CN117314649A

CN117314649A - Information processing method and device and electronic equipment

Info

Publication number: CN117314649A
Application number: CN202311282860.4A
Authority: CN
Inventors: 李小林; 郭相林; 刘微
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2023-09-28
Filing date: 2023-09-28
Publication date: 2023-12-29

Abstract

The application discloses an information processing method, an information processing device and electronic equipment. Relates to the field of artificial intelligence, financial science and technology or other related fields, and the method comprises the following steps: receiving first identification information of a target account from a first terminal, wherein the first identification information is obtained by encrypting the initial identification information of the target account by the first terminal; under a preset trusted execution environment, determining first account basic information matched with the first identification information from an account basic information set; based on the first account basic information, determining a first financial product recommendation result and a first account classification result corresponding to the target account in a trusted execution environment, wherein the first account classification result is a potential account or a non-potential account; and sending the first financial product recommendation result and the first account classification result to the first terminal. By the method and the device, the problems of low safety and low accuracy of the detection result existing in the information processing method in the related technology are solved.

Description

Information processing method and device and electronic equipment

Technical Field

The present disclosure relates to the field of artificial intelligence, financial science and technology, and more particularly, to an information processing method, apparatus, and electronic device.

Background

In recent years, with the rapid development of the internet, data mining technology has developed rapidly, resulting in the conventional financial institutions facing serious challenges and impacts. The financial institutions build information systems for many years, a large amount of information is accumulated, in order to fully embody huge value contained in the information, the financial institutions start to reasonably analyze and utilize the information, however, the existing information processing method has the defects of lower safety, higher consumption, less income and lower utilization rate, so that the existing high-quality information cannot be fully utilized.

Aiming at the problems of low safety and low accuracy of processing results of the information processing method in the related technology, no effective solution is proposed at present.

Disclosure of Invention

The main objective of the present application is to provide an information processing method, an information processing device, and an electronic device, so as to solve the problems of low security and low accuracy of detection results in the information processing method in the related art.

In order to achieve the above object, according to one aspect of the present application, there is provided an information processing method. The method comprises the following steps: receiving first identification information of a target account from a first terminal, wherein the first identification information is obtained by encrypting the initial identification information of the target account by the first terminal; under a preset trusted execution environment, determining first account basic information matched with the first identification information from an account basic information set, wherein the first account basic information at least comprises account portrait data, financial product purchasing behavior data and financial product characteristic data of the target account, and the account basic information set comprises account basic information corresponding to at least one account respectively; based on the first account basic information, determining a first financial product recommendation result and a first account classification result corresponding to the target account in the trusted execution environment, wherein the first account classification result is a potential account or a non-potential account; and sending the first financial product recommendation result and the first account classification result to the first terminal.

Optionally, the first identification information is a first hash value corresponding to the target account, where the first hash value is obtained by performing hash operation on initial identification information of the target account, and determining, in a preset trusted execution environment, first account base information matched with the first identification information from an account base information set includes: respectively carrying out hash operation processing on the account basic information included in the account basic information set to obtain a second hash data set; judging whether the first hash value exists in the second hash data set; and if the first hash value exists in the second hash data set, determining the first account basic information matched with the first hash value from the account basic information set.

Optionally, the determining, based on the first account basic information, a first financial product recommendation result and a first account classification result corresponding to the target account in the trusted execution environment includes: based on the first account basic information, adopting a financial product recommendation model in the trusted execution environment to obtain the first financial product recommendation result and the first account classification result corresponding to the target account.

Optionally, before the obtaining the first financial product recommendation result and the first account classification result corresponding to the target account by adopting a financial product recommendation model in the trusted execution environment based on the first account basic information, the method further includes: acquiring account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts, wherein the account basic information respectively corresponding to the M accounts at least comprises: account portrait data of the corresponding account, financial product purchasing behavior data and financial product feature data; and performing model training under the trusted execution environment based on account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts to obtain the financial product recommendation model.

Optionally, the performing model training in the trusted execution environment based on the account basic information, the financial product recommendation result and the account classification result respectively corresponding to the M accounts to obtain the financial product recommendation model includes: preprocessing account basic information, financial product recommendation results and account classification results corresponding to the M accounts respectively to obtain processed account basic information, financial product recommendation results and account classification results corresponding to the M accounts respectively; performing feature extraction processing on the processed account basic information, the financial product recommendation result and the account classification result which are respectively corresponding to the M accounts to obtain account basic features, financial product features and account behavior features which are respectively corresponding to the M accounts; fusing the account basic features, financial product features and account behavior features corresponding to the M accounts respectively to obtain fused target data features; based on the target data characteristics, training an initial model in the trusted execution environment to obtain the financial product recommendation model.

Optionally, training the initial model in the trusted execution environment based on the target data features to obtain the financial product recommendation model when the initial models are K and K is an integer greater than or equal to 2, including: training K initial models based on the target data characteristics respectively to obtain K first models and model accuracy rates corresponding to the K first models respectively, wherein K is an integer greater than or equal to 2; and taking the first model with the model accuracy larger than or equal to a first preset value in the K first models as the financial product recommendation model.

Optionally, when the financial product recommendation models are L, where L is an integer greater than or equal to 2, the obtaining, based on the first account basic information, the first financial product recommendation result and the first account classification result corresponding to the target account by adopting the financial product recommendation model in the trusted execution environment includes: determining weight values corresponding to the L financial product recommendation models respectively according to model accuracy rates corresponding to the L financial product recommendation models respectively; respectively inputting the first account basic information into the L financial product recommendation models to obtain L financial product recommendation results and L account classification results; based on the weight values respectively corresponding to the L financial product recommendation models and the L financial product recommendation results, obtaining the first financial product recommendation results; and obtaining the first account classification result based on the weight values respectively corresponding to the L financial product recommendation models and the L account classification results.

Optionally, after the obtaining, based on the first account basic information, the first financial product recommendation result and the first account classification result target account corresponding to the target account by adopting a financial product recommendation model, the method further includes: determining the financial amount amplification of the target account based on the financial product purchase amount of the target account in the current financial product purchase period and the financial product purchase amount of the last financial product purchase period, wherein the last financial product purchase period is the previous purchase period of the current financial product purchase period; determining the financial amount increment type of the target account according to the financial amount increment; determining a value type of the target account according to the financial asset amount of the target account; and determining a second account classification result of the target account based on the financial amount increment type, the value type and the first account classification result.

Optionally, the determining the financial amount increment type of the target account according to the financial amount increment includes: judging whether the financial amount amplification is larger than a preset amplification threshold value or not; if the increment of the financial amount is larger than the preset increment threshold, determining that the increment type of the financial amount is a high increment account; if the increment of the financial amount is smaller than or equal to the preset increment threshold, determining that the increment type of the financial amount is a low increment account; the determining the value type of the target account according to the financial asset amount of the target account comprises the following steps: judging whether the financial asset amount is larger than a preset asset threshold; if the financial asset amount is greater than the preset asset threshold, determining that the value type is a high value account; and if the financial asset amount is less than or equal to the preset asset threshold, determining the value type as a basic account.

In order to achieve the above object, according to another aspect of the present application, there is provided an information processing apparatus. The device comprises: the first receiving module is used for receiving first identification information of a target account from a first terminal, wherein the first identification information is obtained by encrypting the initial identification information of the target account by the first terminal; the first matching module is used for determining first account basic information matched with the first identification information from an account basic information set under a preset trusted execution environment, wherein the first account basic information at least comprises account portrait data, financial product purchasing behavior data and financial product characteristic data of the target account, and the account basic information set comprises account basic information corresponding to at least one account respectively; the first classification module is used for determining a first financial product recommendation result and a first account classification result corresponding to the target account under the trusted execution environment based on the first account basic information, wherein the first account classification result is a potential account or a non-potential account; and the first sending module is used for sending the first financial product recommendation result and the first account classification result to the first terminal.

In order to achieve the above object, according to another aspect of the present application, there is also provided an electronic device including one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement any one of the information processing methods described above.

Through the application, the following steps are adopted: receiving first identification information of a target account from a first terminal, wherein the first identification information is obtained by encrypting the initial identification information of the target account by the first terminal; under a preset trusted execution environment, determining first account basic information matched with the first identification information from an account basic information set, wherein the first account basic information at least comprises account portrait data, financial product purchasing behavior data and financial product characteristic data of the target account, and the account basic information set comprises account basic information corresponding to at least one account respectively; based on the first account basic information, determining a first financial product recommendation result and a first account classification result corresponding to the target account in the trusted execution environment, wherein the first account classification result is a potential account or a non-potential account; the first financial product recommendation result and the first account classification result are sent to the first terminal, the purposes of safely and accurately obtaining the first financial product recommendation result and the first account classification result by adopting a financial product recommendation model based on first account basic information are achieved, and the problems of low safety and low detection result accuracy in the information processing method in the related technology are solved. Thereby achieving the effect of improving the safety and accuracy of the information processing method.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:

FIG. 1 is a flow chart of an information processing method provided according to an embodiment of the present application;

FIG. 2 is a schematic diagram of an alternative trusted execution environment according to an embodiment of the present application;

FIG. 3 is a training flow diagram of an alternative financial product recommendation model, according to an embodiment of the present application;

fig. 4 is a schematic diagram of an information processing apparatus provided according to an embodiment of the present application;

fig. 5 is a schematic diagram of an electronic device provided according to an embodiment of the present application.

Detailed Description

It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For convenience of description, the following will describe some terms or terms related to the embodiments of the present application:

privacy intersection (Private set Intersection, PSI) algorithm: is a secure computing method for protecting data privacy that allows two parties to determine common elements between two data sets without exposing the respective private data. Because the data is encrypted, the party cannot directly obtain the private data of the other party, and only the information of the common element can be obtained by comparing the encrypted tags. Thus, the privacy of the data can be protected, and the comparison function of the data can be realized.

Trusted execution environment: is a safe area constructed by a software and hardware method on a computing platform, and the basic idea is that: in hardware, an isolated memory is allocated for sensitive data, all the computation of the sensitive data is performed in the isolated memory, and other parts of the hardware except an authorized interface cannot access information in the isolated memory, so that the privacy computation of the sensitive data is realized.

It should be noted that, related information (including, but not limited to, user equipment information, user personal information, etc.) and data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party. For example, an interface is provided between the system and the relevant user or institution, before acquiring the relevant information, the system needs to send an acquisition request to the user or institution through the interface, and acquire the relevant information after receiving the consent information fed back by the user or institution.

In the following, the present application will be described in connection with preferred implementation steps, and fig. 1 is a flowchart of an information processing method according to an embodiment of the present application, as shown in fig. 1, where the method includes the following steps:

Step S101, first identification information of a target account from a first terminal is received, wherein the first identification information is obtained by encrypting the initial identification information of the target account by the first terminal.

Optionally, fig. 2 is a schematic diagram of an alternative trusted execution environment according to an embodiment of the present application, and as shown in fig. 2, the first terminal is a computing initiator for a first financial institution, and the second terminal is a delegated computing party and an algorithm provider for a second financial institution. Before receiving first identification information of a target account from a first terminal, the first terminal initiates financial product recommendation and account classification requirements, and provides task requirement description to a second terminal; the second terminal remotely authenticates whether the trusted execution environment of the first terminal meets preset environmental conditions, namely, the second terminal has certain safety, reliability and credibility, can ensure the authenticity, the integrity and the confidentiality of the executed operation and the processed data, and encrypts and provides an algorithm program; the first terminal authenticates whether the trusted execution environment of the second terminal meets preset environment conditions or not, whether an algorithm meets the preset conditions or not, and requests of financial product recommendation and account classification are initiated after verification is passed; the first terminal carries out hash operation on the initial identification information of the target account to obtain a first hash value, and the first hash value is sent to the second terminal through a trusted channel. By the method, the second terminal cannot see the target account information of the first terminal, and safety and confidentiality of the target account information of the first terminal can be ensured.

Step S102, under a preset trusted execution environment, determining first account basic information matched with first identification information from an account basic information set, wherein the first account basic information at least comprises account portrait data, financial product purchasing behavior data and financial product characteristic data of a target account, and the account basic information set comprises account basic information respectively corresponding to at least one account.

Optionally, the account portrait data may include identity attribute, social attribute, registration information, credit attribute, product preference, consumption characteristics, customer value, and the like, and the financial product purchase behavior data may include financial product purchase frequency, purchase period, purchase amount, and the like, and the financial product feature data may include risk level, recruitment mode, financial product opening form, investment property, and the like. As further shown in fig. 2, the second terminal determines, in a preset trusted execution environment, first account basic information matched with the first identification information from the account basic information set by using a privacy intersection algorithm. The privacy intersection algorithm under the trusted execution environment enables the first terminal to be unable to see the account basic information set of the second terminal, and ensures the security of the account basic information set of the second terminal; the security of the information matching process is improved, and the account information matching process is performed on the premise of protecting the privacy of the account information.

In an optional embodiment, the first identification information is a first hash value corresponding to the target account, where the first hash value is obtained by performing hash operation on initial identification information of the target account, and determining, in a preset trusted execution environment, first account base information matched with the first identification information from the account base information set includes: respectively carrying out hash operation processing on the account basic information included in the account basic information set to obtain a second hash data set; judging whether the first hash value exists in the second hash data set; and if the first hash value exists in the second hash data set, determining first account basic information matched with the first hash value from the account basic information set.

Optionally, the second terminal performs hash operation processing on the account basic information included in the account basic information set by using a preset hash function, so as to obtain a second hash data set. Based on the same hash function, since different input data can generate different hash values and the same input data can generate the same hash value, whether the first hash value exists in the second hash data set is judged; and if the first hash value exists in the second hash data set, determining first account basic information matched with the first hash value from the account basic information set. By the method, the intersection between the account information can be determined under the condition that the original data of the two terminals are not shared, so that the privacy of the account information is protected.

Step S103, based on the first account basic information, determining a first financial product recommendation result and a first account classification result corresponding to the target account in a trusted execution environment, wherein the first account classification result is a potential account or a non-potential account.

Optionally, the first account basic information includes account portrait data, financial product purchasing behavior data and financial product feature data of the target account. Based on the first account basic information, a first financial product recommendation result and a first account classification result corresponding to the target account can be determined in a trusted execution environment, wherein the first financial product recommendation result is high risk (non-recommendation) and low risk (recommendation), and the first account classification result is a potential account or a non-potential account.

In an alternative embodiment, based on the first account basic information, determining a first financial product recommendation result and a first account classification result corresponding to the target account in the trusted execution environment includes: based on the first account basic information, under a trusted execution environment, a financial product recommendation model is adopted to obtain a first financial product recommendation result and a first account classification result corresponding to the target account.

Alternatively, the financial product recommendation model may be a decision tree model, a classification model, a clustering model, an association rule model, a neural network model, or the like. For example, if the decision tree model is used, the existing account can be separated into different account groups, the first financial product recommendation result and whether the potential account is output, whether the account age is less than 30 years old, whether credit card consumption is used is judged if the account age is less than 30 years old, the potential account is used, the risk of purchasing the financial product is judged if the account is not used, the purchase is not recommended if the risk is high, and the purchase is recommended if the risk is low. As also shown in FIG. 2, the second terminal provides a financial product recommendation model and executes in a trusted execution environment. By executing the financial product recommendation model in a trusted execution environment, the safety of the algorithm program can be ensured.

In an optional embodiment, before the financial product recommendation model is adopted in the trusted execution environment based on the first account basic information to obtain the first financial product recommendation result and the first account classification result corresponding to the target account, the method further includes: acquiring account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts, wherein the account basic information respectively corresponding to the M accounts at least comprises: account portrait data of the corresponding account, financial product purchasing behavior data and financial product feature data; based on account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts, model training is carried out in a trusted execution environment, and a financial product recommendation model is obtained.

Optionally, as shown in fig. 3, which is a training flowchart of an optional financial product recommendation model according to an embodiment of the present application, as shown in fig. 3, first, account portrait data and financial product purchase behavior data included in account basic information corresponding to M accounts respectively are obtained, and model training is performed in a trusted execution environment based on the account basic information corresponding to M accounts respectively, and financial product feature data, a financial product recommendation result and an account classification result, so as to obtain a financial product recommendation model. By adopting the trusted execution environment, the running environment is safer, and the safety of account data is ensured.

In an alternative embodiment, model training is performed in a trusted execution environment based on account basic information, financial product recommendation results and account classification results corresponding to the M accounts respectively, to obtain a financial product recommendation model, including: preprocessing account basic information, financial product recommendation results and account classification results corresponding to the M accounts respectively to obtain processed account basic information, financial product recommendation results and account classification results corresponding to the M accounts respectively; performing feature extraction processing on the processed account basic information, the financial product recommendation result and the account classification result which are respectively corresponding to the M accounts to obtain account basic features, financial product features and account behavior features which are respectively corresponding to the M accounts; fusing the account basic features, financial product features and account behavior features corresponding to the M accounts respectively to obtain fused target data features; based on the target data characteristics, training the initial model in a trusted execution environment to obtain a financial product recommendation model.

Optionally, as shown in fig. 3, after data integration, data preprocessing and feature engineering, the data is input into a model for training, specifically, initial basic information of accounts corresponding to M accounts respectively can be matched and integrated with identification information corresponding to M accounts respectively, so as to obtain basic information of accounts corresponding to M accounts respectively; preprocessing account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts, wherein the preprocessing can be data cleaning processing, data deduplication processing and data standardization processing to obtain processed account basic information, financial product recommendation results and account classification results; performing feature extraction processing on the processed account basic information, financial product recommendation results and account classification results by using a feature extraction model to obtain account basic features, financial product features and account behavior features corresponding to the M accounts respectively; carrying out fusion processing on the three characteristics to obtain fused target data characteristics; based on the target data characteristics, training the initial model in a trusted execution environment to obtain a financial product recommendation model.

In an alternative embodiment, training the initial model in a trusted execution environment based on the target data features to obtain a financial product recommendation model when the initial model is K and K is an integer greater than or equal to 2, including: training K initial models based on target data characteristics to obtain K first models and model accuracy rates corresponding to the K first models respectively, wherein K is an integer greater than or equal to 2; and taking the first model with the model accuracy larger than or equal to a first preset value in the K first models as a financial product recommendation model.

Optionally, as shown in fig. 3, the target data features are input into various initial models to perform model algorithm selection, and after model construction, model optimization and evaluation, the data mining process is completed, so as to obtain the financial product recommendation model. Specifically, if the number of the initial models is K, training the K initial models based on the target data characteristics to obtain K first models, and model accuracy corresponding to the K first models respectively, wherein the first model with the highest model accuracy in the K first models is used as a financial product recommendation model.

In an optional embodiment, when the physical property recommendation models are L, where L is an integer greater than or equal to 2, based on the first account basic information, in a trusted execution environment, a financial product recommendation model is adopted to obtain a first financial product recommendation result and a first account classification result corresponding to the target account, where the first account recommendation result and the first account classification result include: determining weight values corresponding to the L financial product recommendation models according to model accuracy rates corresponding to the L financial product recommendation models respectively; respectively inputting the first account basic information into L financial product recommendation models to obtain L financial product recommendation results and L account classification results; based on the weight values respectively corresponding to the L financial product recommendation models and the L financial product recommendation results, obtaining a first financial product recommendation result; and obtaining a first account classification result based on the weight values respectively corresponding to the L financial product recommendation models and the L account classification results.

Optionally, if the financial product recommendation models are L, determining weight values corresponding to the L financial product recommendation models according to model accuracy corresponding to the L financial product recommendation models, respectively, inputting the first account basic information to the L financial product recommendation models to obtain L financial product recommendation results and L account classification results, and obtaining the first account classification results according to the weight values corresponding to the L financial product recommendation models and the L financial product recommendation results and the weight values corresponding to the L financial product recommendation models and the L account classification results. By giving different weights to different financial product recommendation models, the influence of the different models can be adjusted according to the accuracy of the models, so that a first financial product recommendation result and a first account classification result can be obtained more accurately.

In an optional embodiment, after obtaining the first financial product recommendation result and the first account classification result target account corresponding to the target account by adopting the financial product recommendation model based on the first account basic information, the method further includes: determining the financial amount amplification of the target account based on the financial product purchase amount of the target account in the current financial product purchase period and the financial product purchase amount of the last financial product purchase period, wherein the last financial product purchase period is the previous purchase period of the current financial product purchase period; according to the financial amount increase, determining the financial amount increase type of the target account; determining the value type of the target account according to the financial asset amount of the target account; and determining a second account classification result of the target account based on the financial amount increment type, the value type and the first account classification result.

Optionally, the increase of the financial amount of each month of the target account can be determined according to the purchase amount of the financial product of the target account in the current month and the purchase amount of the financial product of the previous month, and then the increase type of the financial amount of the target account is determined according to the increase; and determining the value type of the target account according to the financial asset amount of the target account. Based on the financial amount increment type, the value type and the first account classification result, a second account classification result of the target account is determined, a first weight value corresponding to the financial amount increment type, a second weight value corresponding to the value type and a third weight value corresponding to the first account classification result can also be determined, and based on the financial amount increment type, the value type, the first account classification result, the first weight value, the second weight value and the third weight value, a second account classification result is determined. The key factors for classifying accounts are better captured by setting weight values for the increment of the financial amount, the value type and the first account classification result, so that the second account classification result is more accurately obtained.

In an alternative embodiment, determining the financial amount increase type of the target account according to the financial amount increase includes: judging whether the increment of the financial amount is larger than a preset increment threshold; if the increment of the financial amount is larger than the preset increment threshold, determining that the increment type of the financial amount is a high increment account; if the increment of the financial amount is smaller than or equal to a preset increment threshold, determining that the increment type of the financial amount is a low increment account; determining a value type of the target account based on the financial asset amount of the target account, including: judging whether the financial asset amount is larger than a preset asset threshold value or not; if the financial asset amount is greater than the preset asset threshold, determining that the value type is a high value account; if the financial asset amount is less than or equal to the preset asset threshold, determining the value type as the base account.

Optionally, judging whether the increment of the financial amount is larger than a preset increment threshold, wherein the preset increment threshold can be 20%, and if the increment of the financial amount is larger than 20%, the account is a high increment account; if the increment of the financial amount is less than or equal to 20%, the account is a low increment account. Judging whether the financial asset amount is greater than a preset asset threshold, wherein the preset asset threshold can be 100 ten thousand, and if the financial asset amount is greater than 100 ten thousand, the financial asset amount is a high-value account; if the amount of the financial asset is less than or equal to 100 ten thousand, then it is the base account.

Step S104, the first financial product recommendation result and the first account classification result are sent to the first terminal.

Optionally, after the first financial product recommendation result and the first account classification result are sent to the first terminal through the trusted channel, the first terminal may give a final target account recommendation result according to the first financial product recommendation result and the first account classification result, in combination with the existing service logic of the second terminal, where the service logic may be: customers with higher deposit amounts on duty or accounts often more understand the reasonable configuration of assets and avoidance risk, and pay more attention to products with high income and higher risk level; and for office workers who pay house credits and car credits regularly every month with stable income, the fund mobility of the office workers is poor, so that the office workers pay more attention to financial products with stable income. And the first terminal matches the final target account recommendation result completion information and returns the final target account recommendation result completion information to the service system for reference by a service manager.

Through the steps S101 to S104, the purposes of safely and accurately obtaining the first financial product recommendation result and the first account classification result by adopting the financial product recommendation model based on the first account basic information can be achieved, and the problems of low safety and low detection result accuracy of the information processing method in the related technology are solved. Thereby achieving the effect of improving the safety and accuracy of the information processing method.

Based on the above examples and optional embodiments, the present application proposes an optional implementation, the method comprising a model training phase and a model application phase, wherein:

the financial product recommendation model is trained by the following steps:

step S11, obtaining account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts, wherein the account basic information respectively corresponding to the M accounts at least comprises: account portrait data of the corresponding account, financial product purchasing behavior data and financial product feature data.

And step S12, preprocessing account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts.

And S13, carrying out feature extraction processing on the processed account basic information, the financial product recommendation result and the account classification result which are respectively corresponding to the M accounts to obtain account basic features, financial product features and account behavior features which are respectively corresponding to the M accounts.

And S14, carrying out fusion processing on account basic features, financial product features and account behavior features corresponding to the M accounts respectively to obtain fused target data features.

And step S15, training the initial model under a trusted execution environment based on the target data characteristics to obtain a financial product recommendation model.

The model application stage is realized by the following modes:

step S21, receiving first identification information of a target account from a first terminal, wherein the first identification information is a first hash value corresponding to the target account, and the first hash value is obtained by performing hash operation on the initial identification information of the target account.

And S22, respectively carrying out hash operation processing on the account basic information included in the account basic information set to obtain a second hash data set.

Step S23, judging whether the first hash value exists in the second hash data set.

In step S24, if the first hash value exists in the second hash data set, the first account base information matched with the first hash value is determined from the account base information set.

Step S25, based on the first account basic information, a financial product recommendation model is adopted in a trusted execution environment to obtain a first financial product recommendation result and a first account classification result corresponding to the target account.

Step S26, a first financial product recommendation result and a first account classification result are sent to the first terminal.

The embodiment of the application can at least realize the following technical effects: the security of account information is ensured; and accurately positioning potential accounts in advance, and subdividing potential clients. For example, the account group with financial product purchasing intent but not purchasing financial products is accurately positioned in the existing account, the account is divided into different account groups according to the product types, the corresponding financial products are recommended to the different account groups, the accuracy of financial product recommendation is greatly improved, and the marketing cost is reduced.

Based on the above examples and alternative embodiments, the present application proposes another alternative embodiment, the method comprising the steps of:

step S201, the first terminal sends first identification information of a target account to the second terminal;

step S202, under a preset trusted execution environment, the second terminal determines first account basic information matched with first identification information from an account basic information set, wherein the first account basic information at least comprises account portrait data, financial product purchasing behavior data and financial product characteristic data of a target account, and the account basic information set comprises account basic information respectively corresponding to at least one account;

Step S203, the second terminal determines a first financial product recommendation result and a first account classification result corresponding to the target account under a trusted execution environment based on the first account basic information, wherein the first account classification result is a potential account or a non-potential account;

in step S204, the second terminal sends the first financial product recommendation result and the first account classification result to the first terminal.

It should be noted that, related information (including, but not limited to, user equipment information, user personal information, etc.) and data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by a user or sufficiently authorized by each party. For example, an interface is provided between the system and the relevant user or institution, before acquiring the relevant information, the system needs to send an acquisition request to the user or institution through the interface, and acquire the relevant information after receiving the consent information fed back by the user or institution. It should also be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.

The embodiment of the application also provides an information processing device, and it should be noted that the information processing device of the embodiment of the application can be used for executing the information processing method provided by the embodiment of the application. The information processing apparatus provided in the embodiment of the present application is described below.

Fig. 4 is a schematic diagram of an information processing apparatus according to an embodiment of the present application. As shown in fig. 4, the apparatus includes: a first receiving module 401, a first matching module 402, a first sorting module 403, a first transmitting module 404, wherein,

a first receiving module 401, configured to receive first identification information of a target account from a first terminal, where the first identification information is obtained by encrypting, by the first terminal, initial identification information of the target account;

the first matching module 402 is connected to the first receiving module 401, and is configured to determine, in a preset trusted execution environment, first account basic information that matches the first identification information from an account basic information set, where the first account basic information at least includes account portrait data, financial product purchase behavior data, and financial product feature data of a target account, and the account basic information set includes account basic information corresponding to at least one account respectively;

The first classification module 403 is connected to the first matching module 402, and is configured to determine, based on the first account basic information, a first financial product recommendation result and a first account classification result corresponding to the target account in a trusted execution environment, where the first account classification result is a potential account or a non-potential account;

the first sending module 404 is connected to the first classification module 403, and is configured to send the first financial product recommendation result and the first account classification result to the first terminal.

In the present application, a first receiving module 401 is configured to receive first identification information of a target account from a first terminal, where the first identification information is obtained by encrypting, by the first terminal, initial identification information of the target account; the first matching module 402 is configured to determine, in a preset trusted execution environment, first account basic information that is matched with the first identification information from an account basic information set, where the first account basic information at least includes account portrait data, financial product purchase behavior data, and financial product feature data of a target account, and the account basic information set includes account basic information corresponding to at least one account respectively; the first classification module 403 is configured to determine, based on the first account basic information, a first financial product recommendation result and a first account classification result corresponding to the target account in a trusted execution environment, where the first account classification result is a potential account or a non-potential account; the first sending module 404 is configured to send the first financial product recommendation result and the first account classification result to the first terminal. The method achieves the aim of safely and accurately obtaining the first financial product recommendation result and the first account classification result by adopting the financial product recommendation model based on the first account basic information, and solves the problems of low safety and low detection result accuracy of the information processing method in the related technology. Thereby achieving the effect of improving the safety and accuracy of the information processing method.

In an alternative embodiment, the first matching module includes: the first processing sub-module is used for respectively carrying out hash operation processing on the account basic information included in the account basic information set to obtain a second hash data set; the first judging submodule is used for judging whether a first hash value exists in the second hash data set or not; and the first determining sub-module is used for determining the first account basic information matched with the first hash value from the account basic information set if the first hash value exists in the second hash data set.

In an alternative embodiment, the first classification module includes: the second determining sub-module is used for obtaining a first financial product recommendation result and a first account classification result corresponding to the target account by adopting a financial product recommendation model under a trusted execution environment based on the first account basic information.

In an alternative embodiment, the apparatus further comprises: the first obtaining sub-module is used for obtaining account basic information, financial product recommendation results and account classification results which are respectively corresponding to the M accounts, wherein the account basic information which is respectively corresponding to the M accounts at least comprises: account portrait data of the corresponding account, financial product purchasing behavior data and financial product feature data; and the third determination submodule is used for carrying out model training under a trusted execution environment based on account basic information, financial product recommendation results and account classification results which are respectively corresponding to the M accounts to obtain a financial product recommendation model.

In an alternative embodiment, the third determining sub-module includes: the second processing sub-module is used for preprocessing account basic information, financial product recommendation results and account classification results corresponding to the M accounts respectively to obtain processed account basic information, financial product recommendation results and account classification results corresponding to the M accounts respectively; the third processing sub-module is used for carrying out feature extraction processing on the processed account basic information, the financial product recommendation result and the account classification result which are respectively corresponding to the M accounts to obtain account basic features, financial product features and account behavior features which are respectively corresponding to the M accounts; the fourth processing sub-module is used for carrying out fusion processing on account basic features, financial product features and account behavior features corresponding to the M accounts respectively to obtain fused target data features; and the fourth determining submodule is used for training the initial model under a trusted execution environment based on the target data characteristics to obtain a financial product recommendation model.

In an alternative embodiment, the fourth determining sub-module includes: the first training submodule is used for training the K initial models respectively based on the target data characteristics to obtain K first models and model accuracy rates corresponding to the K first models respectively, wherein K is an integer greater than or equal to 2; and the fifth determining submodule is used for taking a first model with the model accuracy larger than or equal to a first preset value in the K first models as a financial product recommendation model.

In an alternative embodiment, the second determining sub-module includes: a sixth determining submodule, configured to determine weight values corresponding to the L financial product recommendation models respectively according to model accuracy corresponding to the L financial product recommendation models respectively; the first input sub-module is used for inputting the first account basic information into the L financial product recommendation models respectively to obtain L financial product recommendation results and L account classification results; a seventh determining submodule, configured to obtain a first financial product recommendation result based on the weight values respectively corresponding to the L financial product recommendation models and the L financial product recommendation results; and the eighth determining submodule is used for obtaining a first account classification result based on the weight values corresponding to the L financial product recommendation models and the L account classification results.

In an alternative embodiment, the apparatus further comprises: a ninth determining submodule, configured to determine an increase in the financial amount of the target account based on the financial product purchase amount of the target account in the current financial product purchase period and the financial product purchase amount of the last financial product purchase period, where the last financial product purchase period is a previous purchase period of the current financial product purchase period; a tenth determination submodule, configured to determine a financial amount increment type of the target account according to the financial amount increment; an eleventh determination submodule, configured to determine a value type of the target account according to the financial asset amount of the target account; and the twelfth determining submodule is used for determining a second account classification result of the target account based on the financial amount increment type, the value type and the first account classification result.

In an alternative embodiment, the tenth determination submodule includes: the second judging submodule is used for judging whether the increment of the financial amount is larger than a preset increment threshold value or not; a thirteenth determination submodule, configured to determine that the financial amount increment type is a high increment account if the financial amount increment is greater than the preset increment threshold; a fourteenth determination submodule, configured to determine that the financial amount increment type is a low increment account if the financial amount increment is less than or equal to a preset increment threshold; in an alternative embodiment, the eleventh determining sub-module includes: a third judging sub-module for judging whether the amount of the financial asset is larger than a preset asset threshold; a fifteenth determination submodule, configured to determine that the value type is a high-value account if the financial asset amount is greater than a preset asset threshold; a sixteenth determination sub-module for determining the value type as the base account if the financial asset amount is less than or equal to the preset asset threshold.

It should be noted that each of the above modules may be implemented by software or hardware, for example, in the latter case, it may be implemented by: the above modules may be located in the same processor; alternatively, the various modules described above may be located in different processors in any combination.

Here, the first receiving module 401, the first matching module 402, the first classifying module 403, and the first transmitting module 404 correspond to steps S101 to S104 in the embodiment, and the modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the foregoing embodiments. It should be noted that the above modules may be run in a computer terminal as part of the apparatus.

It should be noted that, the optional or preferred implementation manner of this embodiment may be referred to the related description in the embodiment, and will not be repeated herein.

The information processing apparatus includes a processor and a memory, the units and the like are stored as program units in the memory, and the processor executes the program units stored in the memory to realize the corresponding functions.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel may be provided with one or more kernel parameters (for the purposes of this application).

