CN108052983A - Using the method, apparatus and equipment of cluster - Google Patents

Using the method, apparatus and equipment of cluster Download PDF

Info

Publication number
CN108052983A
CN108052983A CN201711460865.6A CN201711460865A CN108052983A CN 108052983 A CN108052983 A CN 108052983A CN 201711460865 A CN201711460865 A CN 201711460865A CN 108052983 A CN108052983 A CN 108052983A
Authority
CN
China
Prior art keywords
msub
application
mrow
classification
cluster
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201711460865.6A
Other languages
Chinese (zh)
Inventor
潘岸腾
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba China Co Ltd
Original Assignee
Guangzhou Youshi Network Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Youshi Network Technology Co Ltd filed Critical Guangzhou Youshi Network Technology Co Ltd
Priority to CN201711460865.6A priority Critical patent/CN108052983A/en
Publication of CN108052983A publication Critical patent/CN108052983A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques

Abstract

The embodiment of the present application discloses a kind of method, apparatus and equipment of application cluster, and this method includes：To each application execution classifying step in multiple applications, to obtain multiple classification set after the multiple application cluster, wherein, the classifying step includes：It obtains and applies multiple alternative classification set before reclassifying；Based on the correlation between application, the value that the application is respectively belonging to corresponding mode classification during the multiple alternative classification set is calculated；The application is reclassified under the highest mode classification of value in the alternative classification set of the application ownership.The method of the embodiment of the present application can be reduced using required human cost is sorted out, and improve the accuracy that application is sorted out.

Description

Using the method, apparatus and equipment of cluster
Technical field
This application involves the method, apparatus and equipment of network technique field, more particularly to application cluster.
Background technology
, it is necessary to classify to different application during the operation of application shop, to generate different special recommendations to use Family.Current way is to carry out manual sort to application by editorial staff.But on the one hand the method for manual sort needs to consume Substantial amounts of manpower, another aspect accuracy depend on the experience of editorial staff, and subjectivity is very strong, can not ensure accuracy rate.
Therefore, a kind of method of application cluster of demand, to overcome above-mentioned technical problem.
The content of the invention
In view of the above problems, the method, apparatus and equipment that have been designed to provide a kind of application and have clustered of the application, reduces Using required human cost is sorted out, the accuracy that application is sorted out is improved.
In order to solve the above technical problems, what the embodiment of the present application was realized in：
In a first aspect, a kind of method of application cluster is provided, including：
To each application execution classifying step in multiple applications, to obtain multiple classification after the multiple application cluster Set, wherein, the classifying step includes：
It obtains and applies multiple alternative classification set before reclassifying；
Based on the correlation between application, calculate the application and be respectively belonging to correspond to during the multiple alternative classification set Mode classification value；
The application is reclassified under the highest mode classification of value in the alternative classification set of the application ownership.
Optionally, before to classifying step described in each application execution in multiple applications, the method further includes：
Determine the maximum iteration of iterative operation, wherein, the iterative operation is included to every in the multiple application Classifying step described in a application execution.
Optionally, the method further includes：
When the number for having performed the iterative operation is reached the maximum iteration after the multiple application cluster Multiple alternative classification set, the multiple classification set being determined as after the final cluster of the multiple application.
Optionally, the method further includes：
If M is less than the maximum iteration, and has performed the number of the iterative operation for M times when the multiple application When the number that the iterative operation is gathered and performed in multiple alternative classification after cluster is M-1 times after the multiple application cluster Multiple alternative category sets unifications cause, then after the multiple application clusters when being M time by the number for having performed the iterative operation Multiple alternative classification set be determined as multiple classification set after the final cluster of the multiple application；
If multiple alternative classification set of the number for having performed iterative operation when being M times after the multiple application cluster Multiple alternative classification set of the number with having performed iterative operation when being M-1 times after the multiple application cluster differ It causes, then performs the iterative operation.
The correlation based between the application calculates the application and is respectively belonging to the multiple alternative category set The value of corresponding mode classification during conjunction, including：
The value of mode classification is calculated according to the following formula：
Wherein, K presentation classes mode, the value of KValue presentation class modes, the classification under k presentation class modes, | Sk | represent the corresponding alternative classification set S of classification kkThe number of the application included, SValuekRepresent alternative classification set SkMiddle bag Correlation between the application included.
Optionally, SValue is calculated according to the following formulak：
Wherein, i, j represent the set S that alternatively classifies respectivelykWhat is included applies i and using j, simi,jIt represents using i and answers With the correlation between j, simi,jIt is determined based on user's set of application i and application j.
Optionally, sim is calculated according to the following formulai,j：
Wherein, UsersInstalllediRepresent that installation is gathered using the user of i, UsersInstallledjRepresent installation Gather using the user of j.
Second aspect provides a kind of device of application cluster, including：
First sorts out processing module, described more to obtain for each application execution classifying step in multiple applications Multiple classification set after a application cluster；Wherein, the classifying step includes：
It obtains and applies multiple alternative classification set before reclassifying；
Based on the correlation between application, calculate the application and be respectively belonging to correspond to during the multiple alternative classification set Mode classification value；
The application is reclassified under the highest mode classification of value in the alternative classification set of the application ownership.
Optionally, described device further includes：
Iterations determining module, for it is described classification processing module to described in each application execution in multiple applications Before classifying step, the maximum iteration of iterative operation is determined, wherein, the iterative operation is included in the multiple application Each application execution described in classifying step.
Optionally, described device further includes：
Second sorts out processing module, and the number for the described first classification processing module to have been performed to the iterative operation reaches Multiple alternative classification set during to the maximum iteration after the multiple application cluster, are determined as the multiple application most Multiple classification set after cluster eventually.
Described device further includes：
3rd sorts out processing module, if it is less than the maximum iteration for M, and the first classification processing module is held Multiple alternative classification when the number of the iterative operation of having gone is M time after the multiple application cluster are gathered returns with described first Multiple alternative classification set of the number that class processing module has performed iterative operation when being M-1 after the multiple application cluster Unanimously, then the described first classification processing module the multiple application cluster when the number of the iterative operation is M times has been performed into Multiple alternative classification set afterwards are determined as multiple classification set after the final cluster of the multiple application；
If the number that the first classification processing module has performed the iterative operation the multiple application cluster when being M times Afterwards it is multiple it is alternative classification set with described first classification processing module performed the number of the iterative operation for M-1 times when institute It is inconsistent to state multiple alternative classification set after multiple application clusters, then performs the iterative operation.
The first classification processing module includes：
First computing module, for calculating the value of mode classification according to the following formula：
Wherein, K presentation classes mode, the value of KValue presentation class modes, the classification under k presentation class modes, | Sk | represent the corresponding alternative classification set S of classification kkThe number of the application included, SValuekRepresent alternative classification set SkMiddle bag Correlation between the application included.
The first classification processing module further includes：
Second computing module, for calculating SValue according to the following formulak：
Wherein, i, j represent the set S that alternatively classifies respectivelykWhat is included applies i and using j, simi,jIt represents using i and answers With the correlation between j, simi,jIt is determined based on user's set of application i and application j.
The first classification processing module further includes：
3rd computing module, for calculating sim according to the following formulai,j：
Wherein, UsersInstalllediRepresent that installation is gathered using the user of i, UsersInstallledjRepresent installation Gather using the user of j.
The third aspect provides a kind of equipment, including：Including processor and it is stored with the memory of computer instruction；
The processor reads the computer instruction, and the method for performing application cluster as the aforementioned.
Fourth aspect provides a kind of storage medium, which is characterized in that is stored with computer instruction, the computer refers to Order is performed the method for realizing application cluster as the aforementioned.
The method, apparatus and equipment of application cluster provided by the embodiments of the present application, for each application in multiple applications It obtains this and applies multiple alternative classification set before reclassifying, and based on the application difference of the correlation calculations between application The application is reclassified the highest classification of value by the value of corresponding mode classification when belonging to multiple alternative classification set Under mode in the alternative classification set of the application ownership, it can return by the way that the method for machine learning is above-mentioned to each application execution Each application is sorted out in the realization of class step, reduces application and sorts out required human cost, improves the accuracy that application is sorted out.
Description of the drawings
According to following detailed descriptions carried out referring to the drawings, the above and other purpose of the application, feature and will preferentially become It obtains obviously.In the accompanying drawings：
Fig. 1 is the flow chart of the method clustered according to the application of one embodiment of the application.
Fig. 2 is another flow chart of the method clustered according to the application of one embodiment of the application.
Fig. 3 is the flow chart of the method clustered according to the application of the specific embodiment of the application.
Fig. 4 is the structure diagram of the device clustered according to the application of one embodiment of the application.
Fig. 5 is the structure diagram according to the equipment of one embodiment of the application.
Specific embodiment
It is in order to make those skilled in the art better understand the technical solutions in the application, real below in conjunction with the application The attached drawing in example is applied, the technical solution in the embodiment of the present 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 Technical staff's all other embodiments obtained without creative efforts should all belong to the application protection Scope.
In this application, a kind of method, apparatus, equipment and the storage medium of application cluster are provided.Below in conjunction with attached The specific embodiment of the application is described in figure.
Referring to Fig. 1, the method for the application cluster that one embodiment of the application provides, including step 110.
Step 110, to each application execution classifying step in multiple applications, after obtaining the multiple application cluster Multiple classification set, wherein, the classifying step includes step 111 to step 113.
In step 110, classification set is corresponding with classification, and any two classification set corresponds in multiple classification set Classification it is different.
Optionally, in some embodiments, multiple applications are numbered, according to number order to every in multiple applications Classifying step described in a application execution.Such as each application in multiple applications can be held according to ascending order is numbered The row classifying step.
Specifically, step 111, obtain and apply multiple alternative classification set before reclassifying.
It should be noted that the quantity that the multiple alternative classification applied before reclassifying are gathered in step 111 It can be applied equal to the quantity of multiple classification set after multiple applications cluster or one multiple alternative before reclassifying The quantity for set of classifying can be less than the quantity of multiple classification set after multiple applications cluster, and different apply again The quantity of alternative classification set before classification can be different.For example, the quantity of multiple classification set after multiple application clusters is 5, the quantity for applying multiple alternative classification set before reclassifying that the number in multiple applications is 1 is 3, in multiple applications Number be 2 apply before reclassifying it is multiple it is alternative classification set quantity be 5.
It is understood that when to each application execution classifying step in multiple applications, it is preceding once to have performed classification The classification set obtained during step is basic using the selection for set of alternatively classifying when classifying step is once performed as after.
For example, there are 4 applications respectively using 1, using 2, using 3 and using 4, it is respectively classification there are 3 classifications 1st, classification 2 and classification 3, wherein 1 corresponding category set of classification are combined into classification set 1, and 2 corresponding category set of classification is combined into category set 2 are closed, 3 corresponding category set of classification is combined into classification set 3.Assuming that each application execution is returned according to ascending order is numbered Class step, and be to include the classification set 1 using 1, including application respectively to the classification set before 2 execution classifying step of application 2 and application 3 classification set 2, include application 4 classification set 3, to using 2 performed classifying step when classification set Become to include the classification set 1, the classification set 2 including application 1, the classification set 3 including application 3 and application 4 using 2, then When performing classifying step to application 3, multiple alternative set of the application 3 of acquisition refer to the above-mentioned category set including using 2 Close 1, the classification set 2 including application 1, the classification set 3 including application 3 and application 4.
Step 112, based on the correlation between application, calculate the application and be respectively belonging to the multiple alternative category set The value of corresponding mode classification during conjunction.
It is understood that calculate the value essence that application is respectively belonging to corresponding mode classification during multiple alternative set Refer to assume respectively using each alternative set belonged in multiple alternative set, it is different standby in alternative set using belonging to Selected works close corresponding different mode classification, calculate the value that application belongs to corresponding mode classification during each alternative set respectively.
For example, 6 applications respectively using 1, using 2, using 3, using 4, using 5 and using 6, there are 3 classes Not Fen Biewei classification 1, classification 2 and classification 3, wherein 1 corresponding category set of classification be combined into classification set 1,2 corresponding classification of classification Collection is combined into category set and closes 2, and 3 corresponding category set of classification is combined into classification set 3, and the application 1 in 6 applications is categorized in category set It in closing 2, is categorized in classification set 1 using 2 and using 3, is categorized in using 4, using 5 and using 6 in classification set 3.Assuming that Classification set 2 and classification set 3 are combined into using 1 multiple alternative category sets before reclassifying, then based on the phase between application Closing property calculates the value for being respectively belonging to classification set 2 and corresponding mode classification during classification set 3 using 1.Specifically, answering It when being belonged to 1 in classification set 2 under corresponding mode classification, is categorized in classification set 2 using 1, returns using 2 and using 3 Class is categorized in using 4, using 5 and using 6 in classification set 3 in classification set 1.It is belonged to using 1 in classification set 3 When corresponding mode classification under, be categorized in classification set 1 using 2 and using 3, sort out using 1, using 4, using 5 and application 6 In classification set 3.
Optionally, in some embodiments, based on multiple using being respectively belonging to described in the correlation calculations between application The value of corresponding mode classification is during alternative classification set：Phase between the application included based on each alternative classification set Closing property calculates the value that the application is respectively belonging to corresponding mode classification during multiple alternative classification set, for example, can root The value of mode classification is calculated according to formula (1)：
Wherein, K presentation classes mode, the value of KValue presentation class modes, the classification under k presentation class modes, | Sk | represent the corresponding alternative classification set S of classification kkThe number of the application included, SValuekRepresent alternative classification set SkMiddle bag Correlation between the application included.
Optionally, as an example, SValue is calculated according to formula (2)k：
Wherein, i, j represent the set S that alternatively classifies respectivelykWhat is included applies i and using j, simi,jIt represents using i and answers With the correlation between j, simi,jIt is determined based on user's set of application i and application j.
Specifically in definite simi,jWhen can sim be calculated according to formula (3)i,j：
Wherein, UsersInstalllediRepresent that installation is gathered using the user of i, UsersInstallledjRepresent installation Gather using the user of j.
It is understood that in formula (3), | UsersInstallledi∩UsersInstallledj| expression was both pacified Dress installs the user's set formed using the user of j using i again, | UsersInstallledi∩UsersInstallledj| table Show that only installation installs using j using i, only and is mounted with to gather using the user that the user of i and application j are formed simultaneously.
As an example it is assumed that it is respectively user 1, user 2, user 3, user 4, user 5 and user 6 to have 6 users, In, user 1, user 2, user 3 are mounted with using i, and user 1, user 2 and user 5 are mounted with using j, then to determine both to have pacified It is user 1 and user 2 that dress, which is installed again using i using the user of j, and only installation is user 3 using the user of i, and only installation is using j's User is user 5, then can be determined using the correlation sim between i and application j according to formula (3)i,j=2/4=0.5.
Step 113, the application is reclassified to alternative point of the application ownership under the highest mode classification of value In class set.
It should be noted that if the alternative category set for being worth the application ownership under highest mode classification is combined into and is holding This refers to keeping this using institute using the alternative classification set belonged to, then reclassifying in step 113 before row step 112 The alternative classification set belonged to is constant.That is, application is reclassified to the classification set belonged to including not changing the application Situation.
For example, 6 applications respectively using 1, using 2, using 3, using 4, using 5 and using 6, there are 3 classes Not Fen Biewei classification 1, classification 2 and classification 3, wherein 1 corresponding category set of classification be combined into classification set 1,2 corresponding classification of classification Collection is combined into category set and closes 2, and 3 corresponding category set of classification is combined into classification set 3, and the application 1 in 6 applications is categorized in category set It in closing 2, is categorized in classification set 1 using 2 and using 3, is categorized in using 4, using 5 and using 6 in classification set 3.Assuming that Classification set 2 and classification set 3 are combined into using 1 multiple alternative category sets before reclassifying, based on the phase between application Closing property is calculated to be respectively belonging to classification set 2 and is found during classification set 3 during the value of corresponding mode classification using 1 using 1 The value of corresponding mode classification is greater than corresponding classification side when belonging to classification set 3 using 1 when belonging to classification set 2 The value of formula will then reclassify using 1 and refer to be referred in set of applications 2 using 1.
In the embodiment of the present application, optionally, as illustrated in FIG. 2, the method for the application cluster of the application further includes step Rapid 120, wherein, the execution sequence of step 120 is before step 110.
Step 120, the maximum iteration of iterative operation is determined, wherein, the iterative operation includes answering the multiple Classifying step described in each application execution in.
That is, an iteration operation is included to each application execution classifying step in multiple applications.It is for example, multiple It is applied using for 5, then an iteration operation includes being performed both by each application in this 5 applications a time above-mentioned classification step Suddenly.
Optionally, in some embodiments, before first time performs iterative operation, the initialization of system is carried out.For example, Pond A is applied there are one assuming that, it is a collection of using, it is necessary to this batch of application is divided into N classes, then in initialization procedure using having in pond In, the application in application pond A is divided into N classes at random, and the corresponding classification set of N classes is denoted as S1, S2 ..., SN, and set Current iteration wheel number (or being interpreted as having performed the number of iterative operation) nowlte=0 has often performed once described change afterwards The numerical value of nowlte is added 1, i.e. nowlte=nowlte+1 by generation operation.
Specifically, in some embodiments, the method for the application cluster of the application further includes：The iteration behaviour will have been performed The number of work reaches multiple alternative classification set after the multiple application cluster during maximum iteration, is determined as the multiple Using multiple classification set after the final cluster of cluster.
For example, 6 applications respectively using 1, using 2, using 3, using 4, using 5 and using 6, there are 4 classes Not Fen Biewei classification 1, classification 2, classification 3 and classification 4, wherein 1 corresponding category set of classification be combined into classification set 1, classification 2 corresponds to Category set be combined into classification set 2,3 corresponding category set of classification be combined into classification set 3, classification 4 correspond to classification set 4.Initially Change process will be categorized in using 1 in classification set 1, be categorized in classification set 2 using 2 and using 3, be sorted out using 4 and application 5 In classification set 3, it is categorized in using 6 in classification set 4.Assuming that according to the ascending order of number in an iteration operation The categorizing operation above-mentioned to this 6 application executions, and maximum iteration be 4, and assume complete first time iterative operation when, should It is reclassified with 1 in classification set 2, is still referred in classification set 2 using 2 and application 3, classification is reclassified using 4 It in set 1, is still categorized in classification set 3, is still referred in classification set 4 using 6, at this time to reach greatest iteration using 5 Number then continues to execute iterative operation, and when the number for having performed iterative operation reaches 4 times, category set is reclassified using 1 It in closing 2, is reclassified using 2 in classification set 1, is still referred in classification set 2 using 3, reclassifies and classifying using 4 It in set 3, reclassifies in classification set 1 using 5, is reclassified using 6 in classification set 4, then will include using 2 Hes Gather 1, the classification set 2 including application 1, the classification set 3 including application 4 and the classification set for including application 6 using 5 classification 4 are determined as the classification set after this 6 applications finally cluster.It is understood that the number of the application in actual scene will be remote Much larger than 6, classification is also far more than 4 classes, and above-mentioned example is used for the purpose of those skilled in the art understand that the application is implemented The method of example.
Specifically, in further embodiments, the method for the application cluster of the embodiment of the present application further includes：If M is less than institute State maximum iteration, and when the number for having performed the iterative operation is M time after the multiple application cluster it is multiple alternatively Multiple alternative category sets of the number that the iterative operation is gathered and performed in classification when being M-1 times after the multiple application cluster Unification causes, then is multiple alternative category sets after M at this time the multiple application cluster by the number for having performed the iterative operation Close multiple classification set after being determined as the final cluster of the multiple application.Alternatively, if time of the iterative operation is performed Number is that multiple alternative classification set after the M clusters of the multiple application at this time with the number for having performed the iterative operation are M-1 Multiple after the multiple application cluster alternatively classify inconsistent when secondary, then perform the iterative operation.
Equally by taking 6 applications above and 4 classifications as an example, it is also assumed that according to number by small in an iteration operation The classifying step above-mentioned to this 6 application executions to big order, and maximum iteration is 4.If second should to this 6 When each application in has been carried out above-mentioned classifying step, reclassifies in classification set 2 using 1, return again using 2 Class is still referred to using 3 in classification set 2 into classification set 1, is reclassified using 4 in classification set 3, using 5 again It is referred in classification set 1, is reclassified using 6 in classification set 4, since the number for having performed iterative operation at this time is less than Maximum iteration 4 then performs iterative operation, the classifying step above-mentioned to each application execution in this 6 applications for the third time. It if when having performed iterative operation for the third time, is still referred in classification set 2 using 1, is still referred in classification set 1 using 2, It is still referred in classification set 2 using 3, is still categorized in classification set 3 using 4, is still referred in classification set 1 using 5, it should It is still categorized in classification set 4 with 6, then it is assumed that performed 4 alternative point after iterative operation after this 6 application clusters for the second time Class set has performed 4 alternative category sets unification causes after iterative operation after this 6 application clusters with third time.It will include application 2 and application 5 classification gather 1, including application 1 classification set 2, including application 4 classification set 3 and include application 6 classification Set 4 is determined as the classification set after this 6 applications finally cluster.
But if above when having performed iterative operation for the third time, reclassified using 1 in classification set 3, using 2 It reclassifies in classification set 2, is reclassified using 3 in classification set 1, reclassified using 4 in classification set 1, It reclassifies in classification set 6, is reclassified using 6 in classification set 6, then it is assumed that performed iteration for the second time using 5 4 alternative classification set after operation after this 6 application clusters and third time have been performed after iterative operation after this 6 application clusters 4 alternative classification set it is inconsistent, it is necessary to continue to execute iterative operation, further classify to this 6 applications.It can manage Solution, though it is once held after continuing to execute iterative operation until reaching maximum iteration or not up to maximum iteration Gone iterative operation when this 6 application clusters after 4 alternative classification set with it is preceding once performed iterative operation when this 6 should When being caused with 4 alternative category set unifications after cluster, stop performing iterative operation.
In other words, if the number that iterative operation is performed is to reach maximum iteration, but grasped in an iteration When being performed, the application for being repartitioned classification set (being reclassified in other words) is not present using the application in pond When, then multiple category set cooperations when this iterative operation has been performed are using the category set after the application in pond finally cluster Close, if when this iterative operation has been performed, using in pond application exist originally repartition classification set (in other words by Reclassify) in application, then needing to continue to execute iterative operation.
Fig. 3 is the method for the application cluster that one specific embodiment of the application provides, including step 210 to step 240.
Step 210, maximum iteration is set, and all applications in application pond are numbered.
For example, setting maximum iteration as 100, using there is M application in pond, the number of application is followed successively by 1,2 ..., M.
Step 220, initialized, all applications in application pond are divided into K classes, the corresponding category set of K classes at random Conjunction is denoted as S1,S2,…,SK, setting current iteration frequency n owlte=0.
Step 230, m-th application is got from the 1st application in sequence, calculates and each application is divided into each point Each application is divided into the application under the mode classification of Maximum Value and is drawn by the value of corresponding mode classification when in class set The classification set assigned to, and record whether each application is repartitioned classification.
It should be noted that the specific implementation of step 230 in the method for application shown in FIG. 1 cluster with answering multiple The realization method of each application execution classifying step in is identical, and to avoid repeating, details are not described herein.
Step 240, the value of nowlte is added 1, judges whether nowlte is greater than or equal to maximum iteration.
Step 250, if nowlte is greater than or equal to maximum iteration, classification during execution of step 230 is exported Gather the cluster result as M application.
Step 260, if nowlte is less than maximum iteration, whether have to apply in judgment step 230 and be repartitioned Classification.
Step 270, if being repartitioned classification without application in step S230, when exporting execution of step 230 Category set cooperation is the cluster result of M application.
Optionally, if judging have in step S230 using classification is repartitioned in step 260, execution is returned Step 230.
According to the specific descriptions of the method above clustered to the application of the application, the side of the application cluster of the application Method obtains this for each applying in multiple applications and multiple alternative classification before reclassifying is applied to gather, and is based on applying Between the correlation calculations applications be respectively belonging to the value of corresponding mode classification during multiple alternative classification set, should by this With reclassifying in the alternative classification set that the application under the highest mode classification of value belongs to, machine learning can be passed through Each application is sorted out in the method classifying step realization above-mentioned to each application execution, reduces application and sorts out required manpower Cost improves the accuracy that application is sorted out.
The method clustered according to the application of the embodiment of the present application is described in detail above in association with Fig. 1 to Fig. 3, below in conjunction with The device clustered according to the application of the embodiment of the present application is described in detail in Fig. 4.Implement since device embodiment is substantially similar to method Example, the relevent part can refer to the partial explaination of embodiments of method.Device embodiment described below is only schematical.
As illustrated in FIG. 4, the device 40 of application cluster provided by the embodiments of the present application includes：
First sorts out processing module 41, for each application execution classifying step in multiple applications, with described in acquisition Multiple classification set after multiple application clusters, wherein, the classifying step includes：
It obtains and applies multiple alternative classification set before reclassifying；
Based on the correlation between application, calculate the application and be respectively belonging to correspond to during the multiple alternative classification set Mode classification value；
The application is reclassified under the highest mode classification of value in the alternative classification set of the application ownership.
In the embodiment of the present application, optionally, as illustrated in FIG. 4, described device 40 further includes：
Iterations determining module 42, for it is described classification processing module to each application execution institute in multiple applications Before stating classifying step, the maximum iteration of iterative operation is determined, wherein, the iterative operation is included to the multiple application In each application execution described in classifying step.
In the embodiment of the present application, optionally, described device 40 further includes：
Second sorts out processing module, and the number for the described first classification processing module to have been performed to the iterative operation reaches Multiple alternative classification set during to the maximum iteration after the multiple application cluster, are determined as the multiple application most Multiple classification set after cluster eventually.
In the embodiment of the present application, optionally, described device 40 further includes：
3rd sorts out processing module, if it is less than the maximum iteration for M, and the first classification processing module is held Multiple alternative classification when the number of the iterative operation of having gone is M time after the multiple application cluster are gathered returns with described first Multiple alternative category sets of the number that class processing module has performed iterative operation when being M-1 times after the multiple application cluster Unification causes, then by the described first classification processing module has performed the number of the iterative operation for M times when the multiple application gather Multiple alternative classification set after class are determined as multiple classification set after the final cluster of the multiple application.
In the embodiment of the present application, optionally, the 3rd classification processing module is additionally operable to：
If the number that the first classification processing module has performed the iterative operation the multiple application cluster when being M times Afterwards it is multiple it is alternative classification set with described first classification processing module performed the number of the iterative operation for M-1 times when institute It is inconsistent to state multiple alternative classification set after multiple application clusters, then performs the iterative operation.
In the embodiment of the present application, optionally, the first classification processing module 41 includes：
First computing module, for calculating the value of mode classification according to the following formula：
Wherein, K presentation classes mode, the value of KValue presentation class modes, the classification under k presentation class modes, | Sk | represent the corresponding alternative classification set S of classification kkThe number of the application included, SValuekRepresent alternative classification set SkMiddle bag Correlation between the application included.
In the embodiment of the present application, optionally, the first classification processing module 41 further includes：
Second computing module, for calculating SValue according to the following formulak：
Wherein, i, j represent the set S that alternatively classifies respectivelykWhat is included applies i and using j, simi,jIt represents using i and answers With the correlation between j, simi,jIt is determined based on user's set of application i and application j.
In the embodiment of the present application, optionally, the first classification processing module 41 further includes：
3rd computing module, for calculating sim according to the following formulai,j：
Wherein, UsersInstalllediRepresent that installation is gathered using the user of i, UsersInstallledjRepresent installation Gather using the user of j.
This is obtained according to the device that the application of the embodiment of the present application clusters to each applying in multiple applications to apply in weight It is new sort out before multiple alternative classification set, and based on the correlation calculations between the application applications be respectively belonging to it is multiple alternatively The application is reclassified the application under the highest mode classification of value and returned by the value of corresponding mode classification during classification set In the alternative classification set belonged to, it can reduce and apply the human cost needed for sorting out, improve the accuracy of application classification.
The equipment of one embodiment according to the application is described in detail below in conjunction with Fig. 5.With reference to figure 5, in hardware view, Equipment includes processor, optionally, including internal bus, network interface, memory.Wherein, memory may include memory, example Such as high-speed random access memory (Random-Access Memory, RAM), it is also possible to further include nonvolatile memory (non-volatile memory), for example, at least 1 magnetic disk storage etc..Certainly, which is also possible that other business institutes The hardware needed.
Processor, network interface and memory can be connected with each other by internal bus, which can be industry Standard architecture (Industry Standard Architecture, ISA) bus, Peripheral Component Interconnect standard (Peripheral Component Interconnect, PCI) bus or expanding the industrial standard structure (Extended Industry Standard Architecture, EISA) bus etc..The bus can be divided into address bus, data/address bus, Controlling bus etc..For ease of representing, only represented in Fig. 5 with a four-headed arrow, it is not intended that an only bus or one kind The bus of type.
Memory, for storing program.Specifically, program can include program code, and said program code includes calculating Machine instructs.Memory can include memory and nonvolatile memory, and provide instruction and data to processor.
Processor reads corresponding computer program into memory and then is run from nonvolatile memory, in logical layer The device of application cluster is formed on face.Processor performs the program that memory is stored, and specifically for performing following operation：
To each application execution classifying step in multiple applications, to obtain multiple classification after the multiple application cluster Set, wherein, the classifying step includes：
It obtains and applies multiple alternative classification set before reclassifying；
Based on the correlation between application, calculate the application and be respectively belonging to correspond to during the multiple alternative classification set Mode classification value；
The application is reclassified under the highest mode classification of value in the alternative classification set of the application ownership.
The above-mentioned method as disclosed in the application Fig. 1 and embodiment illustrated in fig. 2 can be applied in processor or by handling Device is realized.Processor may be a kind of IC chip, have the processing capacity of signal.During realization, the above method Each step can be completed by the instruction of the integrated logic circuit of the hardware in processor or software form.Above-mentioned processing Device can be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit (Network Processor, NP) etc.；Can also be digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate Array (Field-Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or crystalline substance Body pipe logical device, discrete hardware components.Can realize or perform disclosed each method in the embodiment of the present application, step and Logic diagram.General processor can be microprocessor or the processor can also be any conventional processor etc..With reference to The step of method disclosed in the embodiment of the present application, can be embodied directly in hardware decoding processor and perform completion or with decoding Hardware and software module combination in processor perform completion.Software module can be located at random access memory, flash memory, read-only storage In the storage medium of this fields such as device, programmable read only memory or electrically erasable programmable memory, register maturation.It should The step of storage medium is located at memory, and processor reads the information in memory, the above method is completed with reference to its hardware.
Certainly, in addition to software realization mode, the equipment of the application is not precluded from other realization methods, such as logic device Mode of part or software and hardware combining etc., that is to say, that the executive agent of following process flow is not limited to each logic list Member or hardware or logical device.
The embodiment of the present application also proposed a kind of storage medium, which is stored with computer instruction, the calculating Machine instruction is performed the method for realizing application cluster as described above.
In short, the foregoing is merely the preferred embodiment of the application, the protection domain of the application is not intended to limit. It is all within spirit herein and principle, any modifications, equivalent replacements and improvements are made should be included in the application's Within protection domain.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity, Or it is realized by having the function of certain product.A kind of typical realization 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 instruction, data structure, the module of program or other data. The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (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), fast flash memory bank or other memory techniques, read-only optical disc read-only memory (CD-ROM), Digital versatile disc (DVD) or other optical storages, magnetic tape cassette, the storage of tape magnetic rigid disk or other magnetic storage apparatus Or any other non-transmission medium, the information that can be accessed by a computing device available for storage.It defines, calculates according to herein Machine readable medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludability Comprising so that process, method, commodity or equipment including a series of elements are not only including those elements, but also wrap Include other elements that are not explicitly listed or further include for this process, method, commodity or equipment it is intrinsic will Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that wanted including described Also there are other identical elements in the process of element, method, commodity or equipment.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment Point just to refer each other, and the highlights of each of the examples are difference from other examples.It is real especially for system For applying example, since it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method Part explanation.

Claims (18)

  1. A kind of 1. method of application cluster, which is characterized in that including：
    To each application execution classifying step in multiple applications, to obtain multiple category sets after the multiple application cluster It closes, wherein, the classifying step includes：
    It obtains and applies multiple alternative classification set before reclassifying；
    Based on the correlation between application, calculate the application and be respectively belonging to during the multiple alternative classification set corresponding point The value of class mode；
    The application is reclassified under the highest mode classification of value in the alternative classification set of the application ownership.
  2. 2. according to the method described in claim 1, it is characterized in that, described in each application execution in multiple applications Before classifying step, the method further includes：
    Determine the maximum iteration of iterative operation, wherein, the iterative operation is included to each should in the multiple application With the execution classifying step.
  3. 3. according to the method described in claim 2, it is characterized in that, the method further includes：
    It is multiple after the multiple application cluster when the number for having performed the iterative operation is reached the maximum iteration Alternative classification set, the multiple classification set being determined as after the final cluster of the multiple application.
  4. 4. according to the method described in claim 2, it is characterized in that, the method further includes：
    If M is less than the maximum iteration, and the multiple application clusters when the number for having performed the iterative operation is M times It is more after the multiple application cluster when the number that the iterative operation is gathered and performed in multiple alternative classification afterwards is M-1 times A alternative category set unification causes, then more after the multiple application clusters when being M times by the number for having performed the iterative operation A alternative classification set is determined as multiple classification set after the final cluster of the multiple application.
  5. 5. according to the method described in claim 4, it is characterized in that, the method further includes：
    If multiple alternative classification set of the number for having performed iterative operation when being M times after the multiple application cluster are with holding Multiple alternative classification when the number of the iterative operation of having gone is M-1 time after the multiple application cluster gather it is inconsistent, then Perform the iterative operation.
  6. 6. the method according to any one of claims 1 to 5, it is characterized in that, the phase based between the application Guan Xing calculates the value that the application is respectively belonging to corresponding mode classification during the multiple alternative classification set, including：
    The value of mode classification is calculated according to the following formula：
    <mrow> <mi>K</mi> <mi>V</mi> <mi>a</mi> <mi>l</mi> <mi>u</mi> <mi>e</mi> <mo>=</mo> <mfrac> <mrow> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>k</mi> <mo>&amp;Element;</mo> <mi>K</mi> </mrow> </msub> <mo>|</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> <mo>|</mo> <mo>&amp;CenterDot;</mo> <msub> <mi>SValue</mi> <mi>k</mi> </msub> </mrow> <mrow> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>k</mi> <mo>&amp;Element;</mo> <mi>K</mi> </mrow> </msub> <mo>|</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> <mo>|</mo> </mrow> </mfrac> <mo>;</mo> </mrow>
    Wherein, K presentation classes mode, the value of KValue presentation class modes, the classification under k presentation class modes, | Sk| it represents The corresponding alternative classification set S of classification kkThe number of the application included, SValuekRepresent alternative classification set SkInclude Correlation between.
  7. 7. according to the method described in claim 6, it is characterized in that, the method further includes：
    SValue is calculated according to the following formulak：
    <mrow> <msub> <mi>SValue</mi> <mi>k</mi> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>i</mi> <mo>&amp;Element;</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> </mrow> </msub> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>j</mi> <mo>&amp;Element;</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> <mo>,</mo> <mi>i</mi> <mo>&amp;NotEqual;</mo> <mi>j</mi> </mrow> </msub> <msub> <mi>sim</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msub> </mrow> <mrow> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>i</mi> <mo>&amp;Element;</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> </mrow> </msub> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>j</mi> <mo>&amp;Element;</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> <mo>,</mo> <mi>i</mi> <mo>&amp;NotEqual;</mo> <mi>j</mi> </mrow> </msub> <mn>1</mn> </mrow> </mfrac> <mo>;</mo> </mrow>
    Wherein, i, j represent the set S that alternatively classifies respectivelykWhat is included applies i and using j, simi,jRepresent using i and application j it Between correlation, simi,jIt is determined based on user's set of application i and application j.
  8. 8. the method according to the description of claim 7 is characterized in that the method further includes：
    Sim is calculated according to the following formulaI, j：
    <mrow> <msub> <mi>sim</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mo>|</mo> <msub> <mi>UsersInstallled</mi> <mi>i</mi> </msub> <mo>&amp;cap;</mo> <msub> <mi>UsersInstallled</mi> <mi>j</mi> </msub> <mo>|</mo> </mrow> <mrow> <mo>|</mo> <msub> <mi>UsersInstallled</mi> <mi>i</mi> </msub> <mo>&amp;cup;</mo> <msub> <mi>UsersInstallled</mi> <mi>j</mi> </msub> <mo>|</mo> </mrow> </mfrac> <mo>;</mo> </mrow>
    Wherein, UsersInstalllediRepresent that installation is gathered using the user of i, UsersInstallledjRepresent installation using j User set.
  9. 9. a kind of device of application cluster, which is characterized in that including：
    First sorts out processing module, for each application execution classifying step in multiple applications, with obtain it is the multiple should With multiple classification set after cluster, wherein, the classifying step includes：
    It obtains and applies multiple alternative classification set before reclassifying；
    Based on the correlation between application, calculate the application and be respectively belonging to during the multiple alternative classification set corresponding point The value of class mode；
    The application is reclassified under the highest mode classification of value in the alternative classification set of the application ownership.
  10. 10. device according to claim 9, which is characterized in that described device further includes：
    Iterations determining module, for it is described classification processing module to described in each application execution in multiple applications classification Before step, the maximum iteration of iterative operation is determined, wherein, the iterative operation is included to every in the multiple application Classifying step described in a application execution.
  11. 11. device according to claim 10, which is characterized in that described device further includes：
    Second sorts out processing module, and the number for the described first classification processing module to have been performed to the iterative operation reaches institute Multiple alternative classification set after the multiple application cluster during maximum iteration are stated, it is final poly- to be determined as the multiple application Multiple classification set after class.
  12. 12. device according to claim 10, which is characterized in that described device further includes：
    3rd sorts out processing module, if it is less than the maximum iteration for M, and the first classification processing module has performed At multiple alternative classification set and first classification of the number of the iterative operation when being M times after the multiple application cluster Multiple alternative category set unifications of the number that reason module has performed iterative operation when being M-1 times after the multiple application cluster It causes, then the described first classification processing module has been performed after the multiple application clusters when the number of the iterative operation is M times Multiple alternative classification set be determined as multiple classification set after the final cluster of the multiple application.
  13. 13. device according to claim 12, which is characterized in that the 3rd classification processing module is additionally operable to：
    If the number that the first classification processing module has performed the iterative operation is when being M times after the multiple application cluster The number that multiple alternative classification set and the described first classification processing module have performed the iterative operation is described more when being M-1 times Multiple alternative classification set after a application cluster are inconsistent, then perform the iterative operation.
  14. 14. the device according to any one of claim 9 to 13, which is characterized in that described first sorts out processing module bag It includes：
    First computing module, for calculating the value of mode classification according to the following formula：
    <mrow> <mi>K</mi> <mi>V</mi> <mi>a</mi> <mi>l</mi> <mi>u</mi> <mi>e</mi> <mo>=</mo> <mfrac> <mrow> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>k</mi> <mo>&amp;Element;</mo> <mi>K</mi> </mrow> </msub> <mo>|</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> <mo>|</mo> <mo>&amp;CenterDot;</mo> <msub> <mi>SValue</mi> <mi>k</mi> </msub> </mrow> <mrow> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>k</mi> <mo>&amp;Element;</mo> <mi>K</mi> </mrow> </msub> <mo>|</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> <mo>|</mo> </mrow> </mfrac> <mo>;</mo> </mrow>
    Wherein, K presentation classes mode, the value of KValue presentation class modes, the classification under k presentation class modes, | Sk| it represents The corresponding alternative classification set S of classification kkThe number of the application included, SValuekRepresent alternative classification set SkInclude Correlation between.
  15. 15. according to the method for claim 14, which is characterized in that the first classification processing module further includes：
    Second computing module, for calculating SValue according to the following formulak：
    <mrow> <msub> <mi>SValue</mi> <mi>k</mi> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>i</mi> <mo>&amp;Element;</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> </mrow> </msub> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>j</mi> <mo>&amp;Element;</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> <mo>,</mo> <mi>i</mi> <mo>&amp;NotEqual;</mo> <mi>j</mi> </mrow> </msub> <msub> <mi>sim</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msub> </mrow> <mrow> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>i</mi> <mo>&amp;Element;</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> </mrow> </msub> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>j</mi> <mo>&amp;Element;</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> <mo>,</mo> <mi>i</mi> <mo>&amp;NotEqual;</mo> <mi>j</mi> </mrow> </msub> <mn>1</mn> </mrow> </mfrac> <mo>;</mo> </mrow>
    Wherein, i, j represent the set S that alternatively classifies respectivelykWhat is included applies i and using j, simi,jRepresent using i and application j it Between correlation, simi,jIt is determined based on user's set of application i and application j.
  16. 16. device according to claim 15, which is characterized in that the first classification processing module further includes：
    3rd computing module, for calculating sim according to the following formulai,j：
    <mrow> <msub> <mi>sim</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mo>|</mo> <msub> <mi>UsersInstallled</mi> <mi>i</mi> </msub> <mo>&amp;cap;</mo> <msub> <mi>UsersInstallled</mi> <mi>j</mi> </msub> <mo>|</mo> </mrow> <mrow> <mo>|</mo> <msub> <mi>UsersInstallled</mi> <mi>i</mi> </msub> <mo>&amp;cup;</mo> <msub> <mi>UsersInstallled</mi> <mi>j</mi> </msub> <mo>|</mo> </mrow> </mfrac> <mo>;</mo> </mrow>
    Wherein, UsersInstalllediRepresent that installation is gathered using the user of i, UsersInstallledjRepresent installation using j User set.
  17. 17. a kind of equipment, which is characterized in that including processor and be stored with the memory of computer instruction；
    The processor reads the computer instruction, and performs as application described in any item of the claim 1 to 8 clusters Method.
  18. 18. a kind of storage medium, which is characterized in that be stored with computer instruction, the computer instruction is performed realization such as The method of application cluster described in any item of the claim 1 to 8.
CN201711460865.6A 2017-12-28 2017-12-28 Using the method, apparatus and equipment of cluster Pending CN108052983A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711460865.6A CN108052983A (en) 2017-12-28 2017-12-28 Using the method, apparatus and equipment of cluster

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711460865.6A CN108052983A (en) 2017-12-28 2017-12-28 Using the method, apparatus and equipment of cluster

Publications (1)

Publication Number Publication Date
CN108052983A true CN108052983A (en) 2018-05-18

Family

ID=62128741

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711460865.6A Pending CN108052983A (en) 2017-12-28 2017-12-28 Using the method, apparatus and equipment of cluster

Country Status (1)

Country Link
CN (1) CN108052983A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114397867A (en) * 2022-03-18 2022-04-26 山西正合天科技股份有限公司 Industrial personal computer control method and system based on Internet of things

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105426486A (en) * 2015-11-20 2016-03-23 天津大学 Mobile phone app pushing method based on user behavior data
CN106682684A (en) * 2016-11-23 2017-05-17 天津津航计算技术研究所 K-means clustering-based target recognition method
CN107133248A (en) * 2016-02-29 2017-09-05 阿里巴巴集团控股有限公司 The sorting technique and device of a kind of application program
US9824363B1 (en) * 2012-11-16 2017-11-21 Lu Wang Method and system for electronically engaging customers

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9824363B1 (en) * 2012-11-16 2017-11-21 Lu Wang Method and system for electronically engaging customers
CN105426486A (en) * 2015-11-20 2016-03-23 天津大学 Mobile phone app pushing method based on user behavior data
CN107133248A (en) * 2016-02-29 2017-09-05 阿里巴巴集团控股有限公司 The sorting technique and device of a kind of application program
CN106682684A (en) * 2016-11-23 2017-05-17 天津津航计算技术研究所 K-means clustering-based target recognition method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
牛奉高等: ""基于类内距离参数估计的文本聚类评价方法"", 《山西大学学报（自然科学版）》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114397867A (en) * 2022-03-18 2022-04-26 山西正合天科技股份有限公司 Industrial personal computer control method and system based on Internet of things
CN114397867B (en) * 2022-03-18 2022-06-10 山西正合天科技股份有限公司 Industrial personal computer control method and system based on Internet of things

Similar Documents

Publication Publication Date Title
WO2020147488A1 (en) Method and device for identifying irregular group
US11379845B2 (en) Method and device for identifying a risk merchant
CN109544166A (en) A kind of Risk Identification Method and device
CN107305637B (en) Data clustering method and device based on K-Means algorithm
CN109658238A (en) Data processing method and device
CN108763952A (en) A kind of data classification method, device and electronic equipment
US20210149924A1 (en) Clustering of data records with hierarchical cluster ids
TW201833851A (en) Risk control event automatic processing method and apparatus
US6480816B1 (en) Circuit simulation using dynamic partitioning and on-demand evaluation
US20160203228A1 (en) Filtering data objects
CN103309984B (en) The method and apparatus that data process
CN112861522B (en) Aspect-level emotion analysis method, system and model based on dual-attention mechanism
CN109614499A (en) A kind of dictionary generating method, new word discovery method, apparatus and electronic equipment
WO2017039684A1 (en) Classifier
CN111143678B (en) Recommendation system and recommendation method
US11003643B2 (en) Multi-level conflict-free entity clusterings
US20220229854A1 (en) Constructing ground truth when classifying data
CN108052983A (en) Using the method, apparatus and equipment of cluster
WO2021120845A1 (en) Homogeneous risk unit feature set generation method, apparatus and device, and medium
US11960846B2 (en) Embedding inference
CN110825873B (en) Method and device for expanding log exception classification rule
CN116628600A (en) Unbalanced data sampling method and device based on random forest
CN110020780A (en) The method, apparatus and electronic equipment of information output
CN102236652A (en) Method and device for classifying information
CN114238746A (en) Cross-modal retrieval method, device, equipment and storage medium

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
TA01 Transfer of patent application right

Effective date of registration: 20200526

Address after: 310051 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province

Applicant after: Alibaba (China) Co.,Ltd.

Address before: 510627 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 15 layer self unit 02

Applicant before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd.

TA01 Transfer of patent application right
RJ01 Rejection of invention patent application after publication

Application publication date: 20180518

RJ01 Rejection of invention patent application after publication