CN116912004A

CN116912004A - Recommendation information generation method, device, equipment, medium, program product and platform

Info

Publication number: CN116912004A
Application number: CN202310799034.0A
Authority: CN
Inventors: 黄涛; 周怡媛; 陶佳杰; 孟一鸣; 张豫黔
Original assignee: National Pension Insurance Co ltd
Current assignee: National Pension Insurance Co ltd
Priority date: 2023-06-30
Filing date: 2023-06-30
Publication date: 2023-10-20

Abstract

The disclosure provides a recommendation information generation method, device, equipment, medium, program product and platform, which relate to the technical field of artificial intelligence, in particular to the technical fields of big data, information finance and the like, and the specific scheme is as follows: calculating gap information of a target account, and selecting a product combination for making up the gap information based on the gap information; calculating a risk contribution ratio of the products in the product combination based on account information of the target account, wherein the risk contribution ratio is used for representing the contribution ratio of the corresponding products in the total risk of the product combination; calculating the proportion of the products in the product combination based on the risk contribution proportion, wherein the proportion of the products with higher risk contribution proportion in the product combination is lower; generating product recommendation information using the target processor, the product recommendation information including: the proportion of the product in the product combination. The recommendation effect of the product combination can be improved.

Description

Recommendation information generation method, device, equipment, medium, program product and platform

Technical Field

The disclosure relates to the technical field of artificial intelligence, in particular to the technical fields of big data, information finance and the like, and particularly relates to a recommended information generation method, device, equipment, medium, program product and platform.

Background

At present, a network platform provides a lot of products, and users can select the products by themselves or based on the recommended products of the platform. Product recommendation is often performed based on target planning at present.

Disclosure of Invention

The disclosure provides a recommendation information generation method, device, equipment, medium, program product and platform.

According to an aspect of the present disclosure, there is provided a recommendation information generation method including:

calculating gap information of a target account, and selecting a product combination for compensating the gap information based on the gap information, wherein the product combination comprises at least two products;

calculating a risk contribution ratio of the products in the product combination based on account information of the target account, wherein the risk contribution ratio is used for representing the contribution ratio of the corresponding products in the total risk of the product combination;

calculating the proportion of the products in the product combination based on the risk contribution proportion, wherein the higher the risk contribution proportion is, the lower the proportion of the products in the product combination is;

Generating product recommendation information using a target processor, the product recommendation information comprising: the proportion of the product in the product combination.

According to another aspect of the present disclosure, there is provided a recommendation information generating apparatus including:

the first calculation module is used for calculating the gap information of the target account and selecting a product combination for making up the gap information based on the gap information, wherein the product combination comprises at least two products;

a second calculation module, configured to calculate a risk contribution ratio of products in the product combination based on account information of the target account, where the risk contribution ratio is used to represent a ratio of contribution of corresponding products in a total risk of the product combination;

a third calculation module, configured to calculate a proportion of products in the product combination based on the risk contribution proportion, where the proportion of products with a higher risk contribution proportion in the product combination is lower;

the generation module is used for generating product recommendation information by using the target processor, and the product recommendation information comprises: the proportion of the product in the product combination.

According to another aspect of the present disclosure, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the recommendation information generation method provided by the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the recommendation information generation method provided by the present disclosure.

According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the recommendation information generating method provided by the present disclosure.

According to another aspect of the present disclosure, a platform is provided, including an electronic device provided by the present disclosure.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a flow chart of a recommendation information generation method provided by the present disclosure;

FIG. 2 is a schematic illustration of one product scale provided by the present disclosure;

FIG. 3 is a schematic illustration of one price simulation provided by the present disclosure;

FIG. 4 is a schematic illustration of a gap determination to be made up provided by the present disclosure;

FIG. 5 is a schematic illustration of one notch calculation provided by the present disclosure;

fig. 6a to 6e are block diagrams of a recommendation information generating device provided by the present disclosure;

fig. 7 is a block diagram of an electronic device used to implement an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Referring to fig. 1, fig. 1 is a flowchart of a recommendation information generation method provided in the present disclosure, as shown in fig. 1, including the following steps:

Step S101, calculating gap information of a target account, and selecting a product combination for making up the gap information based on the gap information, wherein the product combination comprises at least two products.

The target account is an account registered or existing in the network platform, for example: the user may register a corresponding account, such as a personal care account, an insurance account, etc.

The gap information may be a gap account value indicating that the target account is in a future time period, and in the present disclosure, the account value may refer to a fund, or a virtual account value.

For pension scenarios, the gap information may be a pension gap, i.e., a pension gap, of the user after retirement.

