on the operation historical data to obtain an analysis result, generating a behavior tag matrix according to the analysis result, and determining a target value according to the behavior tag matrix;
determining a sample loss value according to the sample probability value and the target value, and judging whether the sample loss value is smaller than a preset loss threshold value;
and if the sample loss value is smaller than a preset loss threshold value, taking the training model as a customer portrait processing model.
4. The method of generating a customer representation as claimed in claim 3, wherein the inputting the operation history data into a preset training model for model training to obtain a sample probability value corresponding to the training model comprises:
setting input weights between an input layer and a hidden layer in the training model based on the operation history data, and setting output weights between the operation history data and the hidden layer and the output layer in the training model;
computing a hidden vector for the training model based on the operation history data and the input weights;
inputting the hidden vector into the hidden layer for feature extraction based on the output weight to obtain a feature vector;
and inputting the feature vector into the output layer for probability operation to obtain a sample probability value.
5. The customer figure generation method of claim 1, wherein the standardizing the content data to obtain attribute data corresponding to the content data, and generating a customer attribute tag corresponding to the bank customer to be processed according to the attribute data corresponding to the content data comprises:
performing stability analysis on the content data to obtain stability data, and taking the stability data as attribute data to obtain attribute data corresponding to the content data;
and extracting the attribute label in the attribute data, and taking the attribute label as a customer attribute label corresponding to the bank customer to be processed.
6. The method for generating a customer portrait according to claim 1, wherein the authenticating the personal information of the bank customer to be processed and the normalizing the browsing data to obtain the access data corresponding to the browsing data includes:
performing personal information authentication on the bank client to be processed to obtain an authentication result, wherein the authentication result comprises authentication passing and authentication failure;
if the authentication result is that the authentication is passed, calling a preset normalization function to carry out normalization operation on the browsing data to obtain access data corresponding to the browsing data.
7. The customer representation generation method of any of claims 1-6, wherein the determining a customer representation corresponding to the bank customer to be processed from the customer attribute tag and the customer access tag comprises:
performing label clustering on the client attribute labels and the client access labels through a preset clustering algorithm to obtain label clustering results;
and determining the customer portrait of the bank customer to be processed according to the label clustering result.
8. A client representation generating apparatus, said client representation generating apparatus comprising:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring business card data of a bank client to be processed from a preset bank application program to obtain the business card data corresponding to the bank client to be processed, and extracting the data of the business card data to obtain content data and browsing data corresponding to the business card data;
the processing module is used for carrying out standardization processing on the content data to obtain attribute data corresponding to the content data and generating a customer attribute label corresponding to the bank customer to be processed according to the attribute data corresponding to the content data;
the normalization module is used for authenticating personal information of the bank client to be processed and normalizing the browsing data to obtain access data corresponding to the browsing data;
the calculation module is used for inputting the access data into a preset customer portrait processing model to perform user label calculation to obtain a customer access label corresponding to the bank customer to be processed;
and the generating module is used for determining the customer portrait corresponding to the bank customer to be processed according to the customer attribute label and the customer access label.
9. A client representation generating apparatus, characterized in that the client representation generating apparatus comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invoking the instructions in the memory to cause the client representation generating device to perform the client representation generating method of any of claims 1-7.
10. A computer readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement a client representation generation method as recited in any of claims 1-7.
CN202210585685.5A 2022-05-27 2022-05-27 Client portrait generation method, device, equipment and storage medium Pending CN115049423A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210585685.5A CN115049423A (en) 2022-05-27 2022-05-27 Client portrait generation method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210585685.5A CN115049423A (en) 2022-05-27 2022-05-27 Client portrait generation method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN115049423A true CN115049423A (en) 2022-09-13

Family

ID=83160426

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210585685.5A Pending CN115049423A (en) 2022-05-27 2022-05-27 Client portrait generation method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN115049423A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112035742A (en) * 2020-08-28 2020-12-04 康键信息技术（深圳）有限公司 User portrait generation method, device, equipment and storage medium
CN112487284A (en) * 2020-11-17 2021-03-12 中信银行股份有限公司 Bank customer portrait generation method, equipment, storage medium and device
CN113591899A (en) * 2021-06-10 2021-11-02 国网河北省电力有限公司营销服务中心 Power customer portrait recognition method and device and terminal equipment
CN113919437A (en) * 2021-10-22 2022-01-11 平安科技（深圳）有限公司 Method, device, equipment and storage medium for generating client portrait

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112035742A (en) * 2020-08-28 2020-12-04 康键信息技术（深圳）有限公司 User portrait generation method, device, equipment and storage medium
CN112487284A (en) * 2020-11-17 2021-03-12 中信银行股份有限公司 Bank customer portrait generation method, equipment, storage medium and device
CN113591899A (en) * 2021-06-10 2021-11-02 国网河北省电力有限公司营销服务中心 Power customer portrait recognition method and device and terminal equipment
CN113919437A (en) * 2021-10-22 2022-01-11 平安科技（深圳）有限公司 Method, device, equipment and storage medium for generating client portrait

Similar Documents

Publication Publication Date Title
CN112035742B (en) User portrait generation method, device, equipment and storage medium
US10528972B2 (en) Predicting email responses
CN110992167A (en) Bank client business intention identification method and device
CN113901320A (en) Scene service recommendation method, device, equipment and storage medium
JP2002123738A (en) Device and method for processing information and recording medium
CN110659318A (en) Big data based strategy pushing method and system and computer equipment
CN113946752A (en) Financial product recommendation method, device, equipment and storage medium based on big data
CN114817746A (en) Insurance product recommendation method, device, equipment and storage medium
CN112529665A (en) Product recommendation method and device based on combined model and computer equipment
CN113095408A (en) Risk determination method and device and server
CN113946590A (en) Method, device and equipment for updating integral data and storage medium
CN111582932A (en) Inter-scene information pushing method and device, computer equipment and storage medium
CN113919437A (en) Method, device, equipment and storage medium for generating client portrait
CN114371946B (en) Information push method and information push server based on cloud computing and big data
CN112487284A (en) Bank customer portrait generation method, equipment, storage medium and device
CN113723774A (en) Answer scoring method and device, computer equipment and storage medium
CN115082041B (en) User information management method, device, equipment and storage medium
CN115049423A (en) Client portrait generation method, device, equipment and storage medium
KR20190096533A (en) Method and apparatus for providing marketing contents
Ordouei et al. Integrating data mining and knowledge management to improve customer relationship management in banking industry (Case study of Caspian Credit Institution)
US11727402B2 (en) Utilizing machine learning and network addresses to validate online transactions with transaction cards
CN113420018A (en) User behavior data analysis method, device, equipment and storage medium
Mahalle et al. Data Acquisition and Preparation
Granata et al. Impact of Artificial Intelligence on Digital Marketing
CN112528140A (en) Information recommendation method, device, equipment, system and storage medium

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