CN113222760A - User data processing method and related device - Google Patents
User data processing method and related device Download PDFInfo
- Publication number
- CN113222760A CN113222760A CN202110549032.7A CN202110549032A CN113222760A CN 113222760 A CN113222760 A CN 113222760A CN 202110549032 A CN202110549032 A CN 202110549032A CN 113222760 A CN113222760 A CN 113222760A
- Authority
- CN
- China
- Prior art keywords
- transaction
- data
- user
- classification model
- transaction data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a user data processing method and a related device. The method comprises the steps of obtaining transaction data of a user, inputting the transaction data into a pre-trained user classification model to obtain a user grading result, and screening target users according to the user grading result, wherein the target users comprise users capable of participating in a preset event. The method and the device solve the technical problem that the target users cannot be well distinguished. According to the method and the system, the client types are distinguished after the client figures are determined through multiple dimensions, and related activities of target clients participating in the platform are reserved.
Description
Technical Field
The present application relates to the field of computers, and in particular, to a user data processing method and a related apparatus.
Background
The merchant of the platform can regularly organize marketing activities, and user stickiness is improved.
Some users will generate a lot of unreal transactions in order to participate in the platform marketing activities, and actually for the activity amount of the merchant, the real target customers cannot effectively participate in the platform marketing activities, so that the target customers are lost.
Aiming at the problem that the target users cannot be well distinguished in the related technology, an effective solution is not provided at present.
Disclosure of Invention
The present application mainly aims to provide a user data processing method and a related apparatus, so as to solve the problem that a target user cannot be well distinguished.
In order to achieve the above object, according to one aspect of the present application, there is provided a user data processing method.
The user data processing method comprises the following steps: acquiring transaction data of a user, wherein the transaction data at least comprises one of the following data: the system comprises a transaction amount, a transaction channel and a transaction completion condition, wherein the transaction completion condition is recorded after the user pays the transaction amount through a preset transaction channel; inputting the transaction data into a pre-trained user classification model to obtain a user grade division result, wherein the user classification model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: user positive sample data for normal transactions and user negative sample data for abnormal transactions; and screening target users according to the user grade division result, wherein the target users comprise users capable of participating in preset events.
Further, before inputting the transaction data into the pre-trained user classification model, the method further includes: judging whether the transaction statistics number of the same user in the transaction data and the same merchant in a preset time period exceeds a first target threshold value; if the transaction statistics number of the same user in the transaction data and the same merchant in a preset time period does not exceed a first target threshold value, inputting the transaction data serving as a positive sample into a pre-trained user classification model; and if the transaction statistics number of the same user in the transaction data and the same merchant in a preset time period is judged to exceed a first target threshold, inputting the transaction data serving as a negative sample into a pre-trained user classification model.
Further, inputting the transaction data into a pre-trained user classification model, comprising: determining whether the effective transaction statistical number of each transaction channel exceeds a second target threshold value according to different transaction channels; if the effective transaction statistical number of each transaction channel is determined to exceed a second target threshold value according to different transaction channels, inputting the transaction data serving as a negative sample into a pre-trained user classification model; and if the effective transaction statistical number of each transaction channel does not exceed the second target threshold value according to different transaction channels, inputting the transaction data serving as a positive sample into a pre-trained user classification model.
Further, inputting the transaction data into a pre-trained user classification model, comprising: judging whether the transaction amount in the transaction data meets a third target threshold value; if the transaction amount in the transaction data is judged to meet a third target threshold, inputting the transaction data serving as a positive sample into a pre-trained user classification model; if the transaction amount in the transaction data is judged not to meet the third target threshold, inputting the transaction data serving as a negative sample into a pre-trained user classification model;
further, inputting the transaction data into a pre-trained user classification model, comprising: judging whether goods return transaction occurs in the transaction data; and if the return transaction occurs in the transaction data, deducting the transaction statistical number and the corresponding amount, and inputting the transaction data serving as a negative sample into a pre-trained user classification model.
