Operation and maintenance method, device and system for edge computing, electronic device and storage medium

Abstract

The invention discloses an operation and maintenance method, equipment and system for edge computing, electronic equipment and a storage medium, and the method comprises the steps: obtaining AI source data in a target region, and enabling first packet transmission equipment to be arranged in the target region; based on the AI source data, running AI application software corresponding to the AI source data to obtain an AI running result; and sending the AI operation result to an AI operation result response device, wherein the response device is deployed in the target area.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of artificial intelligence, and in particular, to an edge computing operation and maintenance method, system, electronic device, and storage medium. Background Art

[0002] With the development of artificial intelligence (AI) technology, AI technology has been widely used in some target areas, such as factories in industrial production parks, where product quality inspection can be performed based on image classification technology. Deep learning algorithms involved in AI technology, such as convolutional neural networks (CNN), recurrent neural networks (RNN), and self-attention models, have large computational complexity and consume a lot of memory. The model operation depends on many software packages, which occupy memory and disk space.

[0003] When deploying AI technology to industrial production scenarios, some methods can meet the requirements of low cost and easy deployment, but there are risks in data security, data dispersion cannot be centralized, and the latency is large. Other methods may be able to achieve data security and centralized management, but the cost is high and difficult to deploy. In short, the current edge computing operation and maintenance methods cannot simultaneously meet the requirements of low cost, easy deployment, data security, centralized management, and low latency. Summary of the invention

[0004] The embodiments of the present application provide an edge computing operation and maintenance method, system, electronic device, and storage medium, which can solve the problem that the edge computing operation and maintenance method cannot simultaneously meet the requirements of low cost, easy deployment, data security, centralized management, and low latency.

[0005] In a first aspect, an edge computing operation and maintenance method is provided, which is applied to a first packet transmission device, and the method includes: obtaining AI source data in a target area, wherein the first packet transmission device is arranged in the target area; based on the AI ​​source data, running AI application software corresponding to the AI ​​source data to obtain AI operation results; sending the AI ​​operation results to an AI operation result response device, and the response device is deployed in the target area.

[0006] In a second aspect, a packet transmission device is provided, which is arranged in a target area, and the packet transmission device includes: a communication service unit, which is used to obtain AI source data in the target area through a data interface unit; an AI unit, which is used to run corresponding AI application software based on the AI ​​source data to obtain the AI ​​operation result; the communication service unit is also used to send the AI ​​operation result to an AI operation result response device, and the AI ​​operation result response device is deployed in the target area.

[0007] According to a third aspect, an edge computing operation and maintenance system is provided, including: a packet transmission device, the packet transmission device is used to obtain AI source data in a target area; perform AI operations based on the AI ​​source data to obtain AI operation results; and send the AI ​​operation results to an AI operation result response device; a control device, the control device is connected to the packet transmission device and is used to control the packet transmission device; the packet transmission device and the control device are both arranged in the target area.

[0008] In a fourth aspect, an electronic device is provided, the terminal comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions implementing the steps of the method described in the first aspect when executed by the processor.

[0009] In a fifth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0010] In a sixth aspect, a chip is provided, the chip comprising a processor and a communication card slot, the communication card slot and the processor are coupled, and the processor is used to run a program or instruction to implement the steps of the method described in the first aspect.

[0011] In a seventh aspect, a computer program / program product is provided, wherein the computer program / program product is stored in a storage medium and is executed by at least one processor to implement the steps of the method described in the first aspect.

[0012] In an embodiment of the present application, AI source data in a target area is obtained, wherein the first packet transmission device is arranged in the target area; based on the AI ​​source data, the AI ​​application software corresponding to the AI ​​source data is run to obtain an AI operation result; the AI ​​operation result is sent to an AI operation result response device, and the response device is deployed in the target area, which can simultaneously meet the requirements of low cost, easy deployment, data security, centralized management and low latency. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic flowchart of an edge computing operation and maintenance method provided in an embodiment of the present application.

[0014] Figure 2 It is a schematic flowchart of another edge computing operation and maintenance method provided in an embodiment of the present application.

[0015] Figure 3a It is a structural diagram of an edge computing operation and maintenance system provided in an embodiment of the present application.

[0016] Figure 3b It is a structural diagram of another edge computing operation and maintenance system provided in an embodiment of the present application.

[0017] Figure 3c It is a structural diagram of another edge computing operation and maintenance system provided in an embodiment of the present application.

[0018] Figure 4 It is a schematic diagram of the structure of a packet transmission device according to an embodiment of the present invention.

[0019] Figure 5 is a schematic structural diagram of an electronic device according to another embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of this application.

[0021] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.

[0022] like Figure 1 As shown, an embodiment of the present invention provides an edge computing operation and maintenance method, which can be executed by a first packet transmission device, and the first packet transmission device can be the following Figure 3a -c, Figure 4The packet transmission device in the embodiment is executed. In other words, the method can be executed by hardware included in the first packet transmission device or software installed in the first packet transmission device. The method includes the following steps:

[0023] S102: Acquire AI source data in the target area.

[0024] The first packet transmission device is arranged in the target area. The embodiment of the present application can provide edge computing for AI source data in the target area, and the target area can be set according to demand, for example, it can include a factory that needs to perform edge computing as described in the embodiment of the present application. There is also an AI source data acquisition device 1 deployed in the target area, and the AI ​​source data acquisition device 1 can include, for example, a camera for collecting images, a scanner for collecting QR codes, and a recorder for collecting sounds.

[0025] Combined with follow-up Figure 3a As shown, the packet transmission device 31 reuses the packet transmission devices deployed in the target area. In one embodiment, the packet transmission device 31 supports the parsing function of industrial control protocols, such as Modbus or FINS, and can encode and decode industrial computer data. The packet transmission device 31 also has the encoding and decoding function of picture / video data, and the encoding and decoding protocol such as h.264 / h.265 can encode and decode the picture / video data from the camera.

[0026] In one embodiment, this step may include: a first packet transmission device receives the AI ​​source data collected and sent by a data collection device in the target area. The first packet transmission device may be connected to the data collection device through a port. Figure 3a As shown, when the first packet transmission device is the packet transmission device C in the figure, the packet transmission device C is connected to the data acquisition device through a port, and can directly receive the AI ​​source data collected and sent by the data acquisition device in the target area.

[0027] In another optional implementation, this step may include: the first packet transmission device receives the AI ​​source data sent by the second packet transmission device in the target area through the operator slice network, and the second packet transmission device is a device connected to the data collection device that collects the AI ​​source data. Figure 3a As shown, when the first packet transmission device is the packet transmission device B in the figure, the packet transmission device B is not directly connected to the data acquisition device through the port, and can receive the AI ​​source data forwarded by the packet transmission device C through the operator slice network, that is, the packet transmission device C is the second packet transmission device.

[0028] In one embodiment, the packet transmission device 32 may be multiple, and the edge computing data between the multiple packet transmission devices is transmitted through the operator slicing network technology. Specifically, the packet transmission device described in the embodiment of the present application is formed on the basis of the packet transmission device provided by the network operator, and its functions include: operator data transmission function and edge computing function. The operator data transmission function is data transmitted to achieve network connection in the target area. Therefore, the data transmission between the packet transmission devices includes: operator network data and edge computing data. The embodiment of the present application includes edge computing data transmitted using slicing network technology. The edge computing data may include edge computing data including all edge computing operation and maintenance system related data, such as AI source data collected by the AI ​​source data acquisition device, the running results of the AI ​​application software, the processing results after processing the running results, and the control command used by the control device to control the packet transmission device. The transmission method of the operator network data is not limited. Slicing network technology includes technologies that support network slicing functions, including: SPN (Slicing Packet Network) technology or IPRAN (IP Radio Access Network, IP Radio Access Network) technology. Therefore, the edge computing operation and maintenance system provided in the embodiment of the present application realizes the transmission of AI application-related data between the packet transmission devices 31 in the target area through the slicing network technology, so that different packet transmission devices can share computing power.

[0029] S104: Based on the AI ​​source data, run the AI ​​application software corresponding to the AI ​​source data to obtain an AI running result.

[0030] In this step, based on the AI ​​source data, the AI ​​application software corresponding to the AI ​​source data can be run through the AI ​​unit to obtain the AI ​​running result, wherein the AI ​​unit includes an AI acceleration chip or a computing board with an AI acceleration chip, and there is a corresponding relationship between the AI ​​acceleration chip and the AI ​​application software. The corresponding relationship between the AI ​​acceleration chip and the AI ​​application software, for example, the AI ​​acceleration chip marked as 1 is used to run the AI ​​application software of category A, etc.

[0031] In one embodiment, in response to the AI ​​application software configuration command, the correspondence between the AI ​​application software and the AI ​​acceleration chip is adjusted. For example, the original correspondence includes: the AI ​​acceleration chip identified as 1 is used to run the AI ​​application software of category A. In this step, in response to the AI ​​application software configuration command, the correspondence can be adjusted to the AI ​​acceleration chip identified as 2 is used to run the AI ​​application software of category A, etc.

[0032] S106: Send the AI ​​operation result to an AI operation result response device.

[0033] The response device is deployed in the target area. The AI ​​operation result response device includes: the AI ​​source data acquisition device or a third device running an AI application, which processes the AI ​​operation result through the result processing end of the AI ​​application software. The AI ​​operation result response device can be the same device as the AI ​​source data acquisition device, or it can be a different device. For example, the AI ​​source data acquisition device can be a terminal, which collects user data and sends it to a packet transmission device for AI calculation. The packet transmission device can send the AI ​​operation result to the terminal (the above-mentioned AI operation result response device), and the terminal performs subsequent data processing. For another example, the AI ​​source data acquisition device can be a camera, which collects the user's facial image and sends it to the packet transmission device for AI image recognition. The packet transmission device can send the AI ​​operation result to a terminal, and the terminal performs subsequent data processing on the image recognition result.

[0034] Step S106 may include one of the following:

[0035] The AI ​​operation result is sent to the AI ​​operation result response device through the first target port of the first packet transmission device, wherein the first target port is a pre-configured port for communicating with the AI ​​operation result response device. For example, the AI ​​operation result response device is the AI ​​source data acquisition device 1, and the first packet transmission device is Figure 3a In the packet transmission device C, this step can send the AI ​​operation result to the AI ​​source data acquisition device 1 through the first target port of the packet transmission device C.

[0036] The AI ​​operation result is sent to a third packet transmission device directly connected to the AI ​​operation result response device through the operator slice network, so as to send the AI ​​operation result to the AI ​​operation result response device through the second target port of the third packet transmission device. For example, the AI ​​operation result response device is the AI ​​source data acquisition device 1, and the first packet transmission device is Figure 3a In the packet transmission device B, in this step, the packet transmission device B sends the AI ​​operation result to the packet transmission device C through the operator slice network, and the AI ​​operation result is sent to the AI ​​source data collection device 1 through the packet transmission device C. Similarly, this step also includes the case where the AI ​​operation result response device is the third device mentioned above, which is not exhaustive.

[0037] Therefore, in the embodiment of the present application, when there are multiple packet transmission devices, the AI ​​source data collected by the AI ​​source data collection device can be received through the second packet transmission device among the multiple packet transmission devices. The AI ​​source data is forwarded to the first packet transmission device for performing AI operations among the multiple packet transmission devices through the operator slice network through the second packet transmission device. The AI ​​application software corresponding to the AI ​​source data is run through the first packet transmission device to obtain the AI ​​operation result. The AI ​​operation result is sent to the AI ​​operation result response device through the first packet transmission device. In this way, the computing power sharing of multiple packet transmission devices in the target area is achieved.

[0038] like Figure 2 As shown, an embodiment of the present invention provides an edge computing operation and maintenance method, the method comprising the following steps:

[0039] S202: Acquire AI source data in the target area.

[0040] The first packet transmission device is arranged in the target area, and the first packet transmission device may be the packet transmission device in the above embodiment.

[0041] S204: Based on the AI ​​source data, run the AI ​​application software corresponding to the AI ​​source data to obtain an AI running result.

[0042] S206: Send the AI ​​operation result to an AI operation result response device.

[0043] Steps S202-S206 can be performed by Figure 1 The description of the embodiments will not be repeated here to avoid repetition.

[0044] S208: Sending the AI ​​operation result to the control device in the target area.

[0045] In one embodiment, this step may include: sending the AI ​​operation result to a directly connected edge computing device directly connected to the control device through the operator slice network, so that the directly connected edge computing device sends the AI ​​operation result to the control device through a third target port. The directly connected edge computing device is connected to the control device through the third target port set thereon. The data sent to the control device may also include: AI software operation process data, such as collected source data, operation time, etc. The source data may include image data.

[0046] In one embodiment, when there are multiple packet transmission devices in the target area, the control device can configure a direct-connected packet transmission device connected to the control device through a port from the multiple packet transmission devices; and the control device can configure a third target port for connecting to the control device from the multiple ports of the direct-connected packet transmission device. Specifically, the control device provided by the network operator to implement network management can be initialized by the network management software to initially configure the connection port connecting the packet transmission device and the control device during initialization. In one embodiment, in this step, the control device can confirm that the connection port initially configured by the network management software is configured as the third target port connecting the direct-connected packet transmission device and the control device in the embodiment of the present application. In another implementation, in this step, the control device modifies the connection port and configures other ports except the connection port as the third target port connecting the direct-connected packet transmission device and the control device in the embodiment of the present application.

[0047] In one embodiment, step S208 may include: sending the AI ​​operation result to the control device through a fourth target port of the first packet transmission device, wherein the fourth target port is pre-configured as a port for communicating with the control device. Similar to the configuration of the third target port described above, the fourth target port may be configured by the control device.

[0048] The control device can control the packet transmission device, including at least one of the following:

[0049] In one embodiment, before step S202, the control device can also be used to configure a data transmission path of a non-directly connected packet transmission device among the plurality of packet transmission devices; based on the data transmission path, the non-directly connected packet transmission device is controlled to perform routing configuration. Thus, after the direct-connected packet transmission device and the third target port are set, the routing configuration of the non-directly connected packet transmission device can be performed.

[0050] In one embodiment, before step S202, the topological relationship of each packet transmission device in the target area can also be obtained by a control device; and a routing transmission channel between each packet transmission device is configured according to the topological relationship, and the routing transmission channel is used to transmit target business data. The target business data includes the edge computing data.

[0051] In one embodiment, after obtaining the topological relationship, the above-mentioned routing transmission channel can also be manually configured according to the topological relationship of the packet transmission device. In another embodiment, after obtaining the topological relationship, according to the topological relationship of the packet transmission device; send the routing configuration command to the packet transmission device through the control device; control the packet transmission device to perform routing configuration based on the routing configuration command. The topological relationship of the packet transmission device includes: the port identifier of the second packet transmission device, the AI ​​chip identifier of the first packet transmission device, and the port identifier of the result processing end of the AI ​​application software, and the routing configuration command is generated by the control device.

[0052] In one embodiment, the control device may send a port attribute modification command to the packet transmission device; based on the attribute modification command, the port attribute of the first packet transmission device is modified to a dedicated port attribute, and the dedicated port attribute is used to characterize that the transmission path between the first packet transmission device and the outside of the target area is disabled, and data from the dedicated port is prohibited from being transmitted outside the target area. The ports of the first packet transmission device may include the above-mentioned first target port, the fourth target port, and other ports on the first packet transmission device. Thereby, the network management function provided by the operator is restricted, and the data in the target area will not flow out of the edge computing operation and maintenance system provided by the embodiment of the present application, thereby ensuring data security. Optionally, after modifying the port attributes, it is also possible to interact with the operator's network management, and report the information that the factory's operator network port is modified to an AI dedicated application port to the operator's network management. In one embodiment, the control of the packet transmission device by the control device may also include at least one of the following:

[0053] Control the installation of the AI ​​application software in the packet transmission device. This method can be executed by the installation module of the AI ​​application software, which supports uploading the AI ​​application software to the packet transmission device through the network cable and installing or updating it; supports configuring the corresponding data transmission channel for the AI ​​application software, that is, specifying the network port / serial port, and configuring the corresponding packet transmission device, AI chip, and AI computing board. Support the completion of uninstallation of the AI ​​application software.

[0054] Control the uninstallation of the AI ​​application software in the packet transmission device. This method can be executed by the uninstallation module of the AI ​​application software, and supports the completion of the uninstallation of the AI ​​application software.

[0055] Controlling the configuration of the AI ​​application software in the packet transmission device;

[0056] Controlling the update of AI application software in the packet transmission device;

[0057] Control the startup of the AI ​​application software in the packet transmission device; this method can be executed by the control module of the AI ​​application software, which supports the start / stop function of controlling the AI ​​application software.

[0058] Controlling the stopping of the AI ​​application software in the packet transmission device, this method can be executed by a control module of the AI ​​application software, which supports the start / stop function of controlling the AI ​​application software.

[0059] Control the data management of the AI ​​application software in the packet transmission device. This method can be executed by the operation data management module of the AI ​​application software, which supports the acquisition / save / statistics of AI operation process data transmitted from the packet transmission device through the network port, including but not limited to the original image data collected from the production line, operation results, processing time, etc. The module also supports displaying these data to factory staff through the web page / application software UI interface.

[0060] The following uses the ZXCTN 6180H device as an example to explain the specific process in actual usage scenarios.

[0061] Single packet transmission device scenario:

[0062] Through the operator's network management and maintenance, a port of the packet transmission device in the target area is configured as the third target port. After connecting to the control device, the packet transmission device will respond to various instructions of the control device and transmit AI application software related data back to the control device.

[0063] The control device sends AI application software and its data input / output ports, AI processing chip / computing board number to the packet transmission device. After receiving the command from the control device, the packet transmission device will perform automatic routing configuration, such as SPN's VLSS (virtual local switching service technology) to complete the communication between the input data port and the output data port.

[0064] In steps S202 and S204, after the packet transmission device receives the network camera data from the input port, it runs the AI ​​application on the AI ​​acceleration unit and transmits the result to the application end through the output port, and transmits the relevant data of the AI ​​application software back to the control device.

[0065] Multi-packet transmission equipment scenario:

[0066] like Figure 3bAs shown, through the network management and maintenance of the operator, a port of a packet transmission device 31 in the factory is configured as a port connected to the control device 32. And the routing settings are configured for the packet transmission device that is not directly connected to the control device 32, and the data transmission path between the packet transmission device and the control device 32 is specified, and the slice network technology, such as SPN technology and IPRAN, is used for data transmission.

[0067] The AI ​​application software and its related port configuration are issued by the control device. In the non-cross-packet transmission device scenario, the routing configuration method is the same as the routing configuration related steps in the single-packet transmission scenario. In the cross-packet transmission scenario, the relevant data transmission path can use manual routing configuration or automatic routing configuration, such as using typical virtual private wire service (VPWS) technology.

[0068] In steps S202 and S204, after the packet transmission device receives the network camera data from the input port, it runs the AI ​​application on the AI ​​acceleration unit and transmits the result to the application end through the output port, and transmits the relevant data of the AI ​​application software back to the control device.

[0069] Several comparative examples will be introduced below, and the scheme and beneficial effects of the embodiments of the present application will be further illustrated by comparing the embodiments of the present application with the following comparative examples.

[0070] Comparative Example 1: Deployment of AI algorithms based on cloud computing. That is, the factory's AI source data is transmitted to the public cloud through the operator's private network or public network, and then the AI ​​application software on the public cloud is used to run the operation results, and the results are transmitted back to the AI ​​operation result response device through the operator network. Although this method is low-cost and easy to deploy, it has the following disadvantages: a. The industrial production data has already left the factory, and there is a risk of data leakage; b. The data is first sent to the core network through the operator network, and then transmitted to the public cloud, and then the results are transmitted back to the AI ​​operation result response device through the operator network. The data transmission is time-consuming, and the real-time performance required for industrial production cannot be guaranteed.

[0071] In contrast, in the embodiment of the present application, the AI ​​source data in the target area has not been shipped out of the factory, and there is no risk of data leakage; b. Data is processed near the target area, data transmission takes a short time, and the real-time performance required for data processing is guaranteed. That is, the edge computing operation and maintenance method provided in the embodiment of the present application can simultaneously meet the requirements of low cost, easy deployment, data security, centralized management, and low latency.

[0072] Comparative Example 2: Deployment of AI algorithms based on private cloud. This method builds a network and AI server in the factory. The industrial production line terminal transmits the original data required for AI operation to the AI ​​server through the self-built network, and then completes the operation of the industrial AI application software on the server to obtain the operation result, and transmits the operation result back to the AI ​​operation result response device through the self-built network. The data in Comparative Example 2 does not leave the factory, and the real-time performance is guaranteed. However, the construction of the entire AI acceleration system is large in construction, difficult to deploy, and costly. The subsequent operation and maintenance requires a lot of manpower, and the technical requirements for the operation and maintenance personnel are high.

[0073] In comparison, the hardware equipment required for the edge computing operation and maintenance method in the embodiment of the present application can reuse the hardware equipment provided by existing operators, with a small construction workload, simple deployment and easy implementation, low cost, and subsequent operation and maintenance with the operator without the need for additional manpower. That is, the edge computing operation and maintenance method provided in the embodiment of the present application can simultaneously meet the requirements of low cost, easy deployment, data security, centralized management and low latency.

[0074] Comparative Example 3: Add a computer or AI accelerator in the factory, take the camera as the AI ​​source data acquisition device as an example, build an AI chip into the camera, and then complete the operation of the AI ​​algorithm. This comparative example 3 has the advantages of no data leaving the factory, guaranteed real-time performance and easy deployment. However, Comparative Example 3 requires customization of the equipment corresponding to the AI ​​source data acquisition device and has poor versatility, and cannot centrally manage multiple AI applications. Therefore, there is a risk of high cost and low efficiency.

[0075] In contrast, the edge computing operation and maintenance method in the embodiment of the present application centrally manages multiple AI applications through packet transmission equipment and control equipment. That is, the edge computing operation and maintenance method provided in the embodiment of the present application can simultaneously meet the requirements of low cost, easy deployment, data security, centralized management and low latency.

[0076] Figure 3a is a structural diagram of an edge computing operation and maintenance system provided in an embodiment of the present application, such as Figure 3a As shown, the edge computing operation and maintenance system 30 includes: a packet transmission device 31 and a control device 32. The packet transmission device and the control device are both arranged in the target area.

[0077] The packet transmission device 31 is used to obtain AI source data in the target area, perform AI operation based on the AI ​​source data, obtain AI operation results, and send the AI ​​operation results to the AI ​​operation result response device. The control device 32 is connected to the packet transmission device and is used to control the packet transmission device.

[0078] In one embodiment, the control device is connected to a direct-connected packet transmission device via a first network port, the direct-connected packet transmission device is one of a plurality of the packet transmission devices, and the direct-connected packet transmission device is used to receive a control command from the control device via the first network port. Figure 3a As shown in the figure, the packet transmission device A is shown in the figure.

[0079] In one embodiment, the directly connected packet transmission device is further used to forward the control command of the control device to other packet transmission devices through the operator slicing network technology. Figure 3a In the embodiment, the packet transmission device B is not directly connected to the control device 32 through the port, and the packet transmission device A can forward the control command of the control device to the packet transmission device B. The embodiment of the present application can provide edge computing for the AI ​​source data in the target area, and the target area can be set according to the needs, for example, it can include a factory that needs to perform the edge computing described in the embodiment of the present application. There is also an AI source data acquisition device 1 deployed in the target area, and the AI ​​source data acquisition device 1 can include, for example, a camera for collecting images, a scanner for collecting QR codes, and a recorder for collecting sounds. The packet transmission device can be a packet transmission device set by a network operator that provides network connection to the target area. Therefore, the packet transmission device 31 provided in the embodiment of the present application can reuse the packet transmission device provided by the network operator, and only add a chip that provides AI computing, expand the network port and the serial port to provide edge computing functions, which has the advantage of low cost.

[0080] The control device 32 is arranged in the target area, and the control device is connected to the packet transmission device to control the packet transmission device 31. The control device 32 may include AI application management software and operator network management software that can support the control of the packet transmission device and the hardware environment for their operation, for example, it may include devices such as computers or servers. Specifically, the network operator provides a network connection for the target area, and the network management software will run on a certain hardware management device to run. The control device 32 provided in the embodiment of the present application can also be reused on the hardware management device provided by the network operator for the target area, thereby providing management edge computing functions without increasing additional hardware costs.

[0081] The operation and maintenance system based on edge computing can perform AI operations based on the collected data of the AI ​​source data acquisition device in the target area through the packet transmission device 31, and can control the packet transmission device through the control device 32.

[0082] In one embodiment, the packet transmission device 32 may be multiple, and the edge computing data between the multiple packet transmission devices is transmitted through the operator slicing network technology. Specifically, the packet transmission device described in the embodiment of the present application is formed on the basis of the packet transmission device provided by the network operator, and its functions include: operator data transmission function and edge computing function. The operator data transmission function is data transmitted to achieve network connection in the target area. Therefore, the data transmission between the packet transmission devices includes: operator network data and edge computing data. The embodiment of the present application includes edge computing data transmitted using slicing network technology. The edge computing data may include edge computing data including all edge computing operation and maintenance system related data, such as the AI ​​source data collected by the AI ​​source data acquisition device, the running results of the AI ​​application software, the processing results after processing the running results, and the control command used by the control device to control the packet transmission device. The transmission method of the operator network data is not limited. Therefore, the edge computing operation and maintenance system provided in the embodiment of the present application realizes AI application-related data transmission between the packet transmission devices 31 in the target area through slicing network technology, so that different packet transmission devices can share computing power.

[0083] In addition, the packet transmission equipment in the target area is interconnected using the transmission network of the operator network, and the packet transmission equipment in the park can use slicing network technology, for example, SPN (Slicing Packet Network), to provide a dedicated transmission channel for AI-related data to ensure the security and low latency of data transmission. As a result, the AI ​​computing power of the packet transmission equipment 31 in the park can realize computing power sharing, that is, the AI ​​source data collected by the AI ​​source data acquisition device can be received through the second packet transmission device among the multiple packet transmission devices; the AI ​​source data is forwarded to the first packet transmission device for AI calculation among the multiple packet transmission devices through the operator slicing network through the second packet transmission device; the AI ​​application software corresponding to the AI ​​source data is run through the first packet transmission device to obtain the AI ​​operation result. The AI ​​operation result is sent to the control device through the slicing network through the first packet transmission device for easy monitoring.

[0084] In one embodiment, the first network port of a directly connected packet transmission device among the plurality of packet transmission devices is used to connect to the control device. The other non-directly connected packet transmission devices among the plurality of packet transmission devices, except the directly connected packet transmission device, transmit the edge computing data with the directly connected packet transmission device through the slice network, and transmit the edge computing data with the control device through the directly connected packet transmission device. Thus, in the case of including a plurality of the packet transmission devices, the transmission of the edge computing data between the plurality of devices in the edge computing operation and maintenance system is realized. Specifically, the control device provided by the network operator to realize network management can be initialized by the network management software to initially configure the connection port connecting the packet transmission device and the control device 32. In one embodiment, in this step, the control device 32 can confirm that the connection port initially configured by the network management software is configured as the third target port connecting the direct-connected packet transmission device and the control device 32 in the embodiment of the present application. In another implementation, in this step, the control device 32 can also modify the connection port, and configure other ports except the connection port as the third target port connecting the direct-connected packet transmission device and the control device 32 in the embodiment of the present application.

[0085] like Figure 3c As shown, in one embodiment, the packet transmission device may include: a communication service unit 41 and an AI unit 42, specifically as shown in FIG. Figure 4 As described in the embodiments.

[0086] Figure 4 is a schematic diagram of the structure of a packet transmission device provided in an embodiment of the present application, such as Figure 4 As shown, in one embodiment, the packet transmission device 40 includes: a communication service unit 41 and an AI unit 42.

[0087] The communication service unit 41 is used to obtain the AI ​​source data in the target area through the data interface unit 43. The AI ​​unit 42 is used to run the corresponding AI application software based on the AI ​​source data to obtain the AI ​​operation result. The communication service unit 41 is also used to send the AI ​​operation result to the AI ​​operation result response device, and the AI ​​operation result response device is deployed in the target area.

[0088] The data interface unit 43 is connected to the communication service unit 41 for receiving the AI ​​source data in the target area. The data interface unit 43 is also connected to the AI ​​operation result response device for sending the AI ​​operation result to the AI ​​operation result response device, which is deployed in the target area.

[0089] For example, the communication service unit 41 of the packet transmission device A may distribute the AI ​​source data to the AI ​​unit 42 of the packet transmission device A. For another example, the communication service unit 41 of the packet transmission device A may distribute the AI ​​source data to the communication service unit 41 of the packet transmission device B, and the communication service unit 41 of the first packet transmission device B then distributes the AI ​​source data to the AI ​​unit 42 of the packet transmission device B.

[0090] In one embodiment, the AI ​​unit 42 includes an AI acceleration chip or a computing board with an AI acceleration chip, and the AI ​​unit is disposed on a card slot of the packet transmission device. Optionally, the AI ​​unit 42 can return the AI ​​operation result to the communication service unit 41.

[0091] In one embodiment, the AI ​​unit 42 is connected to the communication service unit 41 via a high-speed serial computer expansion bus standard (Peripheral Component Interconnect Express, PCIE) or a network port. Specifically, the connection between the AI ​​unit 42 and the communication service unit 41 can be through PCIE or a network port, as well as PCIE and a network port.

[0092] Therefore, the packet transmission equipment provided in the embodiment of the present application reuses the network port, serial port, communication service board, AI acceleration chip or computing power board in the packet transmission equipment of the operator network, and provides an external interface for the AI ​​source data acquisition equipment in a low-cost, fast and easy-to-deploy manner, realizes data distribution and AI application operation, and realizes rapid networking.

[0093] In one embodiment, the communication service unit 41 is further used to send the AI ​​operation result to the data interface unit, and the data interface unit is further used to send the AI ​​operation result to the AI ​​operation result response device. The AI ​​operation result response device is used to perform subsequent processing on the AI ​​operation result, and the AI ​​operation result response device can be the same device as the AI ​​source data acquisition device, or it can be a different device. For example, the AI ​​source data acquisition device can be a terminal, which collects user data and sends it to the packet transmission device 31 for AI calculation. The packet transmission device 31 can send the AI ​​operation result to the terminal, and the terminal performs subsequent data processing. For another example, the AI ​​source data acquisition device can be a camera, which collects the user's facial image and sends it to the packet transmission device 31 for AI image recognition. The packet transmission device 31 can send the AI ​​operation result to a terminal, and the terminal performs subsequent data processing on the image recognition result.

[0094] In one embodiment, the port attribute of the packet transmission device is set to a dedicated port, and the data from the dedicated port is prohibited from being transmitted outside the target area. Therefore, the embodiment of the present application can ensure that data does not flow out of the edge computing operation and maintenance system, thereby ensuring the data security of the edge computing operation and maintenance system.

[0095] The following is a detailed description of the embodiment of the present application, taking the packet transmission device of model ZXCTN 6180H as an example. The ZXCTN 6180H device is a packet transmission device for a 5G transmission network SPN. The device is presented in the form of a cabinet or a frame, and includes multiple network ports and a communication service board, which can complete the reading and distribution functions of network port data. The device reserves multiple card slots for the expansion of board chips.

[0096] The communication service unit 41 supports the parsing function of industrial control protocols such as Modbus or FINS, and can encode and decode industrial computer data. The communication service unit 41 also has the encoding and decoding function of image / video data, and the encoding and decoding protocols such as h.264 / h.265 can encode and decode the image / video data from the camera.

[0097] The communication service unit 41 may also include a control device response software, which responds to various instructions from the control device. The instructions include at least one of the following:

[0098] The control device is used to configure a data transmission path of a non-directly connected packet transmission device among the plurality of packet transmission devices; and based on the data transmission path, the non-directly connected packet transmission device is controlled to perform routing configuration.

[0099] A computing power orchestration command is sent to the packet transmission device through the control device, and the computing power orchestration command includes at least one of the following: a port identifier of the second packet transmission device, an AI chip identifier of the first packet transmission device, and a port identifier of a result processing end of the AI ​​application software.

[0100] Generate a routing configuration command through the control device according to the port identifier of the second packet transmission device, the AI ​​chip identifier of the first packet transmission device and the port identifier of the result processing end of the AI ​​application software; send the routing configuration command to the packet transmission device through the control device; control the packet transmission device to perform routing configuration based on the routing configuration command.

[0101] The instructions also include the installation, uninstallation, configuration, update, start, stop, data reporting, etc. of the AI ​​application software. The communication service unit 41 may also include network management and operation response software. This module responds to various instructions from the network management and operation, and can set a certain network port as a connection port for connecting the control device. The communication service unit 41 may also include AI operation data forwarding software. After the software obtains the image data of the camera from the network port, it will perform encoding and decoding operations, and then transfer the image to the AI ​​application software and obtain the operation results, and then encode and decode the results and transmit them to the factory application end through the designated network port. At the same time, the operation data of the AI ​​application software can also be transmitted to the console.

[0102] AI unit 42, taking ZXCTN 6180H as an example, the device has multiple card slots reserved, each of which can be inserted with an AI computing board for AI application operation. After inserting the computing board composed of CPU+xilinx2802 chip+storage card, it is connected to the communication service board using PCIE and network port for communication, completing the data transmission required for AI operation, such as pictures, AI operation results, etc.

[0103] The data interface unit 43 may include: multiple external network ports and serial ports, the network port may include a Gigabit Ethernet (GE) or Fast Ethernet (FE) interface network port, the serial port may include multiple physical interfaces RS485 or communication interface Modbus serial ports, and the data interface unit 43 is connected to the communication service board. Its network port can be connected to a network camera / industrial camera, and the camera can transmit the on-site photos taken by the camera to the packet transmission device through the network port.

[0104] The control device can be composed of AI application management software and operator plant network management software and the hardware environment in which it runs. It is located inside the factory and connected to the packet transmission equipment through the network port. The main function of the AI ​​application management software is to manage, upgrade, configure, monitor, count and save the AI ​​operation results of the AI ​​application software running on the packet transmission equipment. In this way, the needs of centralized management in the deployment of AI application software are met. The main function of the operator plant network management software is to manage the operator network port in a restricted manner. The original public network port can be modified into the factory AI application port. In this way, the factory application end only needs to connect to the factory AI application port to transmit data to the packet transmission equipment, thereby speeding up the networking efficiency.

[0105] Optional, such as Figure 5As shown, the embodiment of the present application also provides an electronic device 500, including a processor 501, a memory 502, and a program or instruction stored in the memory 502 and executable on the processor 501, which implements each process of the edge computing operation and maintenance method embodiment when executed by the processor 501, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0106] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned edge computing operation and maintenance method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0107] The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0108] An embodiment of the present application further provides a chip, which includes a processor and a communication card slot, wherein the communication card slot is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned edge computing operation and maintenance method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0109] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0110] The embodiments of the present application further provide a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to implement the various processes of the above-mentioned edge computing operation and maintenance method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0111] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0112] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0113] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. An edge computing operation and maintenance method, applied to a first packet transmission device, the method comprising: Acquire AI source data in a target area, wherein the first packet transmission device is arranged in the target area; Based on the AI ​​source data, running the AI ​​application software corresponding to the AI ​​source data to obtain an AI running result; The AI ​​operation result is sent to an AI operation result response device, and the response device is deployed in the target area.

2. The method according to claim 1, characterized in that The obtaining of AI source data in the target area includes: Receiving the AI ​​source data collected and sent by a data collection device in the target area; or The AI ​​source data is received through the operator slice network from a second packet transmission device in the target area, where the second packet transmission device is a device connected to a data collection device that collects the AI ​​source data.

3. The method according to claim 1, characterized in that The step of running the AI ​​application software corresponding to the AI ​​source data based on the AI ​​source data to obtain the AI ​​running result includes: Based on the AI ​​source data, the AI ​​application software corresponding to the AI ​​source data is run through the AI ​​unit to obtain an AI running result, wherein the AI ​​unit includes an AI acceleration chip or a computing power board with an AI acceleration chip, and there is a corresponding relationship between the AI ​​acceleration chip and the AI ​​application software.

4. The method according to claim 3, characterized in that The method further comprises: In response to the AI ​​application software configuration command, the correspondence between the AI ​​application software and the AI ​​acceleration chip is adjusted.

5. The method according to claim 1, characterized in that Sending the AI ​​operation result to the AI ​​operation result response device includes: Sending the AI ​​operation result to the AI ​​operation result response device through a first target port of the first packet transmission device, wherein the first target port is a pre-configured port for communicating with the AI ​​operation result response device; or The AI ​​operation result is sent to a third packet transmission device directly connected to the AI ​​operation result response device through the operator slice network, so as to send the AI ​​operation result to the AI ​​operation result response device through the second target port of the third packet transmission device.

6. The method according to claim 1, characterized in that Before obtaining the AI ​​source data in the target area, the method further includes: Acquire a topological relationship between each of the packet transmission devices in the target area; A routing transmission channel between each of the packet transmission devices is configured according to the topological relationship, and the routing transmission channel is used to transmit target service data.

7. The method according to claim 1, characterized in that After the AI ​​application software corresponding to the AI ​​source data is run based on the AI ​​source data to obtain the AI ​​running result, the method further includes: The AI ​​operation result is sent to the control device in the target area.

8. The method according to claim 7, characterized in that Sending the AI ​​operation result to the control device in the target area includes: Sending the AI ​​operation result to a directly connected edge computing device directly connected to the control device through the operator slice network, so that the directly connected edge computing device sends the AI ​​operation result to the control device through the third target port; or, The AI ​​operation result is sent to the control device through a fourth target port of the first packet transmission device, wherein the fourth target port is a pre-configured port for communicating with the control device.

9. The method according to claim 8, characterized in that The method further comprises: Receiving a port attribute modification command sent by the control device; Based on the attribute modification command, the port attribute of the first packet transmission device is modified to a dedicated port attribute, where the dedicated port attribute is used to indicate that a transmission path between the first packet transmission device and outside the target area is disabled.

10. The method according to claim 7, characterized in that The control device is used to control at least one of the following: Controlling the installation of AI application software in the packet transmission device; Controlling the uninstallation of the AI ​​application software in the packet transmission device; Controlling the configuration of the AI ​​application software in the packet transmission device; Controlling the update of AI application software in the packet transmission device; Controlling the startup of the AI ​​application software in the packet transmission device; Controlling the stopping of the AI ​​application software in the packet transmission device; Controlling data management of the AI ​​application software in the packet transmission device.

11. A packet transmission device, arranged in a target area, comprising: A communication service unit, used to obtain AI source data in a target area through a data interface unit; An AI unit is used to run corresponding AI application software based on the AI ​​source data to obtain the AI ​​running result; The communication service unit is further used to send the AI ​​operation result to an AI operation result response device, and the AI ​​operation result response device is deployed in the target area.

12. The packet transmission device according to claim 11, characterized in that: The AI ​​unit is connected to the communication service board and includes: The AI ​​unit and the communication service unit are connected via a high-speed serial computer expansion bus standard PCIE or a network port.

13. The packet transmission device according to claim 11, characterized in that: The AI ​​unit includes: an AI acceleration chip or a computing board with an AI acceleration chip, and the AI ​​unit is arranged on a card slot of the packet transmission device.

14. The packet transmission device according to claim 11, characterized in that: The data interface unit is also used to connect with the AI ​​source data acquisition device, the control device, and other packet transmission devices in the target area.

15. An edge computing operation and maintenance system, characterized in that: include: A packet transmission device, the packet transmission device is used to obtain AI source data in a target area; perform AI operation based on the AI ​​source data to obtain an AI operation result; and send the AI ​​operation result to an AI operation result response device; a control device, the control device being connected to the packet transmission device and being used to control the packet transmission device; The packet transmission device and the control device are both arranged in the target area.

16. The edge computing operation and maintenance system according to claim 15, characterized in that: There are multiple packet transmission devices, the control device is connected to the direct-connected packet transmission device through a first network port, the direct-connected packet transmission device is one of the multiple packet transmission devices, and the direct-connected packet transmission device is used to receive a control command from the control device through the first network port; The directly connected packet transmission device is also used to forward the control commands of the control device to other packet transmission devices through the operator slicing network technology.

17. An electronic device, characterized in that: It includes a processor and a memory, the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the edge computing operation and maintenance method as described in any one of claims 1 to 10 are implemented.

18. A readable storage medium, characterized in that: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the steps of the edge computing operation and maintenance method as described in any one of claims 1 to 10 are implemented.

Images