CN110264037A

CN110264037A - A kind for the treatment of method and apparatus of user data

Info

Publication number: CN110264037A
Application number: CN201910400073.2A
Authority: CN
Inventors: 王凯; 何慧梅
Original assignee: Alibaba Group Holding Ltd
Current assignee: Advanced New Technologies Co Ltd; Advantageous New Technologies Co Ltd
Priority date: 2019-05-14
Filing date: 2019-05-14
Publication date: 2019-09-20
Anticipated expiration: 2039-05-14
Also published as: CN110264037B; CN117421702A

Abstract

This application discloses a kind for the treatment of method and apparatus of user data, this method comprises: obtaining the behavioral data of catergories of user, the catergories of user is divided based on service label, includes the timing mark of multiple behavior events and the multiple behavior event in the behavioral data of a user；The timing of the behavior event and behavior event that include in behavioral data based on the catergories of user identifies, and determines the corresponding temporal sequence association rule of the catergories of user；Based on corresponding first temporal sequence association rule of target class user in the catergories of user and corresponding second temporal sequence association rule of non-target class user, the timing rule of conduct of the target class user is determined；Based on the timing rule of conduct of the target class user, determine whether user to be identified belongs to the target class user.

Description

A kind for the treatment of method and apparatus of user data

Technical field

This application involves data processing field more particularly to a kind for the treatment of method and apparatus of user data.

Background technique

In the prior art, it requires to analyze the behavioral data of user under many application scenarios, to carry out decision Processing.For example, in the scene of risk identification, can behavioral data and user to be identified to high risk user behavior number According to being analyzed, to determine whether user to be identified belongs to high risk user based on analysis result.

In general, certain behaviors whether user can occur, or occur when the behavioral data to user is analyzed The number of certain behaviors is analyzed.However, in practical applications, this data analysing method is typically more simple, it can not The behavioral data of user is sufficiently excavated, leads to not carry out effectively decision-making treatment.

Summary of the invention

The embodiment of the present application provides a kind for the treatment of method and apparatus of user data, for solving in the prior art due to not Can the behavioral data to user sufficiently excavated, lead to not the problem of decision-making treatment is effectively performed.

In order to solve the above technical problems, the embodiment of the present application is achieved in that

In a first aspect, proposing a kind of processing method of user data, comprising:

The behavioral data of catergories of user is obtained, the catergories of user is divided based on service label, the behavior number of a user Timing mark including multiple behavior events and the multiple behavior event in；

The timing of the behavior event and behavior event that include in behavioral data based on the catergories of user identifies, and determines The corresponding temporal sequence association rule of the catergories of user；

Based on corresponding first temporal sequence association rule of target class user in the catergories of user and non-target class user couple The second temporal sequence association rule answered determines the timing rule of conduct of the target class user；

Based on the timing rule of conduct of the target class user, determine whether user to be identified belongs to the target class and use Family.

Second aspect proposes a kind of processing unit of user data, comprising:

Acquiring unit obtains the behavioral data of catergories of user, and the catergories of user is divided based on service label, a user Behavioral data in include multiple behavior events and the multiple behavior event timing mark；

Processing unit, the timing of the behavior event and behavior event that include in the behavioral data based on the catergories of user Mark, determines the corresponding temporal sequence association rule of the catergories of user；

Determination unit, based on corresponding first temporal sequence association rule of target class user in the catergories of user and non-targeted Corresponding second temporal sequence association rule of class user, determines the timing rule of conduct of the target class user；

It is described to determine whether user to be identified belongs to based on the timing rule of conduct of the target class user for recognition unit Target class user.

The third aspect, proposes a kind of electronic equipment, which includes:

Processor；And

It is arranged to the memory of storage computer executable instructions, which makes the processor when executed Execute following operation:

Fourth aspect, proposes a kind of computer readable storage medium, the computer-readable recording medium storage one or Multiple programs, one or more of programs are when the electronic equipment for being included multiple application programs executes, so that the electronics Equipment executes following methods:

5th aspect, proposes a kind of processing method of user data, comprising:

Based on the corresponding temporal sequence association rule of the catergories of user, the timing rule of conduct of the catergories of user is determined；

Timing rule of conduct based on the catergories of user generates multiple timing rule of conduct features；

Based on the multiple timing rule of conduct feature, the timing behavioural characteristic of user to be processed is determined, include to generate The sample data of the timing behavioural characteristic carries out model training.

6th aspect, proposes a kind of processing unit of user data, comprising:

First determination unit, be based on the corresponding temporal sequence association rule of the catergories of user, determine the catergories of user when Sequence rule of conduct；

Generation unit, the timing rule of conduct based on the catergories of user generate multiple timing rule of conduct features；

Second determination unit is based on the multiple timing rule of conduct feature, determines that the timing behavior of user to be processed is special Sign, to generate the sample data progress model training for including the timing behavioural characteristic.

7th aspect, proposes a kind of electronic equipment, which includes:

Processor；And

Eighth aspect, proposes a kind of computer readable storage medium, the computer-readable recording medium storage one or Multiple programs, one or more of programs are when the electronic equipment for being included multiple application programs executes, so that the electronics Equipment executes following methods:

The embodiment of the present application use at least one above-mentioned technical solution can reach it is following the utility model has the advantages that

Technical solution provided by the embodiments of the present application, when the behavioral data to user is analyzed, due to fully considering The timing mark for the behavior event for including in behavioral data, it is thereby achieved that the abundant excavation to user behavior data；? When analyzing the behavioral data of catergories of user, due to can the behavioral data to catergories of user sufficiently excavated, obtain It is able to reflect the temporal sequence association rule of catergories of user behavior timing, and then obtains the timing rule of conduct of target class user, therefore, When the timing rule of conduct based on target class user carries out decision-making treatment, effectively decision-making treatment can be carried out.

Detailed description of the invention

In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this The some embodiments recorded in application, for those of ordinary skill in the art, in the premise of not making the creative labor property Under, it is also possible to obtain other drawings based on these drawings.

Fig. 1 is the flow diagram of the processing method of one embodiment user data of the application；

Fig. 2 is the flow diagram of the processing method of one embodiment user data of the application；

Fig. 3 is the structural schematic diagram of one embodiment electronic equipment of the application；

Fig. 4 is the structural schematic diagram of the processing unit of one embodiment user data of the application；

Fig. 5 is the structural schematic diagram of one embodiment electronic equipment of the application；

Fig. 6 is the structural schematic diagram of the processing unit of one embodiment user data of the application.

Specific embodiment

In order to make those skilled in the art better understand the technical solutions in the application, below in conjunction with the application reality The attached drawing in example is applied, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described implementation Example is merely a part but not all of the embodiments of the present application.Based on the embodiment in the application, this field is common The application protection all should belong in technical staff's every other embodiment obtained without creative efforts Range.

Below in conjunction with attached drawing, the technical scheme provided by various embodiments of the present application will be described in detail.

Fig. 1 is the flow diagram of the processing method of one embodiment user data of the application.The user data Processing method is as described below.

S102: the behavioral data of catergories of user is obtained.

In S102, catergories of user can divide to obtain based on service label, and service label can be based on specific application Scene determines, for example, service label may include high risk and low-risk, or may include height in risk identification scene Risk, risk and low-risk；In marketing scene, service label may include target user and non-targeted user.

The behavioral data of catergories of user can be the behavioral data of catergories of user in the set time period, the set period of time It can be not specifically limited here determine according to actual needs.

The present embodiment may comprise steps of when obtaining the behavioral data of catergories of user:

Firstly, obtaining the behavioral data of multiple users with different business label.

It may include multiple rows in the behavioral data of user when obtaining the behavioral data of user by taking a user as an example For the timing of event and multiple behavior event mark, wherein the timing mark of behavior event can characterize behavior event hair Raw sequencing.

For example, the behavior event of user A in a certain period of time includes event 1, event 2, event 3, event 4 and event 5, Wherein, event 1 to event 5 timing mark is followed successively by 2,4,1,3,5, then, the sequencing that event 1 to event 5 occurs according to It is secondary are as follows: event 3, event 1, event 4, event 2, event 5.

It should be noted that in the behavioral data of the multiple users obtained, the row that includes in the behavioral data of different user It may be the same or different for event, timing mark of the identical behavior event in the behavioral data of different user can phase Together, it can also be different, the number that same behavior event occurs in the behavioral data of a user can be once, be also possible to Repeatedly, it is not specifically limited here.

Secondly, being grouped according to behavioral data of the service label to multiple users, the behavioral data of catergories of user is obtained.

In grouping, the behavioral data of the user with identical services label can be divided into one group, obtain a kind of use The behavioral data at family, in this way, based on multiple and different service labels, the behavioral data of available catergories of user.

For example, in the scene of risk identification, it can be according to service label high risk and low-risk, by high risk user's Behavioral data is divided into one group, and the behavioral data of low-risk user is divided into one group, obtains the behavioral data of two class users.

After getting the behavioral data of catergories of user, S104 can be executed.

S104: the timing mark of the behavior event and behavior event that include in the behavioral data based on the catergories of user Know, determines the corresponding temporal sequence association rule of the catergories of user.

In S104, when determining the corresponding temporal sequence association rule of catergories of user, by taking one type user as an example, it can wrap Include following steps:

Firstly, the behavior event for including in the behavioral data based on a kind of user, determines frequent item set.

In the present embodiment, the number of frequent item set can be multiple, when determining frequent item set, can follow following original Then:

One behavior event occurs one or many in the behavioral data of a user, is calculated as primary, one frequently It include at least one behavior event in item collection, which at least occurs in the behavioral data of a user.

Secondly, the timing based on the behavior event for including in frequent item set and frequent item set identifies, one kind user is determined Corresponding temporal sequence association rule.

Specifically, by taking one of frequent item set as an example, when determining temporal sequence association rule, frequent item set pair can be determined The user answered, wherein the corresponding user of frequent item set can be understood as including the behavior thing in the frequent item set in behavioral data The user of part；It, can be according to the behavior event in frequent item set in frequent item set pair after obtaining the corresponding user of frequent item set Timing mark in the behavioral data of the user answered, obtains the corresponding temporal sequence association rule of frequent item set.

After obtaining the corresponding temporal sequence association rule of a frequent item set, it can be obtained based on identical method multiple frequent The corresponding temporal sequence association rule of item collection, the corresponding temporal sequence association rule of multiple frequent item sets are that the corresponding timing of a kind of user is closed Connection rule.

In order to make it easy to understand, can be illustrated for including 3 users in a kind of user below.

Assuming that include 3 users A, B, C in a kind of user, the behavior event for including in the behavioral data of user A, B and C and The timing mark of behavior event is as shown in table 1.

Table 1

User	Behavior event	The timing of behavior event identifies
			A	1	1
A	2	2
			A	3	3
A	4	4
			B	1	1
B	2	2
			B	3	3
B	4	4
			C	1	1
C	3	2
			C	5	3

When determining the corresponding temporal sequence association rule of user A, B, C, firstly, the behavior thing based on user A, B, C in table 1 Part, available following multiple frequent item sets:

(1), (2), (3), (4), (5), (1,2), (1,3), (Isosorbide-5-Nitrae), (1,5), (2,3), (2,4), (3,4), (3,5) (1,2,3), (1,2,4), (1,3,4), (1,3,5), (2,3,4), (1,2,3,4).

Secondly, can determine that the corresponding user of the frequent item set is user A for one of frequent item set (1,2) With user B, the timing based on event 1 and event 2 in the behavioral data of user A and user B is identified, available frequent item set (1,2) corresponding temporal sequence association rule 1 → 2 (→ can also be indicated by other modes).

For other frequent item sets, it can be based on identical method, obtain corresponding temporal sequence association rule, and then obtain The corresponding temporal sequence association rule of user A, B, C:

1,2,3,4,5,1 → 2,1 → 3,1 → 4,1 → 5,2 → 3,2 → 4,3 → 4,3 → 5,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4,1 → 3 → 5,2 → 3 → 4,1 → 2 → 3 → 4.

It optionally,, can also be to more after obtaining multiple frequent item sets during above-mentioned determining temporal sequence association rule A frequent item set is screened, and filters out the frequent item set that length is less than or equal to preset threshold, wherein the length of frequent item set can To be interpreted as the number for the behavior event for including in frequent item set, preset threshold can be determine according to actual needs.

It, can be based on the frequent item set after screening and the frequent episode after screening after being screened to multiple frequent item sets The timing for the behavior event that concentration includes identifies, and obtains temporal sequence association rule.

Still by taking above-mentioned 3 users A, B, C as an example, after obtaining multiple frequent item sets, it can filter out in multiple frequent item sets The frequent item set that length is 1 obtains the frequent item set that length is equal to and more than 2, is based on these frequent item sets and these are frequent The timing for the behavior event for including in item collection identifies, available following temporal sequence association rule:

1 → 2,1 → 3,1 → 4,1 → 5,2 → 3,2 → 4,3 → 4,3 → 5,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4,1 → 3 → 5,2 → 3 → 4,1 → 2 → 3 → 4.

After the method based on above-mentioned record obtains the corresponding temporal sequence association rule of a kind of user, identical side can be based on Method obtains the corresponding temporal sequence association rule of other classes user.

After obtaining the corresponding temporal sequence association rule of catergories of user, S106 can be executed.

S106: it is used based on corresponding first temporal sequence association rule of target class user in the catergories of user and non-target class Corresponding second temporal sequence association rule in family, determines the timing rule of conduct of the target class user.

In S106, target class user can be understood as a kind of user of timing rule of conduct to be determined in catergories of user, Non-target class user can be understood as other classes user in catergories of user in addition to target class user.Here for the ease of difference The corresponding temporal sequence association rule of target class user can be expressed as the first timing by the corresponding temporal sequence association rule of inhomogeneity user The corresponding temporal sequence association rule of non-target class user is expressed as the second temporal sequence association rule by correlation rule.

In the present embodiment, the corresponding timing rule of conduct of target class user can be understood as target class user and behavior thing occur The timing planning that part meets.In the timing rule of conduct for determining target class user, may include steps of:

Based on the first temporal sequence association rule and the second temporal sequence association rule, the target in the first temporal sequence association rule is determined Temporal sequence association rule.

Based on Goal time order correlation rule, the timing rule of conduct of target class user is determined.

When determining Goal time order correlation rule, can at least following three kinds of methods be used:

First method:

The temporal sequence association rule of the second temporal sequence association rule will be not belonging in first temporal sequence association rule as Goal time order Correlation rule.

For example, it is assumed that the first temporal sequence association rule are as follows: 1 → 2,1 → 3,1 → 4,1 → 5,2 → 3,2 → 4,3 → 4,3 → 5,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4,1 → 3 → 5,2 → 3 → 4,1 → 2 → 3 → 4, the second temporal sequence association rule are as follows: 1 → 3,1 → 4,1 → 5,3 → 4,3 → 5,4 → 5,3 → 4 → 5,1 → 3 → 4 → 5, it is possible to by being not belonging in the first temporal sequence association rule The 1 → 2 of second temporal sequence association rule, 2 → 3,2 → 4,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4,1 → 3 → 5,2 → 3 → 4,1 → 2 → 3 → 4 are used as Goal time order correlation rule.

Second method:

Determine identical temporal sequence association rule in the first temporal sequence association rule and the second temporal sequence association rule；Determine that this is identical First confidence level of the temporal sequence association rule in target class user, and the second confidence level in non-target class user；It will In the identical temporal sequence association rule, the ratio of the first confidence level and the second confidence level is not less than the sequential correlation of given threshold Rule is determined as Goal time order correlation rule.

In the present embodiment, the first confidence level and the second confidence level can be obtained based on the determination of identical method.Wherein, first Confidence level can be the probability that the corresponding behavior event of temporal sequence association rule occurs in the behavioral data of target class user, behavior The probability that event occurs in target class user can be defined as, what behavior event occurred in the behavioral data of target class user The ratio of the total number of users of number and target class user.

For example, a temporal sequence association rule 1 → 2 → 3 of user A, B, C for above-mentioned record, corresponding behavior thing Part is event 1, event 2 and event 3, based on table 1 it is found that event 1, event 2 and event 3 are in the behavioral data of user A, B, C The number of appearance is 2, and total number of users 3, therefore, the probability that event 1, event 2 and event 3 occur can regard for 0.67,0.67 For the first confidence level of temporal sequence association rule 1 → 2 → 3.

In addition, the first confidence level is also possible to the corresponding behavior event of temporal sequence association rule in the behavior number of target class user According to the conditional probability of middle appearance.By taking temporal sequence association rule a → b → c as an example, the corresponding behavior thing of temporal sequence association rule a → b → c The conditional probability that part a, b, c occur in the behavioral data of target class user can be defined as, and a, b, c are in target class for behavior event The ratio for the probability that the probability and behavior event a, b occurred in the behavioral data of user occurs in the behavioral data of target class user Value.

For example, the temporal sequence association rule 1 → 2 → 3 of user A, B, C for above-mentioned record, corresponding behavior event are Event 1, event 2 and event 3, based on table 1 it is found that the probability of occurrence of event 1, event 2 and event 3 is 0.67, event 1 and event 2 probability of occurrence is 0.67, and therefore, the conditional probability that event 1, event 2 and event 3 occur can be considered as sequential correlation for 1,1 First confidence level of rule 1 → 2 → 3.

It, can be with base after the method based on above-mentioned record obtains the first confidence level and the second confidence level of temporal sequence association rule Goal time order correlation rule is determined in second method.When determining Goal time order correlation rule, in order to make it easy to understand, can lift Example explanation.

Assuming that the first temporal sequence association rule and the first confidence level are as follows: 1 → 2 (0.67), 1 → 3 (1), 1 → 4 (0.67), 1 → 5 (0.33), 2 → 3 (0.67), 2 → 4 (0.67), 3 → 4 (0.67), 3 → 5 (0.33), 1 → 2 → 3 (0.67), 1 → 2 → 4 (0.67), 1 → 3 → 4 (0.67), 1 → 3 → 5 (0.33), 2 → 3 → 4 (0.67), 1 → 2 → 3 → 4 (0.67), the second timing are closed Connection rule and the second confidence level are as follows: 1 → 3 (0.5), 1 → 4 (0.5), 1 → 5 (0.5), 3 → 4 (0.5), 3 → 5 (0.5), 4 → 5 (1), 3 → 4 → 5 (0.5), 1 → 3 → 4 → 5 (0.5).

It can be seen that in target class user and non-target class user identical temporal sequence association rule be 1 → 3,1 → 4,1 → 5,3 → 4,3 → 5, the first confidence level of these temporal sequence association rules and the ratio of the second confidence level are followed successively by 2,1.33,0.67, 1.33,0.67, it is assumed that given threshold 1 then can be used as Goal time order correlation rule for 1 → 3,1 → 4,3 → 4.

The third method:

The combination for the Goal time order correlation rule that the first method of above-mentioned record and second method are obtained as Goal time order correlation rule.Specific body implementation is not detailed herein.

It should be noted that being directed to three kinds of methods of above-mentioned record, in practical applications, any method can choose Determine Goal time order correlation rule, wherein preferably, be not belonging to the second sequential correlation rule if existing in the first temporal sequence association rule Temporal sequence association rule then, then can choose above-mentioned first method or the third method determines Goal time order correlation rule, no Then, it can choose above-mentioned second method and determine Goal time order correlation rule.

It, can be true based on Goal time order correlation rule after the method based on above-mentioned record obtains Goal time order correlation rule The timing rule of conduct of the class that sets the goal user.

In the timing rule of conduct for determining target class user, a kind of implementation be can be, and directly close Goal time order Connection rule is used as the corresponding timing rule of conduct of target class user.For example, if Goal time order is associated with are as follows: 1 → 2,2 → 3,2 → 4,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4,1 → 3 → 5,2 → 3 → 4,1 → 2 → 3 → 4, then the timing rule of conduct of target class user Are as follows: 1 → 2,2 → 3,2 → 4,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4,1 → 3 → 5,2 → 3 → 4,1 → 2 → 3 → 4.

Another implementation can be, and the Goal time order correlation rule by confidence level not less than setting believability threshold is made For the timing rule of conduct of target class user.

For example, if Goal time order is associated with are as follows: 1 → 2,2 → 3,2 → 4,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4,1 → 3 → 5, 2 → 3 → 4,1 → 2 → 3 → 4, confidence level is followed successively by 0.67,0.67,0.67,0.67,0.67,0.67,0.33,0.67,0.67, Assuming that setting believability threshold as 0.5, then the timing rule of conduct of target class user may is that 1 → 2,2 → 3,2 → 4,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4,2 → 3 → 4,1 → 2 → 3 → 4.

In the present embodiment, the timing rule of conduct that any of the above-described kind of implementation determines target class user can choose, this In be not specifically limited.

After obtaining the timing rule of conduct of target class user, S108 can be executed.

S108: the timing rule of conduct based on the target class user determines whether user to be identified belongs to the target Class user.

User to be identified can be understood as the user without service label, in the timing row based on the target class user It may comprise steps of when determining whether user to be identified belongs to the target class user for rule:

Firstly, obtaining the behavioral data of user to be identified.

It may include the multiple behavior events of user to be identified in the set time period in the behavioral data of user to be identified And the timing mark of multiple behavior event.

Secondly, identified according to the timing for the behavior event and behavior event for including in the behavioral data of user to be identified, Determine the temporal sequence association rule of user to be identified.

When determining the temporal sequence association rule of user to be identified, specific implementation may refer to the determination one of above-mentioned record The content of the corresponding temporal sequence association rule of class user, is not repeated herein description.

Finally, judge whether the temporal sequence association rule of user to be identified hits target the timing rule of conduct of class user, if It is that can then determine that user to be identified belongs to target class user, if it is not, can then determine that user to be identified belongs to non-target class use Family.

For example, as it is known that the timing rule of conduct of target class user are as follows: 1 → 2,2 → 3,2 → 4,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4,2 → 3 → 4,1 → 2 → 3 → 4, then:

Assuming that the temporal sequence association rule of user to be identified are as follows: 3 → 4,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4, by comparing It is found that the temporal sequence association rule 1 → 2 → 3 of user to be identified, 1 → 2 → 4 and 1 → 3 → 4, have hit the timing of target class user Rule of conduct 1 → 2 → 3,1 → 2 → 4 and 1 → 3 → 4, hence, it can be determined that user to be identified belongs to target class user.

Assuming that user's temporal sequence association rule to be identified are as follows: 4 → 5,2 → 3 → 5,2 → 4 → 5,3 → 4 → 5, by comparing may be used Know, any temporal sequence association rule of user to be identified does not hit target any timing rule of conduct of class user, therefore, can be with Determine that user to be identified is not belonging to target class user.

In the present embodiment, after determining that user to be identified belongs to target class user, application scenarios are also based on, treat knowledge Other user is further processed.

For example, in risk identification scene, however, it is determined that user A to be identified belongs to high risk user, then can be directly right User A is intercepted, do not allow user's A access safety page or carry out online transaction etc.；If it is determined that user A belongs to low-risk use Family then directly can carry out access to user A, allow the user A access safety page or carry out online transaction etc..

It, can due to after being identified based on timing rule of conduct to user to be identified in this way, in risk identification scene To be based on, recognition result intercepts user to be identified or therefore access, can reduce system pressure without carrying out other judgements Power, in addition, after determining that user to be identified is low-risk user based on timing rule of conduct, due to being handled without other judgements, Access can be carried out to user to be identified, whole process time-consuming is less, therefore, can promote user experience.

For another example in marketing scene, however, it is determined that user A to be identified belongs to target user, then can push to user A The merchandise news of end article；If it is determined that user A is not belonging to target user, then it can cancel to user A and recommend end article Merchandise news.In this manner it is achieved that precisely push, avoids recommending unwanted merchandise news to user, to promote user's body It tests.

Technical solution provided by the embodiments of the present application, when the behavioral data to user is analyzed, due to fully considering The timing mark for the behavior event for including in behavioral data, it is thereby achieved that the abundant excavation to user behavior data；? When analyzing the behavioral data of catergories of user, due to can the behavioral data to catergories of user sufficiently excavated, obtain It is able to reflect the temporal sequence association rule of catergories of user behavior timing, and then obtains the timing rule of conduct of target class user, therefore, When the timing rule of conduct based on target class user determines whether user to be identified belongs to target class user, can carry out effectively Identification.

Fig. 2 is the flow diagram of the processing method of one embodiment user data of the application, the user data Processing method includes the following steps.

S202: the behavioral data of catergories of user is obtained.

Wherein, catergories of user is divided based on service label, may include multiple behavior things in the behavioral data of a user The timing of part and multiple behavior events mark.

S204: the timing mark of the behavior event and behavior event that include in the behavioral data based on the catergories of user Know, determines the corresponding temporal sequence association rule of the catergories of user；:

The specific implementation of above-mentioned S202 to S204 may refer to the specific implementation of corresponding steps in embodiment illustrated in fig. 1, this In not in repeated description.

S206: being based on the corresponding temporal sequence association rule of the catergories of user, determines the timing behavior rule of the catergories of user Then.

In S206, for one type target class user, it can be determined based on the method recorded in embodiment illustrated in fig. 1 The timing rule of conduct of target class user can be based on identical method after obtaining the timing rule of conduct of target class user Determine the timing rule of conduct of the non-target class user in catergories of user in addition to target class user.

S208: the timing rule of conduct based on the catergories of user generates multiple timing rule of conduct features.

In the present embodiment, a timing rule of conduct feature, multiple timing behaviors are can be generated in a timing rule of conduct The number of rule feature can be equal to the total number of the timing rule of conduct of catergories of user.

For example, the timing rule of conduct of catergories of user include: 1 → 2,2 → 3,2 → 4,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4,1 → 3 → 5,2 → 3 → 4,1 → 2 → 3 → 4,4 → 5,3 → 4 → 5,1 → 3 → 4 → 5, then, based on timing rule of conduct 1 → 2 can be generated timing rule of conduct feature fea1, and timing rule of conduct feature can be generated based on timing rule of conduct 2 → 3 Fea2 ... ..., and so on, available 12 timing rule of conduct feature fea1~fea12.

S210: being based on the multiple timing rule of conduct feature, determine the timing behavioural characteristic of user to be processed, to generate Sample data including the timing behavioural characteristic carries out model training.

It, can when determining the timing behavioural characteristic of user to be processed being based on multiple timing rule of conduct features in S210 To include the following steps:

Firstly, obtaining the behavioral data of user to be processed.

It may include the multiple behavior events of user to be processed in the set time period in the behavioral data of user to be processed And the timing mark of multiple behavior events.

Secondly, the timing of the behavior event and behavior event that include in the behavioral data based on user to be processed identifies, Determine the temporal sequence association rule of user.

What specific implementation may refer to record in above-mentioned embodiment illustrated in fig. 1 determines that the corresponding timing of a kind of user is closed The particular content for joining rule, is not repeated herein description.

Finally, being directed to one of timing rule of conduct feature, it can be determined that the temporal sequence association rule of user to be processed is The corresponding timing rule of conduct of no hit timing rule of conduct feature, wherein the corresponding timing behavior of timing rule of conduct feature Rule is it is to be understood that generate the timing rule of conduct of the timing rule of conduct feature.For example, the fea1 of above-mentioned record is by timing Rule of conduct 1 → 2 generates, then the corresponding timing rule of conduct of fea1 is 1 → 2.

If the determination result is YES, then it can determine that user to be processed has the timing rule of conduct feature otherwise can be true Fixed user to be processed does not have the timing rule of conduct feature.

It, can be with after determining whether user to be processed has a timing rule of conduct feature based on the method for above-mentioned record It based on identical method, determines whether user to be processed has other timing rule of conduct features, is not detailed herein.

In the present embodiment, whether user to be processed there are multiple timing rule of conduct features can be indicated by numerical value, numerical value The timing behavioural characteristic of user to be processed can be considered as.

For example, can be indicated by numerical value 1 if user to be processed has some timing rule of conduct feature；If to be processed User does not have some timing rule of conduct feature, then can be indicated by numerical value 0, numerical value 0 and 1 can be considered as user's to be processed Timing behavioural characteristic.

In order to make it easy to understand, still being said by taking 12 timing rule of conduct feature fea1~fea12 of above-mentioned record as an example It is bright, the corresponding timing rule of conduct of 12 timing rule of conduct feature fea1~fea12 are as follows: 1 → 2,2 → 3,2 → 4,1 → 2 → 3,1 → 2 → 4,1 → 3 → 4,1 → 3 → 5,2 → 3 → 4,1 → 2 → 3 → 4,4 → 5,3 → 4 → 5,1 → 3 → 4 → 5.

Assuming that the temporal sequence association rule of user to be processed includes: 1 → 2,2 → 4,3 → 4,1 → 2 → 3,1 → 3 → 4,1 → 3 → 5,1 → 2 → 3 → 4, then it can determine that user to be processed has timing rule of conduct feature fea1, fea3, fea4, fea6, Fea7, fea9, do not have timing rule of conduct feature fea2, fea5, fea8, fea10, fea11, fea12, by 1 indicate to Managing user has some timing rule of conduct feature, indicates that user to be processed does not have some timing rule of conduct feature by 0, then The timing behavioural characteristic of available user to be processed are as follows: 1,0,1,1,0,1,1,0,1,0,0,0.

In the present embodiment, after determination obtains the timing behavioural characteristic of user to be processed, in the industry of known user to be processed It is engaged in the case where label, the timing behavioural characteristic for being also based on user to be processed obtains sample data, wraps in the sample data The timing behavioural characteristic of user to be processed is included, which can be used for carrying out model training.

For example, after obtaining the timing behavioural characteristic of target class user and non-target class user, it can be by these timing rows It is characterized and carries out model training as sample data, obtain whether user for identification is target class user or non-target class user Model.After obtaining model, when being identified based on model to user to be identified, it can also be recorded in this present embodiment with base Method determines the timing behavioural characteristic of user to be identified, using the timing behavioural characteristic of user to be identified as mode input, is based on The output of model, can determine whether user to be identified belongs to target class user or non-target class user.

Technical solution provided by the embodiments of the present application, when the behavioral data to user is analyzed, due to fully considering The timing mark for the behavior event for including in behavioral data, it is thereby achieved that the abundant excavation to user behavior data；? When analyzing the behavioral data of catergories of user, due to can the behavioral data to catergories of user sufficiently excavated, obtain It is able to reflect the temporal sequence association rule of catergories of user behavior timing, and then obtains the timing rule of conduct of catergories of user, based on more The timing rule of conduct of class user generates multiple timing rule of conduct features, therefore, is based on multiple timing rule of conduct features, Available more galore user's timing behavioural characteristic, to carry out mould based on the sample data for including timing behavioural characteristic After type, the model that can be obtained based on training carries out effectively decision-making treatment.

It is above-mentioned that the application specific embodiment is described.Other embodiments are within the scope of the appended claims. In some cases, the movement recorded in detail in the claims or step can be executed according to the sequence being different from embodiment And desired result still may be implemented.In addition, process depicted in the drawing not necessarily require the particular order shown or Person's consecutive order is just able to achieve desired result.In some embodiments, multitasking and parallel processing are also possible Or it may be advantageous.

Fig. 3 is the structural schematic diagram of one embodiment electronic equipment of the application.Referring to FIG. 3, in hardware view, the electricity Sub- equipment includes processor, optionally further comprising internal bus, network interface, memory.Wherein, memory may be comprising interior It deposits, such as high-speed random access memory (Random-Access Memory, RAM), it is also possible to further include non-volatile memories Device (non-volatile memory), for example, at least 1 magnetic disk storage etc..Certainly, which is also possible that other Hardware required for business.

Processor, network interface and memory can be connected with each other by internal bus, which can be ISA (Industry Standard Architecture, industry standard architecture) bus, PCI (Peripheral Component Interconnect, Peripheral Component Interconnect standard) bus or EISA (Extended Industry Standard Architecture, expanding the industrial standard structure) bus etc..The bus can be divided into address bus, data/address bus, control always Line etc..Only to be indicated with a four-headed arrow in Fig. 3, it is not intended that an only bus or a type of convenient for indicating Bus.

Memory, for storing program.Specifically, program may include program code, and said program code includes calculating Machine operational order.Memory may include memory and nonvolatile memory, and provide instruction and data to processor.

Processor is from the then operation into memory of corresponding computer program is read in nonvolatile memory, in logical layer The processing unit of user data is formed on face.Processor executes the program that memory is stored, and is specifically used for executing following behaviour Make:

The method that the processing unit of user data disclosed in the above-mentioned embodiment illustrated in fig. 3 such as the application executes can be applied to In processor, or realized by processor.Processor may be a kind of IC chip, the processing capacity with signal.? During realization, each step of the above method can pass through the integrated logic circuit of the hardware in processor or software form Instruction is completed.Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit (Network Processor, NP) etc.；It can also be digital signal processor (Digital Signal Processor, DSP), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing Field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device are divided Vertical door or transistor logic, discrete hardware components.It may be implemented or execute and is in the embodiment of the present application disclosed each Method, step and logic diagram.General processor can be microprocessor or the processor is also possible to any conventional place Manage device etc..The step of method in conjunction with disclosed in the embodiment of the present application, can be embodied directly in hardware decoding processor and execute At, or in decoding processor hardware and software module combination execute completion.Software module can be located at random access memory, This fields such as flash memory, read-only memory, programmable read only memory or electrically erasable programmable memory, register maturation In storage medium.The storage medium is located at memory, and processor reads the information in memory, completes above-mentioned side in conjunction with its hardware The step of method.

The method that the electronic equipment can also carry out Fig. 1, and realize the processing unit of user data in the embodiment shown in fig. 1 Function, details are not described herein for the embodiment of the present application.

Certainly, other than software realization mode, other implementations are not precluded in the electronic equipment of the application, for example patrol Collect device or the mode of software and hardware combining etc., that is to say, that the executing subject of following process flow is not limited to each patrol Unit is collected, hardware or logical device are also possible to.

The embodiment of the present application also proposed a kind of computer readable storage medium, the computer-readable recording medium storage one A or multiple programs, the one or more program include instruction, and the instruction is when by the portable electronic including multiple application programs When equipment executes, the method that the portable electronic device can be made to execute embodiment illustrated in fig. 1, and be specifically used for executing following behaviour Make:

Fig. 4 is the structural schematic diagram of the processing unit 40 of one embodiment user data of the application.Referring to FIG. 4, In a kind of Software Implementation, the processing unit 40 of the user data can include: acquiring unit 41, determines processing unit 42 Unit 43 and recognition unit 44, in which:

Acquiring unit 41 obtains the behavioral data of catergories of user, and the catergories of user is divided based on service label, a use It include the timing mark of multiple behavior events and the multiple behavior event in the behavioral data at family；

Processing unit 42, the behavior event for including in the behavioral data based on the catergories of user and behavior event when Sequence mark, determines the corresponding temporal sequence association rule of the catergories of user；

Determination unit 43, based on corresponding first temporal sequence association rule of target class user and non-mesh in the catergories of user Corresponding second temporal sequence association rule of class user is marked, determines the timing rule of conduct of the target class user；

Recognition unit 44 determines whether user to be identified belongs to institute based on the timing rule of conduct of the target class user State target class user.

Optionally, the determination unit 43 determines the timing rule of conduct of the target class user, comprising:

Based on first temporal sequence association rule and second temporal sequence association rule, first sequential correlation is determined Goal time order correlation rule in rule；

Based on the Goal time order correlation rule, the timing rule of conduct of the target class user is determined.

Optionally, the determination unit 43 determines the Goal time order correlation rule in first temporal sequence association rule, packet Include following at least one:

The temporal sequence association rule in first temporal sequence association rule, being not belonging to second temporal sequence association rule is determined For the Goal time order correlation rule；

Determine identical temporal sequence association rule in first temporal sequence association rule and second temporal sequence association rule； It determines first confidence level of the identical temporal sequence association rule in the target class user and is used in the non-target class The second confidence level in family；Timing by the ratio of first confidence level and second confidence level not less than given threshold is closed Connection rule is determined as the Goal time order correlation rule.

Optionally, first confidence level is row of the corresponding behavior event of temporal sequence association rule in the target class user For the probability or conditional probability occurred in data.

Optionally, the recognition unit 44 determines user to be identified based on the timing rule of conduct of the target class user Whether the target class user is belonged to, comprising:

It obtains the behavioral data of the user to be identified, includes multiple behavior events in the behavioral data and described more The timing of a behavior event identifies；

The timing of the behavior event and behavior event that include in behavioral data based on the user to be identified identifies, really The temporal sequence association rule of the fixed user to be identified；

Judge whether the temporal sequence association rule of the user to be identified hits the timing rule of conduct of the target class user；

If so, determining that the user belongs to the target class user；

If not, it is determined that the user is not belonging to the target class user.

Optionally, the processing unit 42 determines the corresponding temporal sequence association rule of the catergories of user, comprising:

For one type user, following operation is executed:

The behavior event for including in behavioral data based on a kind of user, determines frequent item set；

Timing mark based on the behavior event for including in the frequent item set and the frequent item set, determines described one The corresponding temporal sequence association rule of class user.

The method that the processing unit 40 of user data provided by the embodiments of the present application can also carry out Fig. 1, and realize number of users According to processing unit embodiment shown in Fig. 1 function, details are not described herein for the embodiment of the present application.

Fig. 5 is the structural schematic diagram of one embodiment electronic equipment of the application.Referring to FIG. 5, in hardware view, the electricity Sub- equipment includes processor, optionally further comprising internal bus, network interface, memory.Wherein, memory may be comprising interior It deposits, such as high-speed random access memory (Random-Access Memory, RAM), it is also possible to further include non-volatile memories Device (non-volatile memory), for example, at least 1 magnetic disk storage etc..Certainly, which is also possible that other Hardware required for business.

Processor, network interface and memory can be connected with each other by internal bus, which can be ISA (Industry Standard Architecture, industry standard architecture) bus, PCI (Peripheral Component Interconnect, Peripheral Component Interconnect standard) bus or EISA (Extended Industry Standard Architecture, expanding the industrial standard structure) bus etc..The bus can be divided into address bus, data/address bus, control always Line etc..Only to be indicated with a four-headed arrow in Fig. 5, it is not intended that an only bus or a type of convenient for indicating Bus.

The method that the processing unit of user data disclosed in the above-mentioned embodiment illustrated in fig. 5 such as the application executes can be applied to In processor, or realized by processor.Processor may be a kind of IC chip, the processing capacity with signal.? During realization, each step of the above method can pass through the integrated logic circuit of the hardware in processor or software form Instruction is completed.Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit (Network Processor, NP) etc.；It can also be digital signal processor (Digital Signal Processor, DSP), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing Field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device are divided Vertical door or transistor logic, discrete hardware components.It may be implemented or execute and is in the embodiment of the present application disclosed each Method, step and logic diagram.General processor can be microprocessor or the processor is also possible to any conventional place Manage device etc..The step of method in conjunction with disclosed in the embodiment of the present application, can be embodied directly in hardware decoding processor and execute At, or in decoding processor hardware and software module combination execute completion.Software module can be located at random access memory, This fields such as flash memory, read-only memory, programmable read only memory or electrically erasable programmable memory, register maturation In storage medium.The storage medium is located at memory, and processor reads the information in memory, completes above-mentioned side in conjunction with its hardware The step of method.

The method that the electronic equipment can also carry out Fig. 2, and realize the processing unit of user data in the embodiment depicted in figure 2 Function, details are not described herein for the embodiment of the present application.

The embodiment of the present application also proposed a kind of computer readable storage medium, the computer-readable recording medium storage one A or multiple programs, the one or more program include instruction, and the instruction is when by the portable electronic including multiple application programs When equipment executes, the method that the portable electronic device can be made to execute embodiment illustrated in fig. 2, and be specifically used for executing following behaviour Make:

Fig. 6 is the structural schematic diagram of the processing unit 60 of one embodiment user data of the application.Referring to FIG. 6, In a kind of Software Implementation, the processing unit 40 of the user data can include: acquiring unit 61, processing unit 62, first Determination unit 63, generation unit 64 and the second determination unit 65, in which:

Acquiring unit 61 obtains the behavioral data of catergories of user, and the catergories of user is divided based on service label, a use It include the timing mark of multiple behavior events and the multiple behavior event in the behavioral data at family；

Processing unit 62, the behavior event for including in the behavioral data based on the catergories of user and behavior event when Sequence mark, determines the corresponding temporal sequence association rule of the catergories of user；

First determination unit 63 is based on the corresponding temporal sequence association rule of the catergories of user, determines the catergories of user Timing rule of conduct；

Generation unit 64, the timing rule of conduct based on the catergories of user generate multiple timing rule of conduct features；

Second determination unit 65 is based on the multiple timing rule of conduct feature, determines the timing behavior of user to be processed Feature, to generate the sample data progress model training for including the timing behavioural characteristic.

Optionally, second determination unit 65 is based on the multiple timing rule of conduct feature, determines user to be processed Timing behavioural characteristic, comprising:

It obtains the behavioral data of the user to be processed, includes multiple behavior events in the behavioral data and described more The timing of a behavior event identifies；

The timing of the behavior event and behavior event that include in behavioral data based on the user to be processed identifies, really The temporal sequence association rule of the fixed user to be processed；

For one of timing rule of conduct feature, following operation is executed:

Judge the temporal sequence association rule of the user to be processed whether hit the timing rule of conduct feature it is corresponding when Sequence rule of conduct；

If so, determining that the user to be processed has the timing rule of conduct feature；

If not, it is determined that the user to be processed does not have the timing rule of conduct feature.

The method that the processing unit 60 of user data provided by the embodiments of the present application can also carry out Fig. 2, and realize number of users According to processing unit embodiment shown in Fig. 2 function, details are not described herein for the embodiment of the present application.

In short, being not intended to limit the protection scope of the application the foregoing is merely the preferred embodiment of the application. Within the spirit and principles of this application, any modification, equivalent replacement, improvement and so on should be included in the application's Within protection scope.

System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity, Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment The combination of equipment.

Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data. The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM), Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.

It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want There is also other identical elements in the process, method of element, commodity or equipment.

Various embodiments are described in a progressive manner in the application, same and similar part between each embodiment It may refer to each other, each embodiment focuses on the differences from other embodiments.Implement especially for system For example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method Part illustrates.

Claims

1. a kind of processing method of user data, comprising:

The behavioral data of catergories of user is obtained, the catergories of user is divided based on service label, in the behavioral data of a user It is identified including the timing of multiple behavior events and the multiple behavior event；

The timing of the behavior event and behavior event that include in behavioral data based on the catergories of user identifies, described in determination The corresponding temporal sequence association rule of catergories of user；

It is corresponding based on corresponding first temporal sequence association rule of target class user in the catergories of user and non-target class user Second temporal sequence association rule determines the timing rule of conduct of the target class user；

Based on the timing rule of conduct of the target class user, determine whether user to be identified belongs to the target class user.

2. the method as described in claim 1 determines the timing rule of conduct of the target class user, comprising:

Based on first temporal sequence association rule and second temporal sequence association rule, first temporal sequence association rule is determined In Goal time order correlation rule；

3. method according to claim 2 determines the Goal time order correlation rule in first temporal sequence association rule, including Following at least one:

By in first temporal sequence association rule, the temporal sequence association rule for being not belonging to second temporal sequence association rule is determined as institute State Goal time order correlation rule；

Determine identical temporal sequence association rule in first temporal sequence association rule and second temporal sequence association rule；It determines The identical temporal sequence association rule is in the first confidence level in the target class user and in the non-target class user The second confidence level；Sequential correlation by the ratio of first confidence level and second confidence level not less than given threshold is advised Then it is determined as the Goal time order correlation rule.

4. method as claimed in claim 3,

First confidence level is that the corresponding behavior event of temporal sequence association rule goes out in the behavioral data of the target class user Existing probability or conditional probability.

5. the method as described in claim 1 determines that user to be identified is based on the timing rule of conduct of the target class user It is no to belong to the target class user, comprising:

The behavioral data of the user to be identified is obtained, includes multiple behavior events and the multiple row in the behavioral data It is identified for the timing of event；

The timing of the behavior event and behavior event that include in behavioral data based on the user to be identified identifies, and determines institute State the temporal sequence association rule of user to be identified；

If so, determining that the user belongs to the target class user；

6. the method as described in claim 1 determines the corresponding temporal sequence association rule of the catergories of user, comprising:

For one type user, following operation is executed:

Timing mark based on the behavior event for including in the frequent item set and the frequent item set determines a kind of use The corresponding temporal sequence association rule in family.

7. a kind of processing method of user data, comprising:

Based on the multiple timing rule of conduct feature, the timing behavioural characteristic of user to be processed is determined, include described to generate The sample data of timing behavioural characteristic carries out model training.

8. the method for claim 7, being based on the multiple timing rule of conduct feature, the timing of user to be processed is determined Behavioural characteristic, comprising:

The behavioral data of the user to be processed is obtained, includes multiple behavior events and the multiple row in the behavioral data It is identified for the timing of event；

The timing of the behavior event and behavior event that include in behavioral data based on the user to be processed identifies, and determines institute State the temporal sequence association rule of user to be processed；

For one of timing rule of conduct feature, following operation is executed:

Judge whether the temporal sequence association rule of the user to be processed hits the corresponding timing row of the timing rule of conduct feature For rule；

9. a kind of processing unit of user data, comprising:

Acquiring unit obtains the behavioral data of catergories of user, and the catergories of user is divided based on service label, the row of a user For the timing mark in data including multiple behavior events and the multiple behavior event；

Processing unit, the timing mark of the behavior event and behavior event that include in the behavioral data based on the catergories of user Know, determines the corresponding temporal sequence association rule of the catergories of user；

Determination unit is used based on corresponding first temporal sequence association rule of target class user in the catergories of user and non-target class Corresponding second temporal sequence association rule in family, determines the timing rule of conduct of the target class user；

Recognition unit determines whether user to be identified belongs to the target based on the timing rule of conduct of the target class user Class user.

10. a kind of processing unit of user data, comprising:

First determination unit is based on the corresponding temporal sequence association rule of the catergories of user, determines the timing row of the catergories of user For rule；

Second determination unit is based on the multiple timing rule of conduct feature, determines the timing behavioural characteristic of user to be processed, with It generates the sample data including the timing behavioural characteristic and carries out model training.

11. a kind of electronic equipment, comprising:

Processor；And

It is arranged to the memory of storage computer executable instructions, which when executed execute the processor It operates below:

12. a kind of computer readable storage medium, the computer-readable recording medium storage one or more program, described one A or multiple programs are when the electronic equipment for being included multiple application programs executes, so that the electronic equipment is executed with lower section Method:

13. a kind of electronic equipment, comprising:

Processor；And

14. a kind of computer readable storage medium, the computer-readable recording medium storage one or more program, described one A or multiple programs are when the electronic equipment for being included multiple application programs executes, so that the electronic equipment is executed with lower section Method: