WO2022100427A1

WO2022100427A1 - Push method and apparatus for service product information, computer device and medium

Info

Publication number: WO2022100427A1
Application number: PCT/CN2021/126253
Authority: WO
Inventors: 任正
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2020-11-16
Filing date: 2021-10-26
Publication date: 2022-05-19
Also published as: CN112468556B; WO2022100427A9; CN112468556A

Abstract

The present application relates to the technical field of artificial intelligence. Specifically disclosed are a push method and apparatus for service product information, a computer device and a medium. The push method may comprise: constructing a customer information table by using acquired customer data, and performing data conversion on the customer information table to generate a first feature vector table for describing customer information; correspondingly matching the first feature vector table with a second feature vector table for describing service product information, to obtain matching results between customers and service products; and pushing information of at least one service product to the matching customers on the basis of the matching results. The present application pushes, by means of feature vector matching, highly matched service product information to customers, achieving the technical effects of strong pertinence, high success rate and low cost. The present application can realize accurate matching between service products and customers on the basis of degree-of-fitting calculation, and provide customers with the service products they need; and customer experience is thus good. In addition, the present application may also relate to a blockchain technology.

Description

A method and device, computer equipment, and medium for pushing service product information

This application claims the priority of the Chinese patent application filed on November 16, 2020 with the application number 202011280614.1 and the title of the invention is "a method and device for pushing service product information, computer equipment, and medium", all of which are The contents are incorporated herein by reference.

technical field

This application relates to the field of artificial intelligence technology and can be applied to the field of pushing service product information, and specifically provides a method and device, computer equipment, and medium for pushing service product information; in addition, this application also relates to blockchain technology.

Background technique

At present, salespeople mainly rely on manual methods to introduce and recommend financial service products to customers. This traditional method requires the salesman to know the details of the product to be introduced in the early stage, and then to understand the customer's situation based on the communication with the customer before recommendation, and finally to recommend the relevant financial service product to the customer based on the understanding. It can be seen that the traditional recommendation scheme has problems such as low recommendation efficiency, small push force, high dependence on the personal experience of the salesperson, and high labor cost.

In view of this, the inventor found that someone has proposed a scheme for mass information push, allowing customers to choose the financial service products they need. However, when customers are faced with a large number of service and product news, they often ignore it directly. It can be seen that the mass message push scheme is less targeted and has a very low success rate.

Therefore, there is an urgent need to provide a service product information push solution that is highly targeted, has a high success rate, and can reduce labor input costs.

SUMMARY OF THE INVENTION

In order to solve at least one problem existing in the existing service product recommendation solution, the present application can provide a method and apparatus, computer equipment and medium for pushing service product information.

In order to achieve the above technical purpose, the present application provides a method for pushing service product information, which may include, but is not limited to, at least one of the following steps.

Use the acquired customer data to build a customer information table.

Perform at least one data transformation on the customer information table to generate a first feature vector table for describing customer information.

The first feature vector table is matched with the second feature vector table used to describe the service product information, so as to obtain a matching result between the customer and the service product.

Based on the matching result, at least one service product information is pushed to the matched customer.

To achieve the above technical purpose, the present application also provides a push device for service product information, the push device includes but is not limited to an information table construction module, a data conversion module, a vector matching module and a product push module.

An information table building module is used to construct a customer information table using the acquired customer data.

A data conversion module, configured to perform at least one data conversion on the customer information table to generate a first feature vector table for describing customer information.

The vector matching module is configured to perform corresponding matching between the first feature vector table and the second feature vector table used to describe the service product information, so as to obtain the matching result between the customer and the service product.

A product push module, configured to push at least one service product information to a matched customer based on the matching result.

In order to achieve the above technical purpose, the present application can also provide a computer device, the computer device may include a memory and a processor, and the memory stores computer-readable instructions, when the computer-readable instructions are executed by the processor. , causing the processor to execute the method for pushing service product information as described in any embodiment of the present application, the method comprising:

Use the acquired customer data to build a customer information table;

performing at least one data conversion on the customer information table to generate a first feature vector table for describing customer information;

Correspondingly matching the first feature vector table with the second feature vector table used to describe the service product information to obtain a matching result between the customer and the service product;

In order to achieve the above technical purpose, the present application can also provide a storage medium storing computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors can The method for pushing service product information according to any embodiment, the method includes:

Use the acquired customer data to build a customer information table;

Based on the matching result, at least one service product information is pushed to the matched customers.

The beneficial effects of the present application are as follows: the present application innovatively pushes service product information with high matching degree to customers by means of feature vector matching, which has the technical effects of strong pertinence, high success rate and low cost, so that it can effectively At least one problem of poor push effect, low success rate and high cost in the prior art is solved.

Description of drawings

FIG. 1 shows a schematic flowchart of a method for pushing service product information in some embodiments of the present application.

FIG. 2 shows a schematic flowchart of a method for pushing service product information in other embodiments of the present application.

FIG. 3 shows a block diagram of the internal structure of a computer device in one or more embodiments of the present application.

FIG. 4 shows an implementation environment diagram of a method for pushing service product information in one or more embodiments of the present application.

Detailed ways

A method and device, computer equipment and medium for pushing service product information provided by the present application will be explained and described in detail below with reference to the accompanying drawings.

Optionally, the technical solution of the present application can be applied to various information push scenarios, such as medical service product information push scenarios in digital medicine, and financial service product information push scenarios in financial technology.

As shown in FIG. 1 , one or more embodiments of the present application can specifically provide a method for pushing service product information, and the service products of the present application include but are not limited to financial service products. Specifically, the method for pushing service product information may include, but is not limited to, at least one or more of the following steps.

Step 100, using the acquired customer data to construct a customer information table. The application can collect relevant customer data of multiple customers in advance, use the collected customer data as a data source, and then use the data source to form a customer information table. The customer information table in some embodiments of the present application may be represented in the form of a matrix. Each row or column of the matrix is used to represent all data of a customer, and each element in the matrix is used to describe the customer's situation. For example, customer data may include But not limited to age, position, income, liabilities, loans, fixed assets, overseas assets, mortgageable assets, financial management, online banking transactions, marital status, physical condition, etc. This application can also classify customer data, such as customer basic information, social relationship information, personal business information, personal credit information, etc., and can use one type of information as customer data. On the basis of what has been disclosed in this application, other data that can be used to describe the customer's situation can also be used as the user data of this application.

Step 200: Perform at least one data conversion on the customer information table to generate a first feature vector table for describing customer information. The present application standardizes each customer portrait in the form of the first feature vector table, so as to provide strong support for accurately pushing service product messages.

As shown in FIG. 2 , the steps of performing at least one data conversion on the customer information table in some embodiments of the present application include but are not limited to the

following steps

201 and 202 .

Step 201: Set a standard relative value according to the distribution of customer data contained in the customer information table. In some embodiments of the present application, the standard relative value is set according to the most prominent and outstanding data part in the customer information table. Taking the age distribution as an example, in this embodiment, the age of 30-35 is used as the standard relative value.

Step 202 , normalize the customer data in the customer information table based on the standard relative value, so as to realize the data conversion of the customer information table. In the normalization process of this embodiment, the standard relative value can be converted first to obtain a dimensionless scalar. Taking the age distribution as an example, the standard relative value in this embodiment is 30-35 years old, the converted result can be 10, the converted result of 25-30 years old can be 9, and the converted result of 35-40 years old can be. For 9, 40-45 years old can be converted to 8 and so on. Taking the number of online banking transactions as an example, the standard relative value in this embodiment is 1000 times, then the converted result of data greater than or equal to 1000 can be 10, the converted result of 900-1000 can be 9, and the converted result of 800-900 The result can be 8 and so on.

It is understandable that the data conversion step of the customer information table in this application may also adopt other methods, such as using the proportion of various customers to realize the data conversion of the customer information table; The proportion of the number of each customer under a type is used as the characteristic of the customer. Taking the age distribution as an example, among all the current customers, the number of customers aged 30-35 accounts for 39%, and the converted result is 3.9; if the number of customers aged 25-30 accounts for 18%, the converted result is 1.8 Wait. Taking the customer's income as an example, customers with income in 300K-500K account for 66%, and the converted results are 6.6; customers with income in 500K-800K account for 21%, then the converted results are all 2.1 and so on.

In addition, in some embodiments of the present application, multiple pieces of associated customer data in the customer information table may be merged before the normalization process, and then the merged processing result may be used as newly generated customer data. It is understandable that the present application can use newly generated customer data to replace the data used for merging processing, or realize data augmentation based on the original customer data. This embodiment describes liabilities, stock holdings, fixed assets and overseas assets. On this basis, this application can obtain new data - debt ratio, debt ratio = liabilities/(stock holdings + fixed assets + overseas assets ).

The present application also includes a process of constructing a second feature vector table, specifically, before performing corresponding matching between the first feature vector table and the second feature vector table used to describe service product information, the following steps 110 to 112 are further included.

Step 110: Read the product description file that records the service product information. The product description document may be, for example, a text document such as an electronic manual, notification letter, agreement letter, etc. of the financial service product.

Step 111 , extracting a plurality of pieces of service product data related to the target audience customers of the current service product from the product description file.

Step 112, using the service product data to construct a second feature vector table. It can be understood that the formation process of the second feature vector table in the present application can also be similar to the formation process of the first feature vector table, such as including the production process of the product information table, converting the product information table into the second feature vector table through data conversion. feature vector table, etc. The formation process of the second feature vector table in some embodiments may be similar to the formation process of the first feature vector table of the present application.

Step 300: Match the first feature vector table with the second feature vector table used to describe the service product information, so as to obtain a matching result between the customer and the service product.

As shown in FIG. 2 , in some embodiments of the present application, the steps of correspondingly matching the first feature vector table with the second feature vector table used to describe service product information include but are not limited to steps 301 to 303 .

Step 301: Read the first feature vector included in the first feature vector table; wherein one first feature vector is used to describe the information of a customer.

Step 302: Calculate the degree of fit of each of the first eigenvectors and all the second eigenvectors included in the second eigenvector table one by one. It can be seen that for any customer, the application can match various service products with the customer, and quantify the matching result through the calculation of the degree of fit. It is understandable that the number of fit results for any customer in this application is the same as the number of current service products.

In some embodiments of the present application, calculating the degree of fit of each of the first eigenvectors with all the second eigenvectors included in the second eigenvector table one by one includes:

I _cp =∑(f _i ² -q _j ² ) ²

f _i =[d ₁ ,d ₂ ,...d _k ]

q _j =[e ₁ ,e ₂ ,...e _k ]

i=1,2,3...m

j=1,2,3...n

Among them, I _cp represents the degree of fit between the first eigenvector and the second eigenvector, f _i represents the i-th first eigenvector, q _j represents the j-th second eigenvector, and d _k represents the k-th customer data, e _k represents the kth product data, k represents the number of elements in the feature vector, m represents the number of customers, and n represents the number of service products.

In one or more embodiments of the present application, the smaller the degree of fit between the first feature vector and the second feature vector, the greater the relationship between the customer corresponding to the first feature vector and the service product corresponding to the second feature vector. The tighter, the higher the fit.

In step 303, the obtained degree of fit is used as the matching result between the customer and the service product. Therefore, this application can describe the relationship between customers and service products in a very fine manner based on the calculation of the degree of fit, that is, the effective mapping between the products in the service product set and the customers in the customer set is completed, and then from the information of many service products. Screen out the service product information that the current customer actually needs to achieve the main purpose of this application.

Step 400, based on the matching result, push the information of at least one service product to the matching customer. This application pushes at least one piece of appropriate service product information for each customer in a targeted manner, that is, recommends at least one service product for each customer.

Step 500: Collect product sales data corresponding to the pushed service product information, and then modify the customer data in the customer information table based on the product sales data. This process is to test and optimize the customer situation data used according to the sales results of service products. For example, if the sales effect is mainly based on the matching conditions of fixed assets and physical conditions, the follow-up service product information push process will focus on asset conditions and health conditions. Relevant matching; for example, if the sales effect based on the matching condition of marital status is not good, the related matching of marital status will be weakened or deleted in the process of subsequent service product information push. In some embodiments of the present application, customer portraits can also be created individually for customers whose purchases of service products reach a set number, and the created portrait data can be used to find a matching degree with the current customer from the customer information table or the first feature vector table. Target customers who reach a set standard (such as 97%), so as to specifically push the service products that the current customers have purchased for the target customers.

The present application can achieve accurate matching between service products and customers based on the calculation of the degree of fit, and provide customers with service products that they actually need. It can be seen that the present application also has the advantages of better customer experience and the like. The application can also continuously optimize the first feature vector table used to describe customers and the second feature vector table used to describe service products according to the push results, customer situation changes, product situation changes, etc., so the longer the application time is. , the service product information push effect of this application tends to be better.

Some embodiments of the present application can also provide a device for pushing service product information. The device for pushing service product information includes, but is not limited to, an information table building module, a data conversion module, a vector matching module, and a product push module.

The data conversion module is configured to perform at least one data conversion on the customer information table to generate a first feature vector table for describing customer information. The data conversion module in some embodiments of the present application can be specifically configured to set a standard relative value according to the distribution of customer data contained in the customer information table, and can be used to normalize the customer data in the customer information table based on the standard relative value, so as to Realize the data conversion of the customer information table. The data conversion module in some embodiments of the present application is used for combining multiple pieces of related customer data in the customer information table before normalization processing, and for using the combined processing result as newly generated customer data.

The vector matching module is used for correspondingly matching the first feature vector table with the second feature vector table used to describe the service product information, so as to obtain the matching result between the customer and the service product. The vector matching module in some embodiments of the present application is specifically configured to read the first feature vectors included in the first feature vector table and can be used to compare each first feature vector with all the second feature vectors included in the second feature vector table respectively The degree of fit calculation is performed one by one; a first feature vector involved is used to describe the information of a customer.

The apparatus for pushing service product information according to some embodiments of the present application may include a second feature vector table building module. The second feature vector table building module is used to read the product description file that records the service product information in advance, and to extract a plurality of pieces of service product data related to the target audience customers of the current service product from the product description file, and use is used to construct a second feature vector table using the service product data.

The product push module is used to push the information of at least one service product to the matched customers based on the matching result.

In still some embodiments of the present application, the apparatus for pushing service product information may include a customer information table optimization module. The customer information table optimization module can be used to collect product sales data corresponding to the pushed service product information and to modify customer data in the customer information table based on the product sales data.

As shown in FIGS. 3 and 4 , the present application can also provide a computer device 10. The computer device 10 includes a memory and a processor. Computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the processor, the processor Execute the steps of the method for pushing service product information in any embodiment of the present application. The method for pushing service product information may include, but is not limited to, one or more of the following steps: Step 100 , building a customer information table using the acquired customer data. Step 200: Perform at least one data conversion on the customer information table to generate a first feature vector table for describing customer information. The steps of performing at least one data conversion on the customer information table in some embodiments of the present application include but are not limited to the following

steps

201 and 202 . Step 201: Set a standard relative value according to the distribution of customer data contained in the customer information table. Step 202 , normalize the customer data in the customer information table based on the standard relative value, so as to realize the data conversion of the customer information table. In addition, in some embodiments of the present application, multiple pieces of associated customer data in the customer information table are merged before the normalization process, and then the merged processing result is used as newly generated customer data. The present application also includes a process of constructing a second feature vector table, specifically, before performing corresponding matching between the first feature vector table and the second feature vector table used to describe service product information, the following steps 110 to 112 are further included. Step 110: Read the product description file that records the service product information. Step 111 , extracting a plurality of pieces of service product data related to the target audience customers of the current service product from the product description file. Step 112, using the service product data to construct a second feature vector table. Step 300: Match the first feature vector table with the second feature vector table used to describe the service product information, so as to obtain a matching result between the customer and the service product. In some embodiments of the present application, the steps of correspondingly matching the first feature vector table with the second feature vector table used to describe service product information include, but are not limited to, steps 301 to 303 . Step 301: Read the first feature vector included in the first feature vector table; wherein one first feature vector is used to describe the information of a customer. Step 302: Calculate the degree of fit of each of the first eigenvectors and all the second eigenvectors included in the second eigenvector table one by one. In step 303, the obtained degree of fit is used as the matching result between the customer and the service product. Step 400 , based on the matching result, push the information of at least one service product to the matched customer, and specifically push the service product information to the client terminal 20 . Step 500: Collect product sales data corresponding to the pushed service product information, and then modify the customer data in the customer information table based on the product sales data.

The present application may further provide a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors can execute the service product information in any embodiment of the present application. The steps of the push method. The method for pushing service product information may include, but is not limited to, one or more of the following steps: Step 100 , building a customer information table using the acquired customer data. Step 200: Perform at least one data conversion on the customer information table to generate a first feature vector table for describing customer information. The steps of performing at least one data conversion on the customer information table in some embodiments of the present application include but are not limited to the following

steps

201 and 202 . Step 201: Set a standard relative value according to the distribution of customer data contained in the customer information table. Step 202 , normalize the customer data in the customer information table based on the standard relative value, so as to realize the data conversion of the customer information table. In addition, in some embodiments of the present application, multiple pieces of associated customer data in the customer information table are merged before the normalization process, and then the merged processing result is used as newly generated customer data. The present application also includes a process of constructing a second feature vector table, specifically, before performing corresponding matching between the first feature vector table and the second feature vector table used to describe service product information, the following steps 110 to 112 are further included. Step 110: Read the product description file that records the service product information. Step 111 , extracting a plurality of pieces of service product data related to the target audience customers of the current service product from the product description file. Step 112, using the service product data to construct a second feature vector table. Step 300: Match the first feature vector table with the second feature vector table used to describe the service product information, so as to obtain a matching result between the customer and the service product. In some embodiments of the present application, the steps of correspondingly matching the first feature vector table with the second feature vector table used to describe service product information include, but are not limited to, steps 301 to 303 . Step 301: Read the first feature vector included in the first feature vector table; wherein one first feature vector is used to describe the information of a customer. Step 302: Calculate the degree of fit of each of the first eigenvectors and all the second eigenvectors included in the second eigenvector table one by one. In step 303, the obtained degree of fit is used as the matching result between the customer and the service product. Step 400, based on the matching result, push the information of at least one service product to the matching customer. Step 500: Collect product sales data corresponding to the pushed service product information, and then modify the customer data in the customer information table based on the product sales data.

Optionally, the storage medium involved in this application may be non-volatile or volatile.

Logic and/or steps represented in flowcharts or otherwise described herein, for example, may be considered an ordered listing of executable instructions for implementing the logical functions, and may be embodied in any computer-readable storage medium , for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, device or equipment. For the purposes of this specification, a "computer-readable storage medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or apparatus . The computer-readable storage medium may be non-volatile or volatile. More specific examples (non-exhaustive list) of computer readable storage media include the following: electrical connections with one or more wiring (electronic devices), portable computer disk cartridges (magnetic devices), random access memory (RAM, Random Access Memory), Read-Only Memory (ROM, Read-Only Memory), Erasable and Editable Read-Only Memory (EPROM, Erasable Programmable Read-Only Memory, or Flash Memory), Optical Devices, and Portable Optical Disc Read-Only Memory (CDROM, Compact Disc Read-Only Memory). In addition, the computer-readable storage medium may even be paper or other suitable medium on which the program can be printed, as the paper or other medium may be optically scanned, for example, and then edited, interpreted or, if necessary, otherwise Process in a suitable manner to obtain the program electronically and then store it in computer memory.

It should be understood that various parts of this application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or a combination of the following techniques known in the art: Discrete logic circuits, application-specific integrated circuits with suitable combinational logic gate circuits, Programmable Gate Arrays (PGA, Programmable Gate Array), Field Programmable Gate Arrays (FPGA, Field Programmable Gate Array), etc.

In the description of this specification, reference to the terms "this embodiment", "one embodiment", "some embodiments", "example", "specific example", or "some examples" or the like is meant to be combined with the description of the embodiment A particular feature, structure, material, or characteristic described or exemplified is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and combine the different embodiments or examples described in this specification, as well as the features of the different embodiments or examples, without conflicting each other.

In addition, the terms "first" and "second" are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature delimited with "first", "second" may expressly or implicitly include at least one of that feature. In the description of the present application, "plurality" means at least two, such as two, three, etc., unless expressly and specifically defined otherwise.

The present application may be used in numerous general purpose or special purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, including A distributed computing environment for any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including storage devices.

It should be emphasized that, in order to further ensure the privacy and security of the data in the embodiments of the present application, data such as customer data, product information, the first feature vector table and the second feature vector table in one or more embodiments of the present application are also It can be stored in the nodes of a blockchain.

The blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

The above descriptions are only the preferred embodiments of the present application, and are not intended to limit the present application. Any modifications, equivalent replacements and simple improvements made in the substantial content of the present application shall be included in the protection scope of the present application. Inside.

Claims

A method for pushing service product information, comprising:

Use the acquired customer data to build a customer information table;

performing at least one data conversion on the customer information table to generate a first feature vector table for describing customer information;

Correspondingly matching the first feature vector table with the second feature vector table used to describe the service product information to obtain a matching result between the customer and the service product;

Based on the matching result, at least one service product information is pushed to the matched customers.
The method for pushing service product information according to claim 1, wherein the step of correspondingly matching the first feature vector table with the second feature vector table used to describe the service product information comprises:

Read the first feature vector contained in the first feature vector table; wherein, a first feature vector is used to describe the information of a customer;

Calculate the degree of fit of each first eigenvector with all the second eigenvectors contained in the second eigenvector table one by one;

The obtained fit is used as the matching result of customers and service products.
The method for pushing service product information according to claim 2, wherein the calculating the degree of fit of each of the first eigenvectors and all the second eigenvectors included in the second eigenvector table one by one comprises:

I cp =∑(f i 2 -q j 2 ) 2

f i =[d 1 ,d 2 ,...d k ]

q j =[e 1 ,e 2 ,...e k ]

i=1,2,3...m

j=1,2,3...n

Among them, I cp represents the degree of fit between the first eigenvector and the second eigenvector, f i represents the i-th first eigenvector, q j represents the j-th second eigenvector, and d k represents the k-th customer data, e k represents the kth product data, k represents the number of elements in the feature vector, m represents the number of customers, and n represents the number of service products.
The method for pushing service product information according to claim 1, wherein the step of performing at least one data conversion on the customer information table comprises:

Set standard relative values according to the distribution of customer data contained in the customer information table;

The customer data in the customer information table is normalized based on the standard relative value, so as to realize the data conversion of the customer information table.
The method for pushing service product information according to claim 4, wherein the step of performing at least one data conversion on the customer information table further comprises:

Combine multiple pieces of related customer data in the customer information table before normalization;

The combined processing result is used as newly generated customer data.
The method for pushing service product information according to claim 1, wherein before performing the corresponding matching between the first feature vector table and the second feature vector table used to describe the service product information, the method further comprises:

Read the product description document that records the service product information;

Extracting a plurality of pieces of service product data related to the target audience customers of the current service product from the product description file;

A second feature vector table is constructed using the service product data.
The method for pushing service product information according to claim 1, further comprising:

Collect product sales data corresponding to the pushed service product information;

The customer data in the customer information table is modified based on the product sales data.
A push device for service product information, comprising:

The information table building module is used to construct the customer information table using the acquired customer data;

a data conversion module for performing at least one data conversion on the customer information table to generate a first feature vector table for describing customer information;

a vector matching module, configured to perform corresponding matching between the first feature vector table and the second feature vector table used to describe the service product information, so as to obtain a matching result between the customer and the service product;

A product push module, configured to push at least one service product information to a matched customer based on the matching result.
A computer device includes a memory and a processor, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, causes the processor to perform the following method:

Use the acquired customer data to build a customer information table;

performing at least one data conversion on the customer information table to generate a first feature vector table for describing customer information;

Correspondingly matching the first feature vector table with the second feature vector table used to describe the service product information to obtain a matching result between the customer and the service product;

Based on the matching result, at least one service product information is pushed to the matched customer.
The computer device according to claim 9, wherein performing the corresponding matching between the first feature vector table and the second feature vector table for describing service product information comprises:

Read the first feature vector contained in the first feature vector table; wherein, a first feature vector is used to describe the information of a customer;

Calculate the degree of fit of each first eigenvector and all the second eigenvectors contained in the second eigenvector table one by one;

The obtained fit is used as the matching result of customers and service products.
The computer device according to claim 10, wherein performing the calculation of the degree of fit of each of the first eigenvectors and all the second eigenvectors included in the second eigenvector table one by one comprises:

I cp =∑(f i 2 -q j 2 ) 2

f i =[d 1 ,d 2 ,...d k ]

q j =[e 1 ,e 2 ,...e k ]

i=1,2,3...m

j=1,2,3...n

Among them, I cp represents the degree of fit between the first eigenvector and the second eigenvector, f i represents the i-th first eigenvector, q j represents the j-th second eigenvector, and d k represents the k-th customer data, e k represents the kth product data, k represents the number of elements in the feature vector, m represents the number of customers, and n represents the number of service products.
The computer device of claim 9, wherein performing the at least one data conversion on the customer information table comprises:

Set standard relative values according to the distribution of customer data contained in the customer information table;

The customer data in the customer information table is normalized based on the standard relative value, so as to realize the data conversion of the customer information table.
The computer device according to claim 9, wherein, before the corresponding matching between the first feature vector table and the second feature vector table for describing service product information, the processor further executes:

Read the product description document that records the service product information;

Extracting a plurality of pieces of service product data related to the target audience customers of the current service product from the product description file;

A second feature vector table is constructed using the service product data.
The computer device of claim 9, wherein the processor further executes:

Collect product sales data corresponding to the pushed service product information;

The customer data in the customer information table is modified based on the product sales data.
A storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the following methods:

Use the acquired customer data to build a customer information table;

performing at least one data conversion on the customer information table to generate a first feature vector table for describing customer information;

Correspondingly matching the first feature vector table with the second feature vector table used to describe the service product information to obtain a matching result between the customer and the service product;

Based on the matching result, at least one service product information is pushed to the matched customers.
The storage medium according to claim 15, wherein performing the corresponding matching between the first feature vector table and the second feature vector table for describing service product information comprises:

Read the first feature vector contained in the first feature vector table; wherein, a first feature vector is used to describe the information of a customer;

Calculate the degree of fit of each first eigenvector and all the second eigenvectors contained in the second eigenvector table one by one;

The obtained fit is used as the matching result of customers and service products.
The storage medium according to claim 16, wherein performing the calculation of the degree of fit of each of the first eigenvectors and all the second eigenvectors included in the second eigenvector table one by one comprises:

I cp =∑(f i 2 -q j 2 ) 2

f i =[d 1 ,d 2 ,...d k ]

q j =[e 1 ,e 2 ,...e k ]

i=1,2,3...m

j=1,2,3...n

Among them, I cp represents the degree of fit between the first eigenvector and the second eigenvector, f i represents the i-th first eigenvector, q j represents the j-th second eigenvector, and d k represents the k-th customer data, e k represents the kth product data, k represents the number of elements in the feature vector, m represents the number of customers, and n represents the number of service products.
The storage medium of claim 15, wherein performing the at least one data conversion on the customer information table comprises:

Set standard relative values according to the distribution of customer data contained in the customer information table;

The customer data in the customer information table is normalized based on the standard relative value, so as to realize the data conversion of the customer information table.
The storage medium according to claim 15, wherein, before the corresponding matching between the first feature vector table and the second feature vector table for describing service product information, the processor further executes:

Read the product description document that records the service product information;

Extracting a plurality of pieces of service product data related to the target audience customers of the current service product from the product description file;

A second feature vector table is constructed using the service product data.
The storage medium of claim 15, wherein the processor further executes:

Collect product sales data corresponding to the pushed service product information;

The customer data in the customer information table is modified based on the product sales data.