Further, screening out target users according to the user ranking result, wherein the target users include users who can participate in a preset event, and the screening comprises the following steps: acquiring a merchant and a customer, a transaction type, a transaction channel, a transaction amount, a transaction currency, transaction time and transaction frequency of the transaction according to the transaction amount, the transaction channel and the transaction completion condition in the transaction data; calculating the user grading result based on the merchant and the customer of the transaction, the transaction type, the transaction channel, the transaction amount, the transaction currency, the transaction time and the transaction frequency; and screening out users who can participate in the preset event and/or users who cannot participate in the preset event according to the user grading result.
Further, the inputting the transaction data into a pre-trained user classification model to obtain a user classification result includes: and optimizing parameters in the user classification model according to the transaction data accumulated for multiple times so as to verify the authenticity of the transaction completion condition in the transaction data.
In order to achieve the above object, according to another aspect of the present application, there is provided a user data processing apparatus.
The user data processing apparatus according to the present application includes: the acquisition module is used for acquiring transaction data of a user, wherein the transaction data at least comprises one of the following data: the system comprises a transaction amount, a transaction channel and a transaction completion condition, wherein the transaction completion condition is recorded after the user pays the transaction amount through a preset transaction channel; the classification model module is used for inputting the transaction data into a pre-trained user classification model to obtain a user grade division result, wherein the user classification model is obtained by using a plurality of groups of data through machine learning training, and each group of data in the plurality of groups of data comprises: user positive sample data for normal transactions and user negative sample data for abnormal transactions; and the screening module is used for screening target users according to the user grade division result, wherein the target users comprise users capable of participating in preset events.
In order to achieve the above object, according to yet another aspect of the present application, a storage medium is provided, in which a computer program is stored, wherein the computer program is arranged to perform the method when running.
In order to achieve the above object, according to yet another aspect of the present application, there is provided an electronic device comprising a memory and a processor, the memory having a computer program stored therein, the processor being configured to execute the computer program to perform the method.
In the embodiment of the application, the user data processing method and the related device adopt the method of acquiring the transaction data of the user, wherein the transaction data at least comprises one of the following steps: the method comprises the steps that a transaction amount, a transaction channel and a transaction completion condition are recorded after a user pays the transaction amount through a preset transaction channel, a user grade division result is obtained by inputting transaction data into a pre-trained user classification model, and a target user is screened according to the user grade division result, wherein the target user comprises a user who can participate in a preset event, so that the technical effects of providing accurate customer figures, distinguishing the types of customers and reserving marketing activities of high-quality customers to participate in a platform are achieved, and the technical problem that the target user cannot be well distinguished is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
fig. 1 is a schematic diagram of a hardware structure implemented by a user data processing method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart diagram illustrating a user data processing method according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a user data processing apparatus according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. 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.
The inventor finds that if the platform wants to judge the condition of the identity of the client participating in the marketing campaign, the accumulated amount of the transaction for a period of time is mainly considered, the authenticity of the transaction is not limited, and further the result of the marketing campaign is inconsistent with the starting point of the development of the campaign, so that the real client cannot enjoy the campaign reward, and the campaign reward is changed into a commodity which is benefited by a woolen party.
Such situations typically occur including the following:
1) creating an unreal transaction. In order to meet the transaction amount of the activity, a wool party (a user who does not normally transact) can do single large-amount transaction or multiple small-amount transactions at a cooperative merchant, the transactions are not normal consumption transaction behaviors, and the return transaction is done after the marketing activity is participated, so that the activity budget and the activity investment are wasted by the marketing activity host.
2) Real customers cannot effectively participate in marketing campaigns. Due to the specialized and team development of the wool party, independent customers can not compete with the wool party fairly in the aspects of the timeliness of the shopping process and the marketing activity, so that the real customer participation willingness is reduced, and further the authenticity of the activity and the activity holding party are negatively influenced, and the customer loss is caused.
In view of the above, the inventor proposes a user data processing method, which calculates the corresponding value of a customer by analyzing the transaction behavior of the customer to distinguish the quality level of the customer, thereby providing a reference for distinguishing the target users of the marketing campaign capable of participating in the platform.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1, the hardware structure for implementing the present application includes: a user (client) 1, a terminal (PC terminal, mobile terminal) 2, and a background server 3. The background server 3 is configured to implement a user data processing method. And the user 1 participates in the marketing activities of the platform through the terminal 2, and judges and screens out target users in the background server 3.