The product can be financial product or insurance product.

The selecting the product combination for making up the gap information based on the gap information may be selecting at least two products, where the return and/or profit of the at least two products in the future time period can make up the gap information, for example selecting at least two financial products or insurance products, where the at least two financial products or insurance products can make up the pension funds gap of the user after the user retires.

Step S102, calculating the risk contribution proportion of the products in the product combination based on the account information of the target account, wherein the risk contribution proportion is used for representing the proportion of contribution of the corresponding products in the total risk of the product combination.

The account information of the target account may include personal information such as gender, age, or may include risk information that the target account can withstand, or account level information of the target account, etc. In addition, the account information of the target account may be account information associated with the target account on one or more platforms, for example: the target account corresponds to a unique user identity, the account information comprises account information of one or more accounts related to the user identity, and the accounts can be accounts in the same platform or different platforms, so that more information can be obtained through the account information, and the accuracy of risk contribution proportion is improved.

The calculating the risk contribution ratio of the products in the product combination based on the account information of the target account may be calculating the risk contribution ratio of the products in the product combination by using a mapping relationship between the account information and the risk contribution ratio obtained in advance. Specifically, the risk contribution proportion of all or all of the products in the product combination is calculated, for example, the risk contribution proportion of each of the products in the product combination is calculated.

The total risk of the product combination represents the sum of the risks of all the products in the product combination, such as the sum of the fluctuation rates of all the products.

And step 103, calculating the proportion of the products in the product combination based on the risk contribution proportion, wherein the proportion of the products with higher risk contribution proportion in the product combination is lower.

The calculating the proportion of the product in the product combination based on the risk contribution proportion may be to set the proportion of the product in the product combination to be a low proportion for the product with a high risk contribution proportion, and set the proportion of the product in the product combination to be a high proportion for the product with a low risk contribution proportion, so as to reduce the risk of the product combination. Specifically, the proportion of all or part of the products in the product combination is calculated, for example, the proportion of each product in the product combination is calculated

Step S104, generating product recommendation information by using a target processor, wherein the product recommendation information comprises the following steps: the proportion of the product in the product combination.

The product recommendation information is product information recommended to the target account or a user corresponding to the target account. Specifically, the proportion of all or part of the products in the product combination is included, such as the proportion of each product in the product combination.

In the method, the target processor is used for generating the product recommendation information, so that the generated product recommendation information comprises the proportion of the products in the product combination, and the recommendation information comprising the products outside the product combination does not need to be generated, so that the calculation amount of the target processor is reduced, and the generation of the product recommendation information in the electronic equipment with limited resources is facilitated.

In the disclosure, the method is applied to an electronic device, that is, the method includes all steps executed by the electronic device, and the electronic device may be an electronic device such as a server, a computer, a mobile phone, a tablet computer, and the like. The target processor is any one of the processors in the electronic device.

In some embodiments, the step S101 may be to calculate the gap information of the target account by using the target processor, and select the product combination for compensating the gap information based on the gap information, so that only the product in the product combination needs to be selected, but no other product needs to be selected, so that the calculation amount of the target processor may be reduced, thereby being beneficial to generating the product recommendation information in the electronic device with limited resources.

In some embodiments, step S102 may be a step of calculating, using a target processor, a risk contribution ratio of the products in the product combination based on account information of the target account.

In some embodiments, the step S103 may be calculating, using a target processor, a proportion of the products in the product combination to the product combination based on the risk contribution proportion.

In some embodiments, the present disclosure may generate product recommendation information based on a lifetime financial security (Lifelong Financial Security, LFS) concept, such as predicting a pension based on the LFS concept, generating product recommendation information based on the pension.

In the method, the risk contribution proportion of the products in the product combination is calculated based on the account information of the target account, and the proportion of the products in the product combination is calculated based on the risk contribution proportion, so that the proportion of the products with higher risk contribution proportion in the product combination is lower, the risk of the product combination in the finally generated product recommendation information can be reduced, the recommendation effect of the product combination is improved, and the recommendation effect of the product combination is improved, so that the generation of the product recommendation information for a user for many times can be avoided, and further the resource consumption of the electronic equipment is reduced.

In one embodiment, the product combination includes n products, n is an integer greater than 1, and the calculating the proportion of the products in the product combination based on the risk contribution proportion includes:

calculating the proportion of the products in the product combination through an optimization model, wherein the optimization model comprises the following parameters:

the risk contribution ratio of n products, the total volatility of the product combination.

In some embodiments, the optimization model described above is used to solve: the proportion of the products in the product combination when the sum of squares value reaches a target value, wherein the target value comprises a minimum value or a value lower than a preset threshold value;

the sum of squares value is equal to the sum of the squares addition of the first values of the n products;

the first value of the target product is equal to: subtracting a third value of the target product from a second value of the target product, wherein the second value is a product of a proportion of the target product in the product combination and a partial derivative, and the third value is equal to a product of a risk contribution proportion of the target product and the total fluctuation rate, and the partial derivative is equal to a quotient obtained by dividing a partial derivative of the total fluctuation rate by a partial derivative of the proportion of the target product in the product combination;

The target product is any one of the n products.

In some embodiments, the optimization model described above may be expressed as follows:

wherein, the aboveRepresenting the function of the variables w and b, and solving the value of w when the minimum value is solved, wherein b represents the risk contribution proportion, represents the proportion of the product in the product combination, and b _i Represents the risk contribution ratio, w, of the ith product _i Representing the proportion of the ith product in the product combination, R (w) representing the total volatility of the product combination.

The total fluctuation rate of the product combination may also be referred to as a total risk value of the product combination, and the total fluctuation rate of the product combination may be calculated through a risk flat model, or may be calculated based on the fluctuation rate of the products in the product combination, which is not limited thereto.

In the embodiment, the accuracy of the proportion of the product in the product combination can be improved through the optimization model.

In addition, since the optimization model is used to solve: the proportion of the products in the product combination when the sum of squares value reaches the target value can enable the proportion of the products in the product combination to be finally determined, so that the risk of the product combination can be reduced, for example, the risk of the product combination can be minimized.

When the product combinations comprise products with the same risk level, the risk contribution ratio of the products with the same risk level is equal by default.

For example: as shown in fig. 2, the risk levels of the product a, the product B, the product C, the product D and the product E are respectively 20%, 15%, 30%, the product a, the product B, the product C, the product D and the product E, and the fluctuation rates σ of the product a, the product B, the product C, the product D and the product E are respectively 0.015, 0.026, 0.025 and 0.16, wherein the risk levels of the product a, the product B, the product C, the product D and the product E are respectively R3, and the ratio of the product a, the product B, the product C, the product D and the product E is respectively 0.015, 0.026, 0.025 and 0.16, so that the above optimization model is obtained: 0.319,. 01595, 0.1656, 0.0366.

In the present disclosure, the optimization model is not limited to the model described in the above embodiment for solving the proportion of the product in the product combination when the sum of squares reaches the target value, for example: in some embodiments, the optimization model may also be a pre-trained neural network model.

In one embodiment, the calculating the risk contribution ratio of the products in the product combination based on the account information of the target account includes:

calculating the affordable risk level of the target account based on the account information of the target account, and determining the risk contribution ratio of the products in the product combination based on the affordable risk level of the target account and the risk level of the products in the product combination.

The calculating the sustainable risk level of the target account based on the account information of the target account may be calculating the sustainable risk level of the target account based on a preset mapping relationship.

The determining the risk contribution ratio of the products in the product combination based on the sustainable risk level of the target account and the risk level of the products in the product combination may be calculating the risk contribution ratio of each product based on a mapping relationship of the sustainable risk level of the target account, the risk level of the products and the risk contribution ratio.

For example: as shown in table 1:

table 1:

wherein C5, C4, C3, C2 and C1 represent the level of risk that can be tolerated, and 20 to 60 represent the age to which the target account corresponds.

In this embodiment, since the risk contribution ratio of the products in the product combination is determined based on the bearable risk level of the target account and the risk level of the products in the product combination, the risk contribution ratio can be matched with the target account, so that the finally recommended product combination is more suitable for the user corresponding to the target account.

In one embodiment, the method further comprises:

determining an available product set of the target account based on account information of the target account;

the selecting a product combination for making up the gap information based on the gap information includes:

and selecting a product combination for compensating the gap information in the available product set based on the gap information.

The account information of the target account may include personal information such as gender, age, or may include a risk level that the target account can withstand, or account level information of the target account, etc.

The above-described determining the available product set for the target account may determine the available product set according to one of the following rules:

products having a risk level higher than the bearable risk level of the target account must not be recommended;

Products above the low risk level (without low risk level) are not recommended actively for the age of 60 years.

The selecting of the product combination for making up the gap information in the available product set based on the gap information may be selecting a product combination capable of making up the gap information in a future time period in the available product set. For example: at least two products are selected from the set of available products that are capable of compensating for a user's pension gap after the user retires.

In this embodiment, the final recommended product may be more matched with the target account by determining the available product set for the target account based on the account information of the target account.

