User discrimination method, device and equipment

Abstract

The invention relates to the technical field of data processing, in particular to a user discrimination method, device and equipment. The method comprises the steps of obtaining different data generated by each customer in historical transactions by obtaining customer historical transaction information and target product data, then generating a linear vector capable of representing the preference of each customer based on attribute information of the historical transactions of each customer and a corresponding behavior weight, and obtaining the data of each customer according to the linear vector. Obtaining different attribute ratings of the target product for each customer; then determining an attribute rating interval corresponding to each customer preference according to the linear vector of the customer preference; and matching the attribute rating of the target product with the attribute rating interval, and screening customer information conforming to the attribute rating. The problems that in the prior art, due to the fact that a system cannot automatically screen clients through existing data, a target marketing client group is wrong, time experience and communication cost are wasted, the clients are affected, and the client experience is lowered are solved.

Description

Technical Field

[0001] This specification relates to the field of data processing technology, and in particular to a user identification method, device, and equipment. Background Art

[0002] As banking products continue to evolve and innovate, the challenge of identifying customers with similar product preferences and recommending appropriate products is becoming increasingly pressing. The traditional approach involves sending text messages or making phone calls to customers who have historically traded all products, recommending upcoming products. This not only wastes valuable human resources but is also highly uninformed, incurring significant communication costs with little effectiveness. Manually screening customers with similar product preferences would require an enormous amount of data. Currently, customer recommendations for new products rely primarily on manual judgment. For example, to recommend a new product with medium or high risk, a bank relationship manager would need to search through each of their managed accounts and make recommendations based on their experience, judging the likelihood of the product being offered to the customer.

[0003] Existing technology recommends upcoming products via text messages or phone calls to customers who have a history of all product transactions. This approach involves filtering a database for customers with a history of product transactions, extracting their information, and then sending pre-edited new product information via group text messages. Alternatively, customers are sorted by their relationship manager, with the corresponding manager conducting individual, manual phone marketing to introduce and promote the new product. This approach wastes valuable human resources, is highly unreliable, and incurs significant communication costs with little effectiveness. Manually screening customers with similar product preferences generates a massive amount of data, requiring significant human resources. Furthermore, the screening process is highly subjective, potentially exposing customers to unnecessary information. For example, new product recommendations rely heavily on manual judgment, requiring bank relationship managers to individually search through their account pool and make recommendations based on their experience. This experience can vary depending on factors such as the relationship manager's years of work experience, knowledge base, and other factors, leading to incorrect target customer groups, wasted time and effort, and communication costs, negatively impacting the customer experience and reducing customer satisfaction.

[0004] In order to solve the above problems, there is an urgent need for a customer screening method for machine intelligence banking product recommendation based on big data algorithms, which has important practical significance and application value. Summary of the Invention

[0005] To address the inability of existing systems to automatically screen customers based on existing data, the present invention provides a user identification method, device, and apparatus. These methods, using big data algorithms, automatically identify the range and probability of customers who meet the trading preferences of currently issued products, resolving the issue of relying on manual experience to screen potential customers. Furthermore, these methods can effectively reduce the number of advertising messages pushed to users, minimizing spam and improving user experience.

[0006] In order to solve the above technical problems, the specific technical solutions of this specification are as follows:

[0007] On the one hand, the embodiments of this specification provide a user identification method, including:

[0008] Obtaining customer historical transaction information and target product data, wherein the historical transaction information includes attribute information and behavior weights of the customer's historical transactions;

[0009] Generate a linear vector representing each customer's preferences based on the attribute information of each customer's historical transactions and the corresponding behavior weight;

[0010] Obtaining an attribute rating of the target product for each customer based on the linear vector of each customer's preference and the target product data;

[0011] determining an attribute rating interval corresponding to each customer preference according to the linear vector of the customer preferences;

[0012] The attribute rating of the target product is matched with the attribute rating interval, and customer information with matching attribute ratings is screened out.

[0013] Furthermore, obtaining customer historical transaction information and target product data further includes:

[0014] Filter out customers with historical transaction records and their historical transaction information from the historical database;

[0015] Configuring data processing algorithm rules based on target product data, wherein the rules include consistency requirements for the types of customer historical transaction information and target product data;

[0016] The customer's historical transaction information and target product data are processed according to the data processing algorithm rules.

[0017] Furthermore, the behavior weight further includes:

[0018] The behavior weight is the ratio of the customer's transaction amount for a single product to the customer's total product amount;

[0019] The single product amount refers to the inventory amount of a single product held by the customer;

[0020] The total amount of customer products is the sum of the inventory amounts of all products held by the customer.

[0021] Furthermore, generating a linear vector representing each customer preference further includes,

[0022] Calculate the behavior weight of each attribute-rated product held by the customer;

[0023] The behavior weight corresponding to each attribute rating is multiplied by the predefined attribute rating value to generate a linear vector representing the customer's preference.

[0024] Furthermore, obtaining the attribute rating of the target product according to the target product data and the linear vector of the customer preference further includes:

[0025] Calculating the inner product value of the linear vector of the customer preference by using a linear algebra vector inner product method;

[0026] The attribute rating interval of the target product is determined according to the corresponding relationship between the inner product value and the preset attribute rating interval.

[0027] Furthermore, calculating the inner product value of the customer preference linear vector by the linear algebra vector inner product method further includes:

[0028] The linear algebra vector inner product calculation formula is:

[0029]

[0030] Where α is the inner product of the product preference linear vector; x1, x2, x3, x4, x5 are the values ​​of each column of the product preference linear vector, and f(x1, x2, x3, x4, x5, α) is the customer's product preference (the value range is an integer interval [1, 5]), which can be understood as the five-level classification of product risk corresponding to the customer's product preference.

[0031] On the other hand, the embodiment of this specification further provides a user identification device, comprising:

[0032] A data acquisition module is used to obtain customer historical transaction information and target product data, wherein the historical transaction information includes attribute information and behavior weights of customer historical transactions;

[0033] A preference acquisition module is used to generate a linear vector representing each customer's preference based on the attribute information of each customer's historical transactions and the corresponding behavior weight;

[0034] An attribute rating module, configured to obtain an attribute rating of the target product for each customer based on the linear vector of each customer's preference and the target product data;

[0035] A rating interval acquisition module, configured to determine an attribute rating interval corresponding to each customer preference based on the linear vector of the customer preference;

[0036] The customer identification module is used to match the attribute rating of the target product with the attribute rating interval and screen out customer information with consistent attribute ratings.

[0037] On the other hand, an embodiment of this specification further provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor implements the above method when executing the computer program.

[0038] Finally, the embodiments of this specification also provide a computer storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer device, the above method is executed.

[0039] By using the embodiments of this specification, it is possible to automatically screen the scope and probability of customers who meet the transaction preferences of the currently issued product through a big data algorithm, thereby solving the problem of relying on manual experience to screen customers for possible products. By obtaining customer historical transaction information and target product data, the different data generated by each customer in historical transactions is obtained. Then, based on the attribute information and corresponding behavior weights of each customer's historical transactions, a linear vector that can represent each customer's preference is generated. Based on the linear vector of each customer's preference and the target product data, the different attribute ratings of the target product for each customer are obtained. Then, based on the linear vector of each customer's preference, the attribute rating interval corresponding to each customer's preference is determined. The attribute rating of the target product is matched with the attribute rating interval to screen out customer information with consistent attribute ratings. This solves the problem in the prior art that the system cannot automatically screen customers based on existing data, resulting in incorrect target marketing customer groups, wasting time and experience and communication costs, and affecting customers and reducing the customer experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 The figure shows a schematic diagram of a system for implementing a user identification method according to an embodiment of the present specification;

[0042] Figure 2 The figure shows a flow chart of a user identification method according to an embodiment of the present specification;

[0043] Figure 3 The following is a process of obtaining customer historical transaction information and target product data according to an embodiment of this specification;

[0044] Figure 4 The process of generating a linear vector representing each customer's preference according to an embodiment of the present specification is shown;

[0045] Figure 5 Schematic diagram showing the method of obtaining the attribute rating of the target product according to an embodiment of this specification;

[0046] Figure 6 The figure shows a schematic diagram of the structure of a user identification device according to an embodiment of the present specification;

[0047] Figure 7 Shown is a schematic diagram of the structure of a computer device according to an embodiment of this specification.

[0048]

Description of the accompanying drawings

[0049] 101. Terminal;

[0050] 102. Server;

[0051] 601, data acquisition module;

[0052] 602. Preference acquisition module;

[0053] 603, attribute rating module;

[0054] 604. Rating interval acquisition module;

[0055] 605. Customer Identification Module

[0056] 802. Computer equipment;

[0057] 804. Processing equipment;

[0058] 806. Storage resources;

[0059] 808, driving mechanism;

[0060] 810, input / output module;

[0061] 812. Input devices;

[0062] 814. Output device;

[0063] 816. Presentation equipment;

[0064] 818. Graphical User Interface;

[0065] 820, network interface;

[0066] 822, communication link;

[0067] 824. Communication bus. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the embodiments described are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this specification.

[0069] It should be noted that the terms "first," "second," and the like in the description and claims of this specification and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of this specification described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0070] like Figure 1 The system diagram for implementing a user identification method according to an embodiment of this specification is shown. The system may include a terminal 101 and a server 102. A communication connection is established between the terminal 101 and the server 102, enabling data exchange. The terminal 101 can input historical customer transaction information and target product data to the server 102. Based on the attribute information of each customer's historical transactions, the server obtains the target product's attribute rating and matches it with the attribute rating range. The server then selects customers with matching attribute ratings and recommends the target product to matching customers. This effectively reduces the number of advertising messages pushed to users, reduces spam, and improves user experience.

[0071] In the embodiments of this specification, the server 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN, Content Delivery Network), and big data and artificial intelligence platforms.

[0072] In an optional embodiment, the terminal 101 may include, but is not limited to, electronic devices such as smartphones, desktop computers, tablet computers, laptop computers, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices. Optionally, the operating system running on the electronic device may include, but is not limited to, Android, iOS, Linux, and Windows.

[0073] It should be noted that Figure 1 What is shown is only one application environment provided by the present disclosure. In actual applications, other application environments may also be included, which are not limited in the embodiments of this specification.

[0074] In order to solve the problems existing in the prior art, the embodiments of this specification provide a user identification method, apparatus, device and storage medium. Figure 2 The flowchart of a user identification method provided by the embodiment of this specification is shown in this figure. The process of customer screening for machine intelligent banking product recommendations based on big data algorithms is described. The order of steps listed in the embodiment is only one of the many execution orders of steps and does not represent the only execution order. When the actual system or device product is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings. Specifically, Figure 2 As shown, the method may include:

[0075] Step 201: Acquire customer historical transaction information and target product data, wherein the historical transaction information includes attribute information and behavior weights of the customer's historical transactions;

[0076] Step 202: Generate a linear vector representing each customer's preference based on the attribute information of each customer's historical transactions and the corresponding behavior weight;

[0077] Step 203: Obtaining attribute ratings of the target product for each customer based on the linear vector of each customer's preference and the target product data;

[0078] Step 204: determining the attribute rating interval corresponding to each customer preference based on the linear vector of the customer preference;

[0079] Step 205: Match the attribute rating of the target product with the attribute rating interval, and filter out customer information with matching attribute ratings as recommendation objects.

[0080] By using the embodiments of this specification, it is possible to automatically screen the scope and probability of customers who meet the transaction preferences of the currently issued product through a big data algorithm, thereby solving the problem of relying on manual experience to screen customers for possible products. By obtaining customer historical transaction information and target product data, the different data generated by each customer in historical transactions is obtained. Then, based on the attribute information and corresponding behavior weights of each customer's historical transactions, a linear vector that can represent each customer's preference is generated. Based on the linear vector of each customer's preference and the target product data, the different attribute ratings of the target product for each customer are obtained. Then, based on the linear vector of each customer's preference, the attribute rating interval corresponding to each customer's preference is determined. The attribute rating of the target product is matched with the attribute rating interval to screen out customer information with consistent attribute ratings. This solves the problem in the prior art that the system cannot automatically screen customers based on existing data, resulting in incorrect target marketing customer groups, wasting time and experience and communication costs, and affecting customers and reducing the customer experience.

[0081] Specifically, customer preference screening rules are configured, a five-level attribute rating standard is defined (low risk level 1 to high risk level 5), and historical customer transaction information and target product attribute rating data are imported. The historical data includes the attribute information and transaction weights of the customer's historical transactions. The transaction weight is the ratio of the inventory amount of a single product to the total holding amount. Secondly, based on the attribute information and corresponding weights of each customer's historical transactions, a customer preference linear vector with one row and five columns is generated, and its inner product value is calculated to quantify the preference intensity. Then, according to the inner product value, it is mapped to the five preset attribute rating intervals. By comparing the absolute difference between the inner product value and the interval center value, the customer's attribute rating is determined. Finally, the attribute rating of the target product is matched with the customer's attribute rating, and customers with consistent ratings are selected as recommendation targets. During the matching process, if the target rating is at the interval critical value, the interval boundary customer with the smallest absolute difference is preferentially selected to improve the accuracy of the recommendation.

[0082] According to one embodiment of the present specification, in order to obtain the historical transaction information of the customer, such as Figure 3 As shown, obtaining customer historical transaction information and target product data further includes:

[0083] Step 301: Filter out customers with historical transaction records and their historical transaction information from the historical database;

[0084] Step 302: configuring data processing algorithm rules based on the target product data, wherein the rules include consistency requirements for the customer's historical transaction information and the type of the target product data;

[0085] Step 303: Process the customer's historical transaction information and target product data according to the data processing algorithm.

[0086] Specifically, customers with product transaction records are screened from the historical database, and their historical transaction information, including the attribute ratings and transaction weights of the products purchased by the customer, is extracted. Secondly, data processing rules are configured to ensure the type consistency of the customer's historical transaction information and the target product data, and a unified data format and processing logic are established. Subsequently, the attribute ratings, transaction weights (the ratio of the individual product inventory amount to the total amount held) of the customer's purchased products, and the attribute ratings of the target products are imported into the processing device for classification and preprocessing to adapt to the needs of subsequent algorithm analysis. Through these steps, a standardized data foundation is provided for intelligent recommendations based on matching customer preferences with target products.

[0087] According to one embodiment of the present specification, in order to calculate the needs of each customer, the behavior weight further includes:

[0088] The behavior weight is the ratio of the customer's transaction amount for a single product to the customer's total product amount;

[0089] The single product amount refers to the inventory amount of a single product held by the customer;

[0090] The total amount of customer products is the sum of the inventory amounts of all products held by the customer.

[0091] Specifically, the behavioral weight is the ratio of a customer's transaction amount for a single product to the total transaction amount of all products they hold, and is used to quantify a customer's preference for allocating funds to a specific product. Specifically, the transaction amount for a single product refers to the customer's current holdings of that product; the customer's total product balance is the sum of the holdings of all products they hold. By calculating the ratio of the holdings of a single product to the total holdings, a behavioral weight is generated to reflect a customer's investment propensity for products with different attribute ratings, providing a data foundation for subsequent preference modeling and product recommendations.

[0092] According to one embodiment of the present specification, in order to obtain the linear vector of each customer's preference, such as Figure 4 As shown, generating a linear vector representing each customer preference further includes,

[0093] Step 401: Calculate the behavior weight of each attribute-rated product held by the customer;

[0094] Step 402: Multiply the behavior weight corresponding to each attribute rating by a predefined attribute rating value to generate a linear vector representing the customer preference.

[0095] According to one embodiment of the present specification, in order to obtain the attribute rating of the target product, such as Figure 5As shown, obtaining the attribute rating of the target product according to the target product data and the linear vector of the customer preference further includes:

[0096] Step 501: Calculate the inner product value of the linear vector of the customer preference by using the linear algebra vector inner product method;

[0097] Step 502: Determine the attribute rating interval of the target product based on the correspondence between the inner product value and the preset attribute rating interval;

[0098] Specifically, the attribute rating of the bank product the customer has already traded is multiplied by the transaction weight to form a linear vector representing the customer's product preference. The linear algebraic inner product of the vectors is then calculated. The linear vector where the inner product of the linear vector falls is compared with the attribute rating of the customer's product to be sold. The five columns of the product risk rating linear vector are sequentially compared to determine the interval within the linear vector where the currently sold product falls. The upper or lower bound of the interval with the smallest absolute difference between the product attribute rating and the upper and lower limits of the interval is selected as the product to be marketed to customers with similar product preferences. The attribute ratings of the target product include: low risk, medium-low risk, medium risk, medium-high risk, and high risk.

[0099] In another embodiment of the present invention, Figure 6 As shown, calculating the inner product value of the customer preference linear vector by the linear algebra vector inner product method further includes that the linear algebra vector inner product calculation formula is:

[0100] The minimum value of the value is mapped to 5;

[0101]

[0102] Where α is the inner product of the product preference linear vector; x1, x2, x3, x4, x5 are the values ​​of each column of the product preference linear vector, and f(x1, x2, x3, x4, x5, α) is the customer's product preference (the value range is an integer interval [1, 5]), which can be understood as the five-level classification of product risk corresponding to the customer's product preference.

[0103] Exemplarily, a linear vector of customer product preferences is generated, and the inner product of the linear vector is calculated for subsequent processing. Customer product preferences can be clearly divided into several main steps, which work together to classify customer product preferences based on product attribute ratings, amount ratio (weight), generate a linear vector of customer transaction bank product preferences, and calculate the inner product of the vector. The specific steps of identifying customer product preferences include: generating a product preference linear vector and calculating the inner product of the product preference linear vector. Generating a product preference linear vector includes: obtaining the weights of the customer's five attribute rating products, where the weights are equal to the amount of transactions for this type of product / the amount of transactions for all products. Multiplying the weights by the attribute ratings of the corresponding products results in a product preference linear vector with one row and five columns. Calculating the inner product of the product preference linear vector includes: using the linear algebra vector inner product method to calculate the inner product of the linear vector. Among them, the calculation of the inner product of the product preference linear vector uses the linear algebra inner product calculation method, which is obtained by taking the square root of the sum of the squares of the five columns of the linear vector.

[0104] Afterwards, the five rating columns of the product risk rating linear vector are sequentially compared to determine which interval of the linear vector the currently sold product falls into. The upper or lower bound of the interval with the smallest absolute difference between the product attribute rating and the upper and lower limits of the interval is taken as the product that should be promoted to customers with high product preference similarity. As a preferred method, in S4, the attribute rating of the currently traded product multiplied by the proportion weight of the amount is used as the linear vector of the customer's product preference. By calculating the inner product of the linear vector of the customer's products and comparing it with the five column intervals of the linear vector of the customer's products, the attribute rating interval of the customer's product preference is obtained. Customer information whose attribute rating of the currently recommended product matches the attribute rating of the customer's product preference calculated above is screened out.

[0105] In another embodiment of the present specification, a historical database is used to filter out customers with historical transaction records. By obtaining the customer's historical transaction information and target product data, the historical transaction information includes attribute information and behavior weights of the customer's historical transactions, that is, the customer's current savings amount and savings habits can be obtained. The behavior weight of each attribute-rated product held by the customer is then calculated. Based on the attribute information of the customer's historical transactions and the corresponding behavior weights, a linear vector representing the customer's preferences is generated. For example, if a customer's savings amount is close to the upgrade amount of the savings card target product, and the linear vector of the customer's preferences determines that the customer tends to save steadily, the attribute rating of the savings card target product will match the customer's attribute rating range, thereby selecting this customer as a recommended target for increasing savings amount, recommending the customer to save until the target product data amount is reached, thereby improving the customer experience. According to actual operation measurements, before the system was put into operation, when a new financial product was sold, an advertising recommendation message was sent to all customers who had purchased the financial product. After the system was put into operation, the number of push messages decreased by more than 60%, and the recommendation success rate increased by more than 5 times compared to before the system was put into operation.

[0106] The embodiment of this specification also provides a user identification device, such as Figure 6 Shown, including,

[0107] Data acquisition module 601, used to acquire customer historical transaction information and target product data, wherein the historical transaction information includes attribute information and behavior weight of the customer's historical transactions;

[0108] Preference acquisition module 602, for generating a linear vector representing each customer's preference based on the attribute information of each customer's historical transactions and the corresponding behavior weight;

[0109] An attribute rating module 603 is configured to obtain an attribute rating of the target product for each customer based on the linear vector of each customer's preference and the target product data;

[0110] A rating interval acquisition module 604 is configured to determine an attribute rating interval corresponding to each customer preference based on the linear vector of the customer preference;

[0111] The customer identification module 605 is configured to match the attribute rating of the target product with the attribute rating interval, and filter out customer information with matching attribute ratings.

[0112] Since the principle of solving the problem by the above device is similar to that of the above method, the implementation of the above device can refer to the implementation of the above method, and the repeated parts will not be repeated.

[0113] like Figure 7The diagram shows a schematic diagram of the structure of a computer device according to an embodiment of the present specification. The apparatus described in the present specification may be a computer device according to the embodiment, executing the method described above. The computer device 802 may include one or more processing devices 804, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The computer device 802 may also include any storage resources 806 for storing any type of information, such as code, settings, data, etc. For example, and without limitation, the storage resources 806 may include any one or more combinations of the following: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, etc. More generally, any storage resource may use any technology to store information. Furthermore, any storage resource may provide volatile or non-volatile retention of information. Furthermore, any storage resource may represent a fixed or removable component of the computer device 802. In one embodiment, when the processing device 804 executes associated instructions stored in any storage resource or combination of storage resources, the computer device 802 may perform any operation of the associated instructions. The computer device 802 also includes one or more drive mechanisms 808 for interacting with any storage resources, such as a hard disk drive mechanism, an optical disk drive mechanism, and the like.

[0114] The computer device 802 may also include an input / output module 810 (I / O) for receiving various inputs (via input devices 812) and for providing various outputs (via output devices 814). A specific output mechanism may include a presentation device 816 and an associated graphical user interface (GUI) 818. In other embodiments, the input / output module 810 (I / O), input devices 812, and output devices 814 may not be included, and the computer device 802 may simply be a computer device in a network. The computer device 802 may also include one or more network interfaces 820 for exchanging data with other devices via one or more communication links 822. One or more communication buses 824 couple the components described above together.

[0115] The communication link 822 may be implemented in any manner, for example, via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 822 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0116] Corresponding to Figures 2 to 4 In the method, an embodiment of this specification also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described above are executed.

[0117] The embodiment of this specification also provides a computer-readable instruction, wherein when the processor executes the instruction, the program therein causes the processor to execute the following Figures 2 to 4 The method shown.

[0118] It should be understood that in the various embodiments of this specification, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0119] It should also be understood that in the embodiments of this specification, the term "and / or" is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the character " / " in this specification generally indicates that the associated objects are in an "or" relationship.

[0120] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this specification.

[0121] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0122] In the several embodiments provided in this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be an electrical, mechanical or other form of connection.

[0123] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of this specification.

[0124] In addition, the functional units in the various embodiments of this specification may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0125] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this specification is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this specification. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0126] Specific embodiments are used in this specification to illustrate the principles and implementation methods of this specification. The description of the above embodiments is only used to help understand the methods and core ideas of this specification. At the same time, for those skilled in the art, based on the ideas of this specification, there will be changes in the specific implementation methods and application scope. In summary, the contents of this specification should not be understood as limiting this specification.

Claims

1. A user identification method, characterized in that: The method comprises, Obtaining customer historical transaction information and target product data, wherein the historical transaction information includes attribute information and behavior weights of the customer's historical transactions; Generate a linear vector representing each customer's preferences based on the attribute information of each customer's historical transactions and the corresponding behavior weight; Obtaining an attribute rating of the target product for each customer based on the linear vector of each customer's preference and the target product data; determining an attribute rating interval corresponding to each customer preference according to the linear vector of the customer preferences; The attribute rating of the target product is matched with the attribute rating interval, and customer information with matching attribute ratings is screened out.

2. The user identification method according to claim 1, characterized in that: Acquiring customer historical transaction information and target product data further includes: Filter out customers with historical transaction records and their historical transaction information from the historical database; Configuring data processing algorithm rules based on target product data, wherein the rules include consistency requirements for the types of customer historical transaction information and target product data; The customer's historical transaction information and target product data are processed according to the data processing algorithm rules.

3. The user identification method according to claim 2, characterized in that: The behavior weight further includes: The behavior weight is the ratio of the customer's transaction amount for a single product to the customer's total product amount; The single product amount refers to the inventory amount of a single product held by the customer; The total amount of customer products is the sum of the inventory amounts of all products held by the customer.

4. The user identification method according to claim 1, characterized in that: Generating a linear vector representing each customer's preference further includes, Calculate the behavior weight of each attribute-rated product held by the customer; The behavior weight corresponding to each attribute rating is multiplied by the predefined attribute rating value to generate a linear vector representing the customer's preference.

5. The user identification method according to claim 1, characterized in that: Obtaining the attribute rating of the target product according to the target product data and the linear vector of the customer preference further includes: Calculating the inner product value of the linear vector of the customer preference by using a linear algebra vector inner product method; The attribute rating interval of the target product is determined according to the corresponding relationship between the inner product value and the preset attribute rating interval.

6. The user identification method according to claim 5, characterized in that: Calculating the inner product value of the linear vector of the customer preference by the linear algebra vector inner product method further includes: The linear algebra vector inner product calculation formula is: Where α is the inner product of the product preference linear vector; x1, x2, x3, x4, x5 are the values ​​of each column of the product preference linear vector, and f(x1, x2, x3, x4, x5, α) is the customer's product preference (the value range is an integer interval [1, 5]).

7. A user identification device, characterized in that: The device further comprises: A data acquisition module is used to obtain customer historical transaction information and target product data, wherein the historical transaction information includes attribute information and behavior weights of customer historical transactions; A preference acquisition module is used to generate a linear vector representing each customer's preference based on the attribute information of each customer's historical transactions and the corresponding behavior weight; An attribute rating module, configured to obtain an attribute rating of the target product for each customer based on the linear vector of each customer's preference and the target product data; A rating interval acquisition module, configured to determine an attribute rating interval corresponding to each customer preference based on the linear vector of the customer preference; The customer identification module is used to match the attribute rating of the target product with the attribute rating interval and screen out customer information with consistent attribute ratings.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images