As shown in fig. 2, the method includes steps S201 to S203 as follows:
step S201, acquiring transaction data of a user, wherein the transaction data at least includes one of the following: the system comprises a transaction amount, a transaction channel and a transaction completion condition, wherein the transaction completion condition is recorded after the user pays the transaction amount through a preset transaction channel;
step S202, inputting the transaction data into a pre-trained user classification model to obtain a user grade division result, wherein the user classification model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: user positive sample data for normal transactions and user negative sample data for abnormal transactions;
step S203, screening out target users according to the user grade division result, wherein the target users comprise users capable of participating in preset events.
From the above description, it can be seen that the following technical effects are achieved by the present application:
acquiring transaction data of a user, wherein the transaction data at least comprises one of the following data: the method comprises the steps that a transaction amount, a transaction channel and a transaction completion condition are recorded after a user pays the transaction amount through a preset transaction channel, a user grade division result is obtained by inputting transaction data into a pre-trained user classification model, and a target user is screened according to the user grade division result, wherein the target user comprises a user who can participate in a preset event, so that the technical effects of providing accurate customer figures, distinguishing the types of customers and reserving marketing activities of high-quality customers to participate in a platform are achieved, and the technical problem that the target user cannot be well distinguished is solved.
In step S201, the transaction data of the user is obtained through the backend server. Such transaction data may be obtained in real time or may comprise a record of historical transaction data.
As an alternative, the transaction data includes the transaction amount, i.e. the transaction amount generated when each transaction occurs will be recorded in the background server.
As an alternative embodiment, the transaction data includes a transaction channel, i.e. a transaction channel used by the background server to record each transaction occurrence, including offline or online.
As an alternative, the transaction data includes transaction completion, which requires recording transaction type, transaction currency, transaction time, transaction frequency, and the like. The transaction type may be a purchase or sale, a special (promotional) item or a complimentary item, etc. The transaction currency also needs to be recorded in the transaction completion. The transaction time includes the time at which the transaction is completed or the time at which a refund occurs. The transaction frequency records not only the number of user purchases but also the number of purchases made at the same merchant.
As a preferred embodiment, the transaction data includes a record of the transaction completion after the user pays the transaction amount through a preset transaction channel.
In the step S202, a user ranking result may be obtained by inputting the transaction data into a pre-trained user classification model, where the user ranking result includes a low user ranking, a medium user ranking, or a high user ranking, or corresponds to different user rankings according to a score. For example, the value of the customer can be predicted by analyzing the customer behavior, calculating the probability of normal or abnormal behavior of the customer, weighting and summarizing the probability conclusion of the behavior.
As an alternative embodiment, the user classification model is obtained by machine learning training using multiple sets of data, where each set of data in the multiple sets of data includes: user positive sample data for normal transactions and user negative sample data for abnormal transactions.
As a preferred implementation mode, different data provided by different marketing campaign organizers are trained and upgraded to generate personalized user classification models for the different marketing campaign organizers, so that personalized requirements of different marketing campaign organizers such as service features and customer characteristics can be met more accurately.
As a preferred implementation mode, as the use frequency of marketing campaign organizers increases and the processing data increases, that is, the sample data increases, the user classification model is trained more, and the obtained data model has higher pertinence, applicability and accuracy, so that the requirement of business development can be met.
In step S203, target users are screened out according to the user rating result output by the model, where the target users include users that can participate in a preset event.
As an alternative embodiment, the predetermined event includes, but is not limited to, a marketing campaign for the platform.
As a preferred embodiment, the preset event may further include a specified marketing campaign that the user with a preset rating may participate in.
As a preference in this embodiment, before inputting the transaction data into the pre-trained user classification model, the method further includes: judging whether the transaction statistics number of the same user in the transaction data and the same merchant in a preset time period exceeds a first target threshold value; if the transaction statistics number of the same user in the transaction data and the same merchant in a preset time period does not exceed a first target threshold value, inputting the transaction data serving as a positive sample into a pre-trained user classification model; and if the transaction statistics number of the same user in the transaction data and the same merchant in a preset time period is judged to exceed a first target threshold, inputting the transaction data serving as a negative sample into a pre-trained user classification model. And if the transaction statistics number of the same user in the transaction data and the same merchant in a preset time period does not exceed a first target threshold value, inputting the transaction data into a pre-trained user classification model as a positive sample, and otherwise, inputting the transaction data into the pre-trained user classification model as a negative sample.
In specific implementation, the risk that the same customer meets the requirement of transaction number of the activity rule in multiple transactions of the same merchant is reduced by limiting the transaction statistics number of the same merchant in a time period of one customer. The first target threshold is a threshold value of transaction statistics.
As an alternative embodiment, the data entered into the user classification model may be used not only as sample data, but also as newly generated transaction data.
As a preference in this embodiment, inputting the transaction data into a pre-trained user classification model includes: determining whether the effective transaction statistical number of each transaction channel exceeds a second target threshold value according to different transaction channels; if the effective transaction statistical number of each transaction channel is determined to exceed a second target threshold value according to different transaction channels, inputting the transaction data serving as a negative sample into a pre-trained user classification model; and if the effective transaction statistical number of each transaction channel does not exceed the second target threshold value according to different transaction channels, inputting the transaction data serving as a positive sample into a pre-trained user classification model.
When the method is specifically implemented, online transactions and offline transactions are distinguished according to channel standards, and effective statistics of transaction sources of different channels can be limited according to different channels. The second target threshold is a threshold of transaction statistics for transaction from different channel sources.
As an alternative embodiment, the data entered into the user classification model may be used not only as sample data, but also as newly generated transaction data.
As a preference in this embodiment, inputting the transaction data into a pre-trained user classification model includes: judging whether the transaction amount in the transaction data meets a third target threshold value; if the transaction amount in the transaction data is judged to meet a third target threshold, inputting the transaction data serving as a positive sample into a pre-trained user classification model; and if the transaction amount in the transaction data is judged not to meet the third target threshold, inputting the transaction data serving as a negative sample into a pre-trained user classification model.
When the transaction amount meets a certain amount, the transaction amount can reach the standard, and the amount reaching the standard is calculated according to the real transaction. If the transaction amount in the transaction data is judged to meet a third target threshold, inputting the transaction data serving as a positive sample into a pre-trained user classification model; and if the transaction amount in the transaction data is judged not to meet the third target threshold, inputting the transaction data serving as a negative sample into a pre-trained user classification model. The third target threshold is a threshold for a transaction amount.
As an alternative embodiment, the data entered into the user classification model may be used not only as sample data, but also as newly generated transaction data.
As a preference in this embodiment, inputting the transaction data into a pre-trained user classification model includes: judging whether goods return transaction occurs in the transaction data; and if the return transaction occurs in the transaction data, deducting the transaction statistical number and the corresponding amount, and inputting the transaction data serving as a negative sample into a pre-trained user classification model.
In the specific implementation, if the return transaction happens once, the original counting transaction number and the amount are deducted. And if the return transaction occurs in the transaction data, deducting the transaction statistical number and the corresponding amount, and inputting the transaction data serving as a negative sample into a pre-trained user classification model.
As a preferable preference in this embodiment, the screening out target users according to the user ranking result, where the target users include users who can participate in a preset event, includes: acquiring a merchant and a customer, a transaction type, a transaction channel, a transaction amount, a transaction currency, transaction time and transaction frequency of the transaction according to the transaction amount, the transaction channel and the transaction completion condition in the transaction data; calculating the user grading result based on the merchant and the customer of the transaction, the transaction type, the transaction channel, the transaction amount, the transaction currency, the transaction time and the transaction frequency; and screening out users who can participate in the preset event and/or users who cannot participate in the preset event according to the user grading result.
In particular implementations, for a given large data message,
the user ranking results are based on a learning model of the customer's value,
V＝(a(u,M),b(u,Type),c(u,Channle),d(u,Amount),e(u,Currency),f(u,DateTime),g(u,Rate))。
according to the formula, the merchant and the client a (u, M), the transaction Type, b (u, Type), the transaction channel c (u, Channle), the transaction Amount d (u, Amount), the transaction Currency e (u, Currency), the transaction time f (u, DateTime), the transaction frequency g (u, Rate) and other weights with different dimensions are calculated by analyzing the transaction behaviors of the client, so that the good and bad grades of the client are distinguished, and the good and bad grades are used for the division reference of the marketing campaign for distinguishing the client.
The existing about 80% of transaction data can be used to train each parameter of the formula, i.e. the corresponding numerical value is substituted into the formula, and each parameter in the formula is trained to approach the target data. And the obtained learning model is verified by using the residual existing data so as to ensure the accuracy of each parameter in the learning model.
Meanwhile, after the model training is finished, the method can be used for actual production practice, and can predict the quality of customers according to newly generated transaction behavior data to divide the customers.
As a preferable example in this embodiment, the inputting the transaction data into a pre-trained user classification model to obtain a user ranking result further includes: and optimizing parameters in the user classification model according to the transaction data accumulated for multiple times so as to verify the authenticity of the transaction completion condition in the transaction data.
During specific implementation, parameters in the user classification model are optimized according to the transaction data accumulated for multiple times, so that the authenticity of the transaction completion condition in the transaction data is verified. After the model is used for a period of time, the process of formula training is repeated by using newly provided big data, and corresponding parameters are adjusted, so that the formula is closer to the latest development direction.
It should 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 different than presented herein.
According to an embodiment of the present application, there is also provided a user data processing apparatus for implementing the above method, as shown in fig. 3, the apparatus including:
an obtaining module 301, configured to obtain transaction data of a user, where the transaction data includes at least one of: the system comprises a transaction amount, a transaction channel and a transaction completion condition, wherein the transaction completion condition is recorded after the user pays the transaction amount through a preset transaction channel;
a classification model module 302, configured to input the transaction data into a pre-trained user classification model to obtain a user classification result, where the user classification model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data includes: user positive sample data for normal transactions and user negative sample data for abnormal transactions;
and the screening module 303 is configured to screen out target users according to the user ranking result, where the target users include users who can participate in a preset event.
The obtaining module 301 obtains the transaction data of the user through a background server. Such transaction data may be obtained in real time or may comprise a record of historical transaction data.
As an alternative, the transaction data includes the transaction amount, i.e. the transaction amount generated when each transaction occurs will be recorded in the background server.
As an alternative embodiment, the transaction data includes a transaction channel, i.e. a transaction channel used by the background server to record each transaction occurrence, including offline or online.
As an alternative, the transaction data includes transaction completion, which requires recording transaction type, transaction currency, transaction time, transaction frequency, and the like. The transaction type may be a purchase or sale, a special (promotional) item or a complimentary item, etc. The transaction currency also needs to be recorded in the transaction completion. The transaction time includes the time at which the transaction is completed or the time at which a refund occurs. The transaction frequency records not only the number of user purchases but also the number of purchases made at the same merchant.
As a preferred embodiment, the transaction data includes a record of the transaction completion after the user pays the transaction amount through a preset transaction channel.
In the classification model module 302, the transaction data is input into a pre-trained user classification model, so as to obtain a user classification result, where the user classification result includes a low user classification level, a medium user classification level, a high user classification level, or corresponds to different user classifications according to the score. For example, the value of the customer can be predicted by analyzing the customer behavior, calculating the probability of normal or abnormal behavior of the customer, weighting and summarizing the probability conclusion of the behavior.
As an alternative embodiment, the user classification model is obtained by machine learning training using multiple sets of data, where each set of data in the multiple sets of data includes: user positive sample data for normal transactions and user negative sample data for abnormal transactions.
As a preferred implementation mode, different data provided by different marketing campaign organizers are trained and upgraded to generate personalized user classification models for the different marketing campaign organizers, so that personalized requirements of different marketing campaign organizers such as service features and customer characteristics can be met more accurately.
As a preferred implementation mode, as the use frequency of marketing campaign organizers increases and the processing data increases, that is, the sample data increases, the user classification model is trained more, and the obtained data model has higher pertinence, applicability and accuracy, so that the requirement of business development can be met.
The screening module 303 screens out target users according to the user rating result output by the model, where the target users include users who can participate in a preset event.