In one embodiment, the determining the available product set of the target account based on the account information of the target account includes:

determining a candidate product set of the target account based on account information of the target account, wherein the candidate product set comprises a plurality of products;

simulating N account value accumulation conditions of the products in the candidate product set in a first time period, wherein the account value accumulation conditions are used for representing the change condition of the account values in the first time period, and N is an integer greater than 1;

And determining the available product set of the target account in the candidate product set based on N account value accumulation conditions of products in the candidate product set in a first time period.

The determining the candidate product set of the target account based on the account information of the target account may determine the candidate product set according to the following rule:

The first time period may be a time from a current time to the target account or a return or benefit received by the corresponding user from the product combination, or a time from a current time to a retirement of the user.

The simulating the N account value accumulation conditions of the products in the candidate product set in the first time period may be based on the N account value accumulation conditions of the products in the candidate product set in the target time period by a monte carlo simulation method. For example: assuming that the current value of the available product is 1 yuan, the price is subject to geometric brownian motion, N asset accumulation cases of the product from the first time period are generated, for example, N asset accumulation cases of the product from the first time period are generated according to the yield and the fluctuation rate of the product. For some products, if the target date type product expires halfway, the product is converted into a flowable product for growth after expiration. For some products, the minimum guaranteed rate may be determined when modeling the price sequence, such as 3% revenue for a robust account and 0% revenue for a aggressive account.

In this embodiment, since the available product set of the target account is determined in the candidate product set based on the accumulation condition of the N account values of the products in the candidate product set in the first period, the product with higher profit can be supported, so as to improve the profit of the recommended product combination.

In one embodiment, the determining the available product set of the target account in the candidate product set based on N account value accumulation conditions of the products in the product combination over a first period of time includes:

selecting a target account value accumulation condition of the N account value accumulation conditions based on a preset quantile aiming at the products in the candidate product set, generating an account value sequence of the products in a second time period based on the target account value accumulation condition, and converting the account value sequence into the value of the products at the starting point of the second time period, wherein the starting point of the second time period is the end point of the first time period;

selecting at least two products from the candidate product set, and obtaining an available product set of the target account, wherein the at least two products comprise: the value at the beginning of the second time period is higher than other products in the candidate product set, which are products of the candidate product set other than the at least two products.

The second time period may be a time when the user receives a return or benefit from the product combination, or a time when the user retires.

The preset quantile may be 1% quantile, so that the most robust account value accumulation condition can be selected from the N account value accumulation conditions, so as to improve reliability of recommended product combination. For example: the distribution of the final price of 1 element is shown in fig. 3, and 1% quantile is about 4 elements denoted by 301, wherein the frequency number in fig. 3 represents the number occupied in the sample set.

The selecting the target account value accumulation condition based on the N account value accumulation conditions of the preset quantiles may be selecting the target account value accumulation condition in which the starting product value is located at the value of the preset quantile in the second period, for example, selecting the target account value accumulation condition in which the starting product value is located at the value of 1% of the quantile in the second period.

The generating the account value sequence of the product in the second time period based on the target account value accumulation condition may be generating the account value sequence of the product in the second time period based on the account value of the target account value accumulation condition at the start point of the second time period and the tariff table of the product, where the account value sequence may be an asset sequence, that is, an asset that can be acquired every time in the second time period.

The converting the sequence of account values to the value of the product at the start of the second time period may be based on an expected return of the product. For example: the total value of the sequence of account values is 200 tens of thousands, and there is a benefit to this 200 tens of thousands, so that the value converted to the start of the product at said second time period may be 180 or 150 tens of thousands.

The selecting of at least two products from the candidate product set may be selecting at least two products having the highest value at the start of the second time period, such as selecting the highest 3 products, from the candidate products.

In this embodiment, since the at least two products include: the value at the beginning of the second time period is higher than the other products in the candidate product set, so that the selected available product set can be realized as the product with higher benefit, such as selecting the 3 products with highest benefit.

It should be noted that, in the present disclosure, the N account value accumulation cases of the products in the candidate product set in the first period are not limited, and in the embodiment of determining the available product set of the target account in the candidate product set, for example: in addition to the above-described determination of the available product set based on the value of the start point of the second period, the total profit in the second period may be calculated based on N kinds of account value accumulation conditions, and the plurality of products having the highest profit may be selected as the available product set. Or simulating the profit situation of each product directly based on Monte Carlo, and selecting a plurality of products with highest profits as an available product set.

