CN116467613A

CN116467613A - Application classification method and device, electronic equipment and computer readable storage medium

Info

Publication number: CN116467613A
Application number: CN202310313091.3A
Authority: CN
Inventors: 文静雅; 贺卉珍; 李新印; 张蕊
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2023-03-28
Filing date: 2023-03-28
Publication date: 2023-07-21

Abstract

The disclosure provides an application classification method and device, electronic equipment and a computer readable storage medium, which can be applied to the technical field of big data, the technical field of information security and the technical field of finance. The application grading method comprises the following steps: constructing a plurality of first calling feature matrices associated with the plurality of classified applications, and constructing a second calling feature matrix associated with the application to be classified; classifying the plurality of classified applications based on clustering results of the clustering of the plurality of first call feature matrices, and outputting at least one reference application set; classifying the second calling feature matrix by using the clustering result to determine a target reference application set to which the application to be classified belongs; and determining a second application level of the application to be classified according to the first application level corresponding to the target classified application in the target reference application set.

Description

Application classification method and device, electronic equipment and computer readable storage medium

Technical Field

The present disclosure relates to the fields of big data technology, information security technology, financial technology, and the like, and in particular, to an application classification method, apparatus, device, medium, and program product.

Background

Along with the continuous promotion of the enterprise's fine management degree, the inside information system of enterprise realizes different demands and management and control through dividing different application grades, realizes the rational utilization of resource.

In the process of implementing the disclosed concept, the inventor finds that at least the following problems exist in the related art: for a newly added application system, application grade division is often carried out by means of personal experience, on one hand, the working efficiency is low, more human resources are wasted, on the other hand, because large subjective cognitive deviation exists in artificial qualitative classification, the classification standard is ambiguous, the classification result accuracy is low, the referenceis low, and different importance degrees of the application system cannot be accurately embodied.

Disclosure of Invention

In view of the foregoing, the present disclosure provides an application ranking method, apparatus, device, medium and program product.

In one aspect of the present disclosure, there is provided an application ranking method including:

constructing a plurality of first calling feature matrixes associated with the plurality of classified applications, and constructing a second calling feature matrix associated with the application to be classified, wherein the first calling feature matrix is used for representing a first calling relationship between the plurality of classified applications, and the second calling feature matrix is used for representing a second calling relationship between the application to be classified and the plurality of classified applications;

Classifying the plurality of classified applications based on clustering results of the clustering of the plurality of first call feature matrices, and outputting at least one reference application set;

classifying the second calling feature matrix by using the clustering result to determine a target reference application set to which the application to be classified belongs;

and determining a second application level of the application to be classified according to the first application level corresponding to the target classified application in the target reference application set.

According to an embodiment of the present disclosure, wherein constructing a plurality of first call feature matrices associated with a plurality of ranked applications comprises:

reading application grade data of a plurality of graded applications and first calling relation data representing calling relations among the plurality of graded applications from a database;

a plurality of first call feature matrices associated with the plurality of ranked applications are constructed based on the application ranking data and the first call relationship data.

According to an embodiment of the present disclosure, constructing a second call feature matrix associated with an application to be ranked includes:

reading application grade data of a plurality of graded applications and second calling relation data representing calling relations between the application to be graded and the plurality of graded applications from a database;

And constructing a second calling feature matrix associated with the application to be ranked based on the application ranking data and the second calling relation data.

According to an embodiment of the present disclosure, wherein,

the values of the elements in the first call feature matrix are used to characterize: the number of applications of each class that the classified application calls and the number of applications of each class that are called;

the values of the elements in the second call feature matrix are used to characterize: the number of applications of each class to be invoked by the hierarchical application and the number of applications of each class to be invoked.

According to an embodiment of the present disclosure, clustering the plurality of first call feature matrices includes:

determining the total number of class clusters required to be scheduled for executing clustering according to the total progression corresponding to the application levels of the plurality of classified applications;

performing primary classification on the plurality of first calling feature matrixes according to the application levels of the plurality of classified applications and the total number of class clusters, and determining at least one initial data set;

calculating the average value of at least one first calling feature matrix associated with at least one classified application in each initial data set, and outputting at least one initial cluster center required to be preset for executing clustering;

and based on the at least one initial cluster center, performing iterative clustering on a plurality of first calling feature matrixes contained in the at least one initial data set for a plurality of times, and outputting a clustering result.

According to an embodiment of the present disclosure, the clustering result includes at least one target data set, and at least one target class cluster center associated with the at least one target data set, each target data set including at least one first call feature matrix associated with at least one hierarchical application.

Classifying the second calling feature matrix by using the clustering result, wherein determining the target reference application set to which the application to be classified belongs comprises the following steps:

respectively calculating the similarity between the second calling feature matrix and the center of at least one target class cluster to obtain at least one target similarity value;

and determining a target reference application set to which the application to be classified belongs according to at least one target similarity value.

According to an embodiment of the present disclosure, calculating the similarity between the second call feature matrix and the center of the at least one target class cluster, respectively, to obtain at least one target similarity value includes:

respectively calculating at least one Euclidean distance between the second calling feature matrix and the center of at least one target class cluster;

at least one target similarity value is determined based on the at least one euclidean distance.

Another aspect of the disclosure provides an application ranking apparatus, which includes a construction module, a clustering module, a categorizing module, and a determining module.

The system comprises a construction module, a first calling feature matrix and a second calling feature matrix, wherein the construction module is used for constructing a plurality of first calling feature matrices associated with a plurality of classified applications and constructing a second calling feature matrix associated with an application to be classified, the first calling feature matrix is used for representing a first calling relation among the plurality of classified applications, and the second calling feature matrix is used for representing a second calling relation between the application to be classified and the plurality of classified applications;

the clustering module is used for classifying the classified applications based on clustering results of the clustering processing of the first calling feature matrixes and outputting at least one reference application set;

the classifying module is used for classifying the second calling feature matrix by using the clustering result and determining a target reference application set to which the application to be classified belongs;

and the determining module is used for determining a second application grade of the application to be graded according to the first application grade corresponding to the target graded application in the target reference application set.

According to an embodiment of the disclosure, the build module comprises a first read unit, a first build unit.

The first reading unit is used for reading application grade data of a plurality of graded applications and first calling relation data representing calling relations among the plurality of graded applications from the database; and a first construction unit for constructing a plurality of first call feature matrices associated with the plurality of classified applications based on the application class data and the first call relationship data.

According to an embodiment of the disclosure, the building block comprises a second reading unit, a second building unit.

The second reading unit is used for reading application grade data of the plurality of graded applications and second calling relation data representing calling relations between the application to be graded and the plurality of graded applications from the database; and the second construction unit is used for constructing a second calling feature matrix associated with the application to be classified based on the application grade data and the second calling relation data.

According to an embodiment of the present disclosure, wherein: the values of the elements in the first call feature matrix are used to characterize: the number of applications of each class that the classified application calls and the number of applications of each class that are called; the values of the elements in the second call feature matrix are used to characterize: the number of applications of each class to be invoked by the hierarchical application and the number of applications of each class to be invoked.

According to an embodiment of the disclosure, the clustering module includes a first determining unit, a preliminary classifying unit, a first calculating unit, and an iterating unit.

The first determining unit is used for determining the total number of clusters required to be scheduled for executing clustering processing according to the total number of levels corresponding to the application levels of the plurality of classified applications; the primary classification unit is used for performing primary classification on the plurality of first calling feature matrixes according to the application levels of the plurality of classified applications and the total number of class clusters, and determining at least one initial data set; the first calculation unit is used for calculating the average value of at least one first calling feature matrix associated with at least one classified application in each initial data set and outputting at least one initial cluster center required to be preset for executing clustering; and the iteration unit is used for carrying out repeated iterative clustering on a plurality of first calling feature matrixes contained in at least one initial data set based on at least one initial class cluster center and outputting a clustering result.

The classifying module comprises a second calculating unit and a second determining unit.

The second calculation unit is used for calculating the similarity between the second calling feature matrix and the center of at least one target class cluster respectively to obtain at least one target similarity value; and the second determining unit is used for determining a target reference application set to which the application to be classified belongs according to at least one target similarity value.

According to an embodiment of the disclosure, the second computing unit comprises a computing subunit, a determining subunit.

The computing subunit is used for respectively computing at least one Euclidean distance between the second calling feature matrix and the center of at least one target class cluster; and the determining subunit is used for determining at least one target similarity value according to the at least one Euclidean distance.

Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the application classification method described above.

Another aspect of the present disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above-described application ranking method.

Another aspect of the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the above-described application ranking method.

According to the embodiment of the disclosure, the automatic objective rating of the application to be classified is realized by constructing the feature matrix for representing the calling relation among the applications and processing the data of the feature matrix, so that manpower is liberated, and the upgrading efficiency is improved. Meanwhile, classified applications are reclassified through clustering of a feature matrix, classified applications are classified into classified application clusters which are similar to calling features of the classified applications through classification, and the application levels of the classified applications are determined according to the application levels of the classified applications in the application clusters. According to the embodiment of the disclosure, the processing method considers the problem that the historical classification result of the classified application is not necessarily accurate along with the continuous change of the application calling relationship, and reclassifies the classified applications through clustering processing, so that the classification result of the classified application can be corrected and updated, historical classification errors can be avoided, meanwhile, an accurate reference data basis is provided for the subsequent classification processing of the application to be classified, and the objectivity, accuracy and referenceof the final classification result are further improved.

Drawings

The foregoing and other objects, features and advantages of the disclosure will be more apparent from the following description of embodiments of the disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates an application scenario diagram of an application ranking method, apparatus, device, medium and program product according to an embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow diagram of an application ranking method according to an embodiment of the present disclosure;

FIG. 3 schematically illustrates an exemplary diagram of call relationships exhibited by a first call feature matrix and a second call feature matrix in accordance with an embodiment of the present disclosure;

FIG. 4 schematically illustrates an example diagram of inter-application call pointing according to an embodiment of the present disclosure;

FIG. 5 schematically illustrates a flow chart of an application ranking method according to another embodiment of the present disclosure;

FIG. 6 schematically illustrates a block diagram of an application ranking apparatus according to an embodiment of the disclosure;

fig. 7 schematically illustrates a block diagram of an electronic device adapted to implement an application ranking method according to an embodiment of the disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.

Where expressions like "a plurality of" A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g., "a system having a plurality of" A, B and C shall include, but not be limited to, a system having a alone, B alone, C alone, a and B, a and C, B and C, and/or A, B, C, etc.).

In embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc., of the data involved (including, but not limited to, user personal information) all comply with relevant legal regulations, are used for legal purposes, and do not violate well-known. In particular, necessary measures are taken for personal information of the user, illegal access to personal information data of the user is prevented, and personal information security, network security and national security of the user are maintained.

In embodiments of the present disclosure, the user's authorization or consent is obtained before the user's personal information is obtained or collected.

It should be noted that, the application classification method and apparatus according to the embodiments of the present disclosure may be applied to the technical field of big data, or may be applied to the technical field of finance, or may be applied to any field other than the technical field of big data and the financial field, and the application fields of the application classification method and apparatus according to the embodiments of the present disclosure are not limited.

Embodiments of the present disclosure provide an application ranking method, comprising:

constructing a plurality of first calling feature matrixes associated with the plurality of classified applications, and constructing a second calling feature matrix associated with the application to be classified, wherein the first calling feature matrix is used for representing a first calling relationship between the plurality of classified applications, and the second calling feature matrix is used for representing a second calling relationship between the application to be classified and the plurality of classified applications; classifying the plurality of classified applications based on clustering results of the clustering of the plurality of first call feature matrices, and outputting at least one reference application set; classifying the second calling feature matrix by using the clustering result to determine a target reference application set to which the application to be classified belongs; and determining a second application level of the application to be classified according to the first application level corresponding to the target classified application in the target reference application set.

Fig. 1 schematically illustrates an application scenario diagram of an application ranking method, apparatus, device, medium and program product according to an embodiment of the present disclosure.

As shown in fig. 1, an application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is a medium used to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 through the network 104 using a plurality of the first terminal device 101, the second terminal device 102, the third terminal device 103, to receive or send messages, etc. Various communication client applications, such as a shopping class application, a web browser application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc. (by way of example only) may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103.

The first terminal device 101, the second terminal device 102, the third terminal device 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for websites browsed by the user using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.

In the application scenario of the embodiment of the present disclosure, a user may initiate, to the server 105, a request for acquiring an application classification to be performed on an application to be classified through the first terminal device 101, the second terminal device 102, and the third terminal device 103, and in response to the user request, the server 105 may execute the application classification method of the embodiment of the present disclosure, construct a plurality of first call feature matrices associated with a plurality of classified applications, construct a second call feature matrix associated with the application to be classified, determine a target reference application set to which the application to be classified belongs based on processing on the plurality of first call feature matrices and the second call feature matrices, determine an application class of the application to be classified according to an application class corresponding to the target classified application in the target reference application set, output an application classification result, and display the application classification result to the user through the first terminal device 101, the second terminal device 102, and the third terminal device 103.

It should be noted that, the application ranking method provided by the embodiments of the present disclosure may be generally performed by the server 105. Accordingly, the application ranking apparatus provided by the embodiments of the present disclosure may be generally provided in the server 105. The application ranking method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103 and/or the server 105. Accordingly, the application ranking apparatus provided by the embodiments of the present disclosure may also be provided in a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103 and/or the server 105.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

The application ranking method of the disclosed embodiments will be described in detail below by way of fig. 2 to 6 based on the scenario described in fig. 1.

Fig. 2 schematically illustrates a flow chart of an application ranking method according to an embodiment of the present disclosure.

As shown in fig. 2, the application ranking method of this embodiment includes operations S201 to S204.

In operation S201, constructing a plurality of first call feature matrices associated with a plurality of classified applications, and constructing a second call feature matrix associated with an application to be classified;

in operation S202, classifying a plurality of classified applications based on a clustering result of clustering the plurality of first call feature matrices, and outputting at least one reference application set;

in operation S203, classifying the second call feature matrix by using the clustering result, and determining a target reference application set to which the application to be classified belongs;

in operation S204, a second application level of the application to be ranked is determined according to the first application level corresponding to the target ranked application in the target reference application set.

According to an embodiment of the present disclosure, in operation S201, a first call feature matrix and a second call feature matrix are constructed, which may be constructed based on application level data of a plurality of classified applications and inter-application call relationship data, and the inter-application call relationship data may include, for example, first call relationship data representing call relationships between the plurality of classified applications and second call relationship data representing call relationships between an application to be classified and the plurality of classified applications. The first calling feature matrix is used for representing a first calling relation between the plurality of classified applications, and the second calling feature matrix is used for representing a second calling relation between the application to be classified and the plurality of classified applications.

According to an embodiment of the present disclosure, after the first call feature matrix and the second call feature matrix are constructed, classification of the plurality of classified applications is achieved by performing clustering processing on the plurality of first call feature matrices in operation S202. Here, it is considered that the history classification result of the classified applications is not necessarily accurate with the continuous change of the application call relationship, and therefore, reclassifying the plurality of classified applications is achieved by the clustering process, and thus, the classification result of the classified applications can be corrected and updated.

According to an embodiment of the present disclosure, the clustering result may include a plurality of data class clusters, each data class cluster corresponding to one reference application set, and in operation S203, the second call feature matrix is categorized by using the clustering result, for example, the second call feature matrix may be categorized into a class cluster most similar to the second call feature matrix, so as to determine a target reference application set to which the application to be classified belongs.

According to an embodiment of the present disclosure, the target ranked applications in the target reference application set may be all the ranked applications included in the target reference application set, or one or several ranked applications may be selected from the target reference application set as target ranked applications.

In the case that the target ranked application is all the ranked applications in the target reference application set, or in the case that the target ranked application is several ranked applications selected from the target reference application set, in operation S204, the second application level of the application to be ranked is determined according to the first application level corresponding to the target ranked application in the target reference application set, for example, the application level with the highest duty ratio in the plurality of ranked applications may be determined as the application level of the application to be ranked.

In the case where the target ranked application is a ranked application selected from the set of target reference applications, the application level of the target ranked application may be directly regarded as the application level of the target ranked application.

According to the embodiment of the disclosure, the automatic objective rating of the application to be classified is realized by constructing the feature matrix for representing the calling relation among the applications and processing the data of the feature matrix, so that manpower is liberated, and the upgrading efficiency is improved. Meanwhile, classified applications are reclassified through clustering of a feature matrix, classified applications are classified into classified application clusters which are similar to calling features of the classified applications through classification, and the application levels of the classified applications are determined according to the application levels of the classified applications in the application clusters.

According to the embodiment of the disclosure, the processing method considers the problem that the historical classification result of the classified application is not necessarily accurate along with the continuous change of the application calling relationship, and reclassifies the classified applications through clustering processing, so that the classification result of the classified application can be corrected and updated, historical classification errors can be avoided, meanwhile, an accurate reference data basis is provided for the subsequent classification processing of the application to be classified, and the objectivity, accuracy and referenceof the final classification result are further improved.

According to embodiments of the present disclosure, the values of the elements in the first call feature matrix may be used to characterize: the number of applications of each class that the classified application calls and the number of applications of each class that are called; the values of the elements in the second call feature matrix may be used to characterize: the number of applications of each class to be invoked by the hierarchical application and the number of applications of each class to be invoked.

Fig. 3 schematically illustrates an exemplary diagram of call relationships exhibited by a first call feature matrix and a second call feature matrix according to an embodiment of the disclosure. The data synchronization in table 1 demonstrates the call relationships demonstrated by the first call feature matrix and the second call feature matrix according to the example shown in fig. 3.

TABLE 1

As shown in fig. 3 and table 3, the first call feature matrix or the second call feature matrix is in the form of:

the first calling feature matrix or the second calling feature matrix is in a plurality of rows and corresponds to the unused application level respectively. The first calling feature matrix or the second calling feature matrix comprises two columns, and the element x in the first column _i1 The number of (i) represents the number of applications of each class that the classified application (or application to be classified) is called; element x in the second column _i2 The number of (i) represents the number of applications of each class called by the classified application (or the application to be classified). For example, x ₁₁ A value of 5, indicating that the ranked application (or application to be ranked) is invoked by 5 primary applications; x is x ₁₂ The value of (1) is 6, which means that the classified application (or the application to be classified) calls 6 primary applications; x is x ₃₁ A value of 2, indicating that the ranked application (or application to be ranked) is invoked by 2 tertiary applications; x is x ₂₂ A value of 6 indicates that the ranked application (or application to be ranked) invoked 6 secondary applications.

According to the embodiment of the disclosure, the first calling feature matrix and the second calling feature matrix which are constructed not only comprise calling direction information among applications, but also comprise calling or called application grade information and application quantity information, calling relations among the applications are fully reflected from multiple dimensions, data processing is carried out based on the feature matrix, and the obtained classification and grading results of the applications are objective and accurate.

According to an embodiment of the present disclosure, the construction of the plurality of first call feature matrices associated with the plurality of classified applications and the construction of the second call feature matrix associated with the application to be classified may be constructed based on application class data (table 2 below) and inter-application call relationship data (table 3 below) of the plurality of classified applications, and specifically, the following method may be adopted.

The method comprises the steps of reading application grade data of a plurality of classified applications from a database, representing first calling relation data of calling relations among the plurality of classified applications, and representing second calling relation data of calling relations between an application to be classified and the plurality of classified applications.

TABLE 2

Application system name	Application level
		Application system X	1 grade/2 grade/3 grade/4 grade/5 grade

The application level data of the hierarchical application is shown in table 2, and the information in the table includes the application system name and the application level (as an example in the table, the application system is divided into 5 levels altogether, for example, 1 to 5).

The first call relationship data of the call relationship between the plurality of classified applications (1-4) and the second call relationship data characterizing the call relationship between the application N to be classified and the plurality of classified applications may be stored in a data table, such as table 3 (call registry based on application interface).

TABLE 3 Table 3

Called party name	Calling party name
		Application system 2	Application system 1
Application system 3	Application system 2
		Application system N	Application system 2
Application system 4	Application system N

FIG. 4 schematically illustrates an example diagram of inter-application call pointing according to an embodiment of the present disclosure. The inter-application call direction indicated in fig. 4 is based on the data in table 3, and the arrow is directed to the call direction.

After the application level data and the inter-application call relationship data of the plurality of classified applications are read, a plurality of first call feature matrices associated with the plurality of classified applications can be constructed based on the application level data and the first call relationship data, and a second call feature matrix associated with the application to be classified can be constructed based on the application level data and the second call relationship data.

According to the embodiment of the disclosure, after the first calling feature matrixes are constructed, the first calling feature matrixes are clustered to achieve reclassification of the classified applications. The clustering process may employ a variety of clustering algorithms, such as k-means, k-means++, bi-kmeans, DBSCAN, and the like.

The above clustering process will be described below by taking the K-Means algorithm as an example.

The K-Means algorithm is an unsupervised clustering algorithm, where K represents the number of categories and Means represents the mean. It is an algorithm that clusters data points by means of means. The K-Means algorithm divides similar data through preset K values and initial center points of each category, and optimal clustering results are obtained through mean iterative optimization after division. The K-Means algorithm mainly uses euclidean distance to measure similarity between data, that is, the smaller the euclidean distance between data is, the higher the data similarity is.

According to the embodiment of the disclosure, the feature vector of each application system is constructed according to the call relation among the applications in the service link, the K-Means clustering algorithm is used for dividing the application system in the enterprise into a plurality of application clusters with similar call features, and the clustering result and the center point of each application cluster are finally output. The number of the class clusters and the center of the initial class clusters need to be determined in advance by adopting a K-Means algorithm.

Specifically, clustering the plurality of first call feature matrices includes:

and (11) determining the K value of the cluster-like number. And determining the total number of class clusters required to be scheduled for executing the clustering process according to the total number of levels corresponding to the application levels of the plurality of classified applications. The K value may be determined based on the number of levels to which the classified application corresponds. For example, an enterprise classifies an application system into 5 levels, thus determining k=5.

Operation 12, determining an application initial cluster-like center.

Performing primary classification on the plurality of first calling feature matrixes according to the application levels of the plurality of classified applications and the total number of class clusters, and determining at least one initial data set; and calculating the average value of at least one first calling feature matrix associated with at least one classified application in each initial data set, and outputting at least one initial cluster center required for executing clustering.

For example, according to the application class of the classified application and the total number of class clusters (class 5), the classified application is divided into 5 application clusters, if application a is classified into class 1 application, application B is classified into class 1 application, application C is classified into class 2 application, and application D is classified into class 3 application … …, then application a and application B … … belonging to class 1 application are divided into the same application cluster, application C … … belonging to class 2 application is divided into the same application cluster, and application D … … belonging to class 3 application is divided into the same application cluster.

And calculating to obtain the respective center point of each cluster as the center C of the initial cluster _k The calculation method is as shown in the following formula (1).

The calculation method is to take the arithmetic average value of each element in all application matrix vectors in the cluster, see the following formula (2).

Wherein x is _ij The values of the elements in the matrix vector are represented, and n represents the number of applications in the application cluster k.

And 13, based on at least one initial cluster center, performing iterative clustering on a plurality of first calling feature matrixes contained in at least one initial data set for a plurality of times, and outputting a clustering result.

Specifically, the Euclidean distance between each application and each center point can be calculated, and the application clusters to which the application system belongs are rearranged according to the nearest distance.

For example, compute application X to application cluster k center point C _k Euclidean distance d (X, C) _k ) The following (3)

Calculating the center points of the application clusters again according to the secondary clustering result, comparing the new center points of the k clusters with the original center points, ending iteration when the center points are not changed any more and the application attribution application clusters are not changed any more, and outputting a final clustering result and the center points C of the application clusters _k Otherwise, the above operation 13 is repeated.

According to the embodiment of the disclosure, reclassifying of the plurality of classified applications is achieved through clustering, so that the classification results of the classified applications can be corrected and updated, and historical classification errors can be avoided. The hierarchical application is marked with the original application level information, so that the K-Means clustering algorithm has strong advantages in the process of determining the number of the clusters and the center of the initial clusters, the more accurate number of the clusters and the center of the initial clusters can accelerate algorithm convergence, the subsequent iterative calculation process is reduced, and the calculation speed is increased.

and (21) respectively calculating the similarity between the second calling feature matrix and the center of at least one target class cluster to obtain at least one target similarity value.

Firstly, respectively calculating at least one Euclidean distance between a second calling feature matrix and the center of at least one target class cluster; and then determining at least one target similarity value according to the at least one Euclidean distance.

Calculating Euclidean distance d (S, C) from application S to be classified to central point of each application cluster _k ) The following (4)

An operation 22 determines a target reference application set to which the application to be ranked belongs according to at least one target similarity value. For example, the application cluster with the shortest center point is used as the application home cluster to be classified.

Fig. 5 schematically illustrates a flow chart of an application ranking method according to another embodiment of the present disclosure.

According to the application classification method, firstly, feature vectors of each application system are constructed according to calling relations among applications in a service link, an enterprise internal application system is divided into a plurality of application clusters with similar calling features by using a K-Means clustering algorithm, then, euclidean distance between an application to be classified and a central point of each application cluster is calculated, an application cluster with the shortest distance is selected as an application attribution cluster to be classified, and an application class with the highest proportion in the application cluster is used as an application class of the application to be classified. Operations S501-S508 are specifically described in fig. 5.

As shown in fig. 5, in operation S501, application level data (refer to table 2 in the foregoing embodiment) of a plurality of classified applications and call relationship data between applications (refer to table 3 in the foregoing embodiment) are collected, call feature matrices for the classified applications are constructed, and call feature matrices for the applications to be classified are constructed, and a specific construction method refers to a description of the construction of the first call feature matrix and the second call feature matrix in the foregoing embodiment, which is not repeated herein.

In operations S502-S505, the plurality of classified applications are subjected to clustering processing using a K-Means algorithm, classified based on the clustering result, and output at least one reference application set and at least one cluster-like center.

The number of clusters and the initial cluster center are determined in advance by using the K-Means algorithm, specifically, in operation S502, application clusters are divided according to the existing application level system, and the initial cluster center of each application cluster is calculated. And performing iterative computation in S503-S505, re-iterating the application clusters and re-iterating the class cluster centers until the values of the class cluster centers are unchanged, and outputting a final classification result and the class cluster centers. The specific method for performing the clustering process may refer to the method for performing the clustering process on the plurality of first call feature matrices in the foregoing embodiment, which is not described herein.

In operations S506-S507, the clustering result is used to classify the application to be classified according to the clustering result (including at least one application cluster and at least one cluster center associated with the at least one application cluster), and a target application cluster to which the application to be classified belongs is determined.

Specifically, in operation S506, euclidean distances to be applied to centers of the clusters in a hierarchical manner are calculated, and in operation S507, the euclidean distances are classified into target application clusters with shortest distances. For a specific processing method, reference may be made to the operation of classifying the second call feature matrix by using the clustering result in the foregoing embodiment, which is not described herein.

In operation S508, the application level with the highest number of the target application clusters is counted and used as the application level of the application to be classified.

Based on the application classification method, the disclosure further provides an application classification device. The device will be described in detail below in connection with fig. 6.

Fig. 6 schematically illustrates a block diagram of an application ranking apparatus according to an embodiment of the disclosure.

As shown in fig. 6, the application ranking apparatus 600 of this embodiment includes a construction module 601, a clustering module 602, a categorizing module 603, and a determining module 604.

The construction module 601 is configured to construct a plurality of first call feature matrices associated with the plurality of classified applications, and construct a second call feature matrix associated with the application to be classified, where the first call feature matrix is used to characterize a first call relationship between the plurality of classified applications, and the second call feature matrix is used to characterize a second call relationship between the application to be classified and the plurality of classified applications;

A clustering module 602, configured to classify the plurality of classified applications based on a clustering result of the clustering process on the plurality of first call feature matrices, and output at least one reference application set;

the classifying module 603 is configured to perform classifying processing on the second invoking feature matrix by using the clustering result, and determine a target reference application set to which the application to be classified belongs;

the determining module 604 is configured to determine a second application level of the application to be ranked according to a first application level corresponding to the target ranked application in the target reference application set.

According to an embodiment of the present disclosure, wherein the build module 601 comprises a first reading unit, a first build unit.

According to an embodiment of the present disclosure, the building block 601 comprises a second reading unit, a second building unit.

According to an embodiment of the present disclosure, the clustering module 602 includes a first determining unit, a preliminary classifying unit, a first calculating unit, and an iterating unit.

The categorizing module 603 includes a second calculating unit, a second determining unit.

Any of the building module 601, the clustering module 602, the categorizing module 603, the determining module 604 may be combined in one module for implementation, or any of the modules may be split into multiple modules, according to embodiments of the present disclosure. Alternatively, at least some of the functionality of one or more of the modules may be combined with at least some of the functionality of other modules and implemented in one module. According to embodiments of the present disclosure, a plurality of the building module 601, the clustering module 602, the categorizing module 603, the determining module 604 may be implemented at least in part as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable way of integrating or packaging circuitry, or in any one of or a suitable combination of three of software, hardware, and firmware. Alternatively, a plurality of the building module 601, the clustering module 602, the categorizing module 603, the determining module 604 may be at least partially implemented as computer program modules which, when executed, may perform the respective functions.

As shown in fig. 7, an electronic device 700 according to an embodiment of the present disclosure includes a processor 701 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. The processor 701 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor 701 may also include on-board memory for caching purposes. The processor 701 may comprise a single processing unit or a plurality of processing units for performing different actions of the method flows according to embodiments of the disclosure.

In the RAM 703, various programs and data necessary for the operation of the electronic apparatus 700 are stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. The processor 701 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 702 and/or the RAM 703. Note that the program may be stored in one or more memories other than the ROM 702 and the RAM 703. The processor 701 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the electronic device 700 may further include an input/output (I/O) interface 705, the input/output (I/O) interface 705 also being connected to the bus 704. The electronic device 700 may also include one or more of the following components connected to an input/output (I/O) interface 705: an input section 706 including a keyboard, a mouse, and the like; an output portion 707 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 708 including a hard disk or the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The drive 710 is also connected to an input/output (I/O) interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read therefrom is mounted into the storage section 708 as necessary.

The present disclosure also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, the computer-readable storage medium may include ROM 702 and/or RAM 703 and/or one or more memories other than ROM 702 and RAM 703 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowcharts. The program code, when executed in a computer system, causes the computer system to implement the application ranking method provided by the embodiments of the present disclosure.

The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 701. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed over a network medium in the form of signals, downloaded and installed via the communication section 709, and/or installed from the removable medium 711. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709, and/or installed from the removable medium 711. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 701. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

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

Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.

Claims

1. An application ranking method, comprising:

constructing a plurality of first calling feature matrixes associated with a plurality of classified applications, and constructing a second calling feature matrix associated with an application to be classified, wherein the first calling feature matrixes are used for representing first calling relations among the plurality of classified applications, and the second calling feature matrixes are used for representing second calling relations between the application to be classified and the plurality of classified applications;

2. The method of claim 1, wherein constructing a plurality of first call feature matrices associated with a plurality of ranked applications comprises:

and constructing a plurality of first calling feature matrixes associated with a plurality of the graded applications based on the application grade data and the first calling relation data.

3. The method of claim 2, wherein constructing a second call feature matrix associated with the application to be ranked comprises:

And constructing a second calling feature matrix associated with the application to be classified based on the application grade data and the second calling relation data.

4. The method of claim 3, wherein,

the values of the elements in the first call feature matrix are used to characterize: the number of the applications of each class called by the classified application and the number of the applications of each class called;

the values of the elements in the second call feature matrix are used to characterize: and the number of the applications of each class called by the application to be classified and the number of the applications of each class called.

5. The method of claim 1, wherein clustering the plurality of first call feature matrices comprises:

determining the total number of clusters required to be scheduled for executing the clustering process according to the total number of levels corresponding to the application levels of the plurality of classified applications;

performing primary classification on the plurality of first call feature matrices according to application levels of the plurality of classified applications and the total number of class clusters, and determining at least one initial data set;

calculating the average value of at least one first calling feature matrix associated with at least one classified application in each initial data set, and outputting at least one initial cluster center required to be scheduled for executing the clustering process;

And based on the at least one initial cluster center, performing iterative clustering on a plurality of first calling feature matrixes contained in the at least one initial data set for a plurality of times, and outputting the clustering result.

6. The method of any of claims 1-5, wherein the clustering result comprises at least one target data set, and at least one target class cluster center associated with the at least one target data set, each of the target data sets comprising at least one first invocation feature matrix associated with at least one hierarchical application;

classifying the second call feature matrix by using the clustering result, wherein determining the target reference application set to which the application to be classified belongs comprises:

respectively calculating the similarity between the second calling feature matrix and at least one target cluster center to obtain at least one target similarity value;

and determining a target reference application set to which the application to be classified belongs according to the at least one target similarity value.

7. The method of claim 6, wherein calculating the similarity between the second call feature matrix and the at least one target class cluster center, respectively, to obtain at least one target similarity value comprises:

and determining the at least one target similarity value according to the at least one Euclidean distance.

8. An application ranking apparatus comprising:

the system comprises a construction module, a first calling feature matrix and a second calling feature matrix, wherein the construction module is used for constructing a plurality of first calling feature matrices associated with a plurality of classified applications, the first calling feature matrix is used for representing a first calling relation among the plurality of classified applications, and the second calling feature matrix is used for representing a second calling relation among the plurality of classified applications and the to-be-classified applications;

the clustering module is used for classifying the plurality of classified applications based on clustering results of the clustering processing of the plurality of first calling feature matrixes and outputting at least one reference application set;

the classifying module is used for classifying the second calling feature matrix by utilizing the clustering result and determining a target reference application set to which the application to be classified belongs;

and the determining module is used for determining the second application grade of the application to be graded according to the first application grade corresponding to the target graded application in the target reference application set.

9. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs,

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

10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to any of claims 1-7.

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