As an alternative embodiment, the predetermined event includes, but is not limited to, a marketing campaign for the platform.
As a preferred embodiment, the preset event may further include a specified marketing campaign that the user with a preset rating may participate in.
It will be apparent to those skilled in the art that the modules or steps of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present application is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method for processing user data, comprising:
acquiring transaction data of a user, wherein the transaction data at least comprises one of the following data: the system comprises a transaction amount, a transaction channel and a transaction completion condition, wherein the transaction completion condition is recorded after the user pays the transaction amount through a preset transaction channel;
inputting the transaction data into a pre-trained user classification model to obtain a user grade division result, wherein the user classification model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: user positive sample data for normal transactions and user negative sample data for abnormal transactions;
and screening target users according to the user grade division result, wherein the target users comprise users capable of participating in preset events.
2. The method of claim 1, wherein prior to entering the transaction data into a pre-trained user classification model, further comprising:
judging whether the transaction statistics number of the same user in the transaction data and the same merchant in a preset time period exceeds a first target threshold value;
if the transaction statistics number of the same user in the transaction data and the same merchant in a preset time period does not exceed a first target threshold value, inputting the transaction data serving as a positive sample into a pre-trained user classification model;
and if the transaction statistics number of the same user in the transaction data and the same merchant in a preset time period is judged to exceed a first target threshold, inputting the transaction data serving as a negative sample into a pre-trained user classification model.
3. The method of claim 2, wherein inputting the transaction data into a pre-trained user classification model comprises:
determining whether the effective transaction statistical number of each transaction channel exceeds a second target threshold value according to different transaction channels;
if the effective transaction statistical number of each transaction channel is determined to exceed a second target threshold value according to different transaction channels, inputting the transaction data serving as a negative sample into a pre-trained user classification model;
and if the effective transaction statistical number of each transaction channel does not exceed the second target threshold value according to different transaction channels, inputting the transaction data serving as a positive sample into a pre-trained user classification model.
4. The method of claim 2, wherein inputting the transaction data into a pre-trained user classification model comprises:
judging whether the transaction amount in the transaction data meets a third target threshold value;
if the transaction amount in the transaction data is judged to meet a third target threshold, inputting the transaction data serving as a positive sample into a pre-trained user classification model;
and if the transaction amount in the transaction data is judged not to meet the third target threshold, inputting the transaction data serving as a negative sample into a pre-trained user classification model.
5. The method of claim 2, wherein inputting the transaction data into a pre-trained user classification model comprises:
judging whether goods return transaction occurs in the transaction data;
and if the return transaction occurs in the transaction data, deducting the transaction statistical number and the corresponding amount, and inputting the transaction data serving as a negative sample into a pre-trained user classification model.
6. The method according to claim 1, wherein the screening out target users according to the user ranking result, wherein the target users include users who can participate in a preset event, comprises:
acquiring a merchant and a customer, a transaction type, a transaction channel, a transaction amount, a transaction currency, transaction time and transaction frequency of the transaction according to the transaction amount, the transaction channel and the transaction completion condition in the transaction data;
calculating the user grading result based on the merchant and the customer of the transaction, the transaction type, the transaction channel, the transaction amount, the transaction currency, the transaction time and the transaction frequency;
and screening out users who can participate in the preset event and/or users who cannot participate in the preset event according to the user grading result.
7. The method of claim 1, wherein inputting the transaction data into a pre-trained user classification model to obtain a user ranking result further comprises:
and optimizing parameters in the user classification model according to the transaction data accumulated for multiple times so as to verify the authenticity of the transaction completion condition in the transaction data.
8. A user data processing apparatus, comprising:
the acquisition module is used for acquiring transaction data of a user, wherein the transaction data at least comprises one of the following data: the system comprises a transaction amount, a transaction channel and a transaction completion condition, wherein the transaction completion condition is recorded after the user pays the transaction amount through a preset transaction channel;
the classification model module is used for inputting the transaction data into a pre-trained user classification model to obtain a user grade division result, wherein the user classification model is obtained by using a plurality of groups of data through machine learning training, and each group of data in the plurality of groups of data comprises: user positive sample data for normal transactions and user negative sample data for abnormal transactions;
and the screening module is used for screening target users according to the user grade division result, wherein the target users comprise users capable of participating in preset events.