In one embodiment, the calculating the breach information of the target account includes:

calculating a gap sequence of the target account based on account information of the target account, wherein the gap sequence comprises gap information of a plurality of time points in a third time period;

converting the gap sequence into account values at the start of a third time period;

setting an account target of the target account in the third time period based on the account value of the starting point of the third time period, wherein the account target is used for representing the account value acquired by the target account in the third time period;

and calculating gap information to be compensated of the target account based on the account target and product information of the product held by the target account.

The third period may be the same as the second period in time when the user receives the return or benefit of the product combination or when the user retires.

The calculating the gap sequence of the target account based on the account information of the target account may be calculating the gap sequence of the target account based on the income sequence and the expense sequence of the target account, for example, calculating the pension gap in the pension period, each month or each year. For example: as shown in fig. 4, the gap sequence is calculated based on the income sequence and the expense sequence.

The above-mentioned converting the gap sequence into the account value at the start of the third time period may be converting the total account value of the gap sequence into the account value at the start of the third time period, for example: the total account value of the gap sequence is 250 ten thousand, and due to a certain benefit of the asset, only 200 ten thousand is needed to reach the starting point of the 250 ten thousand in the third time period, for example, only 200 ten thousand is needed at the pension taking point, so that 250 ten thousand can be taken during pension taking, for example: the picking period refers to the picking time of the client pension, and can be set to be 60-80 years old, and the picking period starts at 60 years old. Therefore, the gap discount value at the beginning of the picking period refers to the discount value at the age of 60 years, that is, 200 ten thousand gaps can be satisfied at the age of 60 years. For example: as shown in fig. 4, the notch sequence is translated to a retirement origin notch translation value.

The setting of the account target of the target account in the third period based on the account value of the start point of the third period may be setting the account target of the target account in the third period according to the account value of the start point of the third period, for example: according to the current living standard of the user, the living standard can be heightened or lowered by the pension target, for example, 10 ten thousand of the living standard is needed in one year, if the account value of the starting point of the third time period is lower, the living standard can be heightened, and if the account value of the starting point of the third time period is higher, the account target can be lowered, namely, the living standard can be lowered. For example: as shown in fig. 4, the retirement origin endowment target is set based on the retirement origin gap discount value and the endowment target proportion.

The product information of the products already held by the target account may be product information of the products already purchased by the target account, such as return information or profit information of the products.

The calculating the gap information to be compensated for the target account based on the account target and the product information of the product held by the target account may be determining a part of gaps corresponding to the account target that can be compensated based on the product information of the product held by the target account, and the remaining gaps are the gap information to be compensated. For example: as shown in fig. 4, an uncompensated part 401 is finally calculated.

In this embodiment, the gap information to be compensated of the target account can be calculated based on the account target and the product information of the product held by the target account, so that the accuracy of the gap information to be compensated can be improved.

In some embodiments, the gap information to be filled may be a gap of the date, i.e. the amount to be filled in each period. For example: as shown in fig. 5, the total gap 501 minus the disposable gap 502 is equal to the expiration gap 503, where the disposable gap 502 is completed by a disposable amount 504 and the expiration gap 503 is completed by an expiration amount 505.

It should be noted that, the present disclosure is not limited to calculating the notch information of the target account in the above manner, for example: for some users without the product, the notch information can be set directly based on the operation of the user.

In one embodiment, the product recommendation information further includes at least one of:

payment information of the product combination and income information of the product combination

The payment information of the product combination is obtained through calculation in the following mode:

and simulating the income of the preset proportion of the products in the product combination, and calculating payment information of the product combination based on the income of the preset proportion of the products in the product combination and the gap information.

The payment information of the product combination may be payment information of the product combination, i.e. payment information of a fixed period, such as payment information of each month, or payment information of the product combination may be disposable payment information.

The benefit information of the product combination may be an account value that can be retrieved during a retrieval period (e.g., the second period and the third period), such as an amount that can be retrieved after retirement.

The benefit of simulating the preset proportions of the products in the product combination may be a benefit of simulating the preset proportions of the products in the product combination in terms of geometric brownian motion.

The benefit of the predetermined ratio may be 1% benefit, such as modeling the lowest 1% benefit in terms of geometric brownian motion. This results in a higher reliability of the product combination due to the lower yields.

The calculating the payment information of the product combination based on the profit of the product in the product combination in the preset proportion and the gap information may be making up the payment information of the gap information when the profit of the product in the product combination is the profit of the product in the preset proportion.

The payment information of the gap information can be the minimum amount of money for a period of time or the minimum one-time payment.

In this embodiment, the payment information of the product combination is calculated based on the profit of the product in the product combination in the preset proportion and the gap information, so that the accuracy of the payment information of the product combination can be improved on the premise of meeting the reliability of the product combination.

