Edge computing task distribution method, device, equipment and medium

Abstract

The present invention provides an edge computing task distribution method, device, equipment and medium, the method comprising: semantically segmenting the data to be transmitted to obtain different types of semantic slicing tasks; based on the data analysis capability of each edge node and the data security level of the semantic slicing task, the semantic slicing task is allocated to determine the slicing tasks to be allocated corresponding to each edge node; and the slicing tasks to be allocated are distributed to the corresponding edge nodes. The present invention is used to solve the defect of low data transmission efficiency between edge nodes in the prior art, ensure lower latency of edge computing when performing cross-node data analysis and processing, meet the needs of reducing network occupancy and reducing network costs by reducing the size of transmitted data, or do not affect the normal operation of the business in the case of poor network quality, meet availability requirements, and improve the overall efficiency of the edge computing system.

Description

Technical Field

[0001] The present invention relates to the field of computer communication network technology, and in particular to an edge computing task distribution method, device, equipment and medium. Background Art

[0002] Compared with the traditional model that is completely based on the cloud, the edge system architecture deploys cloud functions such as storage, computing, processing and networking on the side close to the end user. In recent years, the edge computing industry has gradually played an important role in ICT infrastructure in various industries due to its low latency and high bandwidth capabilities, rapid technological development and continuous market expansion.

[0003] However, the current standards and technologies of edge computing systems are mainly aimed at the functions and interactions of various modules within a unified system. With the in-depth development of industry applications such as the industrial Internet, the interactive needs of edge computing systems are gradually increasing. During the interaction of edge computing systems, a large amount of data needs to be transmitted over the network, especially video data, which will occupy a large amount of network resources.

[0004] Therefore, there is an urgent need for a processing method to improve the data transmission efficiency between edge nodes in an edge computing system. Summary of the invention

[0005] The present invention provides an edge computing task distribution method, device, equipment and medium, which are used to solve the defect of low data transmission efficiency between edge nodes in the prior art and improve the data transmission efficiency between edge nodes.

[0006] The present invention provides an edge computing task distribution method, comprising:

[0007] Semantically segment the data to be transmitted to obtain different types of semantic slicing tasks;

[0008] Based on the data analysis capability of each edge node and the data security level of the semantic slicing task, the semantic slicing task is allocated, and the slicing task to be allocated corresponding to each edge node is determined;

[0009] Distribute the slice tasks to be assigned to the corresponding edge nodes.

[0010] According to an edge computing task distribution method provided by the present invention, semantic segmentation is performed on the data to be transmitted to obtain different types of semantic slicing tasks, including:

[0011] Obtaining a preset semantic environment type, wherein the semantic environment type includes data segmentation rules corresponding to a plurality of different application scenarios;

[0012] Based on the type of semantic environment, the data to be transmitted is divided into multiple semantic slices to obtain different types of semantic slice tasks.

[0013] According to an edge computing task distribution method provided by the present invention, based on the data analysis capability of each edge node and the data security level of the semantic slicing task, the semantic slicing task is allocated, and the to-be-allocated slicing task corresponding to each edge node is determined, including:

[0014] Determining that the slicing task to be assigned includes sensitive data;

[0015] Based on the sensitive data, determine the data security level corresponding to the slicing task to be assigned;

[0016] If the data security level exceeds the preset security threshold, the to-be-allocated slice task is allocated to the local edge node;

[0017] If the data security level does not exceed the preset security threshold, the semantic slicing tasks are allocated based on the data analysis capabilities of each edge node, and the slicing tasks to be allocated to other edge nodes in the edge nodes except the local edge node are determined.

[0018] According to an edge computing task distribution method provided by the present invention, the semantic slicing tasks are distributed based on the data analysis capability of each edge node, and the slicing tasks to be distributed to other edge nodes in each edge node except the local edge node are determined, including:

[0019] Determine a semantic slice tag corresponding to the semantic slice task;

[0020] Match the node capability deployment identifier in the node capability deployment list with the semantic slice tag to determine the slice tasks to be allocated to other edge nodes in each of the edge nodes except the local edge node;

[0021] The node capability deployment identifier is used to characterize the data analysis capability.

