CN116051178A - Data processing method, device, electronic equipment and computer readable medium - Google Patents

Abstract

The application discloses a data processing method, a device, electronic equipment and a computer readable medium, which relate to the technical field of big data processing, and one specific embodiment comprises the steps of responding to the acquisition of user transaction data, acquiring a corresponding user identifier, and acquiring a corresponding user portrait according to the user identifier; generating a classification model based on the user representation; invoking a classification model to determine a user rating based on the user transaction data; generating excitation information based on the user grade, and further acquiring feedback information of the user based on the excitation information; and updating the user portrait based on the feedback information, and further updating the user grade according to the updated user portrait. Therefore, the user viscosity is enhanced, the data processing efficiency can be improved, and the success rate of data recommendation is improved.

Description

Data processing method, device, electronic equipment and computer readable medium

Technical Field

The present disclosure relates to the field of big data processing technologies, and in particular, to a data processing method, a device, an electronic apparatus, and a computer readable medium.

Background

In the development process of the order-receiving merchants, the workload of business management is also increased rapidly along with the rapid increase of the number of the order-receiving merchants. The high-contribution merchant is judged by manually consulting the merchant running water report, deposit and other data, and then the merchant is given preference in a manner of reducing the commission. However, due to the explosive growth of the traffic, the manual operation cannot meet the service requirement, and the service processing efficiency is low.

Disclosure of Invention

In view of this, embodiments of the present application provide a data processing method, apparatus, electronic device, and computer readable medium, which can solve the problem of low service processing efficiency when the existing traffic is exploded.

To achieve the above object, according to one aspect of the embodiments of the present application, there is provided a data processing method, including:

responding to the obtained user transaction data, obtaining a corresponding user identifier, and obtaining a corresponding user portrait according to the user identifier;

generating a classification model based on the user representation;

invoking a classification model to determine a user rating based on the user transaction data;

generating excitation information based on the user grade, and further acquiring feedback information of the user based on the excitation information;

and updating the user portrait based on the feedback information, and further updating the user grade according to the updated user portrait.

Optionally, acquiring the corresponding user portrait according to the user identifier includes:

and obtaining user portraits corresponding to the user identifications in each preset dimension.

Optionally, generating the classification model based on the user representation includes:

acquiring a user grade label corresponding to a user picture corresponding to each preset dimension;

And taking the user portraits corresponding to each preset dimension as input of an initial neural network model, taking the corresponding user grade labels as expected output of the initial neural network model, training the initial neural network model, and finally generating a classification model.

Optionally, determining the user level includes:

generating a current user portrait according to the user transaction data;

the current user representation is input to the classification model to output a corresponding user level.

Optionally, generating the excitation information includes:

invoking a class library to determine a corresponding next class according to the user class;

and acquiring the next-level preference information corresponding to the next level, and further generating the excitation information based on the next-level preference information, the user level and the next level.

Optionally, generating incentive information based on the offer information, the user level, and the next level includes:

acquiring current grade preferential information corresponding to the user grade, and further generating preferential difference information based on the current grade preferential information and next grade preferential information;

incentive information is generated based on the offer difference information, the user level, and the next level.

Optionally, after updating the user level according to the updated user portrait, the method further comprises:

Based on the updated user grade, determining user preferential information, further generating a data report based on the user preferential information, and sending the data report to a preset processing node.

In addition, the application also provides a data processing device, which comprises:

the first acquisition unit is configured to respond to the acquisition of the user transaction data, acquire the corresponding user identification and acquire the corresponding user portrait according to the user identification;

a model generation unit configured to generate a classification model based on the user representation;

a rank determination unit configured to invoke the classification model to determine a user rank based on the user transaction data;

the second acquisition unit is configured to generate excitation information based on the user grade, and further acquire feedback information of the user based on the excitation information;

and the updating unit is configured to update the user portrait based on the feedback information and further update the user grade according to the updated user portrait.

Optionally, the first acquisition unit is further configured to:

and obtaining user portraits corresponding to the user identifications in each preset dimension.

Optionally, the model generation unit is further configured to:

acquiring a user grade label corresponding to a user picture corresponding to each preset dimension;

And taking the user portraits corresponding to each preset dimension as input of an initial neural network model, taking the corresponding user grade labels as expected output of the initial neural network model, training the initial neural network model, and finally generating a classification model.

Optionally, the rank determination unit is further configured to:

generating a current user portrait according to the user transaction data;

the current user representation is input to the classification model to output a corresponding user level.

Optionally, the second acquisition unit is further configured to:

invoking a class library to determine a corresponding next class according to the user class;

and acquiring the next-level preference information corresponding to the next level, and further generating the excitation information based on the next-level preference information, the user level and the next level.

Optionally, the second acquisition unit is further configured to:

acquiring current grade preferential information corresponding to the user grade, and further generating preferential difference information based on the current grade preferential information and next grade preferential information;

incentive information is generated based on the offer difference information, the user level, and the next level.

Optionally, the data processing apparatus further comprises a data report generating unit configured to:

Based on the updated user grade, determining user preferential information, further generating a data report based on the user preferential information, and sending the data report to a preset processing node.

In addition, the application also provides data processing electronic equipment, which comprises: one or more processors; and a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the data processing method as described above.

In addition, the application also provides a computer readable medium, on which a computer program is stored, which when executed by a processor implements a data processing method as described above.

To achieve the above object, according to yet another aspect of the embodiments of the present application, a computer program product is provided.

A computer program product of an embodiment of the present application includes a computer program, which when executed by a processor implements a data processing method provided by the embodiment of the present application.

One embodiment of the above invention has the following advantages or benefits: the method comprises the steps of responding to user transaction data, obtaining corresponding user identifiers, and obtaining corresponding user portraits according to the user identifiers; generating a classification model based on the user representation; invoking a classification model to determine a user rating based on the user transaction data; generating excitation information based on the user grade, and further acquiring feedback information of the user based on the excitation information; and updating the user portrait based on the feedback information, and further updating the user grade according to the updated user portrait. Therefore, the user viscosity is enhanced, the data processing efficiency can be improved, and the success rate of data recommendation is improved.

Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the present application and are not to be construed as unduly limiting the present application. Wherein:

FIG. 1 is a schematic diagram of the main flow of a data processing method according to one embodiment of the present application;

FIG. 2 is a schematic diagram of the main flow of a data processing method according to one embodiment of the present application;

FIG. 3 is a schematic diagram of the main flow of a data processing method according to one embodiment of the present application;

FIG. 4 is a schematic flow diagram of a data processing method according to one embodiment of the present application;

FIG. 5 is a schematic diagram of the main units of a data processing apparatus according to an embodiment of the present application;

FIG. 6 is an exemplary system architecture diagram in which embodiments of the present application may be applied;

fig. 7 is a schematic diagram of a computer system suitable for use in implementing the terminal device or server of the embodiments of the present application.

Detailed Description

Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application 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 application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness. In the technical scheme of the application, the aspects of acquisition, analysis, use, transmission, storage and the like of the related user personal information all meet the requirements of related laws and regulations, are used for legal and reasonable purposes, are not shared, leaked or sold outside the aspects of legal use and the like, and are subjected to supervision and management of a supervision department. Necessary measures should be taken for the personal information of the user to prevent illegal access to such personal information data, ensure that personnel having access to the personal information data comply with the regulations of the relevant laws and regulations, and ensure the personal information of the user. Once these user personal information data are no longer needed, the risk should be minimized by limiting or even prohibiting the data collection and/or deletion.

User privacy is protected by de-identifying data when used, including in some related applications, such as by removing a particular identifier, controlling the amount or specificity of stored data, controlling how data is stored, and/or other methods.

FIG. 1 is a schematic diagram of the main flow of a data processing method according to an embodiment of the present application, as shown in FIG. 1, the data processing method includes:

step S101, corresponding user identifiers are acquired in response to the user transaction data, and corresponding user portraits are acquired according to the user identifiers.

In this embodiment, the execution body (for example, may be a server) of the data processing method may detect whether the user transaction data is acquired by means of a wired connection or a wireless connection. When user transaction data is acquired, user identification corresponding to the transaction data can be acquired. The user identifier, such as a user name or a user number or a transaction order number of the user, is not specifically limited in the embodiment of the present application. By way of example, the user transaction data may include deposit transaction data of the user, i.e., transaction data corresponding to a deposit operation of the user. The content of the user transaction data is not particularly limited in the embodiments of the present application. After the execution body acquires the user identification, the execution body can acquire the corresponding user portrait according to the user identification. By way of example, the user representation may be a user representation obtained from analysis of user historical deposit data, historical consumption data, historical loan data, and the like.

Specifically, obtaining the corresponding user portrait according to the user identifier includes: and obtaining user portraits corresponding to the user identifications in each preset dimension.

The number of user portraits to which the user identification corresponds may be plural (i.e., two or more). The user profile may correspond to different dimensions, such as a consumption preference dimension, a deposit line preference dimension, a financial purchase type dimension, an investment risk dimension, and the like. The dimensions corresponding to the user images are not particularly limited in the embodiment of the application.

Step S102, a classification model is generated based on the user portrait.

Specifically, based on the user representation, a classification model is generated, comprising: acquiring a user grade label corresponding to a user picture corresponding to each preset dimension; and taking the user portraits corresponding to each preset dimension as input of an initial neural network model, taking the corresponding user grade labels as expected output of the initial neural network model, training the initial neural network model, and finally generating a classification model.

The classification model may be trained based on one or more user portraits, for example, one user portrayal may be trained to obtain a classification model, or multiple user portraits may be trained together to obtain a classification model. The number of user portraits used in deriving the classification model is not particularly limited in this embodiment.

Step S103, calling a classification model to determine the user grade based on the user transaction data.

Specifically, determining the user level includes: generating a current user portrait according to the user transaction data; specifically, corresponding features in the user transaction data can be extracted based on preset dimensions (such as consumption preference dimensions, deposit line preference dimensions, financial purchase type dimensions and investment risk dimensions), then the features extracted based on the preset dimensions are fused to obtain fusion features, and a user portrait corresponding to the user transaction data is obtained based on the fusion features to serve as a current user portrait. And then inputs the current user portrait to the classification model to output the corresponding user grade.

Step S104, based on the user grade, generating excitation information, and further acquiring feedback information of the user based on the excitation information.

The incentive information may include, for example, up-to-standard requirement information and up-to-standard difference information for the last hierarchy that the user did not reach. By way of example, the incentive information is: "A user you good, your level is the a level at present, the daily interest rate is only 0.009%, if you store q ten thousand yuan again can reach the b level, the daily interest rate can promote to 0.015%, the interest rate difference is 0.006%". The executing user can push the excitation information to the user in a short message or mail mode, and whether feedback information returned by the user is received or not is detected in real time. The feedback information may include "positive feedback to motivational information, such as accepting motivational information and performing an operation to increase the deposit", and "negative feedback to motivational information, such as not receiving feedback information from the user or receiving information that the user does not agree to increase the deposit".

Step S105, updating the user portrait based on the feedback information, and further updating the user grade according to the updated user portrait.

The preference information of the user can be obtained through analysis through the feedback information of the user, and the user portrait is updated according to the preference information of the user. The updated user representation is input to the classification model to obtain an updated user level.

Specifically, after updating the user level according to the updated user portrait, the method further includes: based on the updated user grade, determining user preferential information, further generating a data report based on the user preferential information, and sending the data report to a preset processing node.

And calling a preset grade-preferential information base to find corresponding user preferential information according to the updated user grade. And generating a data report based on the user preference information and sending the data report to a preset processing node. For example, the preset processing node may be a node corresponding to the merchant manager. The data report may include a data report of each checked item of the user under the name of the preset processing node, and may include deposit, asset management scale (Asset Under Management, AUM), transaction fee of receipt, transaction number of receipt, and the like.

In the embodiment, corresponding user identifiers are acquired by responding to the acquired user transaction data, and corresponding user portraits are acquired according to the user identifiers; generating a classification model based on the user representation; invoking a classification model to determine a user rating based on the user transaction data; generating excitation information based on the user grade, and further acquiring feedback information of the user based on the excitation information; and updating the user portrait based on the feedback information, and further updating the user grade according to the updated user portrait. Therefore, the user viscosity is enhanced, the data processing efficiency can be improved, and the success rate of data recommendation is improved.

FIG. 2 is a schematic flow chart of a data processing method according to an embodiment of the present application, as shown in FIG. 2, the data processing method includes:

step S201, corresponding user identification is acquired in response to the user transaction data, and corresponding user portrait is acquired according to the user identification.

The user transaction data may be transaction data corresponding to an operation of purchasing financial resources by a user, for example, may include a number of purchasing financial resources, an amount of purchasing financial resources, a risk level of purchasing financial resources, and the like. After the user transaction data is obtained, the execution body may obtain a corresponding user identifier, for example, a user name or a user account corresponding to the user transaction data, which is not specifically limited in the embodiment of the present application. The execution body may obtain a corresponding user portrait for which a history already exists from the user portrait pool according to the user identification.

Step S202, a classification model is generated based on the user portrait.

Acquiring a user grade label corresponding to a user picture corresponding to each preset dimension; and taking the user portraits corresponding to each preset dimension as input of an initial neural network model, taking the corresponding user grade labels as expected output of the initial neural network model, training the initial neural network model, and finally generating a classification model.

Step S203, a classification model is invoked to determine user ratings based on user transaction data.

Generating a current user portrait according to the user transaction data; specifically, corresponding features in the user transaction data can be extracted based on preset dimensions (such as consumption preference dimensions, deposit line preference dimensions, financial purchase type dimensions and investment risk dimensions), then the features extracted based on the preset dimensions are fused to obtain fusion features, and a user portrait corresponding to the user transaction data is obtained based on the fusion features to serve as a current user portrait. And then inputs the current user portrait to the classification model to output the corresponding user grade.

Step S204, a grade library is called to determine the corresponding next grade according to the user grade.

The ranked ascending or descending user ranks may be included in the rank library. The executing body may determine, according to the user transaction data, a current user level at which the user is located, and further compare the level library to determine a next level of a higher level adjacent to the current user level, for example, the current user level is a y level, and the corresponding next level of the higher level is a z level.

Step S205, obtaining the next-level preference information corresponding to the next level, and generating the motivation information based on the next-level preference information, the user level and the next level.

The next level may have next level preference information of higher interest rate, more gifts, etc. than the current user level, and the execution subject may call the incentive information generating program to generate incentive information based on the next level preference information, the current user level, and the next level. For example, the incentive information may be "the current grade of the a financial transaction purchased by the user is y grade, the interest rate is a%, the gift is J, K, if the B financial transaction purchased by the user is z grade, the interest rate is (a+1)%, and the gift is J, K, L, M".

Step S206, feedback information of the user based on the excitation information is acquired.

The feedback information may include agreement to purchase B financial instrument not actually purchased, agreement to purchase B financial instrument and actually purchased, disagreement to purchase B financial instrument. Further, the executing body may further send corresponding incentive information based on feedback information returned by the user, for example, when the feedback information of the user is "agree to buy B financial resources" but there is no operation of buying B financial resources in practice, the executing body may send a manual service request to the preset processing node, so that the preset processing node calls the corresponding user based on the manual service parent request to introduce B financial resources in detail, thereby improving a success rate of the user to purchase B financial resources.

Step S207, updating the user portrait based on the feedback information, and further updating the user level according to the updated user portrait.

The executing body can update the user portrait based on the feedback information of each time so that the recommendation of the user is more in line with the user requirement, and input the updated user portrait into the classification model to obtain the final user grade and update. Thereby improving the efficiency and accuracy of data processing.

FIG. 3 is a schematic flow chart of a data processing method according to an embodiment of the present application, and as shown in FIG. 3, the data processing method includes:

Step S301, corresponding user identifiers are acquired in response to the user transaction data, and corresponding user portraits are acquired according to the user identifiers.

The user transaction data may be, for example, transaction data generated after a user purchases an item on a shopping platform. After the execution body acquires the user transaction data, the execution body can acquire the corresponding user identification. The user identifier may be, for example, a user name or a nickname of the user generating the user transaction data, and the embodiment of the present application does not specifically limit the user identifier. After the execution body acquires the user identification, the execution body can acquire the historical shopping information according to the user identification, and further call the user portrait generation model to acquire the historical user portrait according to the historical shopping information.

By way of example, the historical shopping information may include the type of website the user browses frequently in the last n months, names of items purchased frequently, prices, attribute information of items purchased frequently, etc., and the embodiment of the present application does not specifically limit the historical shopping information.

Step S302, a classification model is generated based on the user portrait.

The executing body can acquire a user grade label corresponding to a user image corresponding to each preset dimension, wherein the preset dimensions can comprise a browsing website dimension, a purchase item price dimension, a purchase item type dimension, a purchase item attribute dimension and the like; and taking the user portraits corresponding to each preset dimension as input of an initial neural network model, taking the corresponding user grade labels as expected output of the initial neural network model, training the initial neural network model, and finally generating a classification model.

Step S303, a classification model is invoked to determine a user rank based on the user transaction data.

Step S304, a grade library is called to determine the corresponding next grade according to the user grade.

The ranked ascending or descending user ranks may be included in the rank library. The executing body can determine the current user grade of the user according to the user transaction data, and further compare the grade library to determine the next grade of the higher grade adjacent to the current user grade.

The user level may be, for example, a member level at a shopping platform. The corresponding next level may be, for example, a next member level corresponding to a current member level of the user, for example, the current user level is a first-level member, and the next level is a second-level member.

Step S305, obtaining the next-level preference information corresponding to the next level.

The next-level discount information corresponding to the next level may be, for example, discount information of the next level.

Step S306, current grade preferential information corresponding to the user grade is obtained, and preferential difference information is generated based on the current grade preferential information and the next grade preferential information.

For example, the discount information of the current level of the user is 8.5-fold discount, and the discount information of the corresponding next level is 5-fold discount. The preference difference information may be the next level of preference less the current level of preference by 3.5 fold.

Step S307, incentive information is generated based on the offer difference information, the user level and the next level.

For example, the motivation information may be "the user is your, you are the first-level member, the purchased article enjoys 8.5-fold preference, if you are charged to reach P-ary, the user can upgrade to the second-level member, the purchased article enjoys 5-fold preference, the difference of the preferential discount of the second-level member and the first-level member is 3.5-fold, YY-ary can be saved for you a year, and if you want to upgrade to the second-level member, online customer service can be contacted.

Step S308, feedback information of the user based on the excitation information is acquired.

By way of example, the feedback information may correspond to a transacting secondary member or a non-transacting secondary member.

Step S309, updating the user portrait based on the feedback information, and further updating the user level according to the updated user portrait.

The current preference of the user can be obtained through analysis according to the feedback information of the user, the user portrait can be updated based on the feedback information, and the updated user portrait is input into the classification model to obtain the updated user grade. Therefore, the user viscosity can be enhanced, the data processing efficiency can be improved, and the success rate of data recommendation can be improved.

Fig. 4 is a schematic flow chart of a data processing method according to an embodiment of the present application. As shown in fig. 4:

1) The process starts from the generation of the classification model, and the classification model is obtained and then delivered to the standard engine;

2) The merchant data acquisition is completed by the system, and is imported into a standard engine and is imported into a merchant manager management platform for generating a merchant data report;

3) After acquiring merchant data and a classification model, the standard-reaching engine calculates a preferential execution basis, and the calculated data is supplied to a preferential execution module for preferential execution;

4) The preferential execution module supplies the preferential to be executed to each downstream transaction system;

5) The standard-reaching engine gives standard-reaching and non-standard-reaching results to the merchant incentive module to inform the merchant of the level condition of the contribution degree;

6) The preferential execution module can provide preferential execution conditions for the manager management platform of the commercial tenant for generating a preferential report of the commercial tenant.

For example, the logic included in the classification model includes an assessment period, an assessment standard, a product of the preferential enjoyment after the commercial tenant reaches the standard, a strength of enjoying the preferential enjoyment, and a quota of the preferential enjoyment. The classification model input needs to follow the rule of 'one person input and one person rechecking' of the operation system, reduces the generation of errors, and simultaneously needs to support the inquiry of the flow, inquire the history record of the rule, input people and recheck people, and achieve tracking.

Checking period: the assessment period for the contribution degree of the assessment standard to the commercial tenant, which is different in each family and each branch, can be set as the time points of the average of the year, the average of the month and the end of the month.

Assessment standard: the evaluation criteria include deposit of settlement account number bound by the merchant terminal, AUM of merchant legal person, AUM of merchant customer information, deposit of merchant legal person, transaction amount of merchant, commission income of merchant, total interest of credit of merchant to public account, credit interest of merchant legal person, credit amount of merchant legal person, credit card grade of merchant legal person, etc.

And (3) preferential products: and products which can enjoy preferential products when the established merchant meets the assessment standard are supported, wherein the products comprise merchant commission preferential, deposit interest preferential, loan amount preferential, fund purchase preferential, physical noble metal preferential, credit card integral preferential, other preferential and the like.

Favorable strength: when the merchant meets the assessment standard, the merchant can enjoy the preferential degree corresponding to different preferential products, including the commission discount points, deposit discount points, loan credit coefficients, foundation commission discount points, real precious metal discount rates, credit card integration coefficients and the like.

Preference amount: the upper limit of the preferential can be enjoyed, and the cost paid by the preferential is controlled, including the total amount of the preferential of merchant commission, the total amount of deposit interest preferential, the total amount of loan interest preferential, the highest elevation amount of loan, the total amount of the preferential of fund, the total amount of the preferential of real noble metal preferential, the total amount of credit card preferential integral, and the like.

