Customer dividing method and system based on multi-dimensional data

Abstract

The invention relates to a customer dividing method and system based on multi-dimensional data, and the method comprises the steps: collecting and obtaining a plurality of pieces of customer data of different dimensions of a customer, carrying out the preprocessing of the plurality of pieces of customer data, and obtaining a plurality of pieces of standard customer data; inputting the plurality of standard customer data into a customer portrait model to obtain corresponding customer portrait information, the customer portrait information including basic portrait information, behavior portrait information and preference portrait information; wherein the customer portrait model is obtained by training a machine learning algorithm model based on sample customer data and corresponding annotation data in advance; and jointly determining customer target portrait information based on the basic portrait information, the behavior portrait information and the preference portrait information, and determining a customer pattern drawing result based on the customer target portrait information.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of data processing technology, and in particular to a customer profiling method and system based on multi-dimensional data. Background Art

[0002] At present, traditional enterprise customer segmentation models are often based on limited customer information and simple classification rules, resulting in inaccurate customer segmentation results, which are difficult to meet the growing precision marketing needs of enterprises. With the development of big data and artificial intelligence technologies, it has become possible to use a variety of data for customer segmentation in related technologies. However, how to effectively integrate these data and improve the accuracy of customer segmentation is still a technical problem that needs to be solved urgently. Summary of the invention

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a customer profiling method and system based on multi-dimensional data.

[0004] In a first aspect, an embodiment of the present disclosure provides a method for customer profiling based on multidimensional data, comprising:

[0005] Collecting and obtaining a plurality of customer data of different dimensions of the customer, and preprocessing the plurality of customer data to obtain a plurality of standard customer data;

[0006] Inputting the plurality of standard customer data into a customer portrait model to obtain corresponding customer portrait information, wherein the customer portrait information includes basic portrait information, behavior portrait information and preference portrait information; wherein the customer portrait model is obtained by pre-training a machine learning algorithm model based on sample customer data and corresponding annotated data;

[0007] The customer target portrait information is jointly determined based on the basic portrait information, behavior portrait information and preference portrait information, and the customer classification result is determined based on the customer target portrait information.

[0008] In one embodiment, the preprocessing of the plurality of customer data includes:

[0009] The plurality of customer data are pre-processed by data cleaning, data integration, data transformation and data reduction; wherein the data transformation includes at least one or more of data normalization, discretization and standardization; and the data reduction includes at least attribute reduction and / or dimension reduction.

[0010] In one embodiment, the plurality of customer data at least includes customer purchase behavior data, and the method further includes:

[0011] Based on the customer purchase behavior data, determine the customer type using the RFM model;

[0012] Based on the customer type and the customer classification result, a final customer classification result is determined.

[0013] In one embodiment, the multiple customer data also include basic customer information, customer interaction behavior data, and external data related to the customer, and the external data includes at least one or more of business registration data, market research data, and social media data.

[0014] In one embodiment, the method further comprises:

[0015] When it is determined that the final customer classification result is inconsistent with the pre-set basic classification category of the customer, the customer is treated as a suspicious customer for tracking and confirmation.

[0016] In one embodiment, the method further comprises:

[0017] A corresponding marketing strategy is determined based on the final customer segmentation result; wherein different customer segmentation results correspond to different marketing strategies.

[0018] In one embodiment, the behavior profile information and preference profile information are at least related to the customer purchase behavior data.

[0019] In a second aspect, an embodiment of the present disclosure provides a customer profiling system based on multidimensional data, characterized by comprising:

[0020] A collection and preprocessing module, used for collecting and acquiring a plurality of customer data of different dimensions of a customer, and preprocessing the plurality of customer data to obtain a plurality of standard customer data;

[0021] A data analysis module, configured to input the plurality of standard customer data into a customer portrait model to obtain corresponding customer portrait information, wherein the customer portrait information includes basic portrait information, behavior portrait information and preference portrait information; wherein the customer portrait model is obtained by pre-training a machine learning algorithm model based on sample customer data and corresponding annotated data;

[0022] The customer profiling module is used to jointly determine customer target profile information based on the basic profile information, behavior profile information and preference profile information, and determine the customer profiling result based on the customer target profile information.

[0023] In a third aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the customer profiling method based on multidimensional data described in any of the above embodiments.

[0024] In a fourth aspect, an embodiment of the present disclosure provides an electronic device, including:

[0025] Processor; and

[0026] Memory for storing computer programs;

[0027] The processor is configured to execute the customer profiling method based on multidimensional data described in any of the above embodiments by executing the computer program.

[0028] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0029] The customer profiling method and system based on multi-dimensional data provided by the disclosed embodiment collects and obtains multiple customer data of different dimensions of customers, pre-processes the multiple customer data, and obtains multiple standard customer data; inputs the multiple standard customer data into the customer portrait model to obtain corresponding customer portrait information, and the customer portrait information includes basic portrait information, behavior portrait information and preference portrait information; wherein the customer portrait model is obtained by pre-training the machine learning algorithm model based on sample customer data and corresponding annotated data; based on the basic portrait information, behavior portrait information and preference portrait information, jointly determine the customer target portrait information, and determine the customer profiling result based on the customer target portrait information. The solution of this embodiment can improve the accuracy and efficiency of customer profiling through the collection, integration and analysis of multi-dimensional data of customers, thereby supporting the formulation of more accurate marketing strategies and service plans, helping financial institutions optimize product portfolios, improve service quality, and enhance market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0032] Figure 1 A flow chart of a method for customer profiling based on multidimensional data according to an embodiment of the present disclosure;

[0033] Figure 2 This is a flow chart of a customer profiling method based on multidimensional data according to another embodiment of the present disclosure;

[0034] Figure 3 This is a flow chart of a customer profiling method based on multidimensional data according to another embodiment of the present disclosure;

[0035] Figure 4A schematic diagram of a customer profiling system based on multi-dimensional data according to an embodiment of the present disclosure;

[0036] Figure 5 Schematic diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0037] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0039] It should be understood that, in the following, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0040] Figure 1 The flowchart of a method for customer profiling based on multidimensional data in an embodiment of the present disclosure is shown below. The method can be executed by a computing device such as a computer. The method for customer profiling based on multidimensional data can include the following steps:

[0041] Step S101: collecting and acquiring a plurality of customer data of different dimensions, and preprocessing the plurality of customer data to obtain a plurality of standard customer data.

[0042] Exemplarily, in one embodiment, the multiple customer data may include customer basic information, customer purchase behavior data, customer interaction behavior data, and external data related to the customer, and the external data includes at least one or more of business registration data, market research data, and social media data.

[0043] For example, if it is an individual customer, the basic customer information may include name, age, gender, occupation, etc. The basic customer information may be used to aggregate data from other sources, and the customer purchase behavior data may include the average monthly balance of financial assets, financial products or other financial investment products, credit cards, various loan information, and consumption habits showing the customer's consumption capacity, etc. If it is a corporate customer, the basic customer information may include the company name, years of establishment, registered capital, paid-in capital, number of employees, industry, etc.

[0044] Customer purchase behavior data may include, for example, the purchase frequency, purchase amount, purchase type, etc. of goods (physical goods or financial goods such as financial management). Customer interaction behavior data may include, for example, online browsing history, social media interaction data, customer service feedback data, etc.

[0045] In one example, the sources of the above-mentioned multiple customer data may be the enterprise's internal CRM system, sales records, customer service records, as well as external social media platforms and data submitted or stored by market research organizations.

[0046] Data acquisition (DAQ) is the basis of data analysis and processing, and accurate data measurement is the basis of data acquisition. Through data acquisition, enterprises can obtain real-time and accurate data, and then conduct refined management and improve decision-making speed and accuracy.

[0047] There are various ways to collect data in this embodiment, mainly including the following: 1. Input collection: enter existing data into the system through the system input page, and update existing information according to actual conditions; 2. Import collection: develop import tools for existing batches of structured data and import them into the system. This method can improve the efficiency of data collection; 3. Interface collection: collect data from other systems into this system through the API interface. This method can realize data sharing and interaction between systems, such as financial statements and industrial and commercial data in other systems.

[0048] In this embodiment, market data and user transaction data (such as customer purchase behavior data) can be collected in real time, and accurate customer profiling can be performed based on the analysis, which can help financial institutions better grasp market changes and user needs and formulate more reasonable investment strategies.

[0049] Data preprocessing is a crucial step in the data analysis process. Through data preprocessing, processed standard customer data can be obtained, which provides a basis for subsequent data analysis. The main purpose of data preprocessing is to improve the quality and availability of the collected original data so that subsequent data analysis and customer profiling can be more accurate and reliable.

[0050] Step S102: Input the plurality of standard customer data into a customer portrait model to obtain corresponding customer portrait information, wherein the customer portrait information includes basic portrait information, behavior portrait information and preference portrait information; wherein the customer portrait model is obtained by pre-training a machine learning algorithm model based on sample customer data and corresponding annotated data;

[0051] Exemplarily, in one embodiment, algorithms such as machine learning of data mining can be applied to conduct in-depth analysis of pre-processed multi-dimensional customer data to construct customer portraits, including basic portraits, behavioral portraits, and preference portraits. Exemplarily, the machine learning algorithm model can be a convolutional neural network model, but it is not limited to this. Any machine learning algorithm model that can be used for classification can be used. The machine learning algorithm model can be iteratively trained in advance based on sample customer data (such as multiple customer data in multiple dimensions after pre-processing) and corresponding annotated data such as portrait type label values ​​until convergence to obtain a customer portrait model.

[0052] Through the customer portrait model, customer portrait information such as basic portrait information, behavior portrait information and preference portrait information can be accurately obtained. The behavior portrait information and preference portrait information are at least related to the customer's purchase behavior data, that is, they represent the customer's purchase behavior characteristics and behavior preference characteristics respectively. This information can be used to accurately segment different types of customers.

[0053] Step S103: Determine customer target portrait information based on the basic portrait information, behavior portrait information and preference portrait information, and determine customer classification results based on the customer target portrait information.

[0054] Exemplarily, the basic profile information, behavior profile information, and preference profile information can be probability values, respectively, indicating the probability that the basic profile, behavior profile, and preference profile of the collected customer are similar to the profile of the preset category of customer. The basic profile information, behavior profile information, and preference profile information can each correspond to a preset weight value, and then the weighted sum can be used to determine the customer target profile information, and finally the customer classification result is determined through the customer target profile information.

[0055] The solution of this embodiment can collect, integrate and analyze the customer's multi-dimensional data, combined with the machine learning algorithm training model to accurately determine the customer segmentation portrait, namely the basic portrait, behavioral portrait and preference portrait, and determine the customer classification results accordingly. This can improve the accuracy and efficiency of customer classification, and then support the formulation of more accurate marketing strategies and service plans, helping financial institutions optimize product portfolios, improve service quality, and enhance market competitiveness.

[0056] In one embodiment, the multiple customer data are preprocessed in step S101, which may specifically include: preprocessing the multiple customer data by data cleaning, data integration, data transformation and data reduction; wherein the data transformation includes at least one or more of data normalization, discretization and standardization; and the data reduction includes at least attribute reduction and / or dimensionality reduction.

[0057] Specifically, the main steps of data preprocessing include: data cleaning, data integration, data transformation, and data reduction, as described below:

[0058] 2.1 Data Cleaning:

[0059] Remove Duplicates: Check and remove duplicate records in a dataset.

[0060] Handling missing values: Identify missing values ​​in the data and take appropriate measures to handle them, such as filling them with the mean, median, mode, or estimating them through interpolation methods.

[0061] Handling outliers: Detect and handle outliers in the data, which may be caused by measurement errors, data entry errors, or extremes in the data itself. Outliers can be handled by removing, replacing, or adjusting according to business logic.

[0062] 2.2 Data Integration:

[0063] Merge data from different data sources into one data store for comprehensive analysis. This involves techniques such as data matching, association, and merging. In the process of data integration, solve problems such as homonymy, synonymy, and data redundancy.

[0064] 2.3 Data Transformation:

[0065] That is, transform the data to make it suitable for a specific analysis method. Common transformations include normalization / standardization, discretization, and data transformation. Normalization / standardization: Convert the data to a uniform scale for comparison and analysis. For example, using z-score standardization can transform the data into a distribution with a mean of 0 and a standard deviation of 1. Discretization: Convert continuous attribute variables into categorical attributes to meet the requirements of certain classification algorithms.

[0066] 2.4 Data Reduction:

[0067] The complexity of data is reduced by selecting meaningful features, i.e., feature data related to customer profiling, data sampling, and dimensionality reduction, thereby improving the efficiency and accuracy of data analysis and customer profiling. Attribute reduction is to find the smallest attribute subset and determine that the probability distribution of the subset is close to the probability distribution of the original data. Dimensionality reduction is to reduce the dimension of data through dimensionality reduction techniques (such as principal component analysis PCA) while retaining as much useful information as possible in the data.

[0068] In this way, the above-mentioned specific data preprocessing in this embodiment can improve the quality and availability of the collected customer data and reduce the analysis risk and complexity, provide strong support for subsequent data analysis customer profiling, and further improve the accuracy and efficiency of customer profiling.

[0069] Based on any one of the above embodiments, in one embodiment, in combination with reference Figure 2 As shown in , the multiple customer data at least include customer purchase behavior data, and the method may further include the following steps:

[0070] Step S201: Based on the customer purchase behavior data, determine the customer type using the RFM model.

[0071] Exemplarily, the RFM model describes the value status of a customer through three indicators: the customer's recent purchase behavior, the overall frequency of purchases, and how much money the customer spent, i.e., the amount of consumption. In the RFM model, R (Recency) indicates how long ago the customer purchased, F (Frequency) indicates the number of times the customer purchased within a period of time, and M (Monetary) indicates the amount of money the customer purchased within a period of time. General analytical CRM focuses on the analysis of customer contribution, while the RFM model emphasizes distinguishing customers by their behavior. In this embodiment, customer value assessment can be performed, and customer segmentation tools such as the RFM model can be used to accurately and meticulously identify different types of customers, such as high-value customers, potential customers, and customers at risk of churn.

[0072] Step S202: Determine a final customer classification result based on the customer type and the customer classification result.

[0073] For example, after the customer type is accurately determined through the RFM model, the previously determined customer classification results can be combined to determine the final customer classification result, which can further improve the accuracy of customer classification.

[0074] In a specific example, the basic information of the company's customers is screened out, and the customer's industry type, financial statements, industrial and commercial annual reports, manual entry and other related information are obtained. The analysis is performed based on the company's industry, number of employees, operating income, assets and liabilities and other multi-dimensional data. The analysis results, i.e. the customer classification results, are as follows:

[0075] For Internet industry customers, the customer classification results include: small, medium and micro enterprises with less than 300 employees or operating income of less than 100 million yuan. Among them, medium-sized enterprises have 100 or more employees and operating income of 10 million yuan or more; small enterprises have 10 or more employees and operating income of 500,000 yuan or more; micro enterprises have less than 10 employees or operating income of less than 500,000 yuan;

[0076] For real estate development and operation enterprises, the customer classification results include: small, medium and micro enterprises with operating income of less than 200,000 yuan or total assets of less than 100 million yuan. Among them, medium-sized enterprises have operating income of 10 million yuan or more and total assets of 50 million yuan or more; small enterprises have operating income of 1 million yuan or more and total assets of 20 million yuan or more; micro enterprises have operating income of less than 1 million yuan or total assets of less than 20 million yuan;

[0077] For catering enterprises, the customer classification results include: small, medium and micro enterprises with less than 300 employees or operating income of less than 100 million yuan. Among them, medium-sized enterprises have 100 or more employees and operating income of 20 million yuan or more; small enterprises have 10 or more employees and operating income of 1 million yuan or more; micro enterprises have less than 10 employees or operating income of less than 1 million yuan;

[0078] For industrial enterprises, the customer classification results include: small, medium and micro enterprises with less than 1,000 employees or less than 400 million yuan in operating income. Among them, medium-sized enterprises with 300 or more employees and operating income of 20 million yuan or more are small enterprises; those with 20 or more employees and operating income of 3 million yuan or more are micro enterprises; those with less than 20 employees or operating income of less than 3 million yuan are micro enterprises, etc.

[0079] Based on any one of the above embodiments, in one embodiment, the method may further include: when it is determined that the final customer classification result is inconsistent with the pre-set basic classification category of the customer, treating the customer as a suspicious customer for tracking and confirmation.

[0080] For example, the above enterprise classification results are compared with the classification categories in the customer basic data, and those with inconsistent classification categories are screened out as suspicious customers for tracking and confirmation. For example, customers with loans in the screening results are further matched according to the enterprise classification scale, loan amount, performance status, etc. For example: customers whose screening results are small and micro enterprises and whose loan amount of a certain bank is more than 10 million yuan or whose total loan amount of all banks is more than 100 million yuan are regarded as suspicious customers.

[0081] In one embodiment, Figure 3 As shown, the method further includes: step S301, determining a corresponding marketing strategy based on the final customer classification result; wherein different customer classification results correspond to different marketing strategies.

[0082] For example, different marketing strategies can be formulated in advance and stored in association with different customer classification results, so that after accurately determining the customer classification results, the marketing strategy can be quickly found and determined. Based on accurate customer classification results, this embodiment allows enterprises to formulate more accurate marketing strategies and improve marketing effects and input-output ratios.

[0083] The bank's potential customer standard is a comprehensive evaluation system that aims to identify customer groups with high growth potential and value. By formulating scientific and reasonable customer segmentation standards and service strategies, banks can better meet customer needs, improve customer satisfaction and loyalty, and achieve their own sustainable development. The above scheme of this embodiment aims to mine deep customer information, summarize and analyze quantitative segmentation indicators, make improvements and innovations for customer fine segmentation, and improve the accuracy of customer segmentation. Accurate customer segmentation can ensure better development of subsequent marketing and services.

[0084] It should be noted that, although the steps of the method in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc. In addition, it is also easy to understand that these steps may be, for example, executed synchronously or asynchronously in multiple modules / processes / threads.

[0085] like Figure 4 As shown, the embodiment of the present disclosure provides a customer profiling system based on multidimensional data, including:

[0086] The collection and preprocessing module 401 is used to collect and obtain multiple customer data of different dimensions of customers, and preprocess the multiple customer data to obtain multiple standard customer data;

[0087] Data analysis module 402, used to input the plurality of standard customer data into a customer portrait model to obtain corresponding customer portrait information, wherein the customer portrait information includes basic portrait information, behavior portrait information and preference portrait information; wherein the customer portrait model is obtained by pre-training a machine learning algorithm model based on sample customer data and corresponding annotated data;

[0088] The customer profiling module 403 is used to jointly determine customer target profile information based on the basic profile information, behavior profile information and preference profile information, and determine the customer profiling result based on the customer target profile information.

[0089] In one embodiment, the acquisition preprocessing module preprocesses the multiple customer data, including: preprocessing the multiple customer data by data cleaning, data integration, data transformation and data reduction; wherein the data transformation includes at least one or more of data normalization, discretization and standardization; and the data reduction includes at least attribute reduction and / or dimensionality reduction.

[0090] In one embodiment, the plurality of customer data includes at least customer purchase behavior data, and the system may further include a type determination module for determining the customer type using the RFM model based on the customer purchase behavior data. The customer classification module may also be used to determine a final customer classification result based on the customer type and the customer classification result.

[0091] In one embodiment, the multiple customer data also include basic customer information, customer interaction behavior data, and external data related to the customer, and the external data includes at least one or more of business registration data, market research data, and social media data.

[0092] In one embodiment, the system may further include a suspicious customer processing module for: when it is determined that the final customer classification result is inconsistent with the pre-set basic classification category of the customer, the customer is treated as a suspicious customer for tracking and confirmation.

[0093] In one embodiment, the system may further include a strategy determination module, which is used to: determine a corresponding marketing strategy based on the final customer segmentation result; wherein different customer segmentation results correspond to different marketing strategies.

[0094] In one embodiment, the behavior profile information and preference profile information are at least related to the customer purchase behavior data.

[0095] Regarding the system in the above embodiment, the specific manner in which each module performs operations and the corresponding technical effects brought about have been described in detail in the embodiment of the method, and will not be elaborated here.

[0096] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of a module or unit described above can be further divided into multiple modules or units for concretization. The components displayed as modules or units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0097] The embodiments of the present disclosure further provide a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for customer profiling based on multidimensional data described in any one of the embodiments above is implemented.

[0098] Exemplarily, the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0099] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0100] The present disclosure also provides an electronic device, including a processor and a memory, wherein the memory is used to store a computer program, wherein the processor is configured to execute the customer profiling method based on multidimensional data in any of the above embodiments by executing the computer program.

[0101] Refer to the following Figure 5The electronic device 600 according to this embodiment of the present invention is described. Figure 5 The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0102] like Figure 5 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0103] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above method embodiment section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 The steps of the method shown in .

[0104] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0105] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0106] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0107] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0108] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation methods of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the method steps of the above-mentioned embodiments according to the implementation methods of the present disclosure.

[0109] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0110] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A customer profiling method based on multidimensional data, characterized in that: include: Collecting and obtaining a plurality of customer data of different dimensions of the customer, and preprocessing the plurality of customer data to obtain a plurality of standard customer data; Inputting the plurality of standard customer data into a customer portrait model to obtain corresponding customer portrait information, wherein the customer portrait information includes basic portrait information, behavior portrait information and preference portrait information; The customer portrait model is obtained by pre-training a machine learning algorithm model based on sample customer data and corresponding annotated data; The customer target portrait information is jointly determined based on the basic portrait information, behavior portrait information and preference portrait information, and the customer classification result is determined based on the customer target portrait information.

2. The method according to claim 1, characterized in that The preprocessing of the plurality of customer data comprises: The plurality of customer data are pre-processed by data cleaning, data integration, data transformation and data reduction; wherein the data transformation includes at least one or more of data normalization, discretization and standardization; and the data reduction includes at least attribute reduction and / or dimension reduction.

3. The method according to claim 1 or 2, characterized in that: The plurality of customer data at least includes customer purchase behavior data, and the method further includes: Based on the customer purchase behavior data, determine the customer type using the RFM model; Based on the customer type and the customer classification result, a final customer classification result is determined.

4. The method according to claim 3, characterized in that The multiple customer data also include basic customer information, customer interaction behavior data, and external data related to the customer, and the external data at least includes one or more of business registration data, market research data, and social media data.

5. The method according to claim 4, characterized in that The method further includes: When it is determined that the final customer classification result is inconsistent with the pre-set basic classification category of the customer, the customer is treated as a suspicious customer for tracking and confirmation.

6. The method according to claim 4, characterized in that The method further includes: A corresponding marketing strategy is determined based on the final customer segmentation result; wherein different customer segmentation results correspond to different marketing strategies.

7. The method according to claim 4, characterized in that The behavior portrait information and preference portrait information are at least related to the customer purchasing behavior data.

8. A customer profiling system based on multidimensional data, characterized in that: include: A collection and preprocessing module, used for collecting and acquiring a plurality of customer data of different dimensions of a customer, and preprocessing the plurality of customer data to obtain a plurality of standard customer data; A data analysis module, used for inputting the plurality of standard customer data into a customer portrait model to obtain corresponding customer portrait information, wherein the customer portrait information includes basic portrait information, behavior portrait information and preference portrait information; The customer portrait model is obtained by pre-training a machine learning algorithm model based on sample customer data and corresponding annotated data; The customer profiling module is used to jointly determine customer target profile information based on the basic profile information, behavior profile information and preference profile information, and determine the customer profiling result based on the customer target profile information.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for customer profiling based on multidimensional data as claimed in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: processor; as well as Memory for storing computer programs; Wherein, the processor is configured to execute the customer profiling method based on multidimensional data according to any one of claims 1 to 7 by executing the computer program.

Images