9. A storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 7 when executed.
10. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110549032.7A CN113222760A (en) | 2021-05-19 | 2021-05-19 | User data processing method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110549032.7A CN113222760A (en) | 2021-05-19 | 2021-05-19 | User data processing method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113222760A true CN113222760A (en) | 2021-08-06 |
Family
ID=77093328
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110549032.7A Pending CN113222760A (en) | 2021-05-19 | 2021-05-19 | User data processing method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113222760A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108550052A (en) * | 2018-04-03 | 2018-09-18 | 杭州呯嘭智能技术有限公司 | Brush list detection method and system based on user behavior data feature |
| CN109325640A (en) * | 2018-12-07 | 2019-02-12 | 中山大学 | User's Value Prediction Methods, device, storage medium and equipment |
| CN110009417A (en) * | 2019-04-02 | 2019-07-12 | 深圳前海微众银行股份有限公司 | Target customer's screening technique, device, equipment and computer readable storage medium |
| CN110717537A (en) * | 2019-10-08 | 2020-01-21 | 支付宝(杭州)信息技术有限公司 | Method and device for training user classification model and executing user classification prediction |
-
2021
- 2021-05-19 CN CN202110549032.7A patent/CN113222760A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108550052A (en) * | 2018-04-03 | 2018-09-18 | 杭州呯嘭智能技术有限公司 | Brush list detection method and system based on user behavior data feature |
| CN109325640A (en) * | 2018-12-07 | 2019-02-12 | 中山大学 | User's Value Prediction Methods, device, storage medium and equipment |
| CN110009417A (en) * | 2019-04-02 | 2019-07-12 | 深圳前海微众银行股份有限公司 | Target customer's screening technique, device, equipment and computer readable storage medium |
| CN110717537A (en) * | 2019-10-08 | 2020-01-21 | 支付宝(杭州)信息技术有限公司 | Method and device for training user classification model and executing user classification prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110033314B (en) | Advertisement data processing method and device | |
| CN107657486A (en) | A kind of advertisement placement method and device | |
| US20170372338A1 (en) | Trend-factored rfm scores to improve campaign performance | |
| EP3764303A1 (en) | Information processing device, etc. for calculating prediction data | |
| CN107067274A (en) | One DSP real time bid ad system based on blended learning model | |
| CN109428910B (en) | Data processing method, device and system | |
| CN108460627A (en) | Marketing activity scheme method for pushing, device, computer equipment and storage medium | |
| US20170300832A1 (en) | Cross-channel predictive model | |
| US10832262B2 (en) | Modeling consumer activity | |
| CN110009417A (en) | Target customer's screening technique, device, equipment and computer readable storage medium | |
| CN110880127A (en) | Consumption level prediction method and device, electronic equipment and storage medium | |
| CN111311332A (en) | User data processing method and device | |
| CN113674013A (en) | Advertisement bidding adjustment method and system based on merchant self-defined rules | |
| CN107330709B (en) | Method and device for determining target object | |
| CN114691740A (en) | Method, device and equipment for determining user rights and interests and computer storage medium | |
| Mzoughia et al. | An improved customer lifetime value model based on Markov chain | |
| CN113139826A (en) | Method and device for determining distribution authority of advertisement space and computer equipment | |
| CN113222760A (en) | User data processing method and related device | |
| US11403668B2 (en) | Multitask transfer learning for optimization of targeted promotional programs | |
| PUŠNAR et al. | Improving Direct Marketing Activities Effectiveness Using Analytical Models: rfm vs. Logit Model on a Casino Case. | |
| CN115034685A (en) | Customer value evaluation method, customer value evaluation device and computer-readable storage medium | |
| CN115063178A (en) | Method and device for determining sensitivity degree of target group to service scene | |
| CN112862223A (en) | Method and device for evaluating business activity value, decision method, equipment and medium | |
| Hanner et al. | Counting Customers in Mobile Business–The Case of Free to Play | |
| Noor et al. | Telecom Customer’s Segmentation Using Decision Tree to Increase Active Electronic Money Subscribers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |