WO2022267171A1

WO2022267171A1 - Matching method and apparatus for product data adjustment, computer device, and storage medium

Info

Publication number: WO2022267171A1
Application number: PCT/CN2021/109045
Authority: WO
Inventors: 徐从洋; 杨忱宇; 刘大航; 肖甜
Original assignee: 未鲲(上海)科技服务有限公司
Priority date: 2021-06-23
Filing date: 2021-07-28
Publication date: 2022-12-29
Also published as: CN113436022B; CN113436022A

Abstract

A matching method and apparatus for product data adjustment, a computer device, and a storage medium. The method comprises: obtaining investment feature information of a user, and determining the investment type of the user on the basis of the investment feature information and pre-collected user big data (S10); matching the expected return of the user according to the investment type, the expected return comprising several types of different investment products and target proportions of the respective types of investment products (S20); obtaining product data of user's current holdings, and calculating user proportions corresponding to the respective investment products currently held by the user (S30); comparing the user proportions corresponding to the respective types of investment products currently held by the user with the several types of different investment products and target proportions of the respective types of investment products comprised in the expected return to obtain a comparison result (S40); and calling a deep neural network to match a product data adjustment plan for user holdings according to the comparison result (S50). The present method can improve the accuracy of fund product data matching.

Description

Matching method, device, computer equipment and storage medium for product data adjustment

This application claims the priority of the Chinese patent application submitted to the China Patent Office on June 23, 2021, with the application number 202110700032.2, and the title of the invention is "Matching method, device, computer equipment and storage medium for product data adjustment", the entire content of which Incorporated in this application by reference.

technical field

This application relates to the field of transaction data processing of financial technology.

Background technique

With the recognition of fund management by domestic public residents, the number of investors and the amount of investment are increasing. When most investors buy fund products, they know little about the time of purchase, purchase amount, and the risks of purchasing products. Purchasing is based on platform recommendations, and the inventors found that most of the current platform recommendations are popular financial products, such as the top 10 products in terms of income or the top 10 products in the number of investors, and the platform only recommends products for purchase, without specific Purchase time or quantity, the current recommendation method does not match the user's investment type with high accuracy, and cannot adapt to the needs of different users.

technical problem

The investment recommendation of current financial products has a low degree of matching with users.

technical solution

The first aspect of this application proposes a matching method for product data adjustment, including:

Obtain the investment feature information of the user, and determine the user's investment type based on the investment feature information and the pre-collected user big data;

Match the user's expected return according to the investment type, and the expected return includes several different types of investment products and the target ratio of each type of investment product;

Obtain the product data of the user's current position, and calculate the user ratio corresponding to the various investment products currently held by the user according to the product data of the current position;

Comparing the user proportions corresponding to various investment products currently held by the user with the several types of investment products included in the expected return and the target proportions of various investment products to obtain a comparison result;

The deep neural network is invoked to adjust the plan according to the product data of the user's position according to the comparison result.

The second aspect of the present application provides a matching device for product data adjustment, including:

The investment type module obtains the investment feature information of the user, and determines the user's investment type based on the investment feature information and pre-collected user big data;

The expected income module matches the user's expected income according to the investment type, and the expected income includes several types of different investment products and the target ratio of each type of investment product;

The current position module is used to obtain the product data of the user's current position, and calculate the user proportion corresponding to the various investment products currently held by the user according to the product data of the current position;

The income comparison module is used to compare the proportion of users corresponding to various investment products currently held by the user with several different types of investment products included in the expected income and the target proportions of various investment products to obtain the comparison result;

The position adjustment module is used to call the deep neural network to match the product data adjustment plan of the user's position according to the comparison result.

The third aspect of the present application provides a computer device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the product data adjustment matching method is implemented, including: obtaining The user's investment characteristic information, based on the investment characteristic information and the pre-collected user big data, determines the user's investment type; matches the user's expected income according to the investment type, and the expected income includes several types of different investment products and various The target proportion of investment products; obtain the product data of the user's current position, and calculate the user proportion corresponding to the various investment products currently held by the user according to the product data of the current position; The proportion of users in the project is compared with several different types of investment products included in the expected returns and the target proportions of various investment products to obtain the comparison results; the deep neural network is called to adjust the plan according to the comparison results to match the product data of the user's positions.

According to the fourth aspect of the present application, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the matching method for adjusting the product data is implemented, including: acquiring user investment feature information , determine the user's investment type based on the investment feature information and pre-collected user big data; match the user's expected return according to the investment type, and the expected return includes several types of different investment products and the target ratio of each type of investment product ; Obtain the product data of the user's current position, and calculate the user ratio corresponding to the various investment products currently held by the user according to the product data of the current position; compare the user ratio corresponding to the various investment products currently held by the user with the Compare several different types of investment products included in the expected returns and the target ratios of various investment products to obtain the comparison results; call the deep neural network to adjust the plan according to the comparison results to match the product data of the user's holdings.

Beneficial effect

This application provides a method for flexibly and accurately matching and adjusting investment product data. By obtaining the user's investment feature information, the investment feature information includes the user's economic strength data, age data, investment years data, and different investment product data. According to the questionnaire survey data, the user’s investment type is determined based on the investment characteristic information combined with the user’s big data pre-collected by the platform. Users of different investment types have different risks and expected returns, and match the user’s expectations according to the investment type. Income, the expected income includes several different types of investment products and target ratios of various investment products, that is, each type of expected income needs to be configured with investment products with different target ratios. In order to judge whether the product data currently held by the user meets its Investment type, obtain the product data of the user's current position, calculate the user ratio of various investment products currently held by the user according to the product data of the current position, and then compare each type of investment product currently held by the user and the corresponding user ratio with the expected Compare the target proportion of the investment product under the income, get the comparison result, and then call the deep neural network to match the product data that the user needs to adjust according to the comparison result, thereby generating the user's position adjustment plan, including reducing the proportion of the corresponding investment product Or increase the proportion of the corresponding investment products, so as to keep the product data of the user's position to meet the expected return, improve the accuracy of product data matching, and improve the efficiency of product data adjustment of the user's position.

Description of drawings

Fig. 1 is a schematic flow chart of an embodiment of a matching method for product data adjustment of the present application;

FIG. 2 is a schematic flow chart of another embodiment of the matching method for product data adjustment of the present application;

Fig. 3 is a schematic structural diagram of an embodiment of a matching device for product data adjustment of the present application;

Fig. 4 is a schematic block diagram of an embodiment of the computer equipment of the present application.

Embodiments of the present invention

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

Referring to FIG. 1 , an embodiment of the present application provides a matching method for product data adjustment, including steps S10-S50. The detailed description of each step of the product data adjustment matching method is as follows.

S10. Obtain the investment characteristic information of the user, and determine the investment type of the user based on the investment characteristic information and pre-collected user big data.

In this embodiment, the suggestions and matching scenarios applied to financial product investment data include fund investment. Different users have different expectations for fund investment. The platform defines user investment through user questionnaires, user risk levels, and objective strength. Types, users of different investment types have different risks that they can bear, and the risks and benefits are corresponding. In this embodiment, the user's investment type is determined based on the investment feature information combined with the user's investment type big data collected by the platform by acquiring the user's investment feature information. The investment feature information includes the user's economic strength data, age data, Investment years data, and questionnaire survey data on different investment issues, at least one of the above-mentioned data is obtained through different means, so as to obtain the user’s investment characteristic information, and then based on the investment characteristic information combined with the user’s investment type big data collected by the platform To determine the user's investment type, the platform has collected a large amount of user investment characteristic information matching the user's investment type data, and the investment type of different users can be determined according to the user investment type data. In one embodiment, defining the investment types of users includes five investment types, including conservative C1 users, stable C2 users, balanced C3 users, growing C4 users, and aggressive C5 users.

S20. Match the user's expected return according to the investment type, where the expected return includes several types of investment products and target ratios of each type of investment product.

In this embodiment, after the user's investment type is determined, the platform has pre-stated the big data of different user investment types, and the big data includes the reasonable income of users of different investment types. Since risks and benefits coexist, this The embodiment defines the period of reasonable income as the expected income of the investment type. In an application scenario, according to the data collected by the platform, the expected income of the conservative C1 user is defined as 2%-4%; the expected income of the robust C2 is 3%-8%; the expected return of balanced C3 users is 5%-12%; the expected return of growing C4 users is 8%-15%; the expected return of aggressive C5 users is 12%. Then, according to the user's investment type determined above, the corresponding expected return can be matched, wherein the expected return includes several types of different investment products and the target ratio of each type of investment product, and the different objects invested by each fund are defined as investment Products, for example, Fund A invests in stocks, currencies and bonds. Among them, stocks, currencies and bonds are all investment products, and different investment products have corresponding reference returns. The reference return of stock investment products is a1, and currency class investment products The reference income of investment products is a2, and the reference income of bond investment products is a3. By combining different investment products according to a certain ratio, the income of the combined investment products can be obtained. The expected income includes several types of different investments Products and target ratios of various investment products, that is, each type of expected return needs to be configured with investment products with different target ratios. For example, the expected income of a stable C2 user is 3%-8%. Under this expected income, the target proportion of stock investment products needs to be allocated is X1, the target proportion of currency investment products is X2, and the target proportion of bond investment products is X3.

S30. Obtain product data currently held by the user, and calculate user ratios corresponding to various investment products currently held by the user according to the product data currently held by the user.

In this embodiment, in order to judge whether the product data currently held by the user conforms to its investment type, the product data currently held by the user is obtained, and the user ratio of various investment products currently held by the user is calculated according to the product data currently held by the user, wherein , the product data is fund data. Specifically, the fund data currently held by the user is obtained, and the investment products that are heavily held by each fund are obtained. For example, fund A invests in stock G1, and the investment amount accounts for X1% of the total amount of the fund. Fund A also invests in stock G2, and the investment amount accounts for X2% of the total amount of the fund, and also invests in bonds Z1, and the investment amount accounts for X1% of the total amount of the fund X3%, by obtaining the fund data of the user's current holdings, it is possible to calculate the user proportion corresponding to the various investment products currently held by the user, that is, the user proportion of the stock investment product that calculates the fund data of the user's current holdings is Y1, currency The proportion of users of investment products like bonds is Y2, and the proportion of users of bond investment products is Y3.

S40. Comparing the user ratios corresponding to the various investment products currently held by the user with the several types of investment products included in the expected return and the target ratios of each investment product to obtain a comparison result.

S50. Invoke the deep neural network to match the product data adjustment plan of the user's position according to the comparison result.

In this embodiment, after obtaining the proportions of various investment products in the product data currently held by the user, the user proportions corresponding to the various investment products currently held by the user are compared with several types of different investments included in the expected return. Compare the target ratios of products and various investment products. Specifically, compare the user ratio of each type of user’s current holdings of investment products with the target ratio of this type of investment product under the expected return to obtain the comparison result of this type of investment product , the comparison result includes that the proportion of users is not within the range of the target proportion, or the proportion of users is within the range of the target proportion. Then call the deep neural network to match the product data adjustment plan of the user's position according to the comparison result. The deep neural network calculates the deviation value of the product data held by the user according to the comparison result, and then searches the product data according to the deviation value. The deep neural network Tags are added to each product data, and products that can reduce the deviation value are searched according to the tags, so as to match the target product data, and a product data adjustment plan is generated. The position adjustment plan includes, when a certain type of investment product When the user ratio is not within the target ratio range of this type of investment product, if the user ratio is higher than the maximum value of the target ratio range, the matching user’s position adjustment plan is to lower the ratio of the corresponding investment product, if the user ratio is lower than the target ratio The minimum value of the ratio interval matches the user's position adjustment plan to increase the proportion of the corresponding investment product, so as to keep the product data of the user's position to meet the expected return and improve the accuracy of product data matching.

This embodiment provides a method for flexibly and accurately matching and adjusting investment product data. By acquiring the user's investment feature information, the investment feature information includes the user's economic strength data, age data, investment period data, and different investment data. The questionnaire survey data of the product, based on the investment characteristic information combined with the user big data pre-collected by the platform, determines the user's investment type. Users of different investment types have different risks and expected returns that they can bear, and match the user's investment according to the investment type. Expected income, the expected income includes several different types of investment products and target ratios of various investment products, that is, each type of expected income needs to be configured with investment products with different target ratios. In order to judge whether the product data currently held by the user meets the Its investment type, obtain the product data of the user's current position, calculate the user ratio of various investment products currently held by the user according to the product data of the current position, and then compare each type of investment product currently held by the user and the corresponding user ratio with The target ratio of the investment product under the expected return is compared to obtain the comparison result, and then the deep neural network is called to match the product data that the user needs to adjust according to the comparison result, thereby generating the user's position adjustment plan, including reducing the corresponding investment product. Ratio or increase the ratio of the corresponding investment products, so as to keep the product data of the user's position to meet the expected return, improve the accuracy of product data matching, and improve the efficiency of product data adjustment of the user's position.

In one embodiment, the acquisition of product data currently held by the user includes:

Obtain all product data of the user;

All the product data are screened, and the product data lower than the preset ratio are eliminated to obtain the product data currently held by the user.

In this embodiment, in the process of obtaining the fund data currently held by the user, all product data of the user is firstly obtained, and all product data are screened. Some product data in all product data may be obtained by the user for special purposes. It is inconvenient to adjust; or some product data in all product data may be purchased by users to complete platform tasks, and the purchased share is too small. In this embodiment, it will be lower than the preset ratio. Product data is eliminated to obtain the product data of the user's current position. By filtering all product data, the amount of product data calculation is reduced and the matching efficiency of product position adjustment is improved.

In one embodiment, the expected return includes several different types of investment products and the target ratio of each type of investment product is determined in the following manner:

Choose from a number of different investment products;

Obtain the reference income of various investment products within a preset time period;

Establish weight coefficients of various investment products;

Weighted average of various investment projects according to the weight coefficient and the reference income to obtain the preset income;

Inputting the expected income and the preset income into the quantitative model, modifying the weight coefficients of various investment products through the quantitative model until the preset income meets the expected income, and obtaining the target weight coefficients of various investment products;

The target weight coefficient is used as the target ratio of the investment product.

In this embodiment, the expected return includes several types of different investment products and the target ratio of each type of investment product is determined in the following manner. First, several types of different investment products are selected, such as stocks, bonds and monetary funds; Then obtain the reference income of various investment projects within the preset time period. Since the reference income of different investment products is different in different time periods, the corresponding time period is generally obtained according to the characteristics of different investment products. For example, the Shanghai and Shenzhen within one month The 300 index yield is used as the reference income of stock investment products, the CSI All-Bond Index yield within six months is used as the reference income of bond investment products, and the interbank deposit rate is used as the reference income of currency investment products; Establish the weight coefficients of various investment products, and then carry out weighted average of various investment projects according to the weight coefficients and the reference income to obtain the preset income; then input the expected income and the preset income into the quantitative model, The model modifies the weight coefficients of various investment products by continuously modifying the weight coefficients of various investment products until the preset income meets the expected income. When the preset income meets the expected income, various investment products The weight coefficient is the target weight coefficient, and then the target weight coefficient is used as the target ratio of the investment product to determine the expected return. The expected return includes several different types of investment products and the target ratio of each type of investment product.

In one application scenario, r _i represent the reference return of the Shanghai and Shenzhen 300 Index, the reference return of the Shanghai Stock Exchange Treasury Bond Index, and the reference return of interbank deposits, where the weight coefficient of the Shanghai and Shenzhen 300 Index is w ₁ , and the weight of the Shanghai Stock Exchange Treasury Bond Index The coefficient is w ₂ , the weight coefficient w ₃ of interbank deposits, and the default return is E(r). Substituting the expected returns of different investment types into E(r), the following formula can be used to calculate the The weight range of similar investment products, so as to obtain the investment ratio of various investment products corresponding to the expected return of the actual market, and improve the accuracy of fund data matching.

In one embodiment, the calling of the deep neural network to match the product data adjustment plan of the user's position according to the comparison result further includes:

Obtain the knowledge map of the current investment market, and predict the development trend of the investment market based on the knowledge map;

The deep neural network is called to match the product data plan of the user's position according to the development trend and the comparison result.

In this embodiment, when the product data adjustment plan of the user's position is matched according to the user's comparison result, the knowledge map of the current investment market is also obtained, and the development trend of the investment market is predicted based on the knowledge map. The development trend of the investment market, the development trend of the investment market includes the down market, the shock market and the up market, and then match the user's fund product position adjustment plan according to the development trend and the comparison result. Specifically, for different investments Under the development trend of different investment markets, different types of users are matched with different product data plans, so as to adjust the position of product data according to the development trend of the investment market, and ensure the user's rate of return under the development trend of different investment markets. In one application scenario, the risk of the user's investment type is relatively high, such as aggressive C5, and the proportion of stock investment products in the product data of the user's current holdings is relatively large. If the development trend of the investment market is a downward market, the matching The product data adjustment plan is to recommend reducing the holdings of stock investment products, that is, it is recommended to give priority to reducing the holdings of stock funds, and it is recommended to buy bond funds to reduce the proportion of holdings of stock funds and maintain the development trend of the investment market. User investment income.

In one embodiment, as shown in FIG. 2, the product data adjustment plan includes a product purchase plan and a product redemption plan; after calling the deep neural network to match the product data adjustment plan of the user's position according to the comparison result, Also includes:

S51: Obtain the target purchase product and purchase share of the product purchase plan;

S52: Obtain the target redemption products and redemption shares of the product redemption plan;

S53: Generate product data adjustment plan operation information according to the target purchase product and purchase share, the target redemption product and redemption share;

S54: Output the product data adjustment plan operation information.