[0022] According to an edge computing task distribution method provided by the present invention, each edge node internally maintains the node capability deployment list;

[0023] Each edge node is used to broadcast the to-be-updated node capability deployment identifier of the node to be updated to its neighboring nodes, and the to-be-updated node capability deployment identifier is used to update the node capability deployment list.

[0024] According to an edge computing task distribution method provided by the present invention, after distributing the slice task to be assigned to the corresponding edge node, the method includes:

[0025] If the slice task to be assigned belongs to the local edge node, the local computing capacity of the local edge node is obtained;

[0026] If the occupied computing power of the local computing capacity exceeds a preset threshold, the slice task to be allocated will be distributed to other edge nodes other than the local edge node.

[0027] The present invention also provides an edge computing task distribution device, comprising:

[0028] The segmentation module is used to semantically segment the data to be transmitted and obtain different types of semantic slicing tasks;

[0029] An allocation module, configured to allocate the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks, and determine the slicing tasks to be allocated corresponding to each edge node;

[0030] The distribution module is used to distribute the slice tasks to be assigned to the corresponding edge nodes.

[0031] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an edge computing task distribution method as described above is implemented.

[0032] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the edge computing task distribution methods described above.

[0033] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the edge computing task distribution methods described above.

[0034] The present invention provides an edge computing task distribution method, device, equipment and medium, which semantically segments data to obtain different types of semantic slicing tasks, and then distributes the semantic slicing tasks to edge nodes with corresponding data analysis capabilities, so that edge nodes that can provide processing results for semantic slicing tasks can match them, and the data is distributed to corresponding edge nodes by first segmenting and then distributing. It can be used as a method for transmitting data between edge computing nodes, ensuring lower latency when edge computing performs data analysis and processing across nodes, meeting the needs of reducing network occupancy and reducing network costs by reducing the size of transmitted data, or not affecting the normal operation of the business when the network quality is poor, meeting availability requirements, improving the data transmission efficiency between edge nodes, and improving the overall efficiency of the edge computing system. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 This is one of the flow charts of the edge computing task distribution method provided by the present invention;

[0037] Figure 2 This is the second flow chart of the edge computing task distribution method provided by the present invention;

[0038] Figure 3 This is the third flow chart of the edge computing task distribution method provided by the present invention;

[0039] Figure 4 This is the fourth flow chart of the edge computing task distribution method provided by the present invention;

[0040] Figure 5 This is the fifth flow chart of the edge computing task distribution method provided by the present invention;

[0041] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Combine the following Figure 1-Figure 5 The edge computing task distribution method of the present invention is described.

[0044] Please refer to Figure 1 , the edge computing task distribution method provided by the present invention includes:

[0045] Step 10, semantically segmenting the data to be transmitted to obtain different types of semantic slicing tasks;

[0046] In the application scenarios of edge computing systems, with the in-depth development of the industrial Internet industry, the interactive needs of edge computing systems are gradually increasing. During the interaction of edge computing systems, a large amount of data needs to be transmitted in the network, especially video data, which will occupy a large amount of network resources. The present invention proposes an edge computing task distribution method based on semantic communication, which can be used as a way to transmit data between edge computing nodes to reduce the network resources occupied by data transmission, reduce network costs, and reduce network latency.

[0047] The data to be transmitted may include voice data, video data, image data, text data, file data, etc. The embodiment of the present application is applied to an edge computing system, which includes a large number of data analysis and computing nodes, collectively referred to as edge nodes, that is, the edge computing system includes a large number of edge nodes, which are used to provide data analysis and computing resources.

[0048] Step 20, based on the data analysis capability of each edge node and the data security level of the semantic slicing task, the semantic slicing task is allocated, and the slicing task to be allocated corresponding to each edge node is determined;

[0049] After acquiring the data to be transmitted, semantic segmentation is performed on the data to be transmitted to obtain semantic slicing tasks of different semantic types. The purpose of this step is to segment the data to be transmitted into semantic slicing tasks of different semantic types according to different semantic types. Afterwards, the data analysis capabilities of other edge nodes are received, and the slicing tasks that the edge nodes can process are determined based on the data analysis capabilities of the edge nodes, and the slicing tasks to be allocated to the edge nodes are obtained.

[0050] It can be understood that in the task slicing step, the purpose is to slice the data into semantic slicing tasks of different semantic types according to different semantic types and data security levels; in the slicing task allocation step, the purpose is to determine which edge node the slicing task belongs to. In a possible embodiment, first, the data to be transmitted is divided into face data, pedestrian behavior data, voice data, and license plate data, and then the edge node with data analysis capabilities of face data is determined to be a face recognition capability node, and then the face data is allocated to the face recognition capability node, and the pedestrian behavior data, voice data, and license plate data are allocated and distributed, and so on.

[0051] It should be noted that a semantic slice task distribution module is deployed in the edge computing system. The semantic slice task distribution module is used to analyze and process the data to be transmitted, and divide the data to be transmitted into different types of semantic slices, receive the data analysis capabilities of other edge nodes, and assign semantic slice tasks according to the data analysis capabilities of each edge node to obtain the slice tasks to be assigned corresponding to the edge node. By deploying the semantic slice task distribution module, a lower latency is achieved in edge computing when performing data analysis and processing across nodes. By reducing the size of transmitted data, the requirements of reducing network occupancy and reducing network costs are met, the real-time and reliability of data processing and analysis are guaranteed, and the overall efficiency of the edge computing system and the security of not transmitting irrelevant data are improved.

[0052] Among them, the data analysis capability refers to the data analysis capability that each edge node has for certain semantic data. The data analysis capability may include face recognition capability, behavior recognition capability, fire recognition capability, helmet wearing recognition capability, voice recognition capability, etc.

[0053] Step 30, distribute the slice tasks to be assigned to the corresponding edge nodes.

[0054] After the semantic slice tasks are assigned, the obtained slice tasks to be assigned are distributed to the corresponding edge nodes. For example, in one possible example, the face data in the video data is assigned to the face recognition capability node, the pedestrian behavior data is assigned to the pedestrian behavior recognition capability node, the voice data is assigned to the voice recognition node, and the license plate data is assigned to the license plate recognition capability node.

[0055] The present invention provides an edge computing task distribution method, which semantically segments data to obtain different types of semantic slicing tasks, and then distributes the semantic slicing tasks to edge nodes with corresponding data analysis capabilities, so that edge nodes that can provide processing results for semantic slicing tasks can be matched with them, and the data is distributed to corresponding edge nodes by first segmenting and then distributing. It can be used as a data transmission method between edge computing nodes to ensure lower latency when edge computing performs data analysis and processing across nodes. By reducing the size of transmitted data, the needs of reducing network occupancy and reducing network costs are met, or when the network quality is poor, the normal operation of the business is not affected, the availability requirements are met, the data transmission efficiency between edge nodes is improved, and the overall efficiency of the edge computing system is improved.

[0056] In one embodiment, see Figure 2 , Step 10, semantically segment the data to be transmitted to obtain different types of semantic slicing tasks, including:

[0057] Step 11, obtaining a preset semantic environment type, wherein the semantic environment type includes data segmentation rules corresponding to a plurality of different application scenarios;

[0058] Step 12, based on the type of semantic environment, divide the data to be transmitted into multiple semantic slices to obtain different types of semantic slice tasks.

[0059] In the embodiment of the present application, according to the data segmentation rules corresponding to a variety of different application scenarios, the data is divided into different types of semantic slicing tasks according to different semantic environments. The same source data can be semantically segmented by the semantic slicing task distribution module according to the semantic environment type preset by the system, so that it is divided into multiple semantic slicing tasks, each slice contains different semantic content, and the amount of data in each semantic slice is much smaller than the data to be transmitted of the source data.

[0060] The semantic environment type is set by the operator according to actual needs, and the semantic environment type may include road traffic scenes, indoor safety scenes, etc. For example, for the video data collected by the monitoring inside the factory, it is necessary to perform semantic slicing such as abnormal behavior recognition, helmet wearing recognition, and fire recognition. That is, the semantic environment types include behavior type type, helmet recognition type, and fire recognition type. For the video data collected by the monitoring of traffic roads, the semantic environment types may include pedestrian behavior recognition, vehicle behavior recognition, license plate recognition, and traffic violation type recognition.

[0061] Furthermore, it may also include segmenting the semantic slicing task according to the type of semantic environment and marking it accordingly to obtain a semantic slicing mark corresponding to the semantic slicing task.

[0062] In this embodiment, by dividing the data into different types of semantic slices according to different semantic environments, it is possible to divide the data to be transmitted into multiple semantic slices and divide it into semantic slice tasks of different types of semantic environments. Reasonable division according to different types of semantic environments can improve the rationality of data division, thereby further improving the efficiency of transmission between edge nodes.

[0063] In one embodiment, see Figure 3 Step 20, based on the data analysis capability of each edge node and the data security level of the semantic slicing task, the semantic slicing task is allocated, and the slicing task to be allocated corresponding to each edge node is determined, including:

[0064] Step 21, determining that the slice task to be assigned includes sensitive data;

[0065] Step 22: determining the data security level corresponding to the slice task to be assigned based on the sensitive data;

[0066] Step 23: if the data security level exceeds the preset security threshold, the slice task to be allocated is allocated to the local edge node;

[0067] Step 24: If the data security level does not exceed the preset security threshold, the semantic slicing tasks are allocated based on the data analysis capabilities of each edge node, and the slicing tasks to be allocated to other edge nodes in the edge nodes except the local edge node are determined.

[0068] In an embodiment of the present application, sensitivity identification is performed on the slicing task to be assigned to determine whether the slicing task to be assigned contains sensitive data. If the task to be assigned contains sensitive data, the data security level of the sensitive data is determined based on the data type contained in the sensitive data, and the data security level corresponding to the slicing task to be assigned containing sensitive data is obtained.

[0069] Sensitive data can include face, ID card, fingerprint and other data. Data security levels can be divided into high, medium and low levels. High-level slice tasks are assigned to local computing nodes, and medium and low-level slice tasks are assigned to other edge nodes outside local computing nodes.

[0070] For example, analysis requirements involving local or high-security databases such as facial recognition can only be processed locally.

[0071] In the embodiment of the present application, the data security level corresponding to the slice task to be assigned is assigned to the corresponding edge node for processing to avoid data leakage involving sensitive data, thereby improving the security of data processing.

[0072] In one embodiment, see Figure 4 , step 24, allocating the semantic slicing tasks based on the data analysis capability of each edge node, and determining the slicing tasks to be allocated to other edge nodes in each edge node except the local edge node, including:

[0073] Step 241, determining a semantic slice tag corresponding to the semantic slice task;

[0074] Step 242, matching the node capability deployment identifier in the node capability deployment list with the semantic slice tag, and determining the slice tasks to be allocated to other edge nodes in each of the edge nodes except the local edge node;

[0075] The node capability deployment identifier is used to characterize the data analysis capability.

[0076] According to the type of semantic environment, the semantic slicing task is segmented and marked accordingly, and the semantic slicing mark corresponding to the semantic slicing task is obtained. That is, according to the type of semantic environment, the data is divided into different types of semantic slices according to different semantic environments and the semantic slicing tasks are marked, and the semantic slicing mark corresponding to the semantic slicing task is obtained. Among them, the semantic environment type corresponds to the data analysis capability of the edge node.

[0077] For example, when data is generated (especially video data), it is transmitted by the end node within the edge computing system to the node where the semantic slicing task distribution module is deployed. The semantic slicing task distribution module is mainly responsible for analyzing and processing the data to be processed, dividing the data into different types of semantic slices according to different semantic environments and marking them. The labels correspond to the node capability deployment identifiers.

[0078] Match the node capability deployment identifier and the semantic slice tag to achieve matching based on the capabilities deployed by the edge nodes and the processing capabilities required by the semantic slices, so that the nodes that can provide processing results for the semantic slices can be matched with them, improving the allocation efficiency and accuracy of the semantic slice tasks, thereby further improving the data transmission efficiency between edge nodes.

[0079] In one embodiment, each edge node internally maintains the node capability deployment list, and the node capability deployment identifier in the node capability deployment list corresponds to the data analysis capability;

[0080] Each edge node is used to broadcast the to-be-updated node capability deployment identifier of the node to be updated to its neighboring nodes, and the to-be-updated node capability deployment identifier is used to update the node capability deployment list.

[0081] In the edge computing nodes deployed through the computing network, each node sends the data analysis capabilities of the node to the neighboring nodes through broadcasting, such as face recognition capability, behavior recognition capability, fire recognition capability, etc. Each node maintains a neighboring node capability deployment table and uniformly identifies the corresponding capabilities. After the data analysis capabilities deployed by each node are updated (added, deleted, or modified), the updated data analysis capabilities of the node are sent to the neighboring nodes through broadcasting, and the neighboring node capability deployment table is updated immediately.

[0082] In one embodiment, see Figure 5 Step 30, after distributing the slice task to be assigned to the corresponding edge node, includes:

[0083] Step 40: If the slice task to be assigned belongs to the local edge node, obtain the local computing capacity of the local edge node;

[0084] Step 50: If the occupied computing power of the local computing capacity exceeds a preset threshold, the slice task to be allocated is distributed to other edge nodes other than the local edge node.

[0085] In the embodiment of the present application, after the semantic slicing task distribution module completes the semantic slicing and distributes it, it compares the adjacent node capability deployment table maintained internally, and for the data processing capability that the node already has, it can choose whether to process locally or distribute it to other edge computing nodes for processing according to actual needs. It can also include, in the case of being assigned to a local computing node, if the slicing task to be assigned belongs to the local computing node, obtaining the local computing capacity corresponding to the local computing node, and determining whether the occupied capacity of the local computing capacity exceeds the preset threshold; if the local computing capacity has been occupied by more than the preset threshold, such as 80%, it is distributed to other edge computing nodes for processing.

[0086] After the edge computing node completes the semantic slice data analysis, it returns the analysis results (for example, the occurrence of a fire) and the node capability deployment identifier to the source edge computing node. After the source edge computing node obtains the analysis results, it summarizes the results within the system and provides services such as result reporting, alarming, and uploading.

[0087] Furthermore, based on the above-mentioned semantic slicing, maintenance and update of the adjacent node capability deployment table, and hierarchical task distribution of semantic slicing according to data security level, it is possible to achieve normal service of the MEC system under poor network conditions or limited computing power without excessive repeated development and excessive transformation of the existing MEC system. This further realizes the intercommunication of edge ubiquitous computing power, improves service continuity, and improves user experience and service quality.

[0088] The edge computing task distribution device provided by the present invention is described below. The edge computing task distribution device described below and the edge computing task distribution method described above can be referenced to each other.

[0089] The edge computing task distribution device proposed by the present invention includes:

[0090] The segmentation module is used to semantically segment the data to be transmitted and obtain different types of semantic slicing tasks;

[0091] An allocation module, configured to allocate the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks, and determine the slicing tasks to be allocated corresponding to each edge node;

[0092] The distribution module is used to distribute the slice tasks to be assigned to the corresponding edge nodes.

[0093] Furthermore, the segmentation module is also used for:

[0094] Obtaining a preset semantic environment type, wherein the semantic environment type includes data segmentation rules corresponding to a plurality of different application scenarios;

[0095] Based on the type of semantic environment, the data to be transmitted is divided into multiple semantic slices to obtain different types of semantic slice tasks.

[0096] Furthermore, the segmentation module is also used for:

[0097] Determining that the slicing task to be assigned includes sensitive data;

[0098] Based on the sensitive data, determine the data security level corresponding to the slicing task to be assigned;

[0099] If the data security level exceeds the preset security threshold, the to-be-allocated slice task is allocated to the local edge node;

[0100] If the data security level does not exceed the preset security threshold, the semantic slicing tasks are allocated based on the data analysis capabilities of each edge node, and the slicing tasks to be allocated to other edge nodes in the edge nodes except the local edge node are determined.

[0101] Furthermore, the segmentation module is also used for:

[0102] Determine a semantic slice tag corresponding to the semantic slice task;

[0103] Match the node capability deployment identifier in the node capability deployment list with the semantic slice tag to determine the slice tasks to be allocated to other edge nodes in each of the edge nodes except the local edge node;

[0104] The node capability deployment identifier is used to characterize the data analysis capability.

[0105] Furthermore, each edge node internally maintains the node capability deployment list;

[0106] Each edge node is used to broadcast the to-be-updated node capability deployment identifier of the node to be updated to its neighboring nodes, and the to-be-updated node capability deployment identifier is used to update the node capability deployment list.

[0107] Furthermore, the edge computing task distribution device further includes a reallocation module, which is used to:

[0108] If the slice task to be assigned belongs to the local edge node, the local computing capacity of the local edge node is obtained;

[0109] If the occupied computing power of the local computing capacity exceeds a preset threshold, the slice task to be allocated will be distributed to other edge nodes other than the local edge node.

[0110] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the edge computing task distribution method, which includes: semantically segmenting the data to be transmitted to obtain different types of semantic slicing tasks; allocating the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks, and determining the slicing tasks to be allocated corresponding to each edge node; and distributing the slicing tasks to be allocated to the corresponding edge nodes.

[0111] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0112] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the edge computing task distribution method provided by the above methods, which includes: semantically segmenting the data to be transmitted to obtain different types of semantic slicing tasks; allocating the semantic slicing tasks based on the data analysis capabilities of each edge node and the data security level of the semantic slicing tasks, and determining the slicing tasks to be allocated corresponding to each edge node; and distributing the slicing tasks to be allocated to the corresponding edge nodes.

[0113] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the edge computing task distribution method provided by the above methods, the method comprising: semantically segmenting the data to be transmitted to obtain different types of semantic slicing tasks; allocating the semantic slicing tasks based on the data analysis capabilities of each edge node and the data security level of the semantic slicing tasks, and determining the slicing tasks to be allocated corresponding to each edge node; and distributing the slicing tasks to be allocated to the corresponding edge nodes.

[0114] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0115] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for distributing edge computing tasks, characterized in that: include: Semantically segmenting the data to be transmitted to obtain different types of semantic slicing tasks, wherein the semantic slicing tasks include face data and pedestrian behavior data; Based on the data analysis capability of each edge node and the data security level of the semantic slicing task, the semantic slicing task is allocated, and the slicing task to be allocated corresponding to each edge node is determined; Distribute the slice tasks to be assigned to the corresponding edge nodes; Semantically segment the data to be transmitted to obtain different types of semantic slicing tasks, including: Obtaining a preset semantic environment type, wherein the semantic environment type includes data segmentation rules corresponding to a plurality of different application scenarios; Based on the type of the semantic environment, the data to be transmitted is divided into a plurality of semantic slices to obtain different types of semantic slice tasks; Based on the data analysis capability of each edge node and the data security level of the semantic slicing task, the semantic slicing task is allocated, and the slicing task to be allocated corresponding to each edge node is determined, including: Determining that the slicing task to be assigned includes sensitive data; Based on the sensitive data, determine the data security level corresponding to the slicing task to be assigned; If the data security level exceeds the preset security threshold, the to-be-allocated slice task is allocated to the local edge node; If the data security level does not exceed the preset security threshold, the semantic slicing tasks are allocated based on the data analysis capabilities of each edge node, and the slicing tasks to be allocated to other edge nodes in each edge node except the local edge node are determined; Based on the data analysis capability of each edge node, the semantic slicing tasks are allocated, and the slicing tasks to be allocated to other edge nodes in each edge node except the local edge node are determined, including: Determine a semantic slice tag corresponding to the semantic slice task; Match the node capability deployment identifier in the node capability deployment list with the semantic slice tag to determine the slice tasks to be allocated to other edge nodes in each of the edge nodes except the local edge node; The node capability deployment identifier is used to characterize the data analysis capability.

2. The edge computing task distribution method according to claim 1, characterized in that: Each edge node internally maintains the node capability deployment list; Each edge node is used to broadcast the to-be-updated node capability deployment identifier of the node to be updated to its neighboring nodes, and the to-be-updated node capability deployment identifier is used to update the node capability deployment list.

3. The edge computing task distribution method according to claim 1, characterized in that: After distributing the slice task to be assigned to the corresponding edge node, it includes: If the slice task to be assigned belongs to the local edge node, the local computing capacity of the local edge node is obtained; If the occupied computing power of the local computing capacity exceeds a preset threshold, the slice task to be allocated will be distributed to other edge nodes other than the local edge node.

4. An edge computing task distribution device, characterized in that: include: A segmentation module, used to perform semantic segmentation on the data to be transmitted to obtain different types of semantic slicing tasks, wherein the semantic slicing tasks include face data and pedestrian behavior data; An allocation module, configured to allocate the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks, and determine the slicing tasks to be allocated corresponding to each edge node; A distribution module, used to distribute the slice tasks to be assigned to the corresponding edge nodes; Semantically segment the data to be transmitted to obtain different types of semantic slicing tasks, including: Obtaining a preset semantic environment type, wherein the semantic environment type includes data segmentation rules corresponding to a plurality of different application scenarios; Based on the type of the semantic environment, the data to be transmitted is divided into a plurality of semantic slices to obtain different types of semantic slice tasks; Based on the data analysis capability of each edge node and the data security level of the semantic slicing task, the semantic slicing task is allocated, and the slicing task to be allocated corresponding to each edge node is determined, including: Determining that the slicing task to be assigned includes sensitive data; Based on the sensitive data, determine the data security level corresponding to the slicing task to be assigned; If the data security level exceeds the preset security threshold, the to-be-allocated slice task is allocated to the local edge node; If the data security level does not exceed the preset security threshold, the semantic slicing tasks are allocated based on the data analysis capabilities of each edge node, and the slicing tasks to be allocated to other edge nodes in each edge node except the local edge node are determined; Based on the data analysis capability of each edge node, the semantic slicing tasks are allocated, and the slicing tasks to be allocated to other edge nodes in each edge node except the local edge node are determined, including: Determine a semantic slice tag corresponding to the semantic slice task; Match the node capability deployment identifier in the node capability deployment list with the semantic slice tag to determine the slice tasks to be allocated to other edge nodes in each of the edge nodes except the local edge node; The node capability deployment identifier is used to characterize the data analysis capability.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the edge computing task distribution method as described in any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the edge computing task distribution method as described in any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the edge computing task distribution method as described in any one of claims 1 to 3.

Images