Step management: aiming at the same assessment period, assessment standard, preferential product, preferential degree and preferential amount, the classification model, preferential degree and preferential amount can be set in a hierarchical manner, when the assessment standard of higher conditions is met, the higher preferential degree and more preferential amount can be enjoyed, so that merchants are stimulated to make higher contribution.

And (3) merchant data acquisition: the system needs to collect data of all dimensions of the merchant to judge the contribution degree of the merchant. Specifically, merchant identity, merchant information, merchant deposit, merchant asset management size (Asset Under Management, AUM) need to be collected.

Identity of merchant: merchant attributes, contacts, legal, channels, payment instruments.

Merchant information: customer attributes, customer number.

Merchant deposit: the method comprises the steps of depositing on public, depositing on private, depositing on yearly and daily, depositing on month and daily, and depositing on time.

Merchant AUM: AUM for public clients, AUM for private clients, AUM for the year, AUM for the month and day, AUM for the time point.

And (3) a standard engine: and comparing the rule with the acquired merchant data to judge which assessment standard the merchant meets. Specifically, the method comprises the following steps:

and (5) calculating the standard: and exporting which grade of assessment standard the merchant meets as a preferential basis of the downstream module.

Not reaching the standard and calculating: and deriving which grade of assessment standard is not met by the merchant, wherein the assessment standard of the last grade closest to the merchant is used as a data source of the merchant incentive module and the merchant manager management module and is used for encouraging the merchant to realize higher contribution degree.

And (3) preferential execution: and giving the corresponding preferential to the merchant by using the result calculated by the standard reaching engine. Specifically, the method comprises the following steps:

merchant commission offers: the merchant commission is exempted, and the commission of the merchant for the receipt transaction is discounted or preferential according to a certain value or completely free according to the set preferential intensity.

Deposit interest rate offers: and according to the set preference, when the merchant performs deposit, the merchant selects the up-regulation of the deposit interest rate.

Loan interest rate offers: allowing merchants to conduct down-regulation on loans in preset institutions according to the selected interest rate and the set preferential strength.

Loan amount preference: allowing the merchant to adjust up the loan amount of the preset institution according to the set parameters.

Fund purchase offers: allowing merchants to lower the procedure rate according to the set parameters when the preset institutions purchase funds and redeem funds.

Precious metal preference of a real object: allowing merchants to enjoy discounts of prices according to set parameters when the preset institutions purchase physical precious metals.

Credit card credit offers: when the merchant is allowed to use the credit card of the preset institution, the integral is increased by multiplying a certain coefficient according to the setting of the parameter, and the integral accumulation speed is increased.

Other benefits: including payment offers, etc., depending on the product provided.

Merchant incentive: and introducing a standard-reaching engine to calculate a result, and informing the merchant of the standard-reaching and non-standard-reaching preferential assessment standards. Specifically, the method comprises the following steps:

pushing the standard reaching results: through a plurality of channels such as short messages, weChat public numbers, mobile phones, internet and the like, the merchant is informed of the achieved preferential assessment standard, and the merchant is informed of the preferential product, preferential strength and preferential amount.

Pushing unqualified results: the merchant is informed of the latest hierarchical assessment standard which is not reached by a plurality of channels, and the preferential increase which can be enjoyed by the merchant than the current level after the level is reached, so that the merchant is stimulated to realize higher contribution degree.

A merchant manager management platform: the merchant manager is the role of developing merchants. The merchant manager management platform provides various data reports of the function for the merchant manager, provides decision basis for communication between the merchant manager and the merchant, and helps the merchant manager to better excite and store the merchant. The following report can be realized:

merchant data report: the data report of each checked merchant under the name of the merchant manager comprises deposit, AUM, receipt transaction fee, receipt transaction number and the like.

Merchant preferential report form: the merchant enjoys the report of the preferential product, the merchant enjoys the preferential report, and the merchant does not enjoy the preferential report.

The method has the advantage of forming a benign closed loop, and the merchant is used as a flow break to stimulate the merchant to use a bank order-receiving product to increase deposit at a bank, and meanwhile, the method brings benefits to the merchant and stimulates the merchant to further conduct financial activities at the bank, so that the viscosity of the merchant to the bank is enhanced. And the data processing efficiency and the success rate of data recommendation can be improved.

Fig. 5 is a schematic diagram of main units of a data processing apparatus according to an embodiment of the present application. As shown in fig. 5, the data processing apparatus 500 includes a first acquisition unit 501, a model generation unit 502, a rank determination unit 503, a second acquisition unit 504, and an update unit 505.

The first obtaining unit 501 is configured to obtain a corresponding user identifier in response to obtaining user transaction data, and obtain a corresponding user portrait according to the user identifier.

The model generation unit 502 is configured to generate a classification model based on the user representation.

The ranking determination unit 503 is configured to invoke the classification model to determine the user ranking based on the user transaction data.

The second obtaining unit 504 is configured to generate motivational information based on the user level, and further obtain feedback information of the user based on the motivational information.

An updating unit 505 is configured to update the user portraits based on the feedback information, and further to update the user ratings based on the updated user portraits.

In some embodiments, the first acquisition unit 501 is further configured to: and obtaining user portraits corresponding to the user identifications in each preset dimension.

In some embodiments, the model generation unit 502 is further configured to: acquiring a user grade label corresponding to a user picture corresponding to each preset dimension; and taking the user portraits corresponding to each preset dimension as input of an initial neural network model, taking the corresponding user grade labels as expected output of the initial neural network model, training the initial neural network model, and finally generating a classification model.

In some embodiments, the rank determination unit 503 is further configured to: generating a current user portrait according to the user transaction data; the current user representation is input to the classification model to output a corresponding user level.

In some embodiments, the second acquisition unit 504 is further configured to: invoking a class library to determine a corresponding next class according to the user class; and acquiring the next-level preference information corresponding to the next level, and further generating the excitation information based on the next-level preference information, the user level and the next level.

In some embodiments, the second acquisition unit 504 is further configured to: acquiring current grade preferential information corresponding to the user grade, and further generating preferential difference information based on the current grade preferential information and next grade preferential information; incentive information is generated based on the offer difference information, the user level, and the next level.

In some embodiments, the data processing apparatus further comprises a data report generating unit, not shown in fig. 5, configured to: based on the updated user grade, determining user preferential information, further generating a data report based on the user preferential information, and sending the data report to a preset processing node.

It should be noted that, the data processing method and the data processing apparatus of the present application have a corresponding relationship with respect to the implementation content of the embodiment 5, so the repeated content will not be described.

Fig. 6 illustrates an exemplary system architecture 600 in which the data processing methods or data processing apparatus of embodiments of the present application may be applied.

As shown in fig. 6, the system architecture 600 may include terminal devices 601, 602, 603, a network 0 network 604, and a server 605. The network 604 is used as a medium to provide communication links between the terminal devices 601, 602, 603 and the server 605. The network 604 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

A user may interact with the server 605 via the network 604 using the terminal devices 601, 602, 603 to receive or send messages, etc. The terminal devices 601, 602, 603 may have installed thereon 5 various communication client applications, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).

The terminal devices 601, 602, 603 may be various electronic devices having a data processing screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.

The server 605 may be a server providing various services, such as a background management server (by way of example only) providing support for user transaction data acquired by the user using the terminal devices 601, 602, 603. The background management server can respond to the acquisition of the user transaction data to acquire the corresponding user identification, and acquire the corresponding user portrait according to the user identification; generating a classification model based on the user representation; invoking a classification model to determine a user rating based on the user transaction data; generating excitation information based on the user grade, and further acquiring feedback information of the user based on the excitation information; and updating the user portrait based on the feedback information, and further updating the user grade according to the updated user portrait. Therefore, the user viscosity is enhanced, the data processing efficiency can be improved, and the success rate of data recommendation is improved.

It should be noted that, the data processing method provided in the embodiment of the present application is generally executed by the server 605, and accordingly, the data processing apparatus is generally disposed in the server 605.

It should be understood that the number of terminal devices, networks and servers in fig. 6 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to fig. 7, there is illustrated a schematic diagram of a computer system 700 suitable for use in implementing the terminal device of an embodiment of the present application. The terminal device shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data required for the operation of the computer system 700 are also stored. The CPU701, ROM702, and RAM703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

The following components are connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, and the like; an output section 707 including a Cathode Ray Tube (CRT), a liquid crystal credit authorization query processor (LCD), and the like, and a speaker, and the like; a storage section 708 including a hard disk or the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read therefrom is mounted into the storage section 708 as necessary.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments disclosed herein include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709, and/or installed from the removable medium 711. The above-described functions defined in the system of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 701.

It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having 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. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present application may be implemented by software, or may be implemented by hardware. The described units may also be provided in a processor, for example, described as: a processor includes a first acquisition unit, a model generation unit, a rank determination unit, a second acquisition unit, and an update unit. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

As another aspect, the present application also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to obtain a corresponding user identification in response to obtaining user transaction data, and obtain a corresponding user representation according to the user identification; generating a classification model based on the user representation; invoking a classification model to determine a user rating based on the user transaction data; generating excitation information based on the user grade, and further acquiring feedback information of the user based on the excitation information; and updating the user portrait based on the feedback information, and further updating the user grade according to the updated user portrait.

The computer program product of the present application comprises a computer program which, when executed by a processor, implements the data processing method in the embodiments of the present application.

According to the technical scheme of the embodiment of the application, the user viscosity is enhanced, the data processing efficiency can be improved, and the success rate of data recommendation is improved.

The above embodiments do not limit the scope of the application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application are intended to be included within the scope of the present application.

Claims (16)

1. A method of data processing, comprising:

responding to the obtained user transaction data, obtaining a corresponding user identifier, and obtaining a corresponding user portrait according to the user identifier;

generating a classification model based on the user representation;

invoking the classification model to determine a user rating based on the user transaction data;

generating excitation information based on the user grade, and further acquiring feedback information of a user based on the excitation information;

and updating the user portrait based on the feedback information, and further updating the user grade according to the updated user portrait.

2. The method of claim 1, wherein the obtaining the corresponding user representation from the user identification comprises:

and obtaining the user portrait corresponding to the user identifier in each preset dimension.

3. The method of claim 2, wherein the generating a classification model based on the user representation comprises:

acquiring a user grade label corresponding to the user image corresponding to each preset dimension;

and taking the user portrait corresponding to each preset dimension as input of an initial neural network model, taking the corresponding user grade label as expected output of the initial neural network model, training the initial neural network model, and finally generating a classification model.

4. The method of claim 1, wherein the determining the user level comprises:

generating a current user portrait according to the user transaction data;

and inputting the current user portrait to the classification model to output a corresponding user grade.

5. The method of claim 1, wherein the generating excitation information comprises:

invoking a class library to determine a corresponding next class according to the user class;

and acquiring the next-level preference information corresponding to the next level, and further generating excitation information based on the next-level preference information, the user level and the next level.

6. The method of claim 5, wherein the generating incentive information based on the offer information, the user level, and the next level comprises:

acquiring current grade preference information corresponding to the user grade, and further generating preference difference information based on the current grade preference information and the next grade preference information;

and generating incentive information based on the preferential difference information, the user grade and the next grade.

7. The method of claim 1, wherein after the updating the user level based on the updated user representation, the method further comprises:

and determining user preference information based on the updated user grade, generating a data report based on the user preference information, and sending the data report to a preset processing node.

8. A data processing apparatus, comprising:

the first acquisition unit is configured to respond to the acquisition of the user transaction data, acquire a corresponding user identifier and acquire a corresponding user portrait according to the user identifier;

a model generation unit configured to generate a classification model based on the user representation;

A ranking determination unit configured to invoke the classification model to determine a user ranking based on the user transaction data;

the second acquisition unit is configured to generate excitation information based on the user grade, and further acquire feedback information of a user based on the excitation information;

and an updating unit configured to update the user portrait based on the feedback information, and further update the user level based on the updated user portrait.

9. The apparatus of claim 8, wherein the first acquisition unit is further configured to:

and obtaining the user portrait corresponding to the user identifier in each preset dimension.

10. The apparatus of claim 9, wherein the model generation unit is further configured to:

acquiring a user grade label corresponding to the user image corresponding to each preset dimension;

and taking the user portrait corresponding to each preset dimension as input of an initial neural network model, taking the corresponding user grade label as expected output of the initial neural network model, training the initial neural network model, and finally generating a classification model.

11. The apparatus of claim 8, wherein the rank determination unit is further configured to:

generating a current user portrait according to the user transaction data;

and inputting the current user portrait to the classification model to output a corresponding user grade.

12. The apparatus of claim 8, wherein the second acquisition unit is further configured to:

invoking a class library to determine a corresponding next class according to the user class;

and acquiring the next-level preference information corresponding to the next level, and further generating excitation information based on the next-level preference information, the user level and the next level.

13. The apparatus of claim 12, wherein the second acquisition unit is further configured to:

acquiring current grade preference information corresponding to the user grade, and further generating preference difference information based on the current grade preference information and the next grade preference information;

and generating incentive information based on the preferential difference information, the user grade and the next grade.

14. A data processing electronic device, comprising:

One or more processors;

storage means for storing one or more programs,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7.

15. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-7.

16. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-7.

Images