CN115659026A

CN115659026A - Client recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN115659026A
Application number: CN202211321332.0A
Authority: CN
Inventors: 罗家贤
Original assignee: Shenzhen One Account Technology Co ltd
Current assignee: Shenzhen One Account Technology Co ltd
Priority date: 2022-10-26
Filing date: 2022-10-26
Publication date: 2023-01-31

Abstract

The invention relates to an artificial intelligence technology, can recommend high-quality financial users, disclose a customer recommending method, comprising: constructing a decision tree according to all client features in the historical client feature information and feature values corresponding to all the client features, and training the decision tree by using the historical client feature information set to obtain a client recommendation model; and analyzing the client characteristic information of the client to be recommended by using the client recommendation model to obtain the recommendation probability value of each client in the client set to be recommended, and screening the clients in the client set to be recommended to the personnel to be recommended by using the recommendation probability values. The invention also relates to a blockchain technique, and the recommendation probability values can be stored in blockchain link points. The invention also provides a client recommendation device, equipment and a medium. The invention can improve the accuracy of customer recommendation.

Description

Client recommendation method and device, electronic equipment and storage medium

Technical Field

The invention relates to an artificial intelligence technology, in particular to a client recommendation method, a client recommendation device, electronic equipment and a storage medium.

Background

With the development of economy, maintaining high-quality customers becomes an important way for business personnel business expansion in the financial field, and business personnel are required to perform customer recommendation to screen high-quality customers from numerous customers for recommendation.

However, most of the existing customer recommendation methods can only extract the features of a certain dimension of the user to perform customer recommendation such as the amount of a customer order, the number of orders and the like, the dimension of customer screening is single, and the accuracy rate of the customer recommendation is low.

Disclosure of Invention

The invention provides a client recommendation method, a client recommendation device, electronic equipment and a storage medium, and mainly aims to improve the accuracy of client recommendation.

Acquiring a historical client characteristic information set, wherein each piece of historical client characteristic information in the historical client characteristic information set has a corresponding client category;

extracting all client characteristics in the historical client characteristic information and characteristic values corresponding to the client characteristics;

taking the client category as a leaf node, taking the client characteristics as a root node and a child node, connecting all nodes based on the characteristic values to construct a decision tree, and training the decision tree by using the historical client characteristic information set to obtain a client recommendation model;

when a client set to be recommended and client characteristic information of each client in the client set to be recommended are obtained, analyzing the client characteristic information by using the client recommendation model to obtain a recommendation probability value of each client in the client set to be recommended;

and screening the clients in the client set to be recommended according to the recommendation probability value and a preset recommendation threshold value, acquiring client information of the screened clients, and pushing the client information to preset terminal equipment.

Optionally, the creating a decision tree by using the customer category as a leaf node, using the customer feature as a root node and a child node, and connecting all nodes based on the feature value includes:

taking all kinds of client characteristics as nodes and all kinds of client categories as leaf nodes;

calculating the information gain of each node, determining the node corresponding to the maximum information gain as a root node, and taking all nodes except the root node as child nodes;

and starting from the root node based on the information gain, connecting child nodes in a progressive manner by taking the characteristic value of the customer characteristic corresponding to the node as a connection condition, and connecting the child node connected last to the leaf node to obtain the decision tree.

Optionally, the training the decision tree by using the historical customer feature information set to obtain a customer recommendation model includes:

screening historical customer characteristic information in the historical customer characteristic information by using the decision tree to perform category analysis to obtain a corresponding category analysis value;

calculating a model precision error value of the decision tree according to the client category of the historical client characteristic information corresponding to the category analysis value and the category analysis value;

judging whether the model precision error value is smaller than a preset target threshold value or not;

when the model precision error value is larger than or equal to the target threshold value, node weight updating is carried out on the decision tree, and the step of utilizing the decision tree to screen historical customer characteristic information in the historical customer characteristic information for category analysis is returned;

and when the model precision error value is smaller than the target threshold value, outputting the decision tree as a customer recommendation model.

Optionally, the screening, by using the decision tree, the historical customer feature information in the historical customer feature information to perform category analysis to obtain a corresponding category analysis value includes:

randomly selecting historical client characteristic information in the historical client characteristic information set to obtain target historical characteristic information;

and performing category analysis on the target historical characteristic information by using the decision tree to obtain a corresponding category analysis value.

Optionally, the performing category analysis on the target historical feature information by using the decision tree to obtain a corresponding category analysis value includes:

inputting the target historical feature information into the decision tree;

extracting the output value of a leaf node of which the corresponding client category is a preset target category in the decision tree to obtain an initial analysis value;

and adding all the initial analysis values to obtain the category analysis value.

Optionally, the screening, according to the recommendation probability value and a preset recommendation threshold, the clients in the set of clients to be recommended, and obtaining client information of the screened clients to push to a preset terminal device, includes:

selecting a recommendation probability value which is greater than the recommendation threshold value from the recommendation probability values to obtain a target recommendation probability value;

selecting the client corresponding to the target recommendation probability value in the client set to be recommended to obtain a target client;

and acquiring the client information of the target client, and sending the client information to preset terminal equipment.

In order to solve the above problem, the present invention also provides a client recommendation apparatus, including:

the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring a historical client characteristic information set, and each piece of historical client characteristic information in the historical client characteristic information set has a corresponding client category;

the model training module is used for extracting all client features in the historical client feature information and feature values corresponding to the client features; taking the client category as a leaf node, taking the client characteristics as a root node and a child node, connecting all nodes based on the characteristic values to construct a decision tree, and training the decision tree by using the historical client characteristic information set to obtain a client recommendation model;

the client recommendation module is used for analyzing the client characteristic information by using the client recommendation model when acquiring a client set to be recommended and the client characteristic information of each client in the client set to be recommended to obtain a recommendation probability value of each client in the client set to be recommended; and screening the clients in the client set to be recommended according to the recommendation probability value and a preset recommendation threshold value, acquiring client information of the screened clients, and pushing the client information to preset terminal equipment.

In order to solve the above problem, the present invention also provides an electronic device, including:

a memory storing at least one computer program; and

and a processor executing the computer program stored in the memory to implement the client recommendation method described above.

In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the customer recommendation method described above.

The embodiment of the invention trains the decision tree by utilizing the historical customer characteristic information set to obtain a customer recommendation model; when a to-be-recommended client set and client characteristic information of each client in the to-be-recommended client set are obtained, analyzing the client characteristic information by using the client recommendation model to obtain a recommendation probability value of each client in the to-be-recommended client set; the client recommendation model constructed based on the decision tree can analyze various client characteristics, is not limited to single characteristics, has a better analysis effect and higher recommendation accuracy, so that the client recommendation method, the client recommendation device, the electronic equipment and the readable storage medium provided by the embodiment of the invention improve the accuracy of client recommendation.

Drawings

Fig. 1 is a schematic flow chart of a client recommendation method according to an embodiment of the present invention;

FIG. 2 is a block diagram of a client recommendation device according to an embodiment of the present invention;

fig. 3 is a schematic internal structural diagram of an electronic device implementing a client recommendation method according to an embodiment of the present invention;

the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.

The embodiment of the invention provides a client recommendation method. The execution subject of the customer recommendation method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the client recommendation method may be executed by software or hardware installed in the terminal device or the server device, and the software may be a blockchain platform. The server includes but is not limited to: the system comprises a single server, a server cluster, a cloud server or a cloud server cluster, and the like, wherein the server can be an independent server, and can also be a cloud server for providing basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content Delivery Network (CDN), big data, an artificial intelligence platform and the like.

Referring to fig. 1, a flow diagram of a customer recommendation method according to an embodiment of the present invention is shown, in the embodiment of the present invention, the customer recommendation method includes:

s1, obtaining a historical client characteristic information set, wherein each piece of historical client characteristic information in the historical client characteristic information set has a corresponding client type;

in the embodiment of the present invention, the historical client feature information is feature information of a historical client, the historical client is a client in a financial field, and the historical client feature information includes: customer characteristics such as customer address, order amount, order number and the like and corresponding characteristic value information, wherein the customer category is the customer category judged according to the historical customer characteristic information.

S2, extracting all client features in the historical client feature information and feature values corresponding to the client features;

in the embodiment of the invention, in order to judge the influence of different customer characteristics on the customer category, the customer characteristics in the historical customer characteristic information and the characteristic values corresponding to the customer characteristics are extracted.

For example: extracting the client characteristics in the historical client characteristic information as follows: and the customer address corresponds to the characteristic value of Beijing.

S3, taking the client category as a leaf node, taking the client characteristics as a root node and a child node, connecting all nodes based on the characteristic values to construct a decision tree, and training the decision tree by using the historical client characteristic information set to obtain a client recommendation model;

in the embodiment of the invention, in order to further measure the influence of the client types of the clients corresponding to different client characteristics, an artificial intelligence model is constructed to measure the client types of the clients corresponding to different client characteristics, so that the classification of different clients is realized, and the recommendation of the clients is further realized.

Specifically, in the embodiment of the present invention, the client category is used as a leaf node, the client feature is used as a root node and a child node, and a decision tree is constructed by connecting all nodes based on the feature value, including:

Further, in the embodiment of the present invention, the training of the decision tree by using the historical customer feature information set to obtain a customer recommendation model includes:

and calculating a model precision error value of the decision tree according to the client category of the historical client characteristic information corresponding to the category analysis value and the category analysis value.

and when the model precision error value is smaller than the target threshold value, outputting the decision tree as a customer recommended model.

Further, in the embodiment of the present invention, the screening, by using the decision tree, the historical client characteristic information in the historical client characteristic information to perform category analysis, so as to obtain a corresponding category analysis value, where the category analysis value includes:

step A: randomly selecting historical customer characteristic information in the historical customer characteristic information set to obtain target historical characteristic information;

in the embodiment of the invention, after a piece of historical client characteristic information in the historical client characteristic information set is randomly selected to obtain the target historical characteristic information, the target historical characteristic information in the historical client characteristic information set is deleted to obtain a new historical client characteristic information set.

And B: performing category analysis on the target historical characteristic information by using the decision tree to obtain a corresponding category analysis value;

specifically, in the embodiment of the present invention, the target historical feature information is input into the decision tree; extracting the output value of a leaf node of which the corresponding client category is a preset target category in the decision tree to obtain an initial analysis value; and adding all the initial analysis values to obtain the category analysis value.

Further, in the embodiment of the present invention, calculating a model precision error value of the decision tree according to the customer category of the historical customer feature information corresponding to the category analysis value and the category analysis value includes:

determining the client category of the historical client characteristic information corresponding to the category analysis value as a target client category;

determining a category true value according to the category of the target customer;

and calculating by taking the category real value and the category analysis value as variables of a preset error calculation function to obtain the model precision error value.

For example: the client category is a high-value client or a common client, and the category true value corresponding to the client category is 1 when the client category is the high-value client, and the category true value corresponding to the client category is 0 when the client category is the common client.

Further, in the embodiment of the present invention, when the model accuracy error value is greater than or equal to the target threshold, it is proved that the model accuracy cannot meet a preset requirement, and therefore, the weight parameter of the node in the decision tree is adjusted, optionally, in the embodiment of the present invention, the weight of the child node in the decision tree is adjusted by a preset adjustment ratio and a preset adjustment manner, so as to adjust the weight parameter of the node in the decision tree, where the adjustment manner is increasing or decreasing, for example: and if the adjustment proportion is 1% and the adjustment mode is increasing, increasing the weight of the child nodes in the decision tree according to the amplification proportion of 1%. In the invention, the weights of other kinds of nodes in the decision tree can be adjusted to realize the adjustment of the weight parameters, and the adjustment is not limited to this.

S4, when a to-be-recommended client set and client characteristic information of each client in the to-be-recommended client set are obtained, analyzing the client characteristic information by using the client recommendation model to obtain a recommendation probability value of each client in the to-be-recommended client set;

in the embodiment of the invention, the set of the clients to be recommended is a set of clients capable of recommending, the types of the client characteristic information and the historical client characteristic information are the same, and the content is different, and no corresponding client category exists.

Further, in the embodiment of the present invention, the client characteristic information is input into the client recommendation model, and target leaf nodes in all leaf nodes in the client recommendation model are screened based on a preset target category; and extracting output values of all target leaf nodes in the client recommendation model, and accumulating all the output values to obtain the recommendation probability of the client corresponding to the client characteristic information.

Further, in the embodiment of the present invention, the screening target leaf nodes in all leaf nodes in the client recommendation model based on a preset target category includes:

obtaining a client category corresponding to each leaf node in the client recommendation model;

and determining the leaf node of which the corresponding client category is a preset target category as the target leaf node.

In another embodiment of the invention, the recommended probability value can be stored in a block chain node, and the data taking efficiency is improved by using the characteristic of high throughput of the block chain node.

And S5, screening the clients in the client set to be recommended according to the recommendation probability value and a preset recommendation threshold value, acquiring client information of the screened clients and pushing the client information to a preset terminal device.

Optionally, in the embodiment of the present invention, a recommendation probability value greater than the recommendation threshold is selected from the recommendation probability values to obtain a target recommendation probability value; selecting the client corresponding to the target recommendation probability value in the client set to be recommended to obtain a target client; and acquiring the client information of the target client, and sending the client information to preset terminal equipment.

Optionally, the terminal device in the embodiment of the present invention includes an intelligent terminal such as a mobile phone, a computer, and a tablet.

Fig. 2 is a functional block diagram of the client recommendation apparatus according to the present invention.

The client recommendation device 100 of the present invention may be installed in an electronic device. According to the implemented functions, the client recommendation device may include a data acquisition module 101, a model training module 102, and a client recommendation module 103, which may also be referred to as a unit, and refer to a series of computer program segments that can be executed by a processor of an electronic device and can perform fixed functions, and are stored in a memory of the electronic device.

In the present embodiment, the functions regarding the respective modules/units are as follows:

the data acquisition module 101 is configured to acquire a historical client feature information set, where each piece of historical client feature information in the historical client feature information set has a corresponding client category;

the model training module 102 is configured to extract all customer features in the historical customer feature information and feature values corresponding to each customer feature; taking the client category as a leaf node, taking the client characteristics as a root node and a child node, connecting all nodes based on the characteristic values to construct a decision tree, and training the decision tree by using the historical client characteristic information set to obtain a client recommendation model;

the client recommendation module 103 is configured to, when acquiring a to-be-recommended client set and client feature information of each client in the to-be-recommended client set, analyze the client feature information by using the client recommendation model to obtain a recommendation probability value of each client in the to-be-recommended client set; and screening the clients in the client set to be recommended according to the recommendation probability value and a preset recommendation threshold value, acquiring client information of the screened clients, and pushing the client information to preset terminal equipment.

In detail, in the embodiment of the present invention, when the modules in the client recommendation apparatus 100 are used, the same technical means as the client recommendation method described in fig. 1 are used, and the same technical effects can be produced, which is not described herein again.

Fig. 3 is a schematic structural diagram of an electronic device implementing the client recommendation method according to the present invention.

The electronic device may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as a client recommendation program, stored in the memory 11 and executable on the processor 10.

The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as a code of a client recommendation program, etc., but also to temporarily store data that has been output or will be output.

The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., a client recommendation program, etc.) stored in the memory 11 and calling data stored in the memory 11.

The communication bus 12 may be a PerIPheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The communication bus 12 is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

Fig. 3 shows only an electronic device having components, and those skilled in the art will appreciate that the structure shown in fig. 3 does not constitute a limitation of the electronic device, and may include fewer or more components than those shown, or some components may be combined, or a different arrangement of components.

For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power source may also include any component of one or more dc or ac power sources, recharging devices, power failure classification circuits, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

Optionally, the communication interface 13 may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices.

Optionally, the communication interface 13 may further include a user interface, which may be a Display (Display), an input unit (such as a Keyboard (Keyboard)), and optionally, a standard wired interface, or a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The client recommendation program stored in the memory 11 of the electronic device is a combination of a plurality of computer programs, which when executed in the processor 10, can implement:

Specifically, the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer program, which is not described herein again.

Further, the electronic device integrated module/unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. The computer readable medium may be non-volatile or volatile. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM).

Embodiments of the present invention may also provide a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program may implement:

when a to-be-recommended client set and client characteristic information of each client in the to-be-recommended client set are obtained, analyzing the client characteristic information by using the client recommendation model to obtain a recommendation probability value of each client in the to-be-recommended client set;

Further, the computer usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.

The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

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

Furthermore, it will be obvious that the term "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for customer recommendation, the method comprising:

2. The customer recommendation method according to claim 1, wherein constructing a decision tree by using the customer category as leaf nodes, using the customer features as root nodes and child nodes, and connecting all the nodes based on the feature values comprises:

3. The customer recommendation method of claim 1, wherein said training said decision tree using said set of historical customer characteristic information to obtain a customer recommendation model comprises:

4. The customer recommendation method according to claim 3, wherein the using the decision tree to filter the historical customer characteristic information in the historical customer characteristic information for category analysis to obtain a corresponding category analysis value comprises:

randomly selecting historical customer characteristic information in the historical customer characteristic information set to obtain target historical characteristic information;

5. The customer recommendation method of claim 3, wherein performing a category analysis on the target historical feature information using the decision tree to obtain a corresponding category analysis value comprises:

inputting the target historical feature information into the decision tree;

6. The client recommendation method according to any one of claims 1 to 5, wherein the screening the clients in the set of clients to be recommended according to the recommendation probability value and a preset recommendation threshold, and acquiring client information of the screened clients to push the client information to a preset terminal device comprises:

selecting a recommendation probability value which is greater than the recommendation threshold value in the recommendation probability values to obtain a target recommendation probability value;

7. A client recommendation device, comprising:

8. The client recommending device of claim 7, wherein the step of filtering the clients in the set of clients to be recommended according to the recommendation probability value and a preset recommendation threshold, and obtaining client information of the filtered clients to push to a preset terminal device comprises:

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor;

wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the customer recommendation method of any one of claims 1-6.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the customer recommendation method of any one of claims 1 to 6.