In some embodiments, the product recommendation information may further include:

the whole period exchange information, the disposable exchange information, the full life cycle (accumulation period, pension period) fund curve, the gap compensation curve and the account allocation information;

the whole period exchange information can be the whole period exchange amount, the disposable period exchange information can be the disposable amount, and the whole life cycle can be the accumulation period and the pension period.

The account allocation information may be allocation information of a plurality of accounts, such as a funds allocation between a personal account and an insurance account, or a funds allocation between a locked account and a persistent account in a commercial account, in case that the target account includes the plurality of accounts.

In addition, the product recommendation information may further include: tax information, for example: taking one year as an example, the amount of tax paid throughout the year = revenue aggregate-special deduction (five risk-one fee) -deduction fee (5000 x 12) -special additional deduction.

In addition, the product recommendation information may further include: risk level information.

In one embodiment, the method further comprises:

sending the product recommendation information to a terminal corresponding to the target account;

receiving a confirmation request of the terminal responding to the product recommendation information, and generating a product order corresponding to the product recommendation information based on the confirmation request;

and sending a payment request of the product order to the terminal.

The terminal is a terminal device for logging in the target account.

And the terminal receives the product recommendation information and displays the product recommendation information to a user, so that the user can determine whether to purchase the product combination or not based on the product recommendation information, and if so, the terminal returns a confirmation request and completes subsequent payment.

According to the embodiment, the product order can be generated based on the product recommendation information, and the payment operation is performed, so that the situation that a user blindly selects products on a platform to cause frequent interaction between the user and the terminal and the platform is avoided, and the workload of the platform and the terminal is reduced.

In some embodiments, the above method further comprises:

and responding to the payment completion message of the payment request, and sending a feedback message to the terminal at preset time, wherein the feedback message is used for indicating the income of the product combination in a time period corresponding to the preset time.

The feedback message can enable the user to timely see the benefits so as to improve the user experience.

In some embodiments, the above method further comprises:

and responding to the payment completion message of the payment request, and executing an adjustment operation on the platform home page, wherein the adjustment operation comprises at least one of the following steps: adding the related information of the product combination and adding the benefit information of the product combination.

Therefore, the user viscosity of the front page of the platform can be improved through the adjustment operation.

In some embodiments, fine adjustments, such as scaling, may also be made to the product combinations described above based on received user input.

In some embodiments, the above method further comprises:

monitoring account information of the target account;

and under the condition that the account information of the target account is monitored to have change, regenerating the product recommendation information based on the changed account information.

The monitoring of the account information of the target account may be long-term monitoring, such as continuous monitoring or periodic monitoring.

In the case that the account information of the target account is monitored to have a change, the regeneration of the product recommendation information based on the changed account information may be that the product recommendation information is regenerated based on the changed revenue information, such as re-predicting gap information based on the variant revenue information, and then the product recommendation information is generated based on the re-predicted gap information, in the case that the change of the revenue information in the account information of the target account is monitored to reach a preset condition. The preset condition may be a rate of change, such as 20% increase in revenue, or 20% decrease in revenue, etc.

The generation process of regenerating the product recommendation information based on the changed account information is specifically referred to the corresponding description of the previous embodiment, and is not described herein.

In this embodiment, because the account information of the target account is monitored, and the product recommendation information is regenerated based on the changed account information, the product recommendation information of the target account can be timely adjusted, so that the recommendation effect of the generated product recommendation information is better.

In the method, the risk contribution proportion of the products in the product combination is calculated based on the account information of the target account, and the proportion of the products in the product combination is calculated based on the risk contribution proportion, so that the proportion of the products with higher risk contribution proportion in the product combination is lower, the risk of the product combination in the finally generated product recommendation information can be reduced, and the recommendation effect of the product combination is improved.

In addition, the product combination recommended by the present disclosure better meets the actual situation and psychological needs of most people. For example: taking pension as an example, many people do not want to pursue the maximum utility or optimization goal when planning pension schemes, but want to ensure that the level of life is maintained after retirement that is comparable to or slightly better than the current level of life, without reducing their quality of life or becoming a burden to society and home. The gap compensation-based method takes the gap compensation as a starting point, and the funds required for additional deposit or investment of the individual are determined by calculating the pension level required by the individual after retirement and the pension level which can be obtained, so that the purpose of guaranteeing the living standard of the individual after retirement is achieved.

In addition, the product combination recommended by the present disclosure is simpler and more understandable, and is easy to operate and spread. For example: taking pension as an example, the gap compensation-based method does not need to establish a complex model or make abstract assumptions, does not need to set too subjective and random targets and weights, and can calculate the pension gap faced by an individual after retirement and how much funds need to be invested annually or once to compensate the gap only according to some basic data and formulas. Such a method is easier to understand and accept by the average person, and is also easier to popularize and popularize in society.

In addition, the product combination recommended by the method is more flexible and has strong adaptability. For example: taking pension as an example, the gap-filling-based method is not a constant one, but can be adjusted and modified according to the actual situation and market change of the individual. For example, if an individual has increased revenue or decreased expenditure prior to retirement, the funds for the additional savings or investments may be correspondingly decreased; if the individual's living standard increases or decreases after retirement, the amount of pension taken each year or month may be increased or decreased accordingly; if more advantageous or risky investment products or portfolios are presented in the market, the own investment strategy can be adjusted accordingly. Such a method is more adaptable to personal and market changes, thereby ensuring the stability and sustainability of the personal's post-retirement standard of living.

Referring to fig. 6a, fig. 6a is a recommendation information generating device provided in the present disclosure, and as shown in fig. 6a, a recommendation information generating device 600 includes:

the first calculating module 601 is configured to calculate gap information of a target account, and select a product combination for compensating for the gap information based on the gap information, where the product combination includes at least two products;

a second calculation module 602, configured to calculate, based on account information of the target account, a risk contribution ratio of the products in the product combination, where the risk contribution ratio is used to represent a ratio of contribution of the corresponding products in a total risk of the product combination;

a third calculating module 603, configured to calculate a proportion of the products in the product combination based on the risk contribution proportion, where the proportion of the products with a higher risk contribution proportion in the product combination is lower;

a generating module 604, configured to generate product recommendation information using the target processor, where the product recommendation information includes: the proportion of the product in the product combination.

In one embodiment, the product combination includes n products, where n is an integer greater than 1, and the third computing module 603 is configured to:

In one embodiment, the optimization model is used to solve: the proportion of the products in the product combination when the sum of squares value reaches a target value, wherein the target value comprises a minimum value or a value lower than a preset threshold value;

the target product is any one of the n products.

In one embodiment, the second computing module 602 is configured to:

In one embodiment, as shown in fig. 6b, the apparatus further comprises:

a determining module 605, configured to determine an available product set of the target account based on account information of the target account;

the first calculation module 601 is configured to calculate gap information of a target account, and select a product combination for compensating the gap information in the available product set based on the gap information.

In one embodiment, as shown in fig. 6c, the first computing module 601 includes:

a first determining unit 6011 configured to determine a candidate product set of the target account based on account information of the target account, the candidate product set including a plurality of products;

the simulation unit 6012 is configured to simulate N account value accumulation conditions of the products in the candidate product set in a first period, where the account value accumulation conditions are used to represent a change condition of an account value in the first period, and N is an integer greater than 1;

A second determining unit 6013, configured to determine, in the candidate product set, an available product set of the target account based on N account value accumulation conditions of products in the candidate product set in the first period.

In one embodiment, the second determining unit 6013 is configured to:

In one embodiment, as shown in fig. 6d, the first computing module 601 includes:

A first calculation unit 6014 configured to calculate a notch sequence of the target account based on account information of the target account, the notch sequence including notch information at a plurality of time points in a third time period;

a conversion unit 6015 for converting the gap sequence into an account value at the start of the third time period;

a setting unit 6016 configured to set an account target of the target account in the third time period based on an account value of a start point of the third time period, the account target being used to represent an account value that the target account has acquired in the third time period;

and a second calculating unit 6017, configured to calculate gap information to be compensated for by the target account based on the account target and product information of the product held by the target account.

In one embodiment, as shown in fig. 6e, the apparatus further comprises:

a first sending module 606, configured to send the product recommendation information to a terminal corresponding to the target account;

the response module 607 is configured to receive a confirmation request of the terminal in response to the product recommendation information, and generate a product order corresponding to the product recommendation information based on the confirmation request;

a second sending module 608 is configured to send a payment request for the product order to the terminal.

The recommendation information generation device provided by the disclosure can realize each process realized by the recommendation information generation method provided by the disclosure, and achieve the same technical effect, and in order to avoid repetition, the description is omitted here.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, a computer program product, a platform.

Wherein, above-mentioned electronic equipment includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the recommendation information generation method provided by the present disclosure.

The readable storage medium stores computer instructions for causing the computer to execute the recommendation information generation method provided by the present disclosure.

The computer program product described above comprises a computer program which, when executed by a processor, implements the recommendation information generation method provided by the present disclosure.

The platform comprises the electronic equipment provided by the disclosure, and the platform can provide a platform service, for example: the platform performs technical service output to a third party in the form of at least one of a software operation service (Software as a Service, saaS), an application programming interface (Application Programming Interface, API), hypertext markup language generation 5 (HyperText Markup Language, H5), a software development kit (Software Development Kit, SDK), a model-as-a-service (Model as a Service, maaS), and the like.

Fig. 7 illustrates a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 7, the apparatus 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 may also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

Various components in device 700 are connected to I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, etc.; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, an optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer grid, such as the internet, and/or various telecommunications grids.

The computing unit 701 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 701 performs the respective methods and processes described above, for example, the recommendation information generation method. For example, in some embodiments, the recommendation information generation method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 700 via ROM 702 and/or communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the recommendation information generating method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the recommendation information generating method by any other suitable means (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a grid browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication grid). Examples of communication grids include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communications grid. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A recommendation information generation method, comprising:

2. The method of claim 1, wherein the product combination comprises n products, n being an integer greater than 1, the calculating a proportion of products in the product combination based on the risk contribution proportion comprising:

3. The method of claim 2, wherein the optimization model is used to solve: the proportion of the products in the product combination when the sum of squares value reaches a target value, wherein the target value comprises a minimum value or a value lower than a preset threshold value;

the target product is any one of the n products.

4. A method according to any one of claims 1 to 3, wherein the calculating a risk contribution ratio of products in the product combination based on account information of the target account comprises:

5. A method according to any one of claims 1 to 3, the method further comprising:

6. The method of claim 5, wherein the determining the set of available products for the target account based on account information for the target account comprises:

7. The method of claim 6, wherein the determining the set of available products for the target account among the set of candidate products based on N account value accumulation for products in the product combination over a first period of time comprises:

8. The method of any of claims 1-3, the computing breach information of a target account comprising:

9. A method according to any one of claims 1 to 3, the product recommendation information further comprising at least one of:

10. A method according to any one of claims 1 to 3, the method further comprising:

And sending a payment request of the product order to the terminal.

11. A recommendation information generating device comprising:

12. The apparatus of claim 11, wherein the product combination comprises n products, n being an integer greater than 1, the third computing module to:

13. The apparatus of claim 12, wherein the optimization model is to solve for: the proportion of the products in the product combination when the sum of squares value reaches a target value, wherein the target value comprises a minimum value or a value lower than a preset threshold value;

the target product is any one of the n products.

14. The apparatus of any of claims 11 to 13, wherein the second computing module is to:

15. The apparatus according to any one of claims 11 to 13, further comprising:

a determining module, configured to determine an available product set of the target account based on account information of the target account;

the first calculation module is used for calculating gap information of a target account and selecting a product combination for making up the gap information in the available product set based on the gap information.

16. The apparatus of claim 15, wherein the first computing module comprises:

a first determining unit configured to determine a candidate product set of the target account based on account information of the target account, the candidate product set including a plurality of products;

the simulation unit is used for simulating N account value accumulation conditions of the products in the candidate product set in a first time period, wherein the account value accumulation conditions are used for representing the change condition of the account value in the first time period, and N is an integer greater than 1;

And the second determining unit is used for determining the available product set of the target account in the candidate product set based on N account value accumulation conditions of products in the candidate product set in the first time period.

17. The apparatus of claim 16, wherein the second determining unit is configured to:

18. The apparatus of any of claims 11 to 13, the first computing module comprising:

A first calculation unit, configured to calculate a gap sequence of the target account based on account information of the target account, where the gap sequence includes gap information at a plurality of time points in a third time period;

a conversion unit for converting the gap sequence into account values at the start of a third time period;

a setting unit configured to set an account target of the target account in the third time period based on an account value of a start point of the third time period, the account target being used to represent an account value that the target account has acquired in the third time period;

and the second calculation unit is used for calculating the gap information to be compensated of the target account based on the account target and the product information of the product held by the target account.

19. The apparatus of any of claims 11 to 13, the product recommendation information further comprising at least one of:

20. The apparatus according to any one of claims 11 to 13, further comprising:

the first sending module is used for sending the product recommendation information to the terminal corresponding to the target account;

the response module is used for receiving a confirmation request of the terminal responding to the product recommendation information and generating a product order corresponding to the product recommendation information based on the confirmation request;

and the second sending module is used for sending a payment request of the product order to the terminal.

21. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-10.

22. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-10.

23. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-10.

24. A platform comprising the electronic device of claim 21.