In this embodiment, the product data adjustment plan includes a product purchase plan and a product redemption plan. For the adjustment of the product data currently held by the user, in the scenario of not increasing investment, it is necessary to adjust certain products currently held by the user ( Such as fund) redemption, and re-purchase new products, and the product purchase plan includes the target purchase product and the purchase share, that is, which product gold needs to be purchased, and how many shares are purchased, At the same time, the product redemption plan includes the target redemption products and redemption shares, and then obtain the target purchase products and purchase shares of the product purchase plan, obtain the target redemption products and redemption shares of the product redemption plan share, and then generate product data adjustment plan operation information according to the target purchase product and purchase share, the target redemption product and redemption share, and generate corresponding Operation information, through which the customer can intuitively understand the adjustment operation of product data, thereby improving the transparency and efficiency of product data position adjustment.

In one embodiment, after outputting the product data adjustment plan operation information, it further includes:

Receive feedback from users on the operation information of the product data adjustment plan;

If the feedback information is positive feedback information, adjust the planned operation information according to the product data to carry out product purchase and product redemption;

If the feedback information is negative feedback information, output prompt information that the product data currently held by the user does not match the investment type of the user.

In this embodiment, after outputting the product data adjustment plan operation information, the user’s feedback information on the product data adjustment plan operation information is received, that is, after the product data adjustment plan is notified to the user, it is necessary to confirm whether the user executes the product data adjustment plan. Adjust the plan, if so, the information fed back by the user is positive feedback information, if the feedback information is positive feedback information, adjust the plan operation information according to the product data to carry out product purchase and product redemption, preferably, first carry out product redemption After returning to the product purchase, it can be known that the product to be redeemed is the above-mentioned target redemption product and redemption share, and what is purchased is the target purchase product and purchase share, thereby completing the adjustment of product data. And if the user does not execute the product data adjustment plan, the feedback information is negative feedback information. At this time, a prompt message that the product data of the user's current position does not match the user's investment type is output to remind the user of its current position The product data of the product cannot meet the expected return of its user's investment type, thereby improving the transparency of product data position adjustment.

In one embodiment, after outputting the prompt message that the product data currently held by the user does not match the investment type of the user, it further includes:

Judging whether the difference between the user ratio of various investment products currently held by the user and the target ratio of the corresponding investment product included in the expected return exceeds the preset value;

If yes, output the prompt information of re-testing the investment type, so as to update the user's investment type.

In this embodiment, in order to provide users with a more accurate product data matching scheme, after outputting the prompt information that the product data currently held by the user does not match the type of investment of the user, the user ratio of various types of investment products currently held by the user is judged Whether the difference with the target ratio of the corresponding investment product included in the expected return exceeds the preset value, if so, it can be determined that the user does not execute the fund position adjustment plan, and the difference between the user ratio and the target ratio exceeds the preset value Value, it may be that the user's current investment type has changed. At this time, output the prompt message of retesting the investment type to update the user's investment type. In this way, the user's investment type is continuously updated to provide users with more accurate product data. Matching to meet the investment needs of users and improve the accuracy of product position adjustment.

Referring to Figure 3, the present application also provides a matching device for product data adjustment, including:

The investment type module 10 is used to obtain the investment feature information of the user, and determine the user's investment type based on the investment feature information and pre-collected user big data;

The expected return module 20 is used to match the user's expected return according to the investment type, and the expected return includes several types of different investment products and target ratios of various types of investment products;

The current position module 30 is used to obtain the product data of the user's current position, and calculate the user proportion corresponding to the various investment products currently held by the user according to the product data of the current position;

The income comparison module 40 is used to compare the user proportion corresponding to various investment products currently held by the user with the several types of investment products included in the expected income and the target proportions of various investment products to obtain the comparison result ;

The position adjustment module 50 is configured to call the deep neural network to match the product data adjustment plan of the user's position according to the comparison result.

As mentioned above, it can be understood that each component of the product data adjusted matching device proposed in this application can realize the function of any one of the above product data adjusted matching methods.

In one embodiment, the current position module 30 also includes executing:

Obtain all product data of the user;

In one embodiment, the expected return module 20 also includes:

Choose from a number of different investment products;

Establish weight coefficients of various investment products;

In one embodiment, the position adjustment module 50 also includes executing:

Obtain the target purchase products and purchase shares of the product purchase plan;

Obtain the target redemption products and redemption shares of the product redemption plan;

Generate product data adjustment plan operation information according to the target purchase product and purchase share, the target redemption product and redemption share;

Output the product data adjustment plan operation information.

In one embodiment, the position adjustment module 50 also includes executing:

Referring to FIG. 4 , an embodiment of the present application also provides a computer device, which may be a mobile terminal, and its internal structure may be as shown in FIG. 4 . The computer equipment includes a processor, a memory, a network interface, and a display device and an input device connected through a system bus. Wherein, the network interface of the computer device is used to communicate with external terminals through a network connection. The input device of the computer equipment is used for receiving user's input. The computer is designed with a processor to provide computing and control capabilities. The memory of the computer device includes storage media. The storage medium stores an operating system, computer programs and databases. The database of the computer equipment is used to store data, and the storage medium may be non-volatile or volatile. When the computer program is executed by the processor, a matching method for product data adjustment is realized.

The above-mentioned processor executes the above-mentioned matching method for product data adjustment, including: obtaining the investment characteristic information of the user, determining the user's investment type based on the investment characteristic information and pre-collected user big data; matching the user's expectation according to the investment type Income, the expected income includes several different types of investment products and the target ratio of various investment products; obtain the product data of the user's current position, and calculate the corresponding value of the various investment products currently held by the user according to the product data of the current position User ratio; compare the user ratio corresponding to various investment products currently held by the user with several different types of investment products included in the expected return and the target ratio of each type of investment product to obtain the comparison result; call Deepin Neural Network The network adjusts the plan according to the product data of the user's position according to the comparison result.

The computer equipment provides a flexible and accurate method for matching and adjusting investment product data, by obtaining the investment feature information of the user, the investment feature information includes the user's economic strength data, age data, investment years data, and different The questionnaire survey data of investment products, based on the investment characteristic information combined with the user big data pre-collected by the platform, determines the user's investment type. Users of different investment types have different risks and expected returns that they can bear, and match users according to the investment type. The expected return includes several different types of investment products and the target ratios of various investment products, that is, each type of expected return needs to be configured with investment products with different target ratios. In order to determine whether the product data currently held by the user is According to its investment type, obtain the product data of the user's current position, calculate the user proportion of various investment products currently held by the user according to the product data of the current position, and then calculate each type of investment product currently held by the user and the corresponding user proportion Compared with the target ratio of the investment product under the expected return, the comparison result is obtained, and then the deep neural network is called to match the product data that the user needs to adjust according to the comparison result, thereby generating the user's position adjustment plan, including lowering the corresponding investment product ratio or increase the ratio of the corresponding investment product, so as to keep the product data of the user's position to meet the expected return, improve the accuracy of product data matching, and improve the efficiency of product data adjustment of the user's position.

An embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium may be non-volatile or volatile, and a computer program is stored thereon, and the computer program is processed by the A matching method for product data adjustment is implemented when the controller is executed, comprising the steps of: acquiring user investment characteristic information, determining the user's investment type based on the investment characteristic information and pre-collected user big data; matching the user's investment type according to the investment type Expected income, the expected income includes several different types of investment products and the target ratio of various investment products; obtain the product data of the user's current position, and calculate the corresponding value of the various investment products currently held by the user according to the product data of the current position The proportion of users; compare the proportion of users corresponding to various investment products currently held by the user with the target proportions of several types of investment products included in the expected return and obtain the comparison result; call depth The neural network adjusts the plan according to the product data of the user's position according to the comparison result.

The computer-readable storage medium provides a method for flexibly and accurately matching and adjusting investment product data, by obtaining the user's investment feature information, the investment feature information includes the user's economic strength data, age data, investment period data, As well as the questionnaire survey data on different investment products, based on the investment characteristic information combined with the user big data pre-collected by the platform, the user's investment type is determined. Users of different investment types have different risks and expected returns that they can bear. According to the investment The type matches the expected return of the user. The expected return includes several different types of investment products and the target ratios of various investment products, that is, each type of expected return needs to be configured with investment products with different target ratios. In order to judge the user's current holdings Whether the product data conforms to its investment type, obtain the product data of the user's current position, calculate the user proportion of each type of investment product currently held by the user according to the product data of the current position, and then compare each type of investment product currently held by the user and the corresponding Compare the user ratio of the user with the target ratio of the investment product under the expected return, get the comparison result, and then call the deep neural network to match the product data that the user needs to adjust according to the comparison result, thereby generating the user's position adjustment plan, including lowering the corresponding The proportion of the investment product or increase the proportion of the corresponding investment product, so as to maintain the product data of the user's position to meet the expected return, improve the accuracy of product data matching, and improve the efficiency of product data adjustment of the user's position.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods.

Any reference to memory, storage, database or other media provided herein and used in the examples may include non-volatile and/or volatile memory.

Nonvolatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, apparatus, article or method comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, apparatus, article, or method. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional same elements in the process, apparatus, article or method comprising the element.

The above descriptions are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application.

Any equivalent structure or equivalent process transformation made by using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the scope of patent protection of this application.

Claims

A matching method for product data adjustment, including:

Obtain the investment feature information of the user, and determine the user's investment type based on the investment feature information and the pre-collected user big data;

Match the user's expected return according to the investment type, and the expected return includes several different types of investment products and the target ratio of each type of investment product;

Obtain the product data of the user's current position, and calculate the user ratio corresponding to the various investment products currently held by the user according to the product data of the current position;

Comparing the user proportions corresponding to various investment products currently held by the user with the several types of investment products included in the expected return and the target proportions of various investment products to obtain a comparison result;

The deep neural network is invoked to adjust the plan according to the product data of the user's position according to the comparison result.
The matching method for product data adjustment according to claim 1, wherein said acquiring the product data currently held by the user comprises:

Obtain all product data of the user;

All the product data are screened, and the product data lower than the preset ratio are eliminated to obtain the product data currently held by the user.
The matching method for product data adjustment according to claim 1, wherein the expected return includes several types of different investment products and the target ratio of each type of investment product is determined in the following manner:

Choose from a number of different investment products;

Obtain the reference income of various investment products within a preset time period;

Establish weight coefficients of various investment products;

Weighted average of various investment projects according to the weight coefficient and the reference income to obtain the preset income;

Inputting the expected income and the preset income into the quantitative model, modifying the weight coefficients of various investment products through the quantitative model until the preset income meets the expected income, and obtaining the target weight coefficients of various investment products;

The target weight coefficient is used as the target ratio of the investment product.
The matching method for product data adjustment according to claim 1, wherein said invoking the deep neural network to match the product data adjustment plan of the user's position according to the comparison result further includes:

Obtain the knowledge map of the current investment market, and predict the development trend of the investment market based on the knowledge map;

The deep neural network is called to match the product data plan of the user's position according to the development trend and the comparison result.
The matching method for product data adjustment according to claim 1, wherein the product data adjustment plan includes a product purchase plan and a product redemption plan; and the invoking deep neural network matches the product data held by the user according to the comparison result After adjusting the plan, it also includes:

Obtain the target purchase products and purchase shares of the product purchase plan;

Obtain the target redemption products and redemption shares of the product redemption plan;

Generate product data adjustment plan operation information according to the target purchase product and purchase share, the target redemption product and redemption share;

Output the product data adjustment plan operation information.
The matching method of product data adjustment according to claim 5, wherein, after said outputting said product data adjustment plan operation information, it also includes:

Receive feedback from users on the operation information of the product data adjustment plan;

If the feedback information is positive feedback information, adjust the planned operation information according to the product data to carry out product purchase and product redemption;

If the feedback information is negative feedback information, output prompt information that the product data currently held by the user does not match the investment type of the user.
The matching method for product data adjustment according to claim 6, wherein after outputting the prompt information that the product data currently held by the user does not match the user's investment type, it further includes:

Judging whether the difference between the user ratio of various investment products currently held by the user and the target ratio of the corresponding investment product included in the expected return exceeds the preset value;

If yes, output the prompt information of re-testing the investment type, so as to update the user's investment type.
A matching device for product data adjustment, including:

The investment type module is used to obtain the investment characteristic information of the user, and determine the investment type of the user based on the investment characteristic information and the pre-collected user big data;

The expected return module is used to match the user's expected return according to the investment type, and the expected return includes several types of different investment products and the target ratio of each type of investment product;

The current position module is used to obtain the product data of the user's current position, and calculate the user proportion corresponding to the various investment products currently held by the user according to the product data of the current position;

The income comparison module is used to compare the proportion of users corresponding to various investment products currently held by the user with several different types of investment products included in the expected income and the target proportions of various investment products to obtain the comparison result;

The position adjustment module is used to call the deep neural network to match the product data adjustment plan of the user's position according to the comparison result.
A computer device, comprising a memory and a processor, the memory stores a computer program, wherein, when the processor executes the computer program, the product data adjustment matching method is realized, including:

Obtain the investment feature information of the user, and determine the user's investment type based on the investment feature information and the pre-collected user big data;

Match the user's expected return according to the investment type, and the expected return includes several different types of investment products and the target ratio of each type of investment product;

Obtain the product data of the user's current position, and calculate the user ratio corresponding to the various investment products currently held by the user according to the product data of the current position;

Comparing the user proportions corresponding to various investment products currently held by the user with the several types of investment products included in the expected return and the target proportions of various investment products to obtain a comparison result;

The deep neural network is invoked to adjust the plan according to the product data of the user's position according to the comparison result.
The computer device according to claim 9, wherein said acquiring the product data currently held by the user comprises:

Obtain all product data of the user;

All the product data are screened, and the product data lower than the preset ratio are eliminated to obtain the product data currently held by the user.
The computer device according to claim 9, wherein the expected return includes several types of different investment products and the target ratio of each type of investment product is determined by the following method:

Choose from a number of different investment products;

Obtain the reference income of various investment products within a preset time period;

Establish weight coefficients of various investment products;

Weighted average of various investment projects according to the weight coefficient and the reference income to obtain the preset income;

Inputting the expected income and the preset income into the quantitative model, modifying the weight coefficients of various investment products through the quantitative model until the preset income meets the expected income, and obtaining the target weight coefficients of various investment products;

The target weight coefficient is used as the target ratio of the investment product.
The computer device according to claim 9, wherein said invoking the deep neural network matches the product data adjustment plan of the user's position according to the comparison result, further comprising:

Obtain the knowledge map of the current investment market, and predict the development trend of the investment market based on the knowledge map;

The deep neural network is called to match the product data plan of the user's position according to the development trend and the comparison result.
The computer device according to claim 9, wherein the product data adjustment plan includes a product purchase plan and a product redemption plan; after calling the deep neural network to match the product data adjustment plan of the user's position according to the comparison result, Also includes:

Obtain the target purchase products and purchase shares of the product purchase plan;

Obtain the target redemption products and redemption shares of the product redemption plan;

Generate product data adjustment plan operation information according to the target purchase product and purchase share, the target redemption product and redemption share;

Output the product data adjustment plan operation information.
The computer device according to claim 13, wherein, after outputting the product data adjustment plan operation information, further comprising:

Receive feedback from users on the operation information of the product data adjustment plan;

If the feedback information is positive feedback information, adjust the planned operation information according to the product data to carry out product purchase and product redemption;

If the feedback information is negative feedback information, output prompt information that the product data currently held by the user does not match the investment type of the user.
A computer-readable storage medium, on which a computer program is stored, wherein, when the computer program is executed by a processor, the product data adjustment matching method is realized, including:

Obtain the investment feature information of the user, and determine the user's investment type based on the investment feature information and the pre-collected user big data;

Match the user's expected return according to the investment type, and the expected return includes several different types of investment products and the target ratio of each type of investment product;

Obtain the product data of the user's current position, and calculate the user ratio corresponding to the various investment products currently held by the user according to the product data of the current position;

Comparing the user proportions corresponding to various investment products currently held by the user with the several types of investment products included in the expected return and the target proportions of various investment products to obtain a comparison result;

The deep neural network is invoked to adjust the plan according to the product data of the user's position according to the comparison result.
The computer-readable storage medium according to claim 15, wherein said obtaining the product data currently held by the user comprises:

Obtain all product data of the user;

All the product data are screened, and the product data lower than the preset ratio value are eliminated to obtain the product data currently held by the user.
The computer-readable storage medium according to claim 15, wherein the expected return includes several types of different investment products and the target ratio of each type of investment product is determined by:

Choose from a number of different investment products;

Obtain the reference income of various investment products within a preset time period;

Establish weight coefficients of various investment products;

Weighted average of various investment projects according to the weight coefficient and the reference income to obtain the preset income;

Inputting the expected income and the preset income into the quantitative model, modifying the weight coefficients of various investment products through the quantitative model until the preset income meets the expected income, and obtaining the target weight coefficients of various investment products;

The target weight coefficient is used as the target ratio of the investment product.
The computer-readable storage medium according to claim 15, wherein the calling the deep neural network to match the product data adjustment plan of the user's position according to the comparison result, further comprising:

Obtain the knowledge map of the current investment market, and predict the development trend of the investment market based on the knowledge map;

The deep neural network is called to match the product data plan of the user's position according to the development trend and the comparison result.
The computer-readable storage medium according to claim 15, wherein the product data adjustment plan includes a product purchase plan and a product redemption plan; and the invoking deep neural network matches the product data adjustment of the user's position according to the comparison result After planning, also include:

Obtain the target purchase products and purchase shares of the product purchase plan;

Obtain the target redemption products and redemption shares of the product redemption plan;

Generate product data adjustment plan operation information according to the target purchase product and purchase share, the target redemption product and redemption share;

Output the product data adjustment plan operation information.
The computer-readable storage medium according to claim 19, wherein, after outputting the product data adjustment plan operation information, further comprising:

Receive feedback from users on the operation information of the product data adjustment plan;

If the feedback information is positive feedback information, adjust the planned operation information according to the product data to carry out product purchase and product redemption;

If the feedback information is negative feedback information, output prompt information that the product data currently held by the user does not match the investment type of the user.