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the application provides a nonvolatile storage medium, on which a program is stored, which when executed by a processor, implements the above-described information processing method.

The embodiment of the application provides a processor, which is used for running a program, wherein the information processing method is executed when the program runs.

As shown in fig. 5, an embodiment of the present application provides an electronic device, where the electronic device 10 includes a processor, a memory, and a program stored on the memory and executable on the processor, and the processor implements the following steps when executing the program: receiving first identification information of a target account from a first terminal, wherein the first identification information is obtained by encrypting the initial identification information of the target account by the first terminal; under a preset trusted execution environment, determining first account basic information matched with first identification information from an account basic information set, wherein the first account basic information at least comprises account portrait data, financial product purchasing behavior data and financial product characteristic data of a target account, and the account basic information set comprises account basic information corresponding to at least one account respectively; based on the first account basic information, determining a first financial product recommendation result and a first account classification result corresponding to the target account in a trusted execution environment, wherein the first account classification result is a potential account or a non-potential account; and sending the first financial product recommendation result and the first account classification result to the first terminal. The device herein may be a server, PC, PAD, cell phone, etc.

The present application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: receiving first identification information of a target account from a first terminal, wherein the first identification information is obtained by encrypting the initial identification information of the target account by the first terminal; under a preset trusted execution environment, determining first account basic information matched with first identification information from an account basic information set, wherein the first account basic information at least comprises account portrait data, financial product purchasing behavior data and financial product characteristic data of a target account, and the account basic information set comprises account basic information corresponding to at least one account respectively; based on the first account basic information, determining a first financial product recommendation result and a first account classification result corresponding to the target account in a trusted execution environment, wherein the first account classification result is a potential account or a non-potential account; and sending the first financial product recommendation result and the first account classification result to the first terminal.

Optionally, the above computer program product is further adapted to execute a program initialized with the method steps of: respectively carrying out hash operation processing on the account basic information included in the account basic information set to obtain a second hash data set; judging whether the first hash value exists in the second hash data set; and if the first hash value exists in the second hash data set, determining first account basic information matched with the first hash value from the account basic information set.

Optionally, the above computer program product is further adapted to execute a program initialized with the method steps of: based on the first account basic information, under a trusted execution environment, a financial product recommendation model is adopted to obtain a first financial product recommendation result and a first account classification result corresponding to the target account.

Optionally, the above computer program product is further adapted to execute a program initialized with the method steps of: acquiring account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts, wherein the account basic information respectively corresponding to the M accounts at least comprises: account portrait data of the corresponding account, financial product purchasing behavior data and financial product feature data; based on account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts, model training is carried out in a trusted execution environment, and a financial product recommendation model is obtained.

Optionally, the above computer program product is further adapted to execute a program initialized with the method steps of: preprocessing account basic information, financial product recommendation results and account classification results corresponding to the M accounts respectively to obtain processed account basic information, financial product recommendation results and account classification results corresponding to the M accounts respectively; performing feature extraction processing on the processed account basic information, the financial product recommendation result and the account classification result which are respectively corresponding to the M accounts to obtain account basic features, financial product features and account behavior features which are respectively corresponding to the M accounts; fusing the account basic features, financial product features and account behavior features corresponding to the M accounts respectively to obtain fused target data features; based on the target data characteristics, training the initial model in a trusted execution environment to obtain a financial product recommendation model.

Optionally, the above computer program product is further adapted to execute a program initialized with the method steps of: training K initial models based on target data characteristics to obtain K first models and model accuracy rates corresponding to the K first models respectively, wherein K is an integer greater than or equal to 2; and taking the first model with the model accuracy larger than or equal to a first preset value in the K first models as a financial product recommendation model.

Optionally, the above computer program product is further adapted to execute a program initialized with the method steps of: determining weight values corresponding to the L financial product recommendation models according to model accuracy rates corresponding to the L financial product recommendation models respectively; respectively inputting the first account basic information into L financial product recommendation models to obtain L financial product recommendation results and L account classification results; based on the weight values respectively corresponding to the L financial product recommendation models and the L financial product recommendation results, obtaining a first financial product recommendation result; and obtaining a first account classification result based on the weight values respectively corresponding to the L financial product recommendation models and the L account classification results.

Optionally, the above computer program product is further adapted to execute a program initialized with the method steps of: determining the financial amount amplification of the target account based on the financial product purchase amount of the target account in the current financial product purchase period and the financial product purchase amount of the last financial product purchase period, wherein the last financial product purchase period is the previous purchase period of the current financial product purchase period; according to the financial amount increase, determining the financial amount increase type of the target account; determining the value type of the target account according to the financial asset amount of the target account; and determining a second account classification result of the target account based on the financial amount increment type, the value type and the first account classification result.

Optionally, the above computer program product is further adapted to execute a program initialized with the method steps of: judging whether the increment of the financial amount is larger than a preset increment threshold; if the increment of the financial amount is larger than the preset increment threshold, determining that the increment type of the financial amount is a high increment account; if the increment of the financial amount is smaller than or equal to a preset increment threshold, determining that the increment type of the financial amount is a low increment account; judging whether the financial asset amount is larger than a preset asset threshold value or not; if the financial asset amount is greater than the preset asset threshold, determining that the value type is a high value account; if the financial asset amount is less than or equal to the preset asset threshold, determining the value type as the base account.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. An information processing method, characterized by comprising:

receiving first identification information of a target account from a first terminal, wherein the first identification information is obtained by encrypting the initial identification information of the target account by the first terminal;

under a preset trusted execution environment, determining first account basic information matched with the first identification information from an account basic information set, wherein the first account basic information at least comprises account portrait data, financial product purchasing behavior data and financial product characteristic data of the target account, and the account basic information set comprises account basic information corresponding to at least one account respectively;

Based on the first account basic information, determining a first financial product recommendation result and a first account classification result corresponding to the target account in the trusted execution environment, wherein the first account classification result is a potential account or a non-potential account;

and sending the first financial product recommendation result and the first account classification result to the first terminal.

2. The method according to claim 1, wherein the first identification information is a first hash value corresponding to the target account, the first hash value is obtained by performing hash operation on initial identification information of the target account, and the determining, in a preset trusted execution environment, first account base information matched with the first identification information from an account base information set includes:

respectively carrying out hash operation processing on the account basic information included in the account basic information set to obtain a second hash data set;

judging whether the first hash value exists in the second hash data set;

and if the first hash value exists in the second hash data set, determining the first account basic information matched with the first hash value from the account basic information set.

3. The method of claim 1, wherein determining, based on the first account base information, a first financial product recommendation result and a first account classification result corresponding to the target account in the trusted execution environment comprises:

based on the first account basic information, adopting a financial product recommendation model in the trusted execution environment to obtain the first financial product recommendation result and the first account classification result corresponding to the target account.

4. The method of claim 3, wherein prior to obtaining the first financial product recommendation result and the first account classification result corresponding to the target account using a financial product recommendation model in the trusted execution environment based on the first account base information, the method further comprises:

acquiring account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts, wherein the account basic information respectively corresponding to the M accounts at least comprises: account portrait data of the corresponding account, financial product purchasing behavior data and financial product feature data;

And performing model training under the trusted execution environment based on account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts to obtain the financial product recommendation model.

5. The method of claim 4, wherein the performing model training in the trusted execution environment based on account basic information, financial product recommendation results and account classification results respectively corresponding to the M accounts to obtain the financial product recommendation model includes:

preprocessing account basic information, financial product recommendation results and account classification results corresponding to the M accounts respectively to obtain processed account basic information, financial product recommendation results and account classification results corresponding to the M accounts respectively;

performing feature extraction processing on the processed account basic information, the financial product recommendation result and the account classification result which are respectively corresponding to the M accounts to obtain account basic features, financial product features and account behavior features which are respectively corresponding to the M accounts;

fusing the account basic features, financial product features and account behavior features corresponding to the M accounts respectively to obtain fused target data features;

Based on the target data characteristics, training an initial model in the trusted execution environment to obtain the financial product recommendation model.

6. The method according to claim 5, wherein, in the case where the initial models are K, where K is an integer greater than or equal to 2, the training the initial models in the trusted execution environment based on the target data features to obtain the financial product recommendation model includes:

training K initial models based on the target data characteristics respectively to obtain K first models and model accuracy rates corresponding to the K first models respectively, wherein K is an integer greater than or equal to 2;

and taking the first model with the model accuracy larger than or equal to a first preset value in the K first models as the financial product recommendation model.

7. The method of claim 3, wherein, when the financial product recommendation models are L, where L is an integer greater than or equal to 2, the obtaining, based on the first account basic information, the first financial product recommendation result and the first account classification result corresponding to the target account using the financial product recommendation models in the trusted execution environment includes:

Determining weight values corresponding to the L financial product recommendation models respectively according to model accuracy rates corresponding to the L financial product recommendation models respectively;

respectively inputting the first account basic information into the L financial product recommendation models to obtain L financial product recommendation results and L account classification results;

based on the weight values respectively corresponding to the L financial product recommendation models and the L financial product recommendation results, obtaining the first financial product recommendation results;

and obtaining the first account classification result based on the weight values respectively corresponding to the L financial product recommendation models and the L account classification results.

8. The method according to any one of claims 1 to 7, wherein after the obtaining, based on the first account basic information, a first financial product recommendation result and a first account classification result target account corresponding to the target account by using a financial product recommendation model, the method further comprises:

determining the financial amount amplification of the target account based on the financial product purchase amount of the target account in the current financial product purchase period and the financial product purchase amount of the last financial product purchase period, wherein the last financial product purchase period is the previous purchase period of the current financial product purchase period;

Determining the financial amount increment type of the target account according to the financial amount increment;

determining a value type of the target account according to the financial asset amount of the target account;

and determining a second account classification result of the target account based on the financial amount increment type, the value type and the first account classification result.

9. The method of claim 8, wherein the step of determining the position of the first electrode is performed,

the determining the financial amount increment type of the target account according to the financial amount increment comprises the following steps:

judging whether the financial amount amplification is larger than a preset amplification threshold value or not; if the increment of the financial amount is larger than the preset increment threshold, determining that the increment type of the financial amount is a high increment account; if the increment of the financial amount is smaller than or equal to the preset increment threshold, determining that the increment type of the financial amount is a low increment account;

the determining the value type of the target account according to the financial asset amount of the target account comprises the following steps: judging whether the financial asset amount is larger than a preset asset threshold; if the financial asset amount is greater than the preset asset threshold, determining that the value type is a high value account; and if the financial asset amount is less than or equal to the preset asset threshold, determining the value type as a basic account.

10. An information processing apparatus, characterized by comprising:

the first receiving module is used for receiving first identification information of a target account from a first terminal, wherein the first identification information is obtained by encrypting the initial identification information of the target account by the first terminal;

the first matching module is used for determining first account basic information matched with the first identification information from an account basic information set under a preset trusted execution environment, wherein the first account basic information at least comprises account portrait data, financial product purchasing behavior data and financial product characteristic data of the target account, and the account basic information set comprises account basic information corresponding to at least one account respectively;

the first classification module is used for determining a first financial product recommendation result and a first account classification result corresponding to the target account under the trusted execution environment based on the first account basic information, wherein the first account classification result is a potential account or a non-potential account;

and the first sending module is used for sending the first financial product recommendation result and the first account classification result to the first terminal.

11. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the information processing method of any of claims 1-9.