CN-115705414-B - Screening method for edge application, terminal equipment and medium

CN115705414BCN 115705414 BCN115705414 BCN 115705414BCN-115705414-B

Abstract

The invention discloses a screening method of edge application, terminal equipment and a computer readable storage medium. The method comprises the steps of determining attention weights between the edge application nodes and each adjacent node, wherein the adjacent nodes comprise industry client nodes and application scene nodes, fusing first features corresponding to the industry client nodes and second features corresponding to the edge application nodes according to the attention weights to obtain first fused features, fusing third features corresponding to the application scene nodes and the second features according to the attention weights to obtain second fused features, determining target features corresponding to the edge application nodes according to the first fused features and the second fused features, and determining screening results of edge applications corresponding to the edge application nodes according to the target features. The invention aims to achieve the effect of improving the accuracy of the screening result of the edge application.

Inventors

Xing biao
DING DONG
HU HAO
CHEN CHANGJIAO

Assignees

中国移动通信集团浙江有限公司
中国移动通信集团有限公司

Dates

Publication Date: 20260505
Application Date: 20210805

Claims (9)

1. The screening method for the edge application is characterized by comprising the following steps of: Determining the attention weight between an edge application node and each adjacent node, wherein the adjacent nodes comprise industry client nodes and application scene nodes; The method comprises the steps of obtaining a first fusion feature by fusing a first feature corresponding to an industry client node and a second feature corresponding to an edge application node according to the attention weight, and obtaining a second fusion feature by fusing a third feature corresponding to an application scene node and the second feature according to the attention weight, wherein the first feature is determined according to a text feature corresponding to an industry client demand, the second feature is determined according to a text feature corresponding to an edge application evaluation, and the third feature is determined according to a text feature corresponding to an edge application scene description; Determining target features corresponding to the edge application nodes according to the first fusion features and the second fusion features; And determining a screening result of the edge application corresponding to the edge application node according to the target characteristics.
2. The method of claim 1, wherein the step of determining the attention weight between the edge application node and each neighboring node comprises: Acquiring adjacent node characteristics and the second characteristics corresponding to each adjacent node; determining importance of each adjacent node to the edge application node based on a preset shared weight matrix, adjacent node characteristics corresponding to each adjacent node and the second characteristics; and determining the attention weight between the edge application node and each adjacent node according to the importance of each adjacent node to the edge application node.
3. The method for screening edge applications according to claim 1, wherein the step of determining the screening result of the edge application corresponding to the edge application node according to the target feature includes: inputting the target characteristics into a pre-trained screener, and determining the screening result of the edge application through the screener.
4. A method of screening for edge applications according to claim 3, wherein a binary cross entropy binary log loss function is used as an objective function for training the screener during training of the screener.
5. The method for screening edge applications according to claim 1, wherein the step of fusing the first feature corresponding to the industry client node and the second feature corresponding to the edge application node according to the attention weight to obtain a first fused feature, and fusing the third feature corresponding to the application scene node and the second feature according to the attention weight to obtain a second fused feature further comprises: The method comprises the steps of acquiring a first text feature corresponding to an industry client node, a second text feature corresponding to an edge application node and a third text feature corresponding to an application scene node, wherein the first text feature comprises a text feature corresponding to the industry client demand, the second text feature comprises a text feature corresponding to the edge application evaluation, and the third text feature comprises a text feature corresponding to the edge application scene description; Determining the first feature according to the first text feature, determining the second feature according to the second text feature, and determining the third feature according to the third text feature, wherein the first feature, the second feature and the third feature are vectors of preset dimensions.
6. The method of claim 5, wherein prior to the step of determining the attention weights between the edge application node and each neighboring node, further comprising: constructing an abnormal composition network, wherein the abnormal composition network takes the edge application node as a center, and takes the industry client node and the application scene node as neighbor nodes of the edge application node; the step of determining the attention weight between the edge application node and each neighboring node comprises: An attention weight between the edge application node and each neighbor node is determined based on the heterogeneous graph network.
7. Terminal device, characterized in that it comprises a memory, a processor and a screening program for edge applications stored on the memory and executable on the processor, which screening program for edge applications, when executed by the processor, implements the steps of the screening method for edge applications according to any of claims 1 to 6.
8. A terminal device, characterized in that the terminal device comprises: The determining module is used for determining the attention weight between the edge application node and each adjacent node, wherein the adjacent nodes comprise industry client nodes and application scene nodes; The system comprises an industry client node, a first fusion module, a second fusion module and a third fusion module, wherein the industry client node is used for acquiring an edge application node corresponding to the edge application node, the first fusion module is used for fusing a first feature corresponding to the industry client node and a second feature corresponding to the edge application node according to the attention weight to obtain a first fusion feature, and fusing a third feature corresponding to the application scene node and the second feature according to the attention weight to obtain a second fusion feature; The second fusion module is used for determining target features corresponding to the edge application nodes according to the first fusion features and the second fusion features; and the screening module is used for determining the screening result of the edge application corresponding to the edge application node according to the target characteristics.
9. A computer readable storage medium, wherein a screening program of an edge application is stored on the computer readable storage medium, which when executed by a processor, implements the steps of the method of screening an edge application according to any one of claims 1 to 6.

Description

Screening method for edge application, terminal equipment and medium Technical Field The present invention relates to the field of data processing technologies, and in particular, to a screening method for edge applications, a terminal device, and a computer readable storage medium. Background The fifth generation mobile communication is 5G-era everything interconnected, mass internet of things equipment extends upwards, and the aspects of cloud computing mode data processing and cost energy consumption will produce a bottleneck. At the same time, the extremely user experience also requires the cloud content to be extended to users, and for this reason, the rapid development of multi-access edge computing (Mobile Edge Computing, MEC) would be a necessity for technology evolution. The MEC reduces network transmission and service delivery delay by providing flexible network access capability and edge computing service at the edge of the mobile network, improves data security, and gives new development kinetic energy to the vertical industry. The edge computing nodes can be deployed in a core machine room, an important convergence machine room, a common convergence machine room and an access park machine room in a layered mode according to industry client requirements. In the related art, when a third party edge application is deployed in an edge computing node, the third party edge application matching screening mainly depends on manual experience, so that the phenomenon that the deployed edge application cannot provide a function matched with the requirement of a user for the user often occurs. Namely, the related art has the defect of inaccurate screening results of third party edge application. The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art. Disclosure of Invention The invention mainly aims to provide a screening method for edge application, terminal equipment and a computer readable storage medium, aiming at achieving the effect of improving the accuracy of a screening result of the edge application. In order to achieve the above object, the present invention provides a method for screening an edge application, the method for screening an edge application comprising the steps of: Determining the attention weight between an edge application node and each adjacent node, wherein the adjacent nodes comprise industry client nodes and application scene nodes; Fusing a first feature corresponding to the industry client node and a second feature corresponding to the edge application node according to the attention weight to obtain a first fusion feature, and fusing a third feature corresponding to the application scene node and the second feature according to the attention weight to obtain a second fusion feature; Determining target features corresponding to the edge application nodes according to the first fusion features and the second fusion features; And determining a screening result of the edge application corresponding to the edge application node according to the target characteristics. Optionally, the step of determining the attention weight between the edge application node and each neighboring node comprises: Acquiring adjacent node characteristics and the second characteristics corresponding to each adjacent node; determining importance of each adjacent node to the edge application node based on a preset shared weight matrix, adjacent node characteristics corresponding to each adjacent node and the second characteristics; and determining the attention weight between the edge application node and each adjacent node according to the importance of each adjacent node to the edge application node. Optionally, the step of determining the screening result of the edge application corresponding to the edge application node according to the target feature includes: inputting the target characteristics into a pre-trained screener, and determining the screening result of the edge application through the screener. Optionally, during the training process of the filter, a binary cross entropy binary logarithmic loss function is used as an objective function for training the filter. Optionally, the step of fusing the first feature corresponding to the industry client node and the second feature corresponding to the edge application node according to the attention weight to obtain a first fused feature, and fusing the third feature corresponding to the application scene node and the second feature according to the attention weight to obtain a second fused feature further comprises: Acquiring a first text feature corresponding to the industry client node, a second text feature corresponding to the edge application node and a third text feature corresponding to the application scene node; Determining the first feature according to the first text feature, determ