CN107066518B - Data processing method and system - Google Patents
Data processing method and system Download PDFInfo
- Publication number
- CN107066518B CN107066518B CN201710068706.5A CN201710068706A CN107066518B CN 107066518 B CN107066518 B CN 107066518B CN 201710068706 A CN201710068706 A CN 201710068706A CN 107066518 B CN107066518 B CN 107066518B
- Authority
- CN
- China
- Prior art keywords
- variable
- user
- data processing
- representative
- determining
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
Abstract
The embodiment of the application provides a data processing method and a system, wherein the method comprises the following steps: determining a variable set to be selected and variable values thereof according to specific service data of a first user group; the first user group comprises a user group provided with a data processing mode of a specific service; determining a representative variable and a weight thereof according to the variable set to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof; obtaining a variable value of a representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user; the second user comprises a user who does not set the data processing mode of the specific service. The embodiment of the application can improve the first processing success rate and the processing efficiency of data processing.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a data processing method and system.
Background
In the field of data processing, selection of a data processing method is sometimes involved. For example, when the data processing mode is preset by the user, the data processing mode set by the user can be used as the data processing mode of the specific service of the user. When the data processing mode is not preset by the user, the data processing mode can be processed according to a default data processing mode, or a data processing mode is recommended to the user based on user preference and the like to be used as the data processing mode of the specific service of the user.
However, the inventor of the present application finds that, in the prior art, when a data processing manner is recommended for a user based on user preferences, some factors are often selected empirically to extract the user preferences, which may cause some important factors to be ignored, so that the obtained user preferences may not be consistent with the real user preferences of the user, and the data processing manner recommended for the user based on the obtained user preferences may have problems. Therefore, in some service scenarios, the above scheme for automatically recommending a data processing mode to a user may not be applicable, and thus the success rate and processing efficiency of data processing for the first time are affected.
Disclosure of Invention
An object of the embodiments of the present application is to provide a data processing method and system, so as to improve a first-time processing success rate and processing efficiency of data processing.
To achieve the above object, in one aspect, an embodiment of the present application provides a data processing method, including the following steps:
determining a variable set to be selected and variable values thereof according to specific service data of a first user group; the first user group comprises a user group provided with a data processing mode of a specific service;
determining a representative variable and a weight thereof according to the variable set to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof;
obtaining a variable value of a representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user; the second user comprises a user who does not set the data processing mode of the specific service.
On the other hand, an embodiment of the present application further provides a data processing system, including:
the variable acquisition module is used for determining a variable set to be selected and variable values thereof according to the specific service data of the first user group; the first user group comprises a user group provided with a data processing mode of a specific service;
the model acquisition module is used for determining a representative variable and the weight thereof according to the variable set to be selected and the variable value thereof and determining a prediction model according to the representative variable and the weight thereof;
the mode determining module is used for acquiring the variable value of the representative variable of each second user and determining the data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user; the second user comprises a user who does not set the data processing mode of the specific service.
In another aspect, an embodiment of the present application further provides another data processing method, including the following steps:
receiving a data task to be processed of a specific service;
when the user corresponding to the data task to be processed is a second user, matching a corresponding data processing mode from a preset data processing mode set according to the user identification of the user; the data processing mode set is obtained in advance through the following steps:
determining a variable set to be selected and variable values thereof according to specific service data of a first user group; the first user group comprises a user group provided with a data processing mode of a specific service;
determining a representative variable and a weight thereof according to the variable set to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof;
obtaining a variable value of a representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user; the second user comprises a user who does not set the data processing mode of the specific service.
In another aspect, an embodiment of the present application further provides another data processing system, including:
a processor;
a memory for storing data processing means;
wherein, when the data processing device is processed by the processor, the following steps are executed:
receiving a data task to be processed of a specific service;
when the user corresponding to the data task to be processed is a second user, matching a corresponding data processing mode from a preset data processing mode set according to the user identification of the user; the data processing mode set is obtained in advance through the following steps:
determining a variable set to be selected and variable values thereof according to specific service data of a first user group; the first user group comprises a user group provided with a data processing mode of a specific service;
determining a representative variable and a weight thereof according to the variable set to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof;
obtaining a variable value of a representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user; the second user comprises a user who does not set the data processing mode of the specific service.
Therefore, in the embodiment of the application, the variable set to be selected can be determined according to the specific service data of the first user provided with the data processing mode of the specific service; then selecting representative variables from the variable set to be selected, and determining a prediction model by the representative variables; and then predicting the data processing mode of the second user according to the prediction model and by combining the representative variable of the second user which is not provided with the data processing mode of the specific service. The prediction model learns the user preference of the first user, and statistics show that the first-time processing success rate and the processing efficiency of data processing of the first user are very high; therefore, when data processing is subsequently performed on the specific service of the second user based on the prediction model and in combination with the user environment of the second user, the first-time processing success rate and the processing efficiency of the data processing can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort. In the drawings:
FIG. 1 is a flow chart of a data processing method according to an embodiment of the present application;
FIG. 2 is a flow chart of a data processing method according to another embodiment of the present application;
FIG. 3 is a block diagram of a data processing system according to an embodiment of the present application;
fig. 4 is a block diagram of a data processing system according to another embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, 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 a part of the embodiments of the present application, and not all of the 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.
Referring to fig. 1, a data processing method according to an embodiment of the present application includes the following steps:
s101, determining a variable set to be selected and variable values thereof according to specific service data of a first user group; the first user group comprises a user group provided with a data processing mode of a specific service.
In the embodiment of the application, generally, for any application, there are often a plurality of users. In some cases, some applications allow a user to set the data processing mode of a specific service. However, statistics show that for various reasons, only a part of users often set the data processing mode of a specific service (such as a payment service, a download service, a search service, and the like), and the rest of users do not set the data processing mode. Therefore, there may be a part of users (i.e., first users) with data processing methods of specific services set therein and another part of users (i.e., second users) without data processing methods of specific services set therein.
In this embodiment, the specific service data of the first user group may include all service data of the first user group for the specific service. In another embodiment of the present application, the specific service data of the first user group may also include specific service data within a specified time range of the first user group. In an exemplary payment application scenario of the embodiment of the application, the specific service data of the first user group may include, for example, historical payment data within a specified time range of the first user group.
In the embodiment of the present application, the candidate variable set may generally include a plurality of candidate variables. Each candidate variable constitutes a user preference evaluation index or an evaluation dimension which affects the first user group. Therefore, theoretically, the more variables to be selected, the more comprehensive the consideration is, and the more realistic the user preference of the first user group can be reflected. In an exemplary payment application scenario of the present application, the set of variables to be selected may include, for example, a payment channel, a payment scenario, a payment time, a payment amount, and the like. Wherein the channel payment may include: wireless payment, PC payment, agreement payment, etc. The payment scenario may include, for example: paying in the same place, deducting money in batches, repaying house loan, repaying credit card, etc.
In the embodiment of the present application, the variable value of the candidate variable set is the variable value corresponding to each candidate variable, for example, if the service occurrence time of a specific service is taken as a candidate variable, the variable value corresponding to the candidate variable set may be 2016.11.06/12:05:53, 2016.11.10/18:15:24, 2016.11.21/09:20:03, and the like.
Of course, in the embodiment of the present application, for different applications or different services in the same application, the set of variables to be selected is generally different due to different services.
In an exemplary third party payment platform-based payment application scenario of the present application, the set of candidate variables may include a last payment time, a payment frequency, a payment amount, and the like of the first user group. Thus, the variables to be selected and the corresponding variable values thereof can be obtained as shown in the following table 1:
TABLE 1
The above table 1 lists only the candidate variable sets and their variable values of one first user in the first user group by way of example. The variables to be selected contained in the variable sets to be selected of other first users in the first user group are the same as the variables to be selected, and only the corresponding variable values are different.
And S102, determining a representative variable and a weight thereof according to the variable set to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof.
In the embodiment of the application, the influence degree value of each variable to be selected in the set of variables to be selected on the specified target variable can be determined based on a preset variable selection method; then, the specified number of variables to be selected with the maximum influence degree values are used as representative variables, and the corresponding influence degree values are used as the weights of the representative variables. And selecting a part of representative variables from the candidate variable set of the first user group as representative variables. Because the representative variables are preferably selected from all the variables to be selected through the variable selection method, the preferred representative variables in the embodiment of the application can better reflect the user preference of the first user group. In addition, the embodiment of the application does not utilize the candidate variable set, and the purpose of determining the prediction model by utilizing the representative variables is to greatly reduce the calculation amount and save the system resources.
In the embodiment of the present application, the variable selection method may be an Information entropy algorithm, an Information gain algorithm, an IV (Information Value) algorithm, or the like.
In an exemplary embodiment of the present application, the variable selection method may employ an IV algorithm. Specifically, if in a classification problem, the categories of the target variables are of two types: y1, Y2. For an individual A to be predicted, judging whether A belongs to Y1 or Y2, certain information is needed, if the total amount of the information is I, and the needed information is contained in all independent variables C1, C2, C3, … and Cn, the more information is contained in one variable Ci, the greater the contribution of the variable Ci to judging whether A belongs to Y1 or Y2 is, and the greater the information value of the variable Ci is; correspondingly, the larger the IV of Ci, the more Ci should be selected as a representative variable. The calculation formula of IV is as follows:
from the above formula, it can be seen that IV is equivalent to woeiA weighted sum of the values, woeiThe magnitude of the value determines the degree of influence of the independent variable on the target variable. Wherein, woeiReflecting negative example user G under each group i of argumentsiIs aligned with sample user BiRatio of the total weight of the sample to the total weight of the sample GTUser-to-ensemble positive sample user BTThe difference between the occupation ratios.
In an embodiment of the present application, when the representative variables are selected by using an IV algorithm, the independent variables are each to-be-selected variable in the to-be-selected variable set, and the target variable may be a target variable of two categories. Which variable is used as the target variable of the two categories can be determined according to specific application scenarios. For example:
in an exemplary payment application scenario based on a third party payment platform, a user may bind multiple bank cards on an account of the third party payment platform, different bank cards may have different uses, and common bank card uses include: house credit cards, car credit cards, ETC cards, consumer credit cards, and the like. Moreover, some users do not want the card with the designated purpose to be deducted; for example, the money in the user's house loan card is just enough for the next loan, but if the user uses the in-person payment of the third party payment platform before the bank deducts the money, the money in the user's house loan card is deducted; the user does not sense which card is paid and used in the current time, and just the user does not open the account change short message notice of the house credit card, so that the user does not know all the account change short message notice, and the house credit deduction is easy to fail, and the payment is overdue.
Whereas if the user sets the payment selection order for payment (i.e. the user is the first user), for example: the bank card A- > the bank card B- > the bank card C means that the user wants to pay by the bank card A firstly, if the payment of the bank card A fails, the payment is considered for deducting the money of the bank card B, and the like. Generally, the common degree of consumption credit cards is mostly higher than that of house credit cards, and the common cards are mostly higher in the first-time processing success rate of payment (no one is willing to actively find trouble for himself). With this fact, therefore, the exemplary embodiment of the present application makes a reasonable assumption: the more frequently used bank cards by the user, the higher the success rate of the first-time processing of payment, thus combining the predicted payment card preference with the predicted success rate of the first-time processing of payment. Specifically, one bank card with the highest selection priority set by the first user in the payment selection order may be set as a frequently-used card (denoted as 1), and the remaining bank cards set by the first user in the payment selection order may be set as non-frequently-used cards (denoted as 0), so that the frequently-used card 1 and the non-frequently-used card 0 may be used as a target variable of the second classification.
In the scenario of selecting the representative variables based on the IV algorithm, the IV algorithm may obtain an IV value of each candidate variable, and the IV values may be sorted according to size (for example, as shown in table 2 below), so as to select a plurality of candidate variables with the largest IV values as the representative variables. In the exemplary embodiment of the application, how many variables to be selected with the largest IV value are specifically selected as representative variables can be determined through an effect test.
TABLE 2
| Variables to be selected | IV value |
| V1 time of last payment | 1.59 |
| V2 time of success of last payment | 1.52 |
| V3 time of last payment failure | 1.48 |
| V4 days of Payment | … |
| V5 days of success of Payment | … |
| V6 days of failure to pay | … |
| V7 Total Payment | … |
| V8 Total amount of successful Payment | … |
| V9 Total failure Payment amount | … |
| V10 maximum Payment amount | … |
| V11 maximum amount of successful Payment | … |
| V12 maximum amount of failure to pay | … |
| V13 minimum Payment amount | … |
| V14 minimum amount of successful Payment | … |
| V15 minimum amount of failure to pay | … |
| V16 average amount paid | … |
| V17 average amount of successful payments | … |
| V18 average amount of failure to pay | … |
| ………… | … |
In the exemplary embodiment of the present application, after the representative variables are determined, the IV value corresponding to each representative variable may be determined as the weight of the representative variable, so that the prediction model may be determined according to the representative variables and the representative variables. For example, as shown in table 2 above, if V1, V2, and V3 are selected as representative variables, the determined predictive model can be expressed as a weighted sum of the variable values of the respective representative variables, as shown in the following equation:
F＝1.59V1+1.52V2+1.48V2。
s103, obtaining variable values of the representative variables of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable values of the representative variables of each second user; the second user comprises a user who does not set the data processing mode of the specific service.
In an embodiment of the application, after the prediction model is obtained, prediction can be performed according to the prediction model and by combining with a user environment of a second user which is not provided with a data processing mode of a specific service. The user environment of the second user, for which the data processing mode of the specific service is not set, may specify a variable value of the representative variable in a time range. Wherein the representative variables correspond to representative variables in the predictive model.
In this embodiment of the application, the data processing manner of the second user for the specific service may include, for example: a selection prioritization of particular data objects of the second user. Correspondingly, the determining, according to the prediction model and the variable value of the representative variable of each second user, the data processing manner of each second user for the specific service may be: substituting variable values of representative variables corresponding to each specific data object of a second user into the prediction model to obtain predicted values of the specific data object, and then sequencing the predicted values from large to small to serve as a data processing mode of the second user for the specific service; based on the similar processing mode, the data processing mode of each second user for the specific service can be predicted.
In an exemplary embodiment of the present application, if the prediction model is F ═ 1.59V1+1.52V2+1.48V2, there are three specific data objects a, b, and c for a second user X, according to the above method, the variable values of the representative variables (V1a, V2a, and V3a) corresponding to the specific data object a of the second user X can be obtained first, and then the prediction model is substituted to obtain the predicted value Fa of the specific data object a of the second user X, and similarly, the predicted value Fb of the specific data object b of the second user X and the predicted value Fc of the specific data object c can be obtained. And sequencing Fa, Fb and Fc in a descending order, and assuming that the sequencing result is Fa- > Fc- > Fb, the Fa- > Fc- > Fb is the data processing mode of the second user X for the specific service.
In an exemplary embodiment of the present application, the specific data object may be, for example, a payment selection sequence of each bank card bound to an account of a third party payment platform by the second user.
In an embodiment of the present application, after determining the representative variables and their weights according to the set of variables to be selected and their variable values, the method may further include:
and according to a normalization function with the slope decreasing exponentially, normalizing the variable values of the variable set to be selected to obtain the normalized variable values of the variable set to be selected.
Correspondingly, the determining a representative variable and a weight thereof according to the set of variables to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof may include:
determining a representative variable and a weight thereof according to the variable set to be selected and the normalized variable value, and determining a prediction model according to the representative variable and the weight thereof;
correspondingly, the obtaining the variable value of the representative variable of each second user may include:
and normalizing the variable value of the representative variable of each second user according to the normalization function to correspondingly obtain the normalized variable value of the representative variable of each second user.
In the embodiment of the application, a normalization function with an exponentially decreasing slope is selected, and the variable values of the variable set to be selected are normalized, so as to obtain information included in the variation of the variable values of similar variables such as the reaction times, the frequency and the like. For example, in a payment scenario, when the user pays for the first time, the historical frequency of payments changes from 0 to 1; when the user pays 100 th time, the historical payment frequency is changed from 99 th time to 100 th time. Although all are increased once, the payment frequency from 0 to 1 contains a larger amount of information than the payment frequency from 99 to 100. For example, the following steps are carried out: the user enters the social work from school graduation, and the debit card used in school to issue a prize money is used less frequently (becomes less frequently), but the historical cumulative use frequency is high due to long book reading time at school, and the historical use frequency is low due to new payroll cards issued by the company just being taken. Therefore, the payment of the old card is a relatively common one-time payment behavior, and the payment of the new card is a relatively special one-time payment behavior, which represents a certain transition of the life state of the user (embodied as the first payment after the user binds the card). And by adopting a normalization function with the slope in exponential decreasing, and performing normalization processing on the variable values of the variable sets to be selected, the difference can be better reflected, so that the user preference can be more accurately reflected by a subsequently obtained prediction model.
In an exemplary embodiment of the present application, the normalization Function with the exponentially decreasing slope may be, for example, a Logit Function, which is expressed by the following formula:
in an embodiment of the application, after the determining of the data processing manner of each second user for the specific service, the data processing manner of each second user for the specific service may be further updated periodically, so that the data processing manner of the user may adapt to the change of the user preference.
In the embodiment of the application, the variable set to be selected can be determined according to the specific service data of the first user provided with the data processing mode of the specific service; then selecting representative variables from the variable set to be selected, and determining a prediction model by the representative variables; and then predicting the data processing mode of the second user according to the prediction model and by combining the representative variable of the second user which is not provided with the data processing mode of the specific service. The prediction model learns the user preference of the first user, and statistics show that the first-time processing success rate and the processing efficiency of data processing of the first user are very high; therefore, when data processing is subsequently performed on the specific service of the second user based on the prediction model and in combination with the user environment of the second user, the first-time processing success rate and the processing efficiency of the data processing can be improved.
Referring to fig. 2, a data processing method according to an embodiment of the present application includes the following steps:
s201, receiving a data task to be processed of a specific service.
In the embodiment of the present application, the specific service may be any service of an application, such as a payment service, a download service, or a search service.
S202, when the user corresponding to the data task to be processed is a second user, matching a corresponding data processing mode from a preset data processing mode set according to the user identification of the user.
In the embodiment of the present application, the data processing method set is obtained in advance through the following steps:
determining a variable set to be selected and variable values thereof according to specific service data of a first user group; the first user group comprises a user group provided with a data processing mode of a specific service;
determining a representative variable and a weight thereof according to the variable set to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof;
obtaining a variable value of a representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user; the second user comprises a user who does not set the data processing mode of the specific service.
For the details of the corresponding relationship set, reference may be made to the method embodiment shown in fig. 1, which is not described herein again.
In an embodiment of the present application, in order to facilitate fast processing of data tasks, after predicting the data processing manner of each second user, the predicted data processing manners may form an ordered data processing manner set according to a corresponding relationship between the user identifier of the second user and the data processing manner thereof, for example, as shown in table 3 below:
TABLE 3
| User ID | Data processing mode ID | Data processing mode |
| 0001 | 001 | A1->A2->A3 |
| 0002 | 002 | B2->B4->B3->B1 |
| 0003 | 003 | C2->C1 |
In the embodiment of the application, whether the user is the first user or the second user can be determined in advance through a marking mode of the user ID. Therefore, when the data task to be processed of the specific service is received, the user type corresponding to the data task to be processed can be determined according to the user ID of the user corresponding to the data task to be processed. When the user corresponding to the data task to be processed is the second user, executing step S202; when the user corresponding to the data task to be processed is the first user, the data task to be processed can be processed directly according to the data processing mode which is set by the first user and aims at the specific service.
While the process flows described above include operations that occur in a particular order, it should be appreciated that the processes may include more or less operations that are performed sequentially or in parallel (e.g., using parallel processors or a multi-threaded environment).
Referring to fig. 3, a data processing system according to an embodiment of the present application includes:
the variable acquiring module 31 may be configured to determine a set of variables to be selected and variable values thereof according to specific service data of a first user group; the first user group comprises a user group provided with a data processing mode of a specific service;
the model obtaining module 32 may be configured to determine a representative variable and a weight thereof according to the set of variables to be selected and the variable value thereof, and determine a prediction model according to the representative variable and the weight thereof;
the mode determining module 33 may be configured to obtain a variable value of the representative variable of each second user, and determine, according to the prediction model and the variable value of the representative variable of each second user, a data processing mode of each second user for the specific service; the second user comprises a user who does not set the data processing mode of the specific service.
The data processing system of the embodiment of the present application corresponds to the method of the embodiment of the method shown in fig. 1, and therefore, specific details regarding the data processing system of the embodiment of the present application may refer to the embodiment of the method shown in fig. 1, which is not described herein again.
In the embodiment of the application, the variable acquisition module can determine a variable set to be selected according to the specific service data of the first user with the data processing mode of the specific service; the model acquisition module can select representative variables from the variable set to be selected and determine a prediction model by the representative variables; the mode determining module can predict the data processing mode of the second user according to the prediction model and by combining the representative variable of the second user which is not provided with the data processing mode of the specific service. The prediction model learns the user preference of the first user, and statistics show that the first-time processing success rate and the processing efficiency of data processing of the first user are very high; therefore, when data processing is subsequently performed on the specific service of the second user based on the prediction model and in combination with the user environment of the second user, the first-time processing success rate and the processing efficiency of the data processing can be improved.
Referring to fig. 4, the data processing system according to the embodiment of the present invention may include a processor, an internal bus, a memory, and the like in a hardware level, and may also include hardware required by other services. The processor reads a corresponding computer program from the memory into the memory and then runs the computer program, thereby forming the data processing device on a logic level. Of course, besides the software implementation, the embodiments of the present application do not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution main bodies of the following processing flows are not limited to each logic unit, and may also be hardware or logic devices. The memory is used for storing the data processing device; when the data processing device is processed by the processor, the following steps are executed:
receiving a data task to be processed of a specific service;
when the user corresponding to the data task to be processed is a second user, matching a corresponding data processing mode from a preset data processing mode set according to the user identification of the user; the data processing mode set is obtained in advance through the following steps:
determining a variable set to be selected and variable values thereof according to specific service data of a first user group; the first user group comprises a user group provided with a data processing mode of a specific service;
determining a representative variable and a weight thereof according to the variable set to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof;
obtaining a variable value of a representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user; the second user comprises a user who does not set the data processing mode of the specific service.
The data processing system of the embodiment of the present application corresponds to the method of the embodiment of the method shown in fig. 2, and therefore, specific details regarding the data processing system of the embodiment of the present application may refer to the embodiment of the method shown in fig. 2, which is not described herein again.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (16)
1. A data processing method, characterized by comprising the steps of:
determining a variable set to be selected and variable values thereof according to specific service data of a first user group; the first user group comprises a user group provided with a data processing mode of a specific service; at least one variable to be selected contained in the variables to be selected is used for forming a user preference evaluation index of the first user group;
determining a representative variable and a weight thereof according to the variable set to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof;
obtaining a variable value of a representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user; the second user comprises a user which does not set the data processing mode of the specific service; the second user corresponds to at least two specific data objects; the obtaining a variable value of the representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user, includes: substituting variable values of representative variables of each specific data object of the second user into the prediction model to obtain predicted values corresponding to the specific data objects; sorting the specific data objects according to the predicted values; and determining the sequencing result of the specific data object as the data processing mode of the second user for the specific service.
2. The data processing method of claim 1, wherein after determining the representative variables and their weights according to the set of variables to be selected and their variable values, further comprising:
according to a normalization function with the slope decreasing exponentially, normalizing the variable values of the variable set to be selected to obtain the normalized variable values of the variable set to be selected;
correspondingly, the determining a representative variable and a weight thereof according to the set of variables to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof, includes:
determining a representative variable and a weight thereof according to the variable set to be selected and the normalized variable value, and determining a prediction model according to the representative variable and the weight thereof;
correspondingly, the obtaining the variable value of the representative variable of each second user includes:
and normalizing the variable value of the representative variable of each second user according to the normalization function to correspondingly obtain the normalized variable value of the representative variable of each second user.
3. The data processing method according to claim 1 or 2, wherein the determining representative variables and weights thereof according to the set of variables to be selected and variable values thereof comprises:
determining the influence degree value of each variable to be selected in the variable set to be selected on the specified target variable according to a preset variable selection method;
and taking the specified number of variables to be selected with the maximum influence degree values as representative variables, and taking the corresponding influence degree values as the weights of the representative variables.
4. A data processing method according to claim 3, characterized in that the predictive model is a weighted sum of variable values of respective representative variables.
5. The data processing method according to claim 1, further comprising, after the determining the data processing manner for the specific service by each second user, the following steps:
and periodically updating the data processing mode of each second user for the specific service.
6. The data processing method according to claim 1 or 2, wherein the specific service data of the first user group comprises:
specific service data within a specified time range of the first group of users.
7. The data processing method of claim 1, wherein the specific service comprises:
payment traffic, search traffic, or download traffic.
8. A data processing system, comprising:
the variable acquisition module is used for determining a variable set to be selected and variable values thereof according to the specific service data of the first user group; the first user group comprises a user group provided with a data processing mode of a specific service; at least one variable to be selected contained in the variables to be selected is used for forming a user preference evaluation index of the first user group;
the model acquisition module is used for determining a representative variable and the weight thereof according to the variable set to be selected and the variable value thereof and determining a prediction model according to the representative variable and the weight thereof;
the mode determining module is used for acquiring the variable value of the representative variable of each second user and determining the data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user; the second user comprises a user which does not set the data processing mode of the specific service; the second user corresponds to at least two specific data objects; the obtaining a variable value of the representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user, includes: substituting variable values of representative variables of each specific data object of the second user into the prediction model to obtain predicted values corresponding to the specific data objects; sorting the specific data objects according to the predicted values; and determining the sequencing result of the specific data object as the data processing mode of the second user for the specific service.
9. A data processing method, characterized by comprising the steps of:
receiving a data task to be processed of a specific service;
when the user corresponding to the data task to be processed is a second user, matching a corresponding data processing mode from a preset data processing mode set according to the user identification of the second user; the data processing mode set is obtained in advance through the following steps:
determining a variable set to be selected and variable values thereof according to specific service data of a first user group; the first user group comprises a user group provided with a data processing mode of a specific service; at least one variable to be selected contained in the variables to be selected is used for forming a user preference evaluation index of the first user group;
determining a representative variable and a weight thereof according to the variable set to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof;
obtaining a variable value of a representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user; the second user comprises a user which does not set the data processing mode of the specific service; the second user corresponds to at least two specific data objects; the obtaining a variable value of the representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user, includes: substituting variable values of representative variables of each specific data object of the second user into the prediction model to obtain predicted values corresponding to the specific data objects; sorting the specific data objects according to the predicted values; and determining the sequencing result of the specific data object as the data processing mode of the second user for the specific service.
10. The data processing method of claim 9, wherein after determining the representative variables and their weights according to the set of variables to be selected and their variable values, further comprising:
according to a normalization function with the slope decreasing exponentially, normalizing the variable values of the variable set to be selected to obtain the normalized variable values of the variable set to be selected;
correspondingly, the determining a representative variable and a weight thereof according to the set of variables to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof, includes:
determining a representative variable and a weight thereof according to the variable set to be selected and the normalized variable value, and determining a prediction model according to the representative variable and the weight thereof;
correspondingly, the obtaining the variable value of the representative variable of each second user includes:
and normalizing the variable value of the representative variable of each second user according to the normalization function to correspondingly obtain the normalized variable value of the representative variable of each second user.
11. The data processing method according to claim 9 or 10, wherein the determining representative variables and weights thereof according to the set of variables to be selected and variable values thereof comprises:
determining the influence degree value of each variable to be selected in the variable set to be selected on the specified target variable according to a preset variable selection method;
and taking the specified number of variables to be selected with the maximum influence degree values as representative variables, and taking the corresponding influence degree values as the weights of the representative variables.
12. A data processing method according to claim 11, characterized in that the predictive model is a weighted sum of variable values of respective representative variables.
13. The data processing method according to claim 9, further comprising, after the determining the data processing manner for the specific service by each second user, the following steps:
and periodically updating the data processing mode of each second user for the specific service.
14. The data processing method according to claim 9 or 10, wherein the specific service data of the first user group comprises:
specific service data within a specified time range of the first group of users.
15. The data processing method of claim 9, wherein the specific service comprises:
payment traffic, search traffic, or download traffic.
16. A data processing system, comprising:
a processor;
a memory for storing data processing means;
wherein, when the data processing device is processed by the processor, the following steps are executed:
receiving a data task to be processed of a specific service;
when the user corresponding to the data task to be processed is a second user, matching a corresponding data processing mode from a preset data processing mode set according to the user identification of the second user; the data processing mode set is obtained in advance through the following steps:
determining a variable set to be selected and variable values thereof according to specific service data of a first user group; the first user group comprises a user group provided with a data processing mode of a specific service; at least one variable to be selected contained in the variables to be selected is used for forming a user preference evaluation index of the first user group;
determining a representative variable and a weight thereof according to the variable set to be selected and the variable value thereof, and determining a prediction model according to the representative variable and the weight thereof;
obtaining a variable value of a representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user; the second user comprises a user which does not set the data processing mode of the specific service; the second user corresponds to at least two specific data objects; the obtaining a variable value of the representative variable of each second user, and determining a data processing mode of each second user for the specific service according to the prediction model and the variable value of the representative variable of each second user, includes: substituting variable values of representative variables of each specific data object of the second user into the prediction model to obtain predicted values corresponding to the specific data objects; sorting the specific data objects according to the predicted values; and determining the sequencing result of the specific data object as the data processing mode of the second user for the specific service.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710068706.5A CN107066518B (en) | 2017-02-08 | 2017-02-08 | Data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710068706.5A CN107066518B (en) | 2017-02-08 | 2017-02-08 | Data processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107066518A CN107066518A (en) | 2017-08-18 |
| CN107066518B true CN107066518B (en) | 2021-01-08 |
Family
ID=59598746
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710068706.5A Active CN107066518B (en) | 2017-02-08 | 2017-02-08 | Data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107066518B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113837731A (en) * | 2018-04-04 | 2021-12-24 | 创新先进技术有限公司 | Preference setting and service processing system, method, device and equipment |
| CN111796513B (en) * | 2019-04-08 | 2022-09-09 | 阿里巴巴集团控股有限公司 | Data processing method and device |
| CN113077277A (en) * | 2020-01-06 | 2021-07-06 | 北京京邦达贸易有限公司 | Information processing apparatus and method |
| CN111382068B (en) * | 2020-02-29 | 2024-04-09 | 中国平安人寿保险股份有限公司 | Hierarchical testing method and device for large-batch data |
| CN111737166B (en) * | 2020-05-15 | 2023-04-07 | 完美世界(北京)软件科技发展有限公司 | Data object processing method, device and equipment |
| CN113469807B (en) * | 2021-08-31 | 2022-03-01 | 阿里云计算有限公司 | Credit risk determination and data processing method, apparatus, medium, and program product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6687696B2 (en) * | 2000-07-26 | 2004-02-03 | Recommind Inc. | System and method for personalized search, information filtering, and for generating recommendations utilizing statistical latent class models |
| CN104346372A (en) * | 2013-07-31 | 2015-02-11 | 国际商业机器公司 | Method and device for evaluating prediction models |
| CN104778176A (en) * | 2014-01-13 | 2015-07-15 | 阿里巴巴集团控股有限公司 | Data search processing method and device |
| CN104899315A (en) * | 2015-06-17 | 2015-09-09 | 百度在线网络技术（北京）有限公司 | Method and device for pushing user information |
| CN106202088A (en) * | 2015-05-04 | 2016-12-07 | 阿里巴巴集团控股有限公司 | A kind of method and system mating business scenario |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751234B (en) * | 2013-12-31 | 2018-10-19 | 华为技术有限公司 | A kind of prediction technique and device of user's assets |
| CN106126597A (en) * | 2016-06-20 | 2016-11-16 | 乐视控股（北京）有限公司 | User property Forecasting Methodology and device |
-
2017
- 2017-02-08 CN CN201710068706.5A patent/CN107066518B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6687696B2 (en) * | 2000-07-26 | 2004-02-03 | Recommind Inc. | System and method for personalized search, information filtering, and for generating recommendations utilizing statistical latent class models |
| CN104346372A (en) * | 2013-07-31 | 2015-02-11 | 国际商业机器公司 | Method and device for evaluating prediction models |
| CN104778176A (en) * | 2014-01-13 | 2015-07-15 | 阿里巴巴集团控股有限公司 | Data search processing method and device |
| CN106202088A (en) * | 2015-05-04 | 2016-12-07 | 阿里巴巴集团控股有限公司 | A kind of method and system mating business scenario |
| CN104899315A (en) * | 2015-06-17 | 2015-09-09 | 百度在线网络技术（北京）有限公司 | Method and device for pushing user information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107066518A (en) | 2017-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107066518B (en) | Data processing method and system | |
| CN108305158B (en) | Method, device and equipment for training wind control model and wind control | |
| CN108537568B (en) | Information recommendation method and device | |
| CN108764915B (en) | Model training method, data type identification method and computer equipment | |
| CN110852503B (en) | Payment channel selection method and device and payment channel route | |
| CN113643119A (en) | Model training method, business wind control method and business wind control device | |
| CN112966186A (en) | Model training and information recommendation method and device | |
| CN113222578A (en) | Payment method and device | |
| CN115238826B (en) | Model training method and device, storage medium and electronic equipment | |
| CN108920183B (en) | Service decision method, device and equipment | |
| CN109345221A (en) | The checking method and device of resource circulation | |
| CN114997472A (en) | Model training method, business wind control method and business wind control device | |
| CN110134860B (en) | User portrait generation method, device and equipment | |
| CN110033092B (en) | Data label generation method, data label training device, event recognition method and event recognition device | |
| CN113222649A (en) | Method and device for recommending service execution mode | |
| CN112163962A (en) | Method and device for model training and business wind control | |
| CN111325557A (en) | Detection method, device and equipment for merchant risk | |
| CN116485391A (en) | Payment recommendation processing method and device | |
| CN107392408B (en) | Credit score prompt information output method and device | |
| CN115049433A (en) | Model training method and device, storage medium and electronic equipment | |
| CN111523995B (en) | Method, device and equipment for determining characteristic value of model migration | |
| CN109389298B (en) | Service request checking method and device | |
| CN110738562B (en) | Method, device and equipment for generating risk reminding information | |
| CN112579292A (en) | Resource allocation method and device | |
| CN109389157B (en) | User group identification method and device and object group identification method and device |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1241511 Country of ref document: HK |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200925 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200925 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: Greater Cayman, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |