Inspection Parameter Optimization Method and Device Based on Cloud-Edge Collaboration

Abstract

The present application discloses a method and device for optimizing inspection parameters based on cloud-edge collaboration, which relates to the technical field of optimizing inspection parameters. The method includes: receiving an inspection instruction sent by the cloud, determining an inspection target according to the inspection instruction, determining a target terminal device according to the inspection target, obtaining a communication code of the target terminal device, establishing a dedicated data transmission channel according to the communication code, receiving status information uploaded by the target terminal device from the dedicated data transmission channel, determining an operating state of the target terminal device according to the status information, when the operating state is an abnormal state, determining an abnormal amplitude of the operating state, generating an optimization parameter by using the abnormal amplitude through a parameter optimization model, and optimizing operating parameters of the target terminal based on the optimization parameter. Through the above method, it is possible to remotely inspect multiple terminal devices located at different positions and optimize the parameters of each terminal device.

Description

Technical Field

[0001] This application relates to the technical field of inspection parameter optimization, and particularly to an inspection parameter optimization method and device based on cloud-edge collaboration. Background Art

[0002] In modern industry, the stable operation of the state of distribution network equipment is crucial for the economy and safety of the power system. The traditional manual inspection method is difficult to meet the requirements of real-time performance and accuracy. Therefore, a more efficient intelligent inspection method is needed. Currently, the commonly used method is to use drones to inspect distribution network equipment visually. This method can detect a single distribution network equipment, but it cannot detect multiple distribution network equipment simultaneously, and cannot conduct unified inspection on distribution network equipment, which is not conducive to the overall management of distribution network equipment.

[0003] The above content is only used to assist in understanding the technical solution of the present invention, and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide an inspection parameter optimization method and device based on cloud-edge collaboration, aiming to solve the technical problem in the prior art that multiple distribution network equipment cannot be inspected overall and parameter optimization cannot be performed.

[0005] To achieve the above purpose, this application provides an inspection parameter optimization method based on cloud-edge collaboration. The method includes:

[0006] Receive the inspection instruction sent by the cloud, determine the inspection target according to the inspection instruction, and determine the target terminal device according to the inspection target;

[0007] Obtain the communication code of the target terminal device, establish a dedicated data transmission channel according to the communication code, and receive the status information uploaded by the target terminal device from the dedicated data transmission channel;

[0008] Determine the operating state of the target terminal device according to the status information. When the operating state is an abnormal state, determine the abnormal amplitude of the operating state;

[0009] Generate optimization parameters by passing the abnormal amplitude through a parameter optimization model, and optimize the operating parameters of the target terminal based on the optimization parameters.

[0010] In one embodiment, the step of generating optimization parameters by passing the abnormal amplitude through a parameter optimization model and optimizing the operating parameters of the target terminal based on the optimization parameters includes:

[0011] Group the abnormal amplitude, determine the group of the abnormal amplitude, and determine the input layer of the parameter optimization model according to the group;

[0012] Input the abnormal amplitude into the hidden layer through the input layer, and determine the unit weights of each neuron in the hidden layer;

[0013] Determine the initial optimization parameters according to the abnormal amplitude, and weight the initial optimization parameters based on the unit weights to obtain the optimization parameters;

[0014] Optimize the operating parameters of the target terminal based on the optimization parameters.

[0015] In one embodiment, the step of determining the initial optimization parameters according to the abnormal amplitude, weighting the initial optimization parameters based on the unit weights, and obtaining the optimization parameters includes:

[0016] Obtain the abnormal amplitude parameter optimization table, and traverse the abnormal amplitude parameter optimization table based on the abnormal amplitude to determine the corresponding initial optimization parameters;

[0017] Determine the optimization intensity according to the abnormal amplitude, update the unit weights according to the optimization intensity and the hidden layer dimension to obtain the optimized weights;

[0018] Weight the initial optimization parameters with the optimized weights to obtain the optimization parameters.

[0019] In one embodiment, after the step of optimizing the operating parameters of the target terminal based on the optimization parameters, it further includes:

[0020] Determine the optimized operating state of the target terminal after the optimization of the operating parameters;

[0021] Determine the state gain according to the optimized operating state and the operating state, and determine the optimized abnormal amplitude according to the optimized operating state and the standard operating state;

[0022] When the optimized abnormal amplitude is the preset abnormal optimization amplitude, determine the state gain type;

[0023] When the state gain type is positive gain, determine the optimization parameter as the reinforcement factor, and determine the reinforcement discount factor according to the optimized abnormal amplitude, and use the reinforcement factor and the reinforcement discount factor to determine the next optimization intensity;

[0024] Update the optimization parameters according to the next optimization intensity until the operating parameters of the target terminal are within the preset standard threshold.

[0025] In one embodiment, after the step of determining the state gain type when the optimized abnormal amplitude is the preset abnormal optimization amplitude, it further includes:

[0026] When the state gain type is negative gain, invert the optimization parameter, and determine the inverted optimization parameter as the reinforcement factor;

[0027] Determine the reinforcement discount factor according to the optimization anomaly amplitude and the anomaly amplitude;

[0028] Determine the next optimization intensity with the comprehensive reinforcement factor obtained from the reinforcement factor and the reinforcement discount factor.

[0029] In one embodiment, the step of determining the operating state of the target terminal device according to the state information and determining the anomaly amplitude of the operating state when the operating state is an abnormal state includes:

[0030] Split the state information to obtain the performance parameters of each operating dimension in the target terminal device;

[0031] Respectively determine the standard performance parameters of the operating dimension;

[0032] Determine the performance difference of the operating dimension according to the performance parameter and the standard performance parameter;

[0033] Construct a parameter matrix with the operating dimension, initialize the parameter matrix, and write the performance difference into the parameter matrix;

[0034] Determine the follow-up relationship of each element in the parameter matrix, and determine the operating state of the target terminal device based on the state follow-up function corresponding to the follow-up relationship;

[0035] When the operating state is an abnormal state, map the performance difference to the parameter matrix to obtain an anomaly amplitude matrix;

[0036] Determine the anomaly amplitude according to the eigenvalues of the anomaly amplitude matrix.

[0037] In one embodiment, the steps of receiving the inspection instruction sent by the cloud, determining the inspection target according to the inspection instruction, and determining the target terminal device according to the inspection target include:

[0038] Receive the inspection instruction sent by the cloud, unpack the inspection instruction to obtain an instruction frame;

[0039] Traverse the instruction frame to determine the key frame of the instruction frame;

[0040] Take the key frame as a segmentation point, and extract the inspection task of the instruction frame at the segmentation point;

[0041] Identify the inspection task to obtain a device code, and determine the target terminal device according to the device code.

[0042] In one embodiment, the steps of obtaining the communication code of the target terminal device, establishing an exclusive data transmission channel according to the communication code, and receiving the status information uploaded by the target terminal device from the exclusive data transmission channel include:

[0043] Obtain the device information of the target terminal device and read the communication code of the device information;

[0044] Generate a temporary communication key pair according to the inspection instruction and the communication code;

[0045] Send the temporary communication key pair to the target terminal device and receive the feedback information of the target terminal device upon receiving the temporary communication key pair;

[0046] Establish an exclusive data transmission channel based on the feedback information, and receive the status information processed by the temporary communication key based on the exclusive data transmission channel.

[0047] In one embodiment, the step of generating a temporary communication key pair according to the inspection instruction and the communication code includes:

[0048] Determine the inspection task according to the inspection instruction, and generate verification information according to the inspection task;

[0049] Interpolate the verification information and the communication code by frame to obtain a temporary communication code;

[0050] Obtain the timestamp information of the inspection instruction, and generate expiration timestamp information based on the timestamp information;

[0051] Combine the expiration timestamp information and the temporary communication code to obtain a temporary encryption handle;

[0052] Perform an inverse operation on the temporary encryption handle to obtain a temporary decryption handle;

[0053] Generate a temporary communication key pair according to the temporary encryption handle and the temporary decryption handle.

[0054] In addition, to achieve the above object, the present application also proposes an inspection parameter optimization device based on cloud-edge collaboration. The inspection parameter optimization device based on cloud-edge collaboration includes:

[0055] An instruction exchange module, configured to receive an inspection instruction sent by the cloud, determine an inspection target according to the inspection instruction, and determine a target terminal device according to the inspection target;

[0056] A channel establishment module, configured to obtain the communication code of the target terminal device, establish an exclusive data transmission channel according to the communication code, and receive the status information uploaded by the target terminal device from the exclusive data transmission channel;

[0057] A status determination module, configured to determine the operating status of the target terminal device according to the status information, and determine the abnormal amplitude of the operating status when the operating status is an abnormal status;

[0058] A parameter optimization module, configured to generate optimization parameters by passing the abnormal amplitude through a parameter optimization model, and optimize the operating parameters of the target terminal based on the optimization parameters.

[0059] In addition, to achieve the above object, the present application also proposes an inspection parameter optimization device based on cloud-edge collaboration, where the inspection parameter optimization device based on cloud-edge collaboration includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the above-mentioned inspection parameter optimization method based on cloud-edge collaboration.

[0060] In addition, to achieve the above object, the present invention also proposes a storage medium, the storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, it implements the steps of the above-mentioned inspection parameter optimization method based on cloud-edge collaboration.

[0061] In addition, to achieve the above object, the present application also provides a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, it implements the steps of the above-mentioned inspection parameter optimization method based on cloud-edge collaboration.

[0062] The present application provides an inspection parameter optimization method based on cloud-edge collaboration. By receiving an inspection instruction sent by the cloud, determining an inspection target according to the inspection instruction, determining a target terminal device according to the inspection target, obtaining a communication code of the target terminal device, establishing a dedicated data transmission channel according to the communication code, receiving status information uploaded by the target terminal device from the dedicated data transmission channel, determining the operating status of the target terminal device according to the status information, determining the abnormal amplitude of the operating status when the operating status is an abnormal status, generating optimization parameters by passing the abnormal amplitude through a parameter optimization model, and optimizing the operating parameters of the target terminal based on the optimization parameters. By the above method, it is possible to remotely inspect multiple terminal devices at different locations and optimize the parameters of each terminal device. Description of the Drawings

[0063] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0064] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0065] Figure 1 It is a schematic flowchart of the first embodiment of the patrol inspection parameter optimization method based on cloud-edge collaboration of the present application;

[0066] Figure 2 It is a schematic diagram of cloud-edge collaboration of the power system in an embodiment of the patrol inspection parameter optimization method based on cloud-edge collaboration of the present application;

[0067] Figure 3 It is a schematic flowchart of parameter optimization in an embodiment of the patrol inspection parameter optimization method based on cloud-edge collaboration of the present application;

[0068] Figure 4 It is a schematic diagram of reinforcement learning in an embodiment of the patrol inspection parameter optimization method based on cloud-edge collaboration of the present application;

[0069] Figure 5 It is a schematic diagram of the module structure of the patrol inspection parameter optimization device based on cloud-edge collaboration in the embodiment of the present application;

[0070] Figure 6 It is a schematic diagram of the device structure of the hardware operating environment involved in the patrol inspection parameter optimization method based on cloud-edge collaboration in the embodiment of the present application.

[0071] The realization of the purpose of the present application, functional features and advantages will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0072] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0073] To better understand the technical solutions of the present application, the following will be described in detail in combination with the accompanying drawings of the specification and the specific implementation manners.

[0074] The main solution of the embodiment of this application is as follows: Receive the inspection instruction sent by the cloud, determine the inspection target according to the inspection instruction, and determine the target terminal device according to the inspection target; Obtain the communication code of the target terminal device, establish a dedicated data transmission channel according to the communication code, and receive the status information uploaded by the target terminal device from the dedicated data transmission channel; Determine the operating state of the target terminal device according to the status information, and when the operating state is an abnormal state, determine the abnormal amplitude of the operating state; Generate optimization parameters by passing the abnormal amplitude through a parameter optimization model, and optimize the operating parameters of the target terminal based on the optimization parameters.

[0075] Currently, the traditional manual inspection method is difficult to meet the requirements of real-time performance and accuracy. Therefore, a more efficient intelligent inspection method is needed. The commonly used method at present is to use drones to inspect power distribution network equipment visually. This method can detect individual power distribution network equipment, but it cannot detect multiple power distribution network equipment simultaneously, cannot conduct unified inspection on power distribution network equipment, and is not conducive to the overall management of power distribution network equipment.

[0076] This application provides a solution. By receiving the inspection instruction sent by the cloud, determining the inspection target according to the inspection instruction, determining the target terminal device according to the inspection target, obtaining the communication code of the target terminal device, establishing a dedicated data transmission channel according to the communication code, receiving the status information uploaded by the target terminal device from the dedicated data transmission channel, determining the operating state of the target terminal device according to the status information, when the operating state is an abnormal state, determining the abnormal amplitude of the operating state, generating optimization parameters by passing the abnormal amplitude through a parameter optimization model, and optimizing the operating parameters of the target terminal based on the optimization parameters. Through the above method, it is possible to remotely inspect multiple terminal devices at different locations and optimize the parameters of each terminal device.

[0077] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device that can implement the above functions, an inspection parameter optimization device based on cloud-edge collaboration, etc. This embodiment does not make specific limitations in this regard. Hereinafter, an inspection parameter optimization device based on cloud-edge collaboration will be used as an example to illustrate this embodiment and the following embodiments.

[0078] The embodiment of this application provides a method for optimizing inspection parameters based on cloud-edge collaboration. Refer to Figure 1 , Figure 1 which is a schematic flowchart of the first embodiment of the method for optimizing inspection parameters based on cloud-edge collaboration of this application.

[0079] In this embodiment, the inspection parameter optimization method based on cloud-edge collaboration includes steps S10 to S40:

[0080] Step S10, receive the inspection instruction sent by the cloud, determine the inspection target according to the inspection instruction, and determine the target terminal device according to the inspection target.

[0081] It should be noted that in the power system, in order to facilitate centralized inspection and maintenance of terminal devices in each power system, the cloud-edge collaboration method can be used for overall management. Among them, the cloud can establish a control connection relationship with multiple edge devices. Refer to Figure 2 , Figure 2 which is a schematic diagram of cloud-edge collaboration in the power system. Each edge device can be inspected and regulated, and at the same time, each edge device can also inspect and regulate multiple terminal devices, thereby realizing remote inspection of various terminal devices scattered in different regions by the cloud.

[0082] In addition, it should be noted that the inspection instruction can be issued by the cloud and the edge device. Among them, for the inspection instruction issued by the cloud, the receiving party is the edge device. For the inspection instruction issued by the edge device, the receiving party is the terminal device. The target terminal device is the terminal device that needs to perform the inspection task, and the target terminal device can feedback its working parameters according to the inspection instruction.

[0083] It can be understood that when the cloud sends an inspection instruction, the cloud can generate an inspection instruction according to the terminal devices that need to be inspected this time. Since the inspection instruction of the cloud is sent to the edge device and forwarded to the target terminal device by the edge device, it is necessary to obtain the list of target terminal devices connected to each edge device, and use the target terminal device whose inspection parameters need to be optimized this time as the retrieval key value to determine the corresponding edge device. Then, taking the inspection task of the target terminal device as the data packet, generate an inspection instruction sent to the edge device. After the edge device receives the inspection instruction sent by the cloud, it can split the inspection instruction, separate the inspection task of the target terminal device, generate an inspection instruction from the inspection task, and then send it to the target terminal device.

[0084] In a feasible implementation manner, the steps of receiving the inspection instruction sent by the cloud, determining the inspection target according to the inspection instruction, and determining the target terminal device according to the inspection target include:

[0085] Receive the inspection instruction sent by the cloud, unpack the inspection instruction to obtain an instruction frame;

[0086] Traverse the instruction frame to determine the key frame of the instruction frame;

[0087] Taking the key frame as a segmentation point, extract the inspection task of the instruction frame at the segmentation point;

[0088] Identify the inspection task to obtain a device code, and determine the target terminal device according to the device code.

[0089] In a specific implementation, after the edge device receives the inspection instruction sent by the cloud, it can unpack the inspection instruction to obtain an instruction frame. The instruction frame includes the device type of the device to be inspected, the inspection time period, and other special requirements. After obtaining the instruction frame, it can traverse the instruction frame. Since the start and end of each task instruction have identification marks, when traversing the instruction frame, when the start mark and the end mark are detected, the data frames corresponding to the start mark and the end mark can be determined as key frames. The key frames correspond to the task instruction information in the inspection task, and can take the key frames as segmentation points to divide the instruction frame into multiple data frames, and can determine the inspection task of the instruction frame according to the key frame type of each data frame. At the same time, the inspection task can include the target device for executing the current inspection task, and the device code of the target terminal device can be obtained in a table-lookup manner, and the target terminal device can be determined according to the device code.

[0090] Step S20: Obtain the communication code of the target terminal device, establish a dedicated data transmission channel according to the communication code, and receive the status information uploaded by the target terminal device from the dedicated data transmission channel.

[0091] It should be noted that the communication code of the target device is similar to the MAC address of the target device and has device uniqueness. When the target device is added to the power system, it can be determined according to the subordination code of the currently connected edge device. The communication code of the device can be represented by binary numbers, and the specific byte length is set by the devices allowed to access the power system. The dedicated data channel is a dedicated channel for inspection data. When an inspection task needs to be executed, it is established by the edge device and the target terminal device as the two ends of the data channel. The edge device and the target terminal device are each other's data senders and data receivers. The status information includes other information such as the current information, voltage information, temperature information, and power information of the target terminal device.

[0092] In a specific implementation, the communication code of the target terminal device is determined according to the current access status of the edge-side device when the target terminal device accesses the current power system. For example, the communication code of the current edge-side device is 5C, and its corresponding binary code is 01011100. If the current edge-side device has already accessed 123 terminal devices, and after the current device joins, it will become the 124th accessed terminal device, then its corresponding binary code is 01111100, and its communication code can be expressed as 0101110001111100. Then, a dedicated data transmission channel can be established with the target communication terminal using this communication code to receive the status information uploaded by the target terminal device from the dedicated data transmission channel.

[0093] In a feasible implementation manner, the steps of obtaining the communication code of the target terminal device, establishing a dedicated data transmission channel according to the communication code, and receiving the status information uploaded by the target terminal device from the dedicated data transmission channel include:

[0094] Obtain the device information of the target terminal device and read the communication code of the device information;

[0095] Generate a temporary communication key pair according to the inspection instruction and the communication code;

[0096] Send the temporary communication key pair to the target terminal device and receive the feedback information of the target terminal device after receiving the temporary communication key pair;

[0097] Establish a dedicated data transmission channel based on the feedback information, and receive the status information processed by the temporary communication key based on the dedicated data transmission channel.

[0098] In a specific implementation, when determining the target inspection instruction based on the inspection instruction and determining the target terminal device according to the target inspection instruction, the device information corresponding to the communication code can be read according to the device information of the target terminal device, and then a temporary communication key pair is generated according to the communication code and the inspection instruction. The temporary communication key pair includes a public key and a private key. After generating the temporary communication key pair, the temporary communication key pair can be sent to the target terminal device. After receiving the public key, the target device will use it to encrypt the status information to be sent. The edge device detects the data transmission in the dedicated data transmission channel in real time. When receiving the data transmission, it can receive the feedback information of the target terminal device after receiving the temporary communication key pair. After receiving the feedback information of the target terminal device and confirming that both parties can correctly use the temporary communication key pair for encryption and decryption operations, a dedicated data transmission channel can be formally established. This channel ensures that all subsequent data exchanges are encrypted, thus protecting the confidentiality and integrity of the data. After the dedicated data transmission channel is established, the target terminal device will start to regularly send its operating status information (such as voltage, current, temperature, etc.). These information will be encrypted using the previously agreed public key before being sent, and the edge device decrypts the received information using the corresponding private key to obtain the original device status data.

[0099] In a feasible implementation manner, the step of generating a temporary communication key pair according to the inspection instruction and the communication code includes:

[0100] Determine the inspection task according to the inspection instruction, and generate verification information according to the inspection task;

[0101] Interpolate the verification information and the communication code by frame to obtain a temporary communication code;

[0102] Obtain the timestamp information of the inspection instruction, and generate an expiration timestamp information based on the timestamp information;

[0103] Combine the expiration timestamp information and the temporary communication code to obtain a temporary encryption handle;

[0104] Perform an inverse operation on the temporary encryption handle to obtain a temporary decryption handle;

[0105] Generate a temporary communication key pair according to the temporary encryption handle and the temporary decryption handle.

[0106] In a specific implementation, based on the received inspection instruction, specific inspection task details are clarified, including specific parameters to be measured (such as the voltage fluctuation range). Based on these task details, a verification information is generated to ensure the identity and data integrity of both communication parties in subsequent steps. The verification information can be a hash value or a check code generated based on the content of the inspection task. Then, the generated verification information is combined with the communication code of the target device. In this embodiment, the method of frame interpolation is adopted to insert relevant information of the communication code between the data frames of the verification information, or vice versa, so as to generate a new combination - a temporary communication code. This process adds an extra security layer, enabling only devices with the correct communication code to parse the original verification information. The timestamp information in the inspection instruction is obtained, that is, the time when the instruction is issued, and then a expiration timestamp is generated based on this timestamp. The expiration timestamp defines the validity period of this communication. For example, if the set validity period is 2 hours, the expiration timestamp is the current time plus 2 hours. This is done to limit the usage period of the temporary key pair and increase security. The generated expiration timestamp information is combined with the temporary communication code to form a temporary encryption handle (TEH). As a part of the encryption process, the handle contains information about when to stop accepting communications identified by this handle, further enhancing the security measures. For decryption, the inverse operation can be performed on the obtained temporary encryption handle to generate a temporary decryption handle (TDH) for decrypting the data encrypted by the TEH. Finally, using the temporary encryption handle (TEH) and the temporary decryption handle (TDH), a temporary communication key pair is generated. This pair of keys will be used for all encrypted communications during this inspection task. The public key part (usually the TEH) will be sent to the target terminal device, while the private key part (TDH) is retained on the edge device and in the cloud for decrypting the data received from the target device.

[0107] Step S30, determine the operating state of the target terminal device according to the status information, and when the operating state is an abnormal state, determine the abnormal amplitude of the operating state.

[0108] It should be noted that the operating state refers to the index data corresponding to various working parameters of the target terminal device during operation. Each index data has a corresponding threshold value. When the threshold value is exceeded, it can be determined as an abnormal state, and the difference between the abnormal state and the threshold time is the abnormal amplitude.

[0109] In a specific implementation, operating parameters of the target terminal device are obtained according to the status information, such as current value, voltage value, temperature value, etc. Each operating parameter has its corresponding threshold value, and each operating parameter is respectively compared with its corresponding threshold value. If any one of the operating parameters is not within its threshold value, it can be determined that the current target terminal device is in an abnormal state. Next, it is necessary to calculate the specific abnormal amplitude to evaluate the severity of the problem. Taking the current value as an example, the abnormal amplitude corresponding to the current is , where , where is the maximum current value, is the standard current value of the threshold. Similarly, the calculation methods of the voltage abnormal amplitude and the temperature abnormal amplitude are similar to the calculation method of the current abnormal amplitude.

[0110] In a feasible implementation manner, the steps of determining the operating state of the target terminal device according to the status information and determining the abnormal amplitude of the operating state when the operating state is an abnormal state include:

[0111] Split the status information to obtain the performance parameters of each operating dimension in the target terminal device;

[0112] Respectively determine the standard performance parameters of the operating dimension;

[0113] Determine the performance difference of the operating dimension according to the performance parameter and the standard performance parameter;

[0114] Construct a parameter matrix with the operating dimension and initialize the parameter matrix, and write the performance difference into the parameter matrix;

[0115] Determine the follow-up relationship of each element in the parameter matrix, and determine the operating state of the target terminal device based on the state follow-up function corresponding to the follow-up relationship;

[0116] When the operating state is an abnormal state, map the performance difference to the parameter matrix to obtain an abnormal amplitude matrix;

[0117] Determine the abnormal amplitude according to the eigenvalue of the abnormal amplitude matrix.

[0118] In a specific implementation, first, we need to split the status information received from the target terminal device into performance parameters of different operating dimensions. Assuming that we focus on three dimensions of current, voltage, and temperature, the status information can be split into , , which are the actually measured current value, voltage value, and temperature value respectively. Next, it is necessary to determine the standard performance parameters for each operating dimension. These parameters are usually based on the design specifications of the device or historical normal operation data , , , which are the rated current, the rated operating voltage, and the maximum safe operating temperature respectively. Calculate the performance difference of each operating dimension based on the performance parameters and the standard performance parameters. The calculation formula is:

[0119]

[0120]

[0121]

[0122] Then create a parameter matrix , which contains all operating dimensions and their performance differences. Assuming the matrix size is , for the three dimensions in this example, we can construct a .

[0123]

[0124] The follow-up relationship refers to the degree of mutual influence between different performance parameters. For example, too high temperature may cause an increase in current or voltage instability. This relationship can be determined by analyzing the historical data of each parameter or using expert knowledge. Evaluate the overall operating state based on the follow-up relationship. If any one or more performance differences exceed the preset threshold, the device is considered to be in an abnormal state. When it is determined that the device is in an abnormal state, map the performance differences to the parameter matrix to form an abnormal amplitude matrix .

[0125]

[0126] Taking the absolute value here is to uniformly represent the degree of abnormality regardless of the deviation direction.

[0127] Finally, determine the specific abnormal amplitude according to the abnormal amplitude matrix A. This can be completed through mathematical operations, such as finding the maximum value, average value or other statistical quantities of the matrix elements to quantify the degree of abnormality. For example, the maximum abnormal amplitude can be expressed as:

[0128]

[0129] Or calculate the weighted average of the abnormal amplitudes, and the weights can be set according to the influence degree of each dimension on the device operation:

[0130]

[0131] Among them, are the weight coefficients of current, voltage and temperature respectively.

[0132] Step S40: Generate optimized parameters from the abnormal amplitude through a parameter optimization model, and optimize the operating parameters of the target terminal based on the optimized parameters.

[0133] It should be noted that the parameter optimization model is a deep learning reinforcement model, which can continuously adjust the optimization weight of parameter optimization according to the parameter optimization records of the target terminal device, so as to reduce the number of parameter optimization times.

[0134] In a specific implementation, in a power system, especially for key devices such as transformers, using a deep learning reinforcement model to optimize operating parameters is an advanced and effective method. In this way, not only can the abnormal state and its amplitude of the device be identified, but also optimized parameters can be generated to adjust the operating conditions of the device, thereby improving efficiency, extending the device life and reducing the failure risk. First, after determining the abnormal amplitude, it can be used as input and passed to a pre-trained deep learning reinforcement model. This model has been trained with a large amount of historical data, including data under normal operating conditions and data of various abnormal situations. The deep learning reinforcement model usually consists of two parts: a policy network and a value network. The policy network is used to decide which action to take (such as adjusting the current, voltage or temperature settings), and the value network evaluates the goodness or badness of taking a specific action in the current state. For applications in the power system, the model can be trained to minimize energy loss, maximize device reliability or balance the relationship between the two. Among them, the input layer can receive the abnormal amplitude obtained from the target terminal device; the hidden layer processes the input data through multiple layers of neural networks, extracts features and makes decisions; the output layer generates suggestions for optimized operating parameters, such as new set points or adjustment coefficients.

[0135] Based on the output of the model, a set of optimized parameters is generated. These parameters are designed to correct the detected abnormal state and optimize the overall performance of the device. For example, if the abnormal amplitude shows that the current is too high, the model may suggest reducing the load or adjusting the power of the cooling system; if the voltage is unstable, it may propose to reconfigure the voltage regulator. Applying the generated optimized parameters to the actual control system of the target terminal device, the automatic control system can directly adjust the working state of the device according to the model suggestions, or provide them to the operator as a reference for manual adjustment.

[0136] In a feasible implementation manner, the step of generating optimized parameters from the abnormal amplitude through a parameter optimization model and optimizing the operating parameters of the target terminal based on the optimized parameters includes:

[0137] Group the abnormal amplitude, determine the group of the abnormal amplitude, and determine the input layer of the parameter optimization model according to the group;

[0138] Input the abnormal amplitude into the hidden layer through the input layer, and determine the unit weights of each neuron in the hidden layer;

[0139] Determine the initial optimization parameters according to the abnormal amplitude, and weight the initial optimization parameters based on the unit weights to obtain the optimization parameters;

[0140] Optimize the operating parameters of the target terminal based on the optimization parameters.

[0141] Among them, the steps of determining the initial optimization parameters according to the abnormal amplitude, weighting the initial optimization parameters based on the unit weights, and obtaining the optimization parameters include:

[0142] Obtain the abnormal amplitude parameter optimization table, and traverse the abnormal amplitude parameter optimization table based on the abnormal amplitude to determine the corresponding initial optimization parameters;

[0143] Determine the optimization intensity according to the abnormal amplitude, update the unit weights according to the optimization intensity and the hidden layer dimension to obtain the optimized weights;

[0144] Weight the initial optimization parameters with the optimized weights to obtain the optimization parameters.

[0145] In a specific implementation, classify the abnormal amplitude according to its nature or influence degree. The abnormal amplitudes of current, voltage, and temperature can be classified into different groups respectively, or grouped according to the degree of deviation from the standard value (such as slight, medium, severe). In this embodiment, the abnormal amplitudes of current, voltage, and temperature are grouped. Then the abnormal amplitude of each group will be used as part of the input layer to ensure that the model can receive all relevant abnormal information. The input layer may include three input nodes . Then the input can be expressed as . Each neuron in the hidden layer has an associated weight vector, and these weights determine how the input data is processed and passed to the next layer. During training, these weights are continuously adjusted to minimize the model prediction error. Specifically, for a given abnormal amplitude input , the output of the j-th neuron in the hidden layer can be expressed as:

[0146]

[0147] Among them, is the weight connecting input i and the j-th neuron in the hidden layer, is the bias term, is the ReLU non-linear activation function.

[0148] Based on the abnormal amplitude and the current device state, a set of optimization parameters is preliminarily determined. This set of parameters may be default settings based on rules or successful solutions in previous similar situations. Then, the initial optimization parameters are weighted using the unit weights of each neuron in the hidden layer to obtain the final optimization parameters. For example, if the initial optimization parameters are , then the weighted optimization parameter P can be calculated as follows:

[0149]

[0150] where is a matrix composed of the unit weights of the hidden layer, which reflects the influence of different abnormal dimensions on the optimization decision.

[0151] Finally, the obtained optimization parameter P is used to adjust the actual operation parameters of the target terminal device. For example, if the optimization parameter indicates that the operating temperature of the transformer needs to be reduced, the power of the corresponding cooling system will be increased; if it is recommended to adjust the voltage, the set point of the voltage controller will be adjusted accordingly.

[0152] The steps of determining the initial optimization parameters according to the abnormal amplitude, weighting the initial optimization parameters based on the unit weights, and obtaining the optimization parameters include:

[0153] Obtain an abnormal amplitude parameter optimization table, and traverse the abnormal amplitude parameter optimization table based on the abnormal amplitude to determine the corresponding initial optimization parameters;

[0154] Determine the optimization intensity according to the abnormal amplitude, update the unit weights according to the optimization intensity and the hidden layer dimension to obtain the optimization weights;

[0155] Weight the initial optimization parameters with the optimization weights to obtain the optimization parameters.

[0156] In a feasible implementation manner, after the step of optimizing the operating parameters of the target terminal based on the optimization parameters, it further includes:

[0157] Determine the optimized operating state of the target terminal after the optimization of the operating parameters;

[0158] Determine the state gain according to the optimized operating state and the operating state, and determine the optimized abnormal amplitude according to the optimized operating state and the standard operating state;

[0159] When the optimized abnormal amplitude is the preset abnormal optimization amplitude, determine the type of the state gain;

[0160] When the state gain type is positive gain, determine the optimization parameter as the reinforcement factor, and determine the reinforcement discount factor according to the optimization anomaly amplitude, and determine the next optimization intensity with the reinforcement factor and the reinforcement discount factor;

[0161] Update the optimization parameter according to the next optimization intensity until the operating parameter of the target terminal is within the preset standard threshold;

[0162] When the state gain type is negative gain, invert the optimization parameter, and determine the inverted optimization parameter as the reinforcement factor;

[0163] Determine the reinforcement discount factor according to the optimization anomaly amplitude and the anomaly amplitude;

[0164] Determine the comprehensive reinforcement factor obtained from the reinforcement factor and the reinforcement discount factor as the next optimization intensity.

[0165] In specific implementation, refer to Figure 3 , Figure 3 is a schematic diagram of the parameter optimization process. Based on the optimized operating parameters (such as adjusted current, voltage, temperature settings), determine the optimized operating state of the device. This step includes collecting the performance parameters in the new state and comparing them with the previous abnormal state. Next, calculate the state gain before and after optimization. The state gain can be determined by comparing the performance differences before and after optimization. Assume the original performance difference is , and the optimized performance difference is , then the state gain can be expressed as:

[0166]

[0167] If , it indicates that the optimization has brought improvement (positive gain); otherwise, it may be that the optimization did not meet expectations or even caused deterioration (negative gain). At the same time, it is also necessary to compare the optimized operating state with the standard operating state to determine the optimized anomaly amplitude , , where is the actually measured value after optimization, is the standard performance parameter.

[0168] When the state gain is positive, it means that the optimization measure is effective. At this time, regard the currently used optimization parameter as the reinforcement factor RF, and determine the reinforcement discount factor DF according to the optimization anomaly amplitude. The reinforcement discount factor is used to adjust the intensity of the next optimization to avoid over-adjustment. The simplified formula can be expressed as:

[0169]

[0170] Therefore, the next optimization intensity OI is defined as:

[0171]

[0172] If the state gain is negative, it indicates that the optimization direction may be incorrect. In this case, the optimization parameters need to be inverted as the new reinforcement factor, and the reinforcement discount factor is also determined based on the optimization anomaly amplitude. For example, if the original optimization parameter is OP, the new reinforcement factor RF′ is:

[0173]

[0174] Then, the reinforcement discount factor DF and the next optimization intensity OI are calculated using the same formula.

[0175] Refer to Figure 4 , Figure 4 which is a schematic diagram of reinforcement learning. Whether it is a positive or negative gain situation, the optimization parameters need to be updated according to the calculated next optimization intensity OI, and the above process is repeated until all key performance indicators fall within the preset standard thresholds. This process is usually achieved through iteration, and each iteration will re-evaluate the state gain and optimization anomaly amplitude based on the latest operation data, thereby dynamically adjusting the optimization strategy.

[0176] This embodiment provides a patrol inspection parameter optimization method based on cloud-edge collaboration. By receiving the patrol inspection instruction sent by the cloud, determining the patrol inspection target according to the patrol inspection instruction, determining the target terminal device according to the patrol inspection target, obtaining the communication code of the target terminal device, establishing a dedicated data transmission channel according to the communication code, receiving the status information uploaded by the target terminal device from the dedicated data transmission channel, determining the operation status of the target terminal device according to the status information, determining the anomaly amplitude of the operation status when the operation status is an abnormal state, generating optimization parameters by the parameter optimization model with the anomaly amplitude, and optimizing the operation parameters of the target terminal based on the optimization parameters. Through the above method, it is possible to remotely patrol multiple terminal devices at different locations and optimize the parameters of each terminal device.

[0177] It should be noted that the above examples are only for understanding this application and do not constitute a limitation to the patrol inspection parameter optimization method based on cloud-edge collaboration of this application. Any simple transformation in more forms based on this technical concept is within the protection scope of this application.

[0178] This application also provides a patrol inspection parameter optimization device based on cloud-edge collaboration. Please refer to Figure 5 , the patrol inspection parameter optimization device based on cloud-edge collaboration includes:

[0179] The instruction exchange module 10 is configured to receive the inspection instruction sent by the cloud, determine the inspection target according to the inspection instruction, and determine the target terminal device according to the inspection target;

[0180] The channel establishment module 20 is configured to obtain the communication code of the target terminal device, establish a dedicated data transmission channel according to the communication code, and receive the status information uploaded by the target terminal device from the dedicated data transmission channel;

[0181] The status determination module 30 is configured to determine the operating status of the target terminal device according to the status information, and determine the abnormal amplitude of the operating status when the operating status is an abnormal status;

[0182] The parameter optimization module 40 is configured to generate optimization parameters by passing the abnormal amplitude through a parameter optimization model, and optimize the operating parameters of the target terminal based on the optimization parameters.

[0183] In a feasible implementation manner, the parameter optimization module 40 is further configured to group the abnormal amplitudes, determine the group of the abnormal amplitudes, and determine the input layer of the parameter optimization model according to the group; input the abnormal amplitudes into the hidden layer through the input layer, and determine the unit weights of the neurons in the hidden layer; determine the initial optimization parameters according to the abnormal amplitudes, weight the initial optimization parameters based on the unit weights to obtain optimization parameters; and optimize the operating parameters of the target terminal based on the optimization parameters.

[0184] In a feasible implementation manner, the parameter optimization module 40 is further configured to obtain an abnormal amplitude parameter optimization table, traverse the abnormal amplitude parameter optimization table based on the abnormal amplitude to determine the corresponding initial optimization parameters; determine the optimization intensity according to the abnormal amplitude, update the unit weights according to the optimization intensity and the hidden layer dimension to obtain optimized weights; and weight the initial optimization parameters with the optimized weights to obtain optimization parameters.

[0185] In a feasible implementation manner, the parameter optimization module 40 is further configured to determine the optimized operating status of the target terminal after the operating parameter optimization; determine the status gain according to the optimized operating status and the operating status, and determine the optimized abnormal amplitude according to the optimized operating status and the standard operating status; when the optimized abnormal amplitude is a preset abnormal optimization amplitude, determine the status gain type; when the status gain type is a positive gain, determine the optimization parameter as a strengthening factor, and determine a strengthening discount factor according to the optimized abnormal amplitude, and determine the next optimization intensity with the strengthening factor and the strengthening discount factor; and update the optimization parameter according to the next optimization intensity until the operating parameters of the target terminal are within a preset standard threshold.

[0186] In a feasible implementation manner, the parameter optimization module 40 is further configured to, when the state gain type is a negative gain, invert the optimization parameter, and determine the inverted optimization parameter as the reinforcement factor; determine the reinforcement discount factor according to the optimization anomaly amplitude and the anomaly amplitude; and determine the next optimization intensity with the comprehensive reinforcement factor obtained by the reinforcement factor and the reinforcement discount factor.

[0187] In a feasible implementation manner, the state determination module 30 is further configured to split the state information to obtain the performance parameters of each operation dimension in the target terminal device; respectively determine the standard performance parameters of the operation dimension; determine the performance difference of the operation dimension according to the performance parameter and the standard performance parameter; construct a parameter matrix with the operation dimension and initialize the parameter matrix, and write the performance difference into the parameter matrix; determine the follow-up relationship of each element in the parameter matrix, and determine the operation state of the target terminal device based on the state follow-up function corresponding to the follow-up relationship; when the operation state is an abnormal state, map the performance difference to the parameter matrix to obtain an anomaly amplitude matrix; and determine the anomaly amplitude according to the eigenvalue of the anomaly amplitude matrix.

[0188] In a feasible implementation manner, the instruction exchange module 10 is further configured to receive an inspection instruction sent by the cloud, unpack the inspection instruction to obtain an instruction frame; traverse the instruction frame to determine the key frame of the instruction frame; use the key frame as a split point, and extract the inspection task of the instruction frame at the split point; identify the inspection task to obtain a device code, and determine the target terminal device according to the device code.

[0189] In a feasible implementation manner, the channel establishment module 20 is further configured to obtain the device information of the target terminal device and read the communication code of the device information; generate a temporary communication key pair according to the inspection instruction and the communication code; send the temporary communication key pair to the target terminal device, and receive the feedback information of the target terminal device after receiving the temporary communication key pair; establish a dedicated data transmission channel based on the feedback information, and receive the state information processed by the temporary communication key based on the dedicated data transmission channel.

[0190] In a feasible implementation manner, the channel establishment module 20 is further configured to determine an inspection task according to the inspection instruction, generate verification information according to the inspection task; interpolate the verification information and the communication code by frame to obtain a temporary communication code; obtain the timestamp information of the inspection instruction, and generate expiration timestamp information based on the timestamp information; combine the expiration timestamp information with the temporary communication code to obtain a temporary encryption handle; perform an inverse operation on the temporary encryption handle to obtain a temporary decryption handle; and generate a temporary communication key pair according to the temporary encryption handle and the temporary decryption handle.

[0191] The inspection parameter optimization device based on cloud-edge collaboration provided by this application adopts the inspection parameter optimization method based on cloud-edge collaboration in the above embodiment, and can solve the technical problem that multiple power distribution devices cannot be inspected in an overall manner and parameter optimization cannot be performed. Compared with the prior art, the beneficial effects of the inspection parameter optimization device based on cloud-edge collaboration provided by this application are the same as those of the inspection parameter optimization method based on cloud-edge collaboration provided by the above embodiment, and other technical features in the inspection parameter optimization device based on cloud-edge collaboration are the same as the features disclosed in the method of the above embodiment, and will not be elaborated here.

[0192] This application provides an inspection parameter optimization device based on cloud-edge collaboration. The inspection parameter optimization device based on cloud-edge collaboration includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the inspection parameter optimization method based on cloud-edge collaboration in the first embodiment above.

[0193] Next, refer to Figure 6 , which shows a schematic structural diagram of an inspection parameter optimization device based on cloud-edge collaboration suitable for implementing the embodiments of this application. The inspection parameter optimization device based on cloud-edge collaboration in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The inspection parameter optimization device based on cloud-edge collaboration shown is only an example, and should not impose any limitations on the functions and usage scopes of the embodiments of this application.

[0194] As Figure 6As shown in the figure, the inspection parameter optimization device based on cloud-edge collaboration may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the inspection parameter optimization device based on cloud-edge collaboration are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the inspection parameter optimization device based on cloud-edge collaboration to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows an inspection parameter optimization device based on cloud-edge collaboration with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or had alternatively.

[0195] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart may be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above functions defined in the method of the embodiments disclosed in the present application are executed.

[0196] The inspection parameter optimization device based on cloud-edge collaboration provided by the present application adopts the inspection parameter optimization method based on cloud-edge collaboration in the above embodiments, and can solve the technical problems of the inspection parameter optimization based on cloud-edge collaboration. Compared with the prior art, the beneficial effects of the inspection parameter optimization device based on cloud-edge collaboration provided by the present application are the same as those of the inspection parameter optimization method based on cloud-edge collaboration provided by the above embodiments, and other technical features in the inspection parameter optimization device based on cloud-edge collaboration are the same as the features disclosed in the method of the previous embodiment, and will not be elaborated here.

[0197] It should be understood that each part disclosed in this application can be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0198] The above are only specific embodiments of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0199] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the patrol parameter optimization method based on cloud-edge collaboration in the above embodiments.

[0200] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0201] The above computer-readable storage medium can be included in the patrol parameter optimization device based on cloud-edge collaboration; it can also exist separately without being assembled into the patrol parameter optimization device based on cloud-edge collaboration.

[0202] The above computer-readable storage medium carries one or more programs. When the one or more programs are executed by the inspection parameter optimization device based on cloud-edge collaboration, the inspection parameter optimization device based on cloud-edge collaboration is caused to: receive an inspection instruction sent by the cloud, determine an inspection target according to the inspection instruction, and determine a target terminal device according to the inspection target; obtain a communication code of the target terminal device, establish a dedicated data transmission channel according to the communication code, and receive status information uploaded by the target terminal device from the dedicated data transmission channel; determine an operating state of the target terminal device according to the status information, and when the operating state is an abnormal state, determine an abnormal amplitude of the operating state; generate an optimization parameter by using the abnormal amplitude through a parameter optimization model, and optimize an operating parameter of the target terminal based on the optimization parameter.

[0203] Computer program code for performing the operations of the present application may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0204] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in an order different from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0205] The modules involved in the embodiments of this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0206] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned patrol parameter optimization method based on cloud-edge collaboration, and can solve the technical problems of patrol parameter optimization based on cloud-edge collaboration. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the patrol parameter optimization method based on cloud-edge collaboration provided in the above embodiments, and will not be elaborated here.

[0207] This application also provides a computer program product, including a computer program, which when executed by a processor, implements the steps of the above-mentioned patrol parameter optimization method based on cloud-edge collaboration.

[0208] The computer program product provided in this application can solve the technical problems of patrol parameter optimization based on cloud-edge collaboration. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the patrol parameter optimization method based on cloud-edge collaboration provided in the above embodiments, and will not be elaborated here.

[0209] The above are only some embodiments of this application, and do not limit the patent scope of this application. Any equivalent structural transformation made by using the content of the specification and drawings of this application under the technical concept of this application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of this application.

Claims

1. A method for optimizing inspection parameters based on cloud-edge collaboration, characterized in that: The inspection parameter optimization method based on cloud-edge collaboration includes: Receive an inspection instruction sent by the cloud, determine an inspection target according to the inspection instruction, determine a target terminal device according to the inspection target, establish a control connection relationship between the cloud and multiple edge devices, each of the edge devices can inspect and control multiple terminal devices, and the multiple terminal devices are scattered in different areas; Acquire a communication code of the target terminal device, establish a dedicated data transmission channel according to the communication code, and receive status information uploaded by the target terminal device from the dedicated data transmission channel; Determining the operating state of the target terminal device according to the state information, and when the operating state is an abnormal state, determining the abnormal amplitude of the operating state; Grouping the abnormal amplitudes, determining the groups of the abnormal amplitudes, and determining the input layer of the parameter optimization model according to the groups; Inputting the abnormal amplitude into the hidden layer through the input layer, and determining the unit weight of each neuron in the hidden layer; Determine an initial optimization parameter according to the abnormal amplitude, and weight the initial optimization parameter based on the unit weight to obtain an optimization parameter; The operating parameters of the target terminal device are optimized based on the optimization parameters.

2. The method according to claim 1, characterized in that The step of determining the initial optimization parameters according to the abnormal amplitude and weighting the initial optimization parameters based on the unit weights to obtain the optimization parameters comprises: Obtain an abnormal amplitude parameter optimization table, and determine corresponding initial optimization parameters by traversing the abnormal amplitude parameter optimization table based on the abnormal amplitude; Determine an optimization strength according to the abnormal amplitude, and update the unit weight according to the optimization strength and the hidden layer dimension to obtain an optimization weight; The initial optimization parameters are weighted by the optimization weights to obtain optimization parameters.

3. The method according to claim 1, characterized in that After the step of optimizing the operating parameters of the target terminal based on the optimization parameters, the method further includes: Determining an optimized operating state of the target terminal after the operating parameter optimization; Determine a state gain according to the optimized operating state and the operating state, and determine an optimized abnormal amplitude according to the optimized operating state and the standard operating state; When the optimized abnormal amplitude is a preset abnormal optimized amplitude, determining the state gain type; When the state gain type is a forward gain, the optimization parameter is determined as a reinforcement factor, and a reinforcement discount factor is determined according to the optimization abnormal amplitude, and the reinforcement factor and the reinforcement discount factor are used to determine the next optimization intensity; The optimization parameters are updated according to the next optimization intensity until the operating parameters of the target terminal are within a preset standard threshold.

4. The method according to claim 3, characterized in that After the step of determining the state gain type when the optimized abnormal amplitude is a preset abnormal optimized amplitude, the method further includes: When the state gain type is a negative gain, the optimization parameter is negated, and the negated optimization parameter is determined as a reinforcement factor; determining a reinforcement discount factor according to the optimized abnormal amplitude and the abnormal amplitude; The comprehensive enhancement factor obtained by combining the enhancement factor and the enhancement discount factor is determined as the next optimization intensity.

5. The method according to claim 1, characterized in that The step of determining the operating state of the target terminal device according to the state information, and when the operating state is an abnormal state, determining the abnormal amplitude of the operating state comprises: Splitting the state information to obtain performance parameters of each operating dimension in the target terminal device; Determining standard performance parameters of the operating dimensions respectively; Determining a performance difference of the operating dimension according to the performance parameter and the standard performance parameter; constructing a parameter matrix based on the operating dimension, initializing the parameter matrix, and writing the performance difference into the parameter matrix; Determine a following relationship between elements in the parameter matrix, and determine the operating state of the target terminal device based on a state following function corresponding to the following relationship; When the operating state is an abnormal state, mapping the performance difference to the parameter matrix to obtain an abnormal amplitude matrix; The abnormal amplitude is determined according to the eigenvalue of the abnormal amplitude matrix.

6. The method according to claim 1, characterized in that The steps of receiving the inspection instruction sent by the cloud, determining the inspection target according to the inspection instruction, and determining the target terminal device according to the inspection target include: Receive the inspection command sent by the cloud, unpack the inspection command, and obtain the command frame; Traversing the instruction frame to determine a key frame of the instruction frame; Taking the key frame as a segmentation point, extracting the inspection task of the instruction frame at the segmentation point; The inspection task is identified to obtain a device code, and a target terminal device is determined according to the device code.

7. The method according to claim 1, characterized in that The steps of obtaining the communication code of the target terminal device, establishing a dedicated data transmission channel according to the communication code, and receiving the status information uploaded by the target terminal device from the dedicated data transmission channel include: Obtaining device information of the target terminal device and reading a communication code of the device information; Generate a temporary communication key pair according to the inspection instruction and the communication code; Sending the temporary communication key pair to the target terminal device, and receiving feedback information from the target terminal device after receiving the temporary communication key pair; An exclusive data transmission channel is established based on the feedback information, and status information processed with a temporary communication key is received based on the exclusive data transmission channel.

8. The method according to claim 7, characterized in that The step of generating a temporary communication key pair according to the inspection instruction and the communication code comprises: Determine an inspection task according to the inspection instruction, and generate verification information according to the inspection task; Interpolate the verification information and the communication code frame by frame to obtain a temporary communication code; Obtaining timestamp information of the inspection instruction, and generating failure timestamp information based on the timestamp information; Combining the expiration timestamp information with the temporary communication code to obtain a temporary encryption handle; Perform an inverse operation on the temporary encryption handle to obtain a temporary decryption handle; A temporary communication key pair is generated according to the temporary encryption handle and the temporary decryption handle.

9. A patrol parameter optimization device based on cloud-edge collaboration, characterized in that: The inspection parameter optimization device based on cloud-edge collaboration includes: An instruction exchange module is used to receive an inspection instruction sent by the cloud, determine an inspection target according to the inspection instruction, and determine a target terminal device according to the inspection target. A control connection relationship is established between the cloud and multiple edge devices, and each edge device can inspect and control multiple terminal devices, and multiple terminal devices are scattered in different areas; A channel establishment module, used to obtain a communication code of the target terminal device, establish a dedicated data transmission channel according to the communication code, and receive status information uploaded by the target terminal device from the dedicated data transmission channel; A state determination module, configured to determine the operating state of the target terminal device according to the state information, and when the operating state is an abnormal state, determine the abnormal amplitude of the operating state; A parameter optimization module, used for grouping the abnormal amplitudes, determining the groups of the abnormal amplitudes, and determining the input layer of the parameter optimization model according to the groups; Inputting the abnormal amplitude into the hidden layer through the input layer, and determining the unit weight of each neuron in the hidden layer; Determine an initial optimization parameter according to the abnormal amplitude, and weight the initial optimization parameter based on the unit weight to obtain an optimization parameter; The operating parameters of the target terminal are optimized based on the optimization parameters.

Images