Model sharing method, device and storage medium for multiple edge servers

Abstract

The present application discloses a model sharing method, device, and storage medium for multiple edge servers, relating to the field of artificial intelligence technology. The method includes: issuing a baseline model to multiple edge servers; in response to receiving model training information reported by a first edge server for training the baseline model, obtaining reward values ​​corresponding to each of multiple second edge servers other than the first edge server; determining at least one shared edge server corresponding to the first edge server from the multiple second edge servers based on the reward values ​​corresponding to each of the multiple second edge servers and a preset reward threshold; determining address information corresponding to each of the at least one shared edge server, and issuing the address information corresponding to each of the at least one shared edge server to the first edge server, wherein the address information is used by the first edge server to send model sharing information to the shared edge servers. This method can improve the model accuracy of each edge server.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a model sharing method, device, and storage medium for multiple edge servers. Background Art

[0002] With the rapid development of artificial intelligence (AI) technology, more and more scenarios are being tested for security using trained AI models. However, when AI models are used to perform security checks on multiple scenarios, differences in detection data across different scenarios make it difficult for the AI ​​models to maintain high detection accuracy across them.

[0003] Therefore, how to improve the detection accuracy of artificial intelligence models in multiple different scenarios is a technical problem that needs to be solved urgently. Summary of the Invention

[0004] The present application provides a model sharing method, device and storage medium for multiple edge servers to at least solve the problem of low detection accuracy of artificial intelligence models in multiple different scenarios in related technologies.

[0005] On the one hand, the present application provides a model sharing method for multiple edge servers, including:

[0006] Send the benchmark model to multiple edge servers;

[0007] In response to receiving model training information for training the benchmark model reported by the first edge server, obtaining reward values ​​corresponding to each of a plurality of second edge servers other than the first edge server among the plurality of edge servers;

[0008] Determining at least one shared edge server corresponding to the first edge server from the plurality of second edge servers according to the reward values ​​corresponding to the plurality of second edge servers and a preset reward threshold;

[0009] Determine the address information corresponding to at least one shared edge server, and send the address information corresponding to at least one shared edge server to the first edge server; wherein the address information is used by the first edge server to send model sharing information to the shared edge server corresponding to the address information.

[0010] On the other hand, the present application provides a model sharing method for multiple edge servers, including:

[0011] In response to receiving the benchmark model sent by the central server, training the benchmark model to obtain a trained optimization model, and generating model training information for training the benchmark model;

[0012] Report model training information to the central server;

[0013] In response to receiving the address information corresponding to at least one shared edge server sent by the central server, generating model sharing information;

[0014] Based on the address information of each shared edge server, the model sharing information is sent to the shared edge server.

[0015] On the other hand, the present application provides a model sharing method for multiple edge servers, including:

[0016] In response to receiving the model sharing information sent by the first edge server, updating the baseline model based on the model sharing information to obtain an optimized model;

[0017] Generate reward information corresponding to the first edge server and report the reward information to the central server.

[0018] On the other hand, the present application provides a model sharing method for multiple edge servers, including:

[0019] The central server sends the benchmark model to multiple edge servers;

[0020] In response to receiving the benchmark model sent by the central server, the first edge server generates model training information for training the benchmark model and reports the model training information to the central server;

[0021] In response to receiving model training information for training a benchmark model reported by a first edge server, the central server obtains a reward value corresponding to each of a plurality of second edge servers other than the first edge server from the plurality of edge servers; determines at least one shared edge server corresponding to the first edge server from the plurality of second edge servers based on the reward values ​​corresponding to the plurality of second edge servers and a preset reward threshold; determines address information corresponding to each of the at least one shared edge servers, and sends the address information corresponding to each of the at least one shared edge servers to the first edge server;

[0022] In response to receiving the address information corresponding to at least one shared edge server sent by the central server, the first edge server generates model sharing information, and sends the model sharing information to the shared edge server based on the address information of each shared edge server;

[0023] The shared edge server generates reward information corresponding to the first edge server in response to receiving the model sharing information sent by the first edge server, and reports the reward information to the central server;

[0024] The central server receives the reward information reported by the at least one shared edge server, determines the reward value of the first edge server according to the model training information reported by the first edge server and the reward information reported by the at least one shared edge server, and updates the reward value of the first edge server.

[0025] On the other hand, the present application also provides a model sharing device for multiple edge servers, including:

[0026] A first sending module, configured to send the benchmark model to multiple edge servers;

[0027] A first acquisition module is configured to, in response to receiving model training information for training a benchmark model reported by the first edge server, acquire reward values ​​corresponding to respective ones of a plurality of second edge servers other than the first edge server among the plurality of edge servers;

[0028] A first determining module is configured to determine at least one shared edge server corresponding to the first edge server from the plurality of second edge servers based on reward values ​​corresponding to the plurality of second edge servers and a preset reward threshold;

[0029] The first sending module is further configured to determine the address information corresponding to at least one shared edge server and send the address information corresponding to at least one shared edge server to the first edge server; wherein the address information is used by the first edge server to send the model sharing information to the shared edge server corresponding to the address information.

[0030] On the other hand, the present application provides a model sharing device for multiple edge servers, including:

[0031] A first receiving module is configured to, in response to receiving a benchmark model sent by a central server, train the benchmark model to obtain a trained optimization model and generate model training information for training the benchmark model;

[0032] The second sending module is used to report model training information to the central server;

[0033] A first generating module is configured to generate model sharing information in response to receiving address information corresponding to at least one shared edge server sent by the central server;

[0034] The second sending module is further configured to send the model sharing information to the shared edge server based on the address information of each shared edge server.

[0035] On the other hand, the present application provides a model sharing device for multiple edge servers, including:

[0036] A second receiving module is configured to, in response to receiving the model sharing information sent by the first edge server, update the baseline model based on the model sharing information to obtain an optimized model;

[0037] The second generating module is configured to generate reward information corresponding to the first edge server and report the reward information to the central server.

[0038] On the other hand, the present application provides a model sharing method for multiple edge servers, including:

[0039] A first sending module is used for the central server to send the benchmark model to multiple edge servers;

[0040] A first receiving module is configured for the first edge server to generate model training information for training the benchmark model in response to receiving the benchmark model sent by the central server, and report the model training information to the central server;

[0041] a first acquisition module configured for the central server to, in response to receiving model training information for training a benchmark model reported by the first edge server, obtain reward values ​​corresponding to each of a plurality of second edge servers other than the first edge server from the plurality of edge servers; determine, from the plurality of second edge servers, at least one shared edge server corresponding to the first edge server based on the reward values ​​corresponding to the plurality of second edge servers and a preset reward threshold; determine address information corresponding to each of the at least one shared edge servers, and transmit the address information corresponding to each of the at least one shared edge servers to the first edge server;

[0042] The first receiving module is further configured for the first edge server to generate model sharing information in response to receiving address information corresponding to at least one shared edge server sent by the central server, and send the model sharing information to the shared edge server based on the address information of each shared edge server;

[0043] A second receiving module is configured for the shared edge server to generate reward information corresponding to the first edge server in response to receiving the model sharing information sent by the first edge server, and report the reward information to the central server;

[0044] The first determination module is configured to receive, by the central server, reward information reported by at least one shared edge server, determine a reward value of the first edge server based on the model training information reported by the first edge server and the reward information reported by at least one shared edge server, and update the reward value of the first edge server.

[0045] The present application also provides an electronic device, comprising: a memory for storing a computer program; and a processor for implementing the steps of any of the above-mentioned model sharing methods for multiple edge servers when executing the computer program.

[0046] The present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned model sharing methods for multiple edge servers are implemented.

[0047] The present application also provides a computer program product, including a computer program, which implements the steps of any of the above-mentioned model sharing methods for multiple edge servers when the computer program is executed by a processor.

[0048] The present application provides a model sharing method, device and storage medium for multiple edge servers. Since the artificial intelligence model is first trained separately by each edge server, and then the model sharing information generated after the model training is shared with other edge servers, each edge server can rely on the training information of other edge servers and fully utilize the network advantages of each edge server node. While improving the model training efficiency, it can also enable the trained model to maintain high detection accuracy in multiple different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0050] Figure 1 A schematic diagram of an application scenario of a model sharing method for multiple edge servers provided in an embodiment of the present application;

[0051] Figure 2 The process of the model sharing method of multiple edge servers provided in the embodiment of this application Figure 1 ;

[0052] Figure 3 The process of the model sharing method of multiple edge servers provided in the embodiment of this application Figure 2 ;

[0053] Figure 4 The process of the model sharing method of multiple edge servers provided in the embodiment of this application Figure 3 ;

[0054] Figure 5 An interactive flow chart of a model sharing method for multiple edge servers provided in an embodiment of the present application;

[0055] Figure 6 A schematic diagram of the structure of a model sharing device for multiple edge servers provided in an embodiment of the present application;

[0056] Figure 7 This is a schematic diagram of the structure of the electronic device provided in this application. DETAILED DESCRIPTION

[0057] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0058] It should be noted that, in the description of this application, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. The terms "first," "second," etc., in this application are used to distinguish similar objects, and are not used to describe a particular order or sequence.

[0059] With the rapid development of artificial intelligence (AI) technology, more and more scenarios are being tested for security using trained AI models. However, when AI models are used for security testing in multiple scenarios, due to environmental differences, it is difficult for the AI ​​models to maintain high detection accuracy across the scenarios.

[0060] Therefore, how to improve the detection accuracy of artificial intelligence models in multiple different scenarios is a technical problem that needs to be solved urgently.

[0061] For example, with the rapid development of artificial intelligence technology, more and more places, such as hospitals, factories, and schools, have begun to transform themselves into intelligent systems and deploy intelligent monitoring systems based on the same algorithms. These systems typically cover application scenarios such as fire and smoke detection, crowd detection, and electronic fencing, aiming to improve safety and operational efficiency. However, due to differences in environmental conditions, data characteristics, and device performance across different scenarios, traditional single models often struggle to maintain high accuracy and efficiency in all scenarios. Therefore, how to effectively improve the accuracy and robustness of these models in different scenarios and how to achieve collaborative operation of edge servers across various scenarios have become urgent issues to be addressed.

[0062] In response to the above technical problems, the inventor's technical conception is as follows: by connecting edge computing devices in different scenarios into an intelligent training group, sharing model parameters while protecting data privacy, it is possible to integrate the local advantages of each scenario, conduct separate training and centralized optimization of the model, and thus improve the accuracy of the entire system. Accordingly, the specific steps may include: first training the artificial intelligence model separately through each edge server, and then sharing the model sharing information generated after the model training with other edge servers, so that each edge server can rely on the training information of other edge servers. It can be seen that this method can make full use of the network advantages of each edge server node, while improving the efficiency of model training, it can enable the trained model to maintain a high detection accuracy in multiple different scenarios.

[0063] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0064] The specific application environment architecture or specific hardware architecture that the execution of the model sharing method of multiple edge servers depends on is described here. Figure 1 , Figure 1 Schematic diagram of an application scenario of the model sharing method for multiple edge servers provided in an embodiment of the present application. A central server is networked with multiple edge servers (N edge servers are used as an example for illustration) so that the central server and the edge servers can communicate with each other.

[0065] The central server sends a benchmark model to multiple edge servers; the first edge server generates model training information for training the benchmark model in response to receiving the benchmark model sent by the central server, and reports the model training information to the central server; the central server obtains reward values ​​corresponding to multiple second edge servers other than the first edge server from the multiple edge servers in response to receiving the model training information for training the benchmark model reported by the first edge server; determines at least one shared edge server corresponding to the first edge server from the multiple second edge servers based on the reward values ​​corresponding to the multiple second edge servers and a preset reward threshold; determines the address information corresponding to each of the at least one shared edge server, and sends at least one to the first edge server. The first edge server generates model sharing information in response to receiving the address information corresponding to at least one shared edge server sent by the central server, and sends the model sharing information to the shared edge server based on the address information of each shared edge server; the shared edge server generates reward information corresponding to the first edge server in response to receiving the model sharing information sent by the first edge server, and reports the reward information to the central server; the central server receives the reward information reported by the at least one shared edge server, determines the reward value of the first edge server according to the model training information reported by the first edge server and the reward information reported by the at least one shared edge server, and updates the reward value of the first edge server.

[0066] The embodiment of the present application provides a model sharing method for multiple edge servers. This method effectively manages edge servers with different architectures, fully utilizes the network advantages of each edge server node while protecting data privacy, transfers model parameters, and formulates a reward strategy to incentivize each server node to train and share model parameters, thereby effectively improving the accuracy of the algorithm.

[0067] Figure 2 The process of the model sharing method of multiple edge servers provided in the embodiment of this application Figure 1 , the execution subject of the model sharing method of the multiple edge servers can be a terminal device or a server. When the execution subject is a server, it can be a central server. Figure 2 As shown, the embodiment of the present application provides a model sharing method for multiple edge servers. The method is described in detail by taking the execution subject as a central server as an example, as follows:

[0068] S201: Send a benchmark model to multiple edge servers.

[0069] In an embodiment of the present application, the central server and the edge servers are networked so that the networks between the central server and the edge servers can communicate with each other.

[0070] Optionally, the network transmission protocol between the central server and the edge servers is HTTP (Hypertext Transfer Protocol). When training the artificial intelligence model, the central server can send the baseline model to multiple edge servers via the HTTP protocol.

[0071] In an embodiment of the present application, the baseline model is an initial artificial intelligence model in a universal format. The universal format supports format conversion between multiple model training frameworks and is used to enable data transmission between different model training frameworks. Alternatively, the universal format may be an onnx format. The onnx format can support format conversion between multiple model training frameworks.

[0072] For example, the benchmark model is the yolov5 model, which can be trained using the pytorch framework or the tensorflow framework, and can be converted into the onnx format for data transmission.

[0073] S202: In response to receiving model training information for training a benchmark model reported by a first edge server, obtain reward values ​​corresponding to respective second edge servers excluding the first edge server from among the plurality of edge servers.

[0074] In the embodiment of the present application, the first edge server may be any edge server that trains the benchmark model, and the second edge server may be any edge server other than the first edge server among the plurality of edge servers.

[0075] Optionally, the central server stores a reward value for each edge server, which can represent the contribution of each edge server to model training and is used to motivate each edge server to train and share model parameters.

[0076] S203: Determine at least one shared edge server corresponding to the first edge server from the plurality of second edge servers according to the reward values ​​corresponding to the plurality of second edge servers and a preset reward threshold.

[0077] In the embodiment of the present application, there is no specific limitation on the value of the preset reward threshold, and it can be set and modified as needed.

[0078] In some embodiments, the preset reward threshold may be determined according to reward values ​​corresponding to each of the plurality of second edge servers.

[0079] Optionally, the ratio of the number of second edge servers with reward values ​​greater than the preset reward threshold to the total number of the second edge servers is a preset ratio. In this embodiment of the present application, the value of the preset ratio is not specifically limited and can be set and modified as needed. For example, the preset ratio may be 0.7, 0.8, 0.9, etc.

[0080] Exemplarily, the plurality of second edge servers includes 100, of which 90 have a reward value greater than 10, 80 have a reward value greater than 15, and 70 have a reward value greater than 20. In this case, if the preset ratio is set to 0.7, the preset reward threshold is 20. If the preset ratio is set to 0.8, the preset reward threshold is 15. If the preset ratio is set to 0.9, the preset reward threshold is 10.

[0081] S204: Determine the address information corresponding to at least one shared edge server, and send the address information corresponding to at least one shared edge server to the first edge server; wherein the address information is used by the first edge server to send model sharing information to the shared edge server corresponding to the address information.

[0082] Optionally, the address information corresponding to each shared edge server is encrypted virtual address information. This protects the data security of each shared edge server. Accordingly, determining the address information corresponding to at least one shared edge server includes: obtaining initial address information corresponding to at least one shared edge server; and encrypting the initial address information corresponding to at least one shared edge server to obtain the address information corresponding to at least one shared edge server.

[0083] In the embodiment of the present application, the artificial intelligence model is first trained separately by each edge server, and then the model sharing information generated after the model training is shared with other edge servers, so that each edge server can rely on the training information of other edge servers. As can be seen, this method can fully utilize the network advantages of each edge server node, while improving the efficiency of model training, and can enable the trained model to maintain high detection accuracy in multiple different scenarios.

[0084] Furthermore, a method for storing the reward values ​​of each edge server in the central server is described in detail. Optionally, the method further includes:

[0085] S205: Receive reward information reported by at least one shared edge server.

[0086] In an embodiment of the present application, the reward information includes at least one of the following: a model parameter of the baseline model, a third accuracy rate of the baseline model determined by the shared edge server, a fourth accuracy rate of the optimization model determined by the shared edge server, and a parameter amount of the model sharing information.

[0087] S206. Determine a reward value for the first edge server based on the model training information reported by the first edge server and the reward information reported by at least one shared edge server.

[0088] In an embodiment of the present application, the model training information includes at least one of the following: model parameters of the baseline model, training parameters of the optimization model, a first accuracy rate of the baseline model determined by the first edge server, and a second accuracy rate of the optimization model determined by the first edge server; wherein the optimization model is obtained by the first edge server training the baseline model through a training data set and a verification data set.

[0089] Optionally, determining the reward value of the first edge server based on the model training information reported by the first edge server and the reward information reported by at least one shared edge server may include the following steps (1) to (4):

[0090] (1) Determine the model contribution reward value of the first edge server according to the third accuracy of the baseline model and the fourth accuracy of the optimized model reported by each shared edge server.

[0091] Optionally, this step may include:

[0092] (1a) Determine a first accuracy change value of each shared edge server based on the third accuracy of the baseline model and the fourth accuracy of the optimized model reported by each shared edge server; and determine an average accuracy change value based on the first accuracy change value of each shared edge server.

[0093] For example, the third accuracy rate may be expressed as mAP1, and the fourth accuracy rate may be expressed as mAP2.

[0094] Among them, the average value of accuracy change can be expressed as:

[0095]

[0096] Where L represents the number of shared edge servers.

[0097] (1b) Obtaining the optimized model from the target edge server, determining the fifth accuracy of the baseline model and the sixth accuracy of the optimized model, and determining a second accuracy change value based on the fifth accuracy and the sixth accuracy, wherein the target edge server is the edge server with the largest network bandwidth.

[0098] In this step, the central server can calculate the network bandwidth information between it and all edge servers, pull the model from the edge server with the largest network bandwidth, and evaluate the model. Optionally, the central server stores model evaluation pool data for evaluating model effectiveness.

[0099] For example, the fifth accuracy can be expressed as mAP1 0 , the sixth accuracy can be expressed as mAP2 0 .

[0100] The second accuracy change value can be expressed as:

[0101]

[0102] (1c) Perform a weighted summation of the average accuracy change value and the second accuracy change value to obtain the model contribution reward value of the first edge server.

[0103] Exemplarily, the model contribution reward value of the first edge server can be expressed as:

[0104]

[0105] Among them, r m represents the model contribution reward value, L represents the number of shared edge servers, the third accuracy can be expressed as mAP1, the fourth accuracy can be expressed as mAP2, and the fifth accuracy can be expressed as mAP1 0 , the sixth accuracy can be expressed as mAP2 0 , The weight representing the average value of the accuracy change, The weight representing the second accuracy change value.

[0106] In the present application, the model contribution reward value determined by the central server and the model contribution reward value determined by each shared edge server are combined to obtain the model contribution reward value of the first edge server, thereby improving the accuracy of the determined model contribution reward value.

[0107] (2) Determine the model training reward value of the first edge server based on the training parameters of the optimization model reported by the first edge server.

[0108] In an embodiment of the present application, the training parameters of the optimization model include: the number of training iterations, the number of training data sets, the number of verification data sets, and the computing power parameters of the edge server; accordingly, this step may include: determining a first ratio between the number of training iterations and the maximum number of iterations, and determining a second ratio between the number of training data sets and the maximum number of training data sets, and determining a third ratio between the number of data sets and the maximum number of verification data sets, and determining the inverse of the computing power parameter of the edge server; performing weighted summation on the first ratio, the second ratio, the third ratio, and the inverse to obtain a model training reward value for the first edge server.

[0109] Optionally, the weights corresponding to the first ratio, the second ratio, and the third ratio are the same. Accordingly, the model training reward value can be expressed as:

[0110]

[0111] Among them, r t Represents the model training reward value, T c represents the first ratio between the number of training iterations and the maximum number of iterations; d t Represents the second ratio between the number of training data sets and the maximum number of training data sets; d v represents the third ratio between the number of datasets and the maximum number of validation datasets; C represents the computing power parameter of the edge server, Indicates the weights corresponding to the first ratio, the second ratio, and the third ratio, Indicates the weight corresponding to the computing power parameter of the edge server.

[0112] For example, the maximum number of iterations is 100, the maximum number of training data sets is 5000, and the maximum number of validation data sets is 1000. Specifically, the number of training iterations is 50, the number of training data sets is 4000, and the number of validation data sets is 800. At this time, the first ratio is 0.5, the second ratio is 0.8, and the third ratio is 0.8.

[0113] (3) Determine the model sharing reward value of the first edge server based on the parameter quantity of the model sharing information reported by each shared edge server.

[0114] Optionally, this step may include: determining the sum of the parameter quantities of the model sharing information downloaded by the shared edge server from the first edge server based on the parameter quantity of the model sharing information reported by each shared edge server; and determining the model sharing reward value of the first edge server based on the product of the sum of the parameter quantities of the model sharing information downloaded by the shared edge server from the first edge server and a preset coefficient.

[0115] Exemplarily, the model sharing reward value of the first edge server can be expressed as:

[0116]

[0117] Among them, r c represents the model sharing reward value, P represents the sum of the parameters of the model sharing information downloaded by the shared edge server from the first edge server, Indicates the preset coefficient.

[0118] (4) Determine the reward value of the first edge server based on the model contribution reward value, the model training reward value, and the model sharing reward value.

[0119] S206: Update the reward value of the first edge server.

[0120] Figure 3 The process of the model sharing method of multiple edge servers provided in the embodiment of this application Figure 2 .like Figure 3 As shown, the embodiment of the present application provides a model sharing method for multiple edge servers. The method is described in detail by taking the execution subject as the first edge server as an example, as follows:

[0121] S301. In response to receiving a benchmark model sent by a central server, the benchmark model is trained to obtain a trained optimization model, and model training information for training the benchmark model is generated.

[0122] In an embodiment of the present application, this step may include: in response to receiving a benchmark model sent by a central server, obtaining model parameters of the benchmark model; obtaining a training data set and a verification data set, and training the benchmark model through the training data set and the verification data set to obtain a trained optimization model; obtaining the number of training iterations for training the benchmark model, and obtaining the training parameters of the optimization model based on the number of training iterations, the training data set and the verification data set; determining a first accuracy rate corresponding to the benchmark model, and determining a second accuracy rate corresponding to the optimization model; generating model training information for training the benchmark model based on one or more of the model parameters of the benchmark model, the training parameters of the optimization model, the first accuracy rate, and the second accuracy rate.

[0123] In the embodiment of the present application, the first edge server can extract model parameter information by layer according to the model architecture. For example, the yolov5-s model has 214 layers, and the number of parameters in each layer is not the same. The total number of parameters extracted by layer is 7.2M.

[0124] Optionally, the model parameters of the baseline model include: model update time, number of model layers, size of each layer and detection object information; wherein, the detection object information includes status information of at least one detection object in the monitoring scene, and the baseline model is used to determine the security alarm information corresponding to the monitoring scene based on the status information of at least one detection object in the monitoring scene.

[0125] Optionally, the first accuracy rate and the second accuracy rate may be mAP0.5 (mean Average Precision) values, where 0.5 represents the Intersection over Union (IoU) between the model's predicted value and the true value. The method for determining mAP0.5 is not specifically limited herein.

[0126] It should be noted that edge servers can support multiple computing architectures. For example, they can support GPU (Graphics Processing Unit) computing architecture, CPU (Central Processing Unit) computing architecture, NPU (Neural Network Processing Unit) computing architecture, TPU (Tensor Processing Unit) computing architecture, etc.

[0127] In an embodiment of the present application, before the first edge server trains the benchmark model using the training data set and the validation data set to obtain the trained optimized model, it is necessary to convert the benchmark model into the model required by the respective architectures.

[0128] S302: Report model training information to the central server.

[0129] Optionally, the model training information reported is as follows:

[0130] {Minfo;mAP1; mAP1;Training;computing}

[0131] Among them, Minfo: model information, including model update time, number of model layers, size of each layer, detection target, etc.; mAP1: mAP0.5 value of the original model in this environment before the model update; mAP2: mAP0.5 value of the new model in this environment after the model update; Training: training information, total amount of training data, total amount of verification data, number of training iterations; Computing: computing power of the device.

[0132] S303: In response to receiving the address information corresponding to at least one shared edge server sent by the central server, generate model sharing information.

[0133] Optionally, this step may include: in response to receiving the address information corresponding to at least one shared edge server sent by the central server, generating model sharing information according to one or more of the model parameters of the baseline model, the training parameters of the optimization model, the first accuracy rate, the second accuracy rate, and the address information corresponding to at least one shared edge server; and sending the model sharing information to the shared edge server based on the address information of each shared edge server.

[0134] S304: Send model sharing information to the shared edge server based on the address information of each shared edge server.

[0135] In an embodiment of the present application, in order to improve the transmission efficiency of model sharing information, before the first edge server sends the model sharing information to the shared edge server, it can convert the optimized model into a standard model, and divide the model parameters of the converted standard model by layer to obtain the model parameters corresponding to each layer. Then, the model sharing information can be sent to the shared edge server by layer.

[0136] Exemplarily, the model sharing information is sent to the shared edge server as follows:

[0137] {Minfo;mAP1; mAP1;parameter;sharenode}

[0138] Among them, Minfo: model information, including model update time, number of model layers, size of each layer, detection target, etc.; mAP1: mAP0.5 value of the original model in this environment before the model is updated; mAP2: mAP0.5 value of the new model in this environment after the model is updated; parameter: specific parameter values ​​after converting the model to a standard model and dividing the model parameters by layer; sharenode: shareable edge node information.

[0139] It should be noted that, in the embodiment of the present application, when there are multiple shared edge servers, the model sharing information can be sent to the shared edge server according to the transmission bandwidth between the multiple edge servers.

[0140] In some embodiments, the steps for optimizing model parameter transmission are as follows:

[0141] Step 1: Calculate the total number of layers L of the model and the number of parameters M of each layer.

[0142] The model may be an optimized model obtained by training a benchmark model using a training data set and a validation data set by the first edge server, wherein the model sharing information includes the parameter values ​​of each layer of the model.

[0143] Step 2: Calculate the bandwidth information Bij of all edge servers.

[0144] Where Bij is the transmission bandwidth between edge server i and edge server j.

[0145] Optionally, when the parameter amount is M, the required transmission time between two edge servers is:

[0146]

[0147] Here, the unit of M is MB, the unit of bandwidth Bij is Mbps (megabits per second), 1 byte is equal to 8 bits, so the total number of bits is M*8, and the transmission time is the number of bits divided by the bandwidth.

[0148] Step 3: The edge server with the largest bandwidth requests the shared device (ie, the first edge server) to obtain model parameters.

[0149] Step 4: The sharing device (ie, the first edge server) determines whether the requesting device (the edge server with the largest bandwidth in step 3) has the largest bandwidth. If so, the next step is executed; otherwise, the next step is continued.

[0150] Step 5: Determine whether the requesting device (the edge server with the largest bandwidth in step 4) has completed pulling a complete layer of model parameters. If so, proceed to the next step; otherwise, continue waiting.

[0151] Step 6: The requesting device (the edge server with the largest bandwidth in step 4) continues to broadcast the model parameter information.

[0152] Step 7: The remaining edge servers calculate the bandwidth information between the two devices.

[0153] In the embodiment of the present application, the two devices refer to: the first edge server and the edge server with the largest bandwidth in step 4.

[0154] Step 8: Select the device with the largest bandwidth information and pull the model information.

[0155] In some embodiments, when the bandwidth information is the largest, the corresponding transmission time is the smallest, that is, the device with the smallest transmission time is selected to pull the model information.

[0156] Step 9: The remaining devices follow this strategy in turn and pull model parameters from other devices.

[0157] Optionally, when the model parameters of the converted standard model are divided by layer to obtain the model parameters corresponding to each layer, and the model sharing information is sent to the shared edge server by layer, a pair of devices can be selected for each layer of the model so that the transmission time T ij Minimum. Among them, T ij represents the minimum transmission time corresponding to edge server i and edge server j. Then, the total transmission time of the model parameters of this layer is determined by the maximum transmission time of multiple shared edge servers.

[0158] Exemplarily, the standard model includes L layers of model parameters. For each layer of model parameters in the standard model, a pair of devices (i, j) is selected to minimize the transfer time. When it is determined that all L layers of model parameters have been transferred, the total transfer time is calculated.

[0159] For example, the total transmission time is:

[0160]

[0161] Among them, A [i] Indicates the earliest available time of device i; A [j] represents the earliest available time of device j; T ij represents the minimum transmission time between edge server i and edge server j; where starttime i Indicates the time when device i completes the task being executed, where starttime j Indicates the time when device j completes the task being executed. The task being executed can be a model training task within the current device or a data transmission task between the current device and other devices.

[0162] Step 10: Determine whether all model parameters of each layer of each edge server have been pulled. If so, proceed to the next step; otherwise, return to step 7.

[0163] Step 11: Each edge server uploads the model parameters and node information pulled from the previous edge server to the central server.

[0164] In the embodiment of the present disclosure, since two edge servers corresponding to the minimum transmission time are determined according to the network bandwidth between each edge server, the model parameters are transmitted through the two edge servers corresponding to the minimum transmission time, thereby improving the transmission efficiency of the model parameters.

[0165] Figure 4 The process of the model sharing method of multiple edge servers provided in the embodiment of this application Figure 3 .like Figure 4As shown, the embodiment of the present application provides a model sharing method for multiple edge servers. The method is described in detail by taking the execution subject as a shared edge server as an example, as follows:

[0166] S401: In response to receiving model sharing information sent by a first edge server, update a baseline model based on the model sharing information to obtain an optimized model.

[0167] Optionally, the shared edge server receives the model sharing information sent by the first edge server, converts the model sharing information into model parameters corresponding to the shared edge server, and then updates the baseline model based on the converted model parameters to obtain the optimized model.

[0168] S402: Generate reward information corresponding to the first edge server, and report the reward information to the central server.

[0169] Optionally, generating reward information corresponding to the first edge server includes: obtaining a server identifier of the first edge server and a parameter amount of the model sharing information; determining a third accuracy rate corresponding to the baseline model, and determining a fourth accuracy rate corresponding to the optimization model; generating reward information corresponding to the first edge server based on one or more of the model parameters of the baseline model in the model sharing information, the third accuracy rate, the fourth accuracy rate, the server identifier of the first edge server, and the parameter amount of the model sharing information.

[0170] For example, the reward information reported is as follows:

[0171] {Minfo;mAP1; mAP1;Training;computing}

[0172] Among them, Minfo: model information, including model update time, number of model layers, size of each layer, detection target, etc.; mAP1: mAP0.5 value of the original model in this environment before the model update; mAP2: mAP0.5 value of the new model in this environment after the model update; Training: training information, total amount of training data, total amount of verification data, number of training iterations; Computing: computing power of the device.

[0173] Figure 5 This is an interactive flow chart of a model sharing method for multiple edge servers provided in an embodiment of the present application. Figure 5 As shown, an embodiment of the present application provides a model sharing method for multiple edge servers, including:

[0174] S501: The central server sends a benchmark model to multiple edge servers.

[0175] S502: In response to receiving the benchmark model sent by the central server, the first edge server generates model training information for training the benchmark model.

[0176] S503: The first edge server reports model training information to the central server.

[0177] S504: In response to receiving model training information for training the benchmark model reported by the first edge server, the central server obtains a reward value corresponding to each of multiple second edge servers other than the first edge server from the multiple edge servers; determines at least one shared edge server corresponding to the first edge server from the multiple second edge servers based on the reward values ​​corresponding to each of the multiple second edge servers and a preset reward threshold; and determines address information corresponding to each of the at least one shared edge servers.

[0178] S505: The central server sends the corresponding address information of at least one shared edge server to the first edge server.

[0179] S506: In response to receiving the address information corresponding to at least one shared edge server sent by the central server, the first edge server generates model sharing information based on the address information of each shared edge server.

[0180] S507: The first edge server sends the model sharing information to the shared edge server.

[0181] S508: The shared edge server generates reward information corresponding to the first edge server in response to receiving the model sharing information sent by the first edge server.

[0182] S509: The shared edge server reports the reward information to the central server.

[0183] S510: The central server receives reward information reported by at least one shared edge server, determines a reward value of the first edge server based on the model training information reported by the first edge server and the reward information reported by at least one shared edge server, and updates the reward value of the first edge server.

[0184] The model sharing method for multiple edge servers provided in the example of this application first trains the artificial intelligence model separately through each edge server, and then shares the model sharing information generated after the model training with other edge servers, so that each edge server can rely on the training information of other edge servers and make full use of the network advantages of each edge server node. While improving the efficiency of model training, it can also enable the trained model to maintain high detection accuracy in multiple different scenarios.

[0185] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method.

[0186] Figure 6 This is a schematic diagram of the structure of a model sharing device for multiple edge servers provided in an embodiment of the present application. Figure 6 As shown, an embodiment of the present application further provides a model sharing device for multiple edge servers, the device 60 comprising:

[0187] A first sending module 601 is configured to send a reference model to multiple edge servers;

[0188] A first acquisition module 602 is configured to, in response to receiving model training information for training a benchmark model reported by a first edge server, acquire reward values ​​corresponding to respective second edge servers other than the first edge server from among the plurality of edge servers;

[0189] A first determining module 603 is configured to determine at least one shared edge server corresponding to the first edge server from the plurality of second edge servers based on the reward values ​​corresponding to the plurality of second edge servers and a preset reward threshold;

[0190] The first sending module 601 is further configured to determine the address information corresponding to at least one shared edge server and send the address information corresponding to at least one shared edge server to the first edge server; wherein the address information is used by the first edge server to send model sharing information to the shared edge server corresponding to the address information.

[0191] In some embodiments, the method further includes: receiving reward information reported by at least one shared edge server; determining a reward value of the first edge server based on the model training information reported by the first edge server and the reward information reported by at least one shared edge server; and updating the reward value of the first edge server; wherein the model training information includes at least one of the following: model parameters of the baseline model, training parameters of the optimization model, a first accuracy of the baseline model determined by the first edge server, and a second accuracy of the optimization model determined by the first edge server; wherein the optimization model is obtained by the first edge server training the baseline model through a training data set and a verification data set; wherein the reward information includes at least one of the following: model parameters of the baseline model, a third accuracy of the baseline model determined by the shared edge server, a fourth accuracy of the optimization model determined by the shared edge server, and a parameter amount of the model sharing information.

[0192] In some embodiments, determining a reward value of the first edge server based on the model training information reported by the first edge server and the reward information reported by at least one shared edge server includes: determining a model contribution reward value of the first edge server based on the third accuracy of the baseline model and the fourth accuracy of the optimization model reported by each shared edge server; and determining a model training reward value of the first edge server based on the training parameters of the optimization model reported by the first edge server; and determining a model sharing reward value of the first edge server based on the parameter amount of the model sharing information reported by each shared edge server; and determining a reward value of the first edge server based on the model contribution reward value, the model training reward value, and the model sharing reward value.

[0193] In some embodiments, the model contribution reward value of the first edge server is determined based on the third accuracy of the baseline model and the fourth accuracy of the optimization model reported by each shared edge server, including: determining the first accuracy change value of each shared edge server based on the third accuracy of the baseline model and the fourth accuracy of the optimization model reported by each shared edge server; determining the accuracy change average value based on the first accuracy change value of each shared edge server; obtaining the optimization model from the target edge server, determining the fifth accuracy of the baseline model and the sixth accuracy of the optimization model, and determining the second accuracy change value based on the fifth accuracy and the sixth accuracy, the target edge server being the edge server with the largest network bandwidth; performing weighted summation on the accuracy change average value and the second accuracy change value to obtain the model contribution reward value of the first edge server.

[0194] In some embodiments, the training parameters of the optimization model include: the number of training iterations, the number of training data sets, the number of verification data sets, and the computing power parameters of the edge server; accordingly, based on the training parameters of the optimization model reported by the first edge server, the model training reward value of the first edge server is determined, including: determining a first ratio between the number of training iterations and the maximum number of iterations, and determining a second ratio between the number of training data sets and the maximum number of training data sets, and determining a third ratio between the number of data sets and the maximum number of verification data sets, and determining the inverse of the computing power parameter of the edge server; performing weighted summation on the first ratio, the second ratio, the third ratio and the inverse to obtain the model training reward value of the first edge server.

[0195] In some embodiments, determining the model sharing reward value of the first edge server based on the parameter amount of the model sharing information reported by each shared edge server includes: determining the sum of the parameter amounts of the model sharing information downloaded by the shared edge server from the first edge server based on the parameter amount of the model sharing information reported by each shared edge server; and determining the model sharing reward value of the first edge server based on the product of the sum of the parameter amounts of the model sharing information downloaded by the shared edge server from the first edge server and a preset coefficient.

[0196] On the other hand, the present application provides a model sharing device for multiple edge servers, including:

[0197] A first receiving module is configured to, in response to receiving a benchmark model sent by a central server, train the benchmark model to obtain a trained optimization model and generate model training information for training the benchmark model;

[0198] The second sending module is used to report model training information to the central server;

[0199] A first generating module is configured to generate model sharing information in response to receiving address information corresponding to at least one shared edge server sent by the central server;

[0200] The second sending module is further configured to send the model sharing information to the shared edge server based on the address information of each shared edge server.

[0201] In some embodiments, in response to receiving a benchmark model sent by a central server, model training information for training the benchmark model is generated, including: in response to receiving the benchmark model sent by the central server, obtaining model parameters of the benchmark model; obtaining a training data set and a verification data set, and training the benchmark model through the training data set and the verification data set to obtain a trained optimization model; obtaining the number of training iterations for training the benchmark model, and obtaining the training parameters of the optimization model based on the number of training iterations, the training data set and the verification data set; determining a first accuracy rate corresponding to the benchmark model, and determining a second accuracy rate corresponding to the optimization model; generating model training information for training the benchmark model based on one or more of the model parameters of the benchmark model, the training parameters of the optimization model, the first accuracy rate, and the second accuracy rate.

[0202] In some embodiments, the model parameters of the baseline model include: model update time, number of model layers, size of each layer and detection object information; wherein, the detection object information includes status information of at least one detection object in the monitoring scene, and the baseline model is used to determine the security alarm information corresponding to the monitoring scene based on the status information of at least one detection object in the monitoring scene.

[0203] In some embodiments, in response to receiving address information corresponding to at least one shared edge server sent by a central server, generating model sharing information includes: in response to receiving address information corresponding to at least one shared edge server sent by the central server, generating model sharing information based on one or more of model parameters of the baseline model, training parameters of the optimization model, the first accuracy rate, the second accuracy rate, and the address information corresponding to at least one shared edge server; and sending the model sharing information to the shared edge server based on the address information of each shared edge server.

[0204] On the other hand, the present application provides a model sharing device for multiple edge servers, including:

[0205] A second receiving module is configured to, in response to receiving the model sharing information sent by the first edge server, update the baseline model based on the model sharing information to obtain an optimized model;

[0206] The second generating module is configured to generate reward information corresponding to the first edge server and report the reward information to the central server.

[0207] In some embodiments, generating reward information corresponding to the first edge server includes: obtaining a server identifier of the first edge server and a parameter amount of the model sharing information; determining a third accuracy rate corresponding to the baseline model, and determining a fourth accuracy rate corresponding to the optimization model; generating reward information corresponding to the first edge server based on one or more of the model parameters of the baseline model in the model sharing information, the third accuracy rate, the fourth accuracy rate, the server identifier of the first edge server, and the parameter amount of the model sharing information.

[0208] On the other hand, the present application provides a model sharing method for multiple edge servers, including:

[0209] A first sending module is used for the central server to send the benchmark model to multiple edge servers;

[0210] A first receiving module is configured for the first edge server to generate model training information for training the benchmark model in response to receiving the benchmark model sent by the central server, and report the model training information to the central server;

[0211] a first acquisition module configured for the central server to, in response to receiving model training information for training a benchmark model reported by the first edge server, obtain reward values ​​corresponding to each of a plurality of second edge servers other than the first edge server from the plurality of edge servers; determine, from the plurality of second edge servers, at least one shared edge server corresponding to the first edge server based on the reward values ​​corresponding to the plurality of second edge servers and a preset reward threshold; determine address information corresponding to each of the at least one shared edge servers, and transmit the address information corresponding to each of the at least one shared edge servers to the first edge server;

[0212] The first receiving module is further configured for the first edge server to generate model sharing information in response to receiving address information corresponding to at least one shared edge server sent by the central server, and send the model sharing information to the shared edge server based on the address information of each shared edge server;

[0213] A second receiving module is configured for the shared edge server to generate reward information corresponding to the first edge server in response to receiving the model sharing information sent by the first edge server, and report the reward information to the central server;

[0214] The first determination module is configured to receive, by the central server, reward information reported by at least one shared edge server, determine a reward value of the first edge server based on the model training information reported by the first edge server and the reward information reported by at least one shared edge server, and update the reward value of the first edge server.

[0215] For the description of the features in the embodiment corresponding to the model sharing device of multiple edge servers, please refer to the relevant description of the embodiment corresponding to the model sharing method of multiple edge servers, which will not be repeated here.

[0216] Figure 7 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 7 As shown, the electronic device 70 provided in this embodiment includes: at least one processor 701 and a memory 702. Optionally, the device 70 further includes a communication component 703. The processor 701, the memory 702 and the communication component 703 are connected via a bus.

[0217] In a specific implementation process, at least one processor 701 executes the computer-executable instructions stored in the memory 702, so that the at least one processor 701 executes the above-mentioned model sharing method embodiment of multiple edge servers.

[0218] The specific implementation process of the processor 701 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0219] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the application may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0220] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage.

[0221] A bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0222] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps of any of the above-mentioned embodiments of the model sharing method for multiple edge servers when running.

[0223] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0224] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any of the above-mentioned embodiments of the model sharing method for multiple edge servers are implemented.

[0225] An embodiment of the present application also provides another computer program product, including a non-volatile computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps in any of the above-mentioned embodiments of the model sharing method for multiple edge servers.

[0226] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0227] The above is a detailed introduction to the model sharing method, device, equipment and storage medium of multiple edge servers provided by this application. This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method of this application and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of this application, several improvements and modifications can be made to this application, and these improvements and modifications also fall within the scope of protection of the claims of this application.

Claims

1. A model sharing method for multiple edge servers, characterized in that: include: Send the benchmark model to multiple edge servers; In response to receiving model training information for training the benchmark model reported by the first edge server, obtaining reward values ​​corresponding to respective ones of a plurality of second edge servers other than the first edge server among the plurality of edge servers; Determining at least one shared edge server corresponding to the first edge server from the plurality of second edge servers according to the reward values ​​corresponding to the plurality of second edge servers and a preset reward threshold; Determining address information corresponding to each of the at least one shared edge servers, and sending the address information corresponding to each of the at least one shared edge servers to the first edge server; wherein the address information is used by the first edge server to send model sharing information to the shared edge server corresponding to the address information; Also includes: receiving reward information reported by the at least one shared edge server; Determining a reward value for the first edge server based on the model training information reported by the first edge server and the reward information reported by the at least one shared edge server; The reward value of the first edge server is updated.

2. The model sharing method according to claim 1, characterized in that: The model training information includes at least one of the following: model parameters of the baseline model, training parameters of the optimization model, a first accuracy rate of the baseline model determined by the first edge server, and a second accuracy rate of the optimization model determined by the first edge server; wherein the optimization model is obtained by the first edge server training the baseline model using a training dataset and a validation dataset; The reward information includes at least one of the following: a model parameter of the baseline model, a third accuracy rate of the baseline model determined by the shared edge server, a fourth accuracy rate of the optimization model determined by the shared edge server, and a parameter amount of the model sharing information.

3. The model sharing method according to claim 2, characterized in that: The determining the reward value of the first edge server according to the model training information reported by the first edge server and the reward information reported by the at least one shared edge server includes: Determining a model contribution reward value of the first edge server based on the third accuracy of the baseline model and the fourth accuracy of the optimized model reported by each shared edge server; and determining a model training reward value of the first edge server based on the training parameters of the optimized model reported by the first edge server; and determining a model sharing reward value of the first edge server based on the parameter quantity of the model sharing information reported by each shared edge server; A reward value of the first edge server is determined according to the model contribution reward value, the model training reward value, and the model sharing reward value.

4. The model sharing method according to claim 3, characterized in that: The determining, according to the third accuracy of the benchmark model and the fourth accuracy of the optimization model reported by each shared edge server, a model contribution reward value of the first edge server includes: Determining a first accuracy change value of each shared edge server according to the third accuracy of the baseline model and the fourth accuracy of the optimization model reported by each shared edge server; Determining an accuracy change average value based on the first accuracy change value of each shared edge server; Obtaining the optimization model from a target edge server, determining a fifth accuracy of the baseline model and a sixth accuracy of the optimization model, and determining a second accuracy change value based on the fifth accuracy and the sixth accuracy, wherein the target edge server is an edge server with the largest network bandwidth; A weighted sum is performed on the average accuracy change value and the second accuracy change value to obtain a model contribution reward value of the first edge server.

5. The model sharing method according to claim 3, characterized in that: The training parameters of the optimization model include: the number of training iterations, the number of training data sets, the number of validation data sets, and the computing power parameters of the edge server; Accordingly, determining the model training reward value of the first edge server according to the training parameters of the optimization model reported by the first edge server includes: determining a first ratio between the number of training iterations and the maximum number of iterations, and determining a second ratio between the number of training data sets and the maximum number of training data sets, and determining a third ratio between the number of data sets and the maximum number of validation data sets, and determining a reciprocal of a computing power parameter of the edge server; A weighted sum is performed on the first ratio, the second ratio, the third ratio, and the reciprocal to obtain a model training reward value of the first edge server.

6. The model sharing method according to claim 3, characterized in that: The determining, according to the parameter amount of the model sharing information reported by each shared edge server, the model sharing reward value of the first edge server includes: Determining, based on the parameter quantity of the model sharing information reported by each shared edge server, the sum of the parameter quantities of the model sharing information downloaded by the shared edge server from the first edge server; The model sharing reward value of the first edge server is determined according to the product of the sum of the parameter amounts of the model sharing information downloaded by the sharing edge server from the first edge server and a preset coefficient.

7. The model sharing method according to claim 1, characterized in that: The determining the address information corresponding to each of the at least one shared edge servers includes: Obtaining initial address information corresponding to each of the at least one shared edge servers; The initial address information corresponding to each of the at least one shared edge servers is encrypted to obtain the address information corresponding to each of the at least one shared edge servers.

8. The model sharing method according to any one of claims 1 to 7, characterized in that: The benchmark model is an initial artificial intelligence model in a universal format; wherein, the universal format supports format conversion of multiple model training frameworks and is used to realize data transmission between different model training frameworks.

9. A model sharing method for multiple edge servers, characterized in that: include: In response to receiving a benchmark model sent by a central server, training the benchmark model to obtain a trained optimization model, and generating model training information for training the benchmark model; Reporting the model training information to the central server; In response to receiving the address information corresponding to at least one shared edge server sent by the central server, generating model sharing information; Based on the address information of each shared edge server, the model sharing information is sent to the shared edge server, so that the shared edge server generates reward information corresponding to the first edge server in response to receiving the model sharing information sent by the first edge server, and reports the reward information to the central server; and the central server receives the reward information reported by at least one shared edge server; determines the reward value of the first edge server according to the model training information reported by the first edge server and the reward information reported by the at least one shared edge server; and updates the reward value of the first edge server.

10. The model sharing method according to claim 9, characterized in that: The step of generating model training information for training the benchmark model in response to receiving the benchmark model sent by the central server includes: In response to receiving the benchmark model sent by the central server, obtaining model parameters of the benchmark model; Obtaining a training data set and a validation data set, and training the benchmark model using the training data set and the validation data set to obtain a trained optimized model; Obtaining a number of training iterations for training the benchmark model, and obtaining training parameters of the optimization model based on the number of training iterations, the training data set, and the validation data set; Determining a first accuracy rate corresponding to the baseline model, and determining a second accuracy rate corresponding to the optimized model; Model training information for training the baseline model is generated based on one or more of the model parameters of the baseline model, the training parameters of the optimization model, the first accuracy rate, and the second accuracy rate.

11. The model sharing method according to claim 10, characterized in that: The model parameters of the benchmark model include: model update time, number of model layers, size of each layer and detection object information; The detection object information includes status information of at least one detection object in the monitoring scene, and the benchmark model is used to determine the security alarm information corresponding to the monitoring scene based on the status information of at least one detection object in the monitoring scene.

12. The model sharing method according to claim 11, characterized in that: The generating model sharing information in response to receiving the address information corresponding to at least one shared edge server sent by the central server includes: In response to receiving the address information corresponding to each of the at least one shared edge servers sent by the central server, generating model sharing information according to one or more of the model parameters of the baseline model, the training parameters of the optimization model, the first accuracy rate, the second accuracy rate, and the address information corresponding to each of the at least one shared edge servers; The model sharing information is sent to each shared edge server based on the address information of the shared edge server.

13. A model sharing method for multiple edge servers, characterized in that: include: The central server sends the benchmark model to multiple edge servers; In response to receiving the benchmark model sent by the central server, the first edge server generates model training information for training the benchmark model and reports the model training information to the central server; The central server obtains, in response to receiving model training information for training the benchmark model reported by the first edge server, a reward value corresponding to each of a plurality of second edge servers other than the first edge server among the plurality of edge servers; Determining at least one shared edge server corresponding to the first edge server from the plurality of second edge servers according to the reward values ​​corresponding to the plurality of second edge servers and a preset reward threshold; Determine the address information corresponding to each of the at least one shared edge servers, and send the address information corresponding to each of the at least one shared edge servers to the first edge server; The first edge server generates model sharing information in response to receiving the address information corresponding to at least one shared edge server sent by the central server, and sends the model sharing information to the shared edge server based on the address information of each shared edge server; The shared edge server generates reward information corresponding to the first edge server in response to receiving the model sharing information sent by the first edge server, and reports the reward information to the central server; The central server receives the reward information reported by the at least one shared edge server, determines a reward value of the first edge server based on the model training information reported by the first edge server and the reward information reported by the at least one shared edge server, and updates the reward value of the first edge server.

14. An electronic device, characterized in that: include: memory for storing computer programs; A processor, configured to implement the steps of the model sharing method for multiple edge servers as described in any one of claims 1 to 13 when executing the computer program.

15. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the model sharing method for multiple edge servers as described in any one of claims 1 to 13 are implemented.

Images