Method, device, computer equipment, readable storage medium and program product for determining parameters of low-voltage insulating gloves

Abstract

The present application relates to a method, device, computer equipment, readable storage medium and program product for determining parameters of low-voltage insulating gloves. The method comprises: obtaining operating parameters according to operating behavior parameters and operating environment parameters of a target operating scene; inputting the operating parameters into a trained friction analysis model to obtain friction analysis results corresponding to each hand area in the target operating scene output by the friction analysis model; obtaining glove reinforcement area parameters corresponding to the target operating scene according to the friction analysis results of each hand area; collecting hand size data of each operator in the target operating scene, and obtaining glove size category parameters according to the data distribution of the hand size data; obtaining a target parameter set of low-voltage insulating gloves applied to the target operating scene according to the glove reinforcement area parameters and glove size category parameters. The present method can obtain parameters of low-voltage insulating gloves that are more targeted to the target operating scene.

Description

Technical Field

[0001] The present application relates to the field of information technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for determining parameters of a low-voltage insulating glove. Background Art

[0002] Low-voltage insulating gloves are usually used to prevent electric shock to workers' hands in low-voltage operation scenarios of power systems. Compared with medium and high voltage operation scenarios, low-voltage live operation usually has a narrower operating space, the tools used are usually smaller, and the operations required are more delicate. Therefore, low-voltage operations often face more complex working environments and have higher requirements for the adaptability of low-voltage insulating gloves to the working scenarios.

[0003] However, low-voltage insulating gloves are usually designed and manufactured according to uniform parameter specifications, which lack flexibility when facing different working scenarios, thus easily affecting the safety and efficiency of low-voltage operations. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for determining parameters of low-voltage insulating gloves in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for determining parameters of a low-voltage insulating glove, comprising:

[0006] According to the operation behavior parameters and the operation environment parameters of the target operation scene, the operation parameters of the target operation scene are obtained; wherein the operation behavior parameters include hand motion trajectory parameters and hand motion state parameters;

[0007] The operation parameters are input into a trained friction analysis model to obtain friction analysis results corresponding to each hand area in the target operation scene output by the friction analysis model; wherein the friction analysis model is trained using operation parameter samples corresponding to sample operation scenes; the operation parameter samples include operation behavior parameter samples, operation environment parameter samples and friction data samples corresponding to the sample operation scenes;

[0008] According to the friction analysis results of each of the hand regions, obtaining glove reinforcement region parameters corresponding to the target working scenario;

[0009] Collecting hand size data of each operator in the target working scene, and obtaining glove size category parameters corresponding to the target working scene according to data distribution of the hand size data;

[0010] According to the glove reinforcement area parameters and the glove size category parameters, a target parameter set of the low-voltage insulating gloves applied in the target working scenario is obtained.

[0011] In one embodiment, the trained friction analysis model is trained by the following steps: obtaining the operating parameter sample corresponding to the sample operating scene; inputting the operating behavior parameter sample and the operating environment parameter sample contained in the operating parameter sample into a neural network model based on a multi-layer perceptron to obtain the friction analysis result corresponding to the sample operating scene output by the neural network model; according to the difference between the friction analysis result corresponding to the sample operating scene and the friction data sample contained in the operating parameter sample, adjusting the model parameters of the neural network model using a gradient descent-based optimization algorithm to obtain the trained friction analysis model.

[0012] In one of the embodiments, before obtaining the operating parameters of the target operating scene based on the operating behavior parameters and operating environment parameters of the target operating scene, the method further includes: using an inertial sensor to obtain acceleration parameters and angular velocity parameters of multiple first hand sampling points in the operating process of the target operating scene, and obtaining the hand motion state parameters based on the acceleration parameters and the angular velocity parameters; using an optical tracking device to track the motion trajectories of multiple second hand sampling points in the operating process, and obtaining the hand motion trajectory parameters based on the motion trajectories; and obtaining the operating behavior parameters based on the hand motion state parameters and the hand motion trajectory parameters.

[0013] In one embodiment, the operating parameter samples used to train the friction analysis model also include surface structure parameter samples and wear data samples of each surface area of ​​the low-voltage insulating glove sample in the sample operating scene; the operating parameters of the target operating scene also include surface structure parameters of each surface area of ​​the low-voltage insulating glove in the target operating scene; the friction analysis results of each hand area output by the friction analysis model include friction analysis data and wear analysis data of the hand area; after obtaining the glove reinforcement area parameters corresponding to the target operating scene according to the friction analysis results of each hand area, it also includes: determining the glove reinforcement area parameters corresponding to the target operating scene according to the glove reinforcement area parameters the target reinforced area of ​​the low-voltage insulating gloves; when the friction analysis data and the wear analysis data corresponding to the target reinforced area do not meet the preset conditions, using the friction analysis model to iteratively optimize the surface structure parameters of the target reinforced area until the target surface structure parameters that make the friction analysis data and the wear analysis data of the target reinforced area meet the preset conditions are obtained, and then the iteration is stopped; the target parameter set of the low-voltage insulating gloves applied to the target operation scenario is obtained according to the glove reinforced area parameters and the glove size category parameters, including: obtaining the target parameter set according to the glove reinforced area parameters, the glove size category parameters and the target surface structure parameters of the target reinforced area.

[0014] In one embodiment, the surface structure parameters of the surface area include protrusion structure parameters of the surface area and / or sandblasting strengthening structure parameters.

[0015] In one of the embodiments, the counting of hand size data of each operator in the target operation scene and obtaining the size category parameters of the low-voltage insulating gloves according to the data distribution of the hand size data include: counting the dimensional data corresponding to each hand dimension of each operator in the target operation scene, and obtaining the hand size data according to the dimensional data corresponding to each hand dimension; wherein the hand dimensions include finger length, palm length, palm width and palm thickness; counting the average value and standard deviation of the dimensional data corresponding to each hand dimension respectively; determining the dimensional data interval corresponding to each hand dimension of each size category according to the average value and standard deviation of the dimensional data corresponding to each hand dimension; determining the target dimensional parameters corresponding to each hand dimension of each size category according to the data median of each dimensional data interval corresponding to each size category; and obtaining the size category parameters of the low-voltage insulating gloves according to each target dimensional parameters corresponding to each size category.

[0016] In a second aspect, the present application also provides a device for determining parameters of a low-voltage insulating glove, comprising:

[0017] An acquisition module, used to acquire operation behavior parameters and operation environment parameters of a target operation scene; wherein the operation behavior parameters include hand motion trajectory parameters and hand motion state parameters;

[0018] A friction analysis module, used for inputting the working behavior parameters and the working environment parameters into a trained friction analysis model, and obtaining the friction analysis results of each hand area in the target working scene output by the friction analysis model; wherein the friction analysis model is trained using working parameter samples corresponding to sample working scenes; the working parameter samples include working behavior parameter samples, working environment parameter samples and friction data samples corresponding to the sample working scenes;

[0019] A first parameter determination module, configured to obtain the glove reinforcement area parameters corresponding to the target working scene according to the friction analysis results of each of the hand areas;

[0020] A second parameter determination module is used to collect hand size data of each operator in the target working scene, and obtain glove size category parameters corresponding to the target working scene according to data distribution of the hand size data;

[0021] The parameter set determination module is used to obtain a target parameter set of the low-voltage insulating gloves applied in the target working scenario according to the glove reinforcement area parameters and the glove size category parameters.

[0022] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0023] According to the operation behavior parameters and the operation environment parameters of the target operation scene, the operation parameters of the target operation scene are obtained; wherein the operation behavior parameters include hand motion trajectory parameters and hand motion state parameters;

[0024] The operation parameters are input into a trained friction analysis model to obtain friction analysis results corresponding to each hand area in the target operation scene output by the friction analysis model; wherein the friction analysis model is trained using operation parameter samples corresponding to sample operation scenes; the operation parameter samples include operation behavior parameter samples corresponding to the sample operation scenes, the operation environment parameter samples, and friction data samples;

[0025] According to the friction analysis results of each of the hand regions, obtaining glove reinforcement region parameters corresponding to the target working scenario;

[0026] Collecting hand size data of each operator in the target working scene, and obtaining glove size category parameters corresponding to the target working scene according to data distribution of the hand size data;

[0027] According to the glove reinforcement area parameters and the glove size category parameters, a target parameter set of the low-voltage insulating gloves applied in the target working scenario is obtained.

[0028] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0029] According to the operation behavior parameters and the operation environment parameters of the target operation scene, the operation parameters of the target operation scene are obtained; wherein the operation behavior parameters include hand motion trajectory parameters and hand motion state parameters;

[0030] The operation parameters are input into a trained friction analysis model to obtain friction analysis results corresponding to each hand area in the target operation scene output by the friction analysis model; wherein the friction analysis model is trained using operation parameter samples corresponding to sample operation scenes; the operation parameter samples include operation behavior parameter samples, operation environment parameter samples and friction data samples corresponding to the sample operation scenes;

[0031] According to the friction analysis results of each of the hand regions, obtaining glove reinforcement region parameters corresponding to the target working scenario;

[0032] Collecting hand size data of each operator in the target working scene, and obtaining glove size category parameters corresponding to the target working scene according to data distribution of the hand size data;

[0033] According to the glove reinforcement area parameters and the glove size category parameters, a target parameter set of the low-voltage insulating gloves applied in the target working scenario is obtained.

[0034] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0035] According to the operation behavior parameters and the operation environment parameters of the target operation scene, the operation parameters of the target operation scene are obtained; wherein the operation behavior parameters include hand motion trajectory parameters and hand motion state parameters;

[0036] The operation parameters are input into a trained friction analysis model to obtain friction analysis results corresponding to each hand area in the target operation scene output by the friction analysis model; wherein the friction analysis model is trained using operation parameter samples corresponding to sample operation scenes; the operation parameter samples include operation behavior parameter samples, operation environment parameter samples and friction data samples corresponding to the sample operation scenes;

[0037] According to the friction analysis results of each of the hand regions, obtaining glove reinforcement region parameters corresponding to the target working scenario;

[0038] Collecting hand size data of each operator in the target working scene, and obtaining glove size category parameters corresponding to the target working scene according to data distribution of the hand size data;

[0039] According to the glove reinforcement area parameters and the glove size category parameters, a target parameter set of the low-voltage insulating gloves applied in the target working scenario is obtained.

[0040] The above-mentioned method, device, computer equipment, computer-readable storage medium and computer program product for determining parameters of the low-voltage insulating gloves first obtain the operating parameters of the target operating scene based on the operating behavior parameters and operating environment parameters of the target operating scene, and then input the operating parameters into the trained friction analysis model to obtain the friction analysis results corresponding to each hand area in the target operating scene output by the friction analysis model, and then obtain the glove reinforcement area parameters corresponding to the target operating scene based on the friction analysis results of each hand area, and obtain the glove size category parameters corresponding to the target operating scene by statistically analyzing the hand size data of each operator in the target operating scene according to the data distribution of the hand size data, and then obtain the target parameter set of the low-voltage insulating gloves applied to the target operating scene based on the glove reinforcement area parameters and the glove size category parameters.

[0041] This scheme, for a specific low-voltage operation scene, can obtain operation parameters that can reflect the characteristics of the target operation scene by collecting the operation environment parameters of the scene and the operation behavior parameters including the hand motion trajectory parameters and the hand motion state parameters. Then, by inputting the operation parameters into the trained friction analysis model, the friction force on each area of ​​the hand during the operation of the target operation scene can be accurately analyzed by the model to obtain the corresponding friction analysis results, and then the area in the target operation scene where the low-voltage insulating gloves need to be strengthened can be determined based on the friction analysis results to obtain the corresponding glove strengthening area parameters. At the same time, by statistically analyzing the hand size data of each staff member in the target operation scene and determining the glove size category parameters of the target operation scene based on their distribution, the glove size category parameters that can match the low-voltage insulating gloves with the hand sizes of most staff members can be determined based on the sizes of the front-line staff in the target operation scene. Therefore, by using the target parameter set obtained according to the glove reinforcement area parameters and the glove size category parameters, low-voltage insulating gloves can be designed and produced that can adapt to the operating characteristics of the target operating scenario and can adapt to the hand size of the front-line workers who need to perform the target operation, thereby effectively ensuring the safety and efficiency of the target low-voltage operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 It is a schematic flow chart of a method for determining parameters of low-voltage insulating gloves in one embodiment;

[0044] Figure 2 is a flow chart of a training process of a trained friction analysis model in one embodiment;

[0045] Figure 3 A schematic diagram of a process for obtaining operation behavior parameters in one embodiment;

[0046] Figure 4 A schematic diagram of a process for obtaining a target parameter set in one embodiment;

[0047] Figure 5 A schematic diagram of a process for obtaining size category parameters in one embodiment;

[0048] Figure 6 is a structural block diagram of a device for determining parameters of low-voltage insulating gloves in one embodiment;

[0049] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] In one embodiment, Figure 1 As shown, a method for determining parameters of low-voltage insulating gloves is provided. This embodiment uses the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0052] Step S101, obtaining the operation parameters of the target operation scene according to the operation behavior parameters and the operation environment parameters of the target operation scene.

[0053] Specifically, the target operation scene may be an operation scene that requires the use of low-voltage insulating gloves for low-voltage live operations. Among them, the operation behavior parameters may include hand motion trajectory parameters and hand motion state parameters. The hand motion trajectory parameters may include the motion trajectory of different positions of the hand (for example, multiple different first hand sampling points distributed on the fingers and palms) during the operation of the target operation in the target operation scene, and the hand motion state parameters may include parameters such as speed and acceleration of different positions of the hand (for example, multiple different second hand sampling points on the fingers and palms) during the target operation. Among them, the operation environment parameters may be parameters that can reflect the environmental characteristics of the target operation scene, for example, they may include but are not limited to obstacle information in the target operation scene (for example, the type, number, relative position, etc. of obstacles existing in the operation scene), operation space information (for example, the width, depth, height range, etc. of the operation space), operation environment information (for example, ambient temperature, humidity, etc.), operation tool type information, etc.

[0054] In this step, the operation behavior parameters and the operation environment parameters of the target operation scene may be combined to obtain operation parameters including these parameters.

[0055] Step S102 , inputting the operation parameters into the trained friction analysis model to obtain the friction analysis results corresponding to each hand area in the target operation scene output by the friction analysis model.

[0056] Exemplarily, the friction analysis model can be trained using multiple work parameter samples corresponding to multiple sample work scenes. Optionally, each work parameter sample can include a work behavior parameter sample, a work environment parameter sample, and a friction data sample corresponding to the corresponding sample work scene. By training the neural network model using multiple work parameter samples, a friction analysis model can be obtained that can accurately analyze the friction force on each area of ​​the hand in different low-pressure work scenes according to the work parameters of the scene.

[0057] Optionally, the friction analysis model may be a neural network model based on a multi-layer perceptron. In this step, the operating parameters of the target operating scene may be converted into corresponding vectors and then input into the trained friction analysis model.

[0058] By inputting the operation parameters of the target operation scene into the trained friction analysis model, the friction analysis results corresponding to each hand area output by the model can be obtained. The friction analysis results of the hand area may include the magnitude and direction of the friction force on the hand area, and may also include information such as the ranking of the friction force magnitude on the hand area among the friction force magnitudes corresponding to all hand areas.

[0059] Step S103, obtaining glove reinforcement area parameters corresponding to the target working scene according to the friction analysis results of each hand area.

[0060] The glove reinforcement area parameter may include information indicating a glove reinforcement area that needs to be reinforced on the low-voltage insulating gloves.

[0061] Optionally, in this step, based on the friction analysis results of each hand area, each hand area can be sorted in order from large to small according to the friction force they are subjected to, and then the hand areas ranked before the preset positions are used as the glove reinforcement areas that need to be strengthened on the low-voltage insulating gloves.

[0062] Optionally, in this step, based on the friction analysis results of each hand area, the hand area subjected to a friction force greater than a preset threshold value can be identified as a glove reinforcement area that needs to be reinforced on the low-voltage insulating glove.

[0063] Step S104, collecting statistics on the hand size data of each operator in the target working scene, and obtaining the glove size category parameters corresponding to the target working scene according to the data distribution of the hand size data.

[0064] The operator of the target operation scene may be a worker who needs to wear low-voltage insulating gloves to perform low-voltage live operations in the target operation scene. In this step, the hand size data of each operator of the target operation scene may be counted and analyzed, so as to obtain the data distribution corresponding to the hand size data of all operators.

[0065] Exemplarily, the hand size data collected for operators may include size data of various hand dimensions, such as finger length, palm length, palm width, and palm thickness. The measurement of each dimensional data may be performed, for example, by manual measurement or three-dimensional scanning.

[0066] After obtaining the hand size data of each operator, the hand size data can be divided into multiple preset hand size categories (for example, including XS, S, M, L, XL, etc.) by, for example, performing cluster analysis on the data of each dimension or grouping the data based on the average value and standard deviation of each dimension.

[0067] Then, according to the value range of each dimension data corresponding to each hand size category, the glove size parameters that can be adapted to the hand size category can be determined. Exemplarily, the glove size parameters may include parameters such as finger length, palm length, palm width, and palm thickness of the glove. Then, according to the glove size parameters corresponding to each hand size category, the glove size category parameters of the low-voltage insulating gloves can be obtained.

[0068] Step S105, obtaining a target parameter set of low-voltage insulating gloves applied in a target working scenario according to the glove reinforcement area parameters and the glove size category parameters.

[0069] Among them, according to the glove reinforcement area parameters and glove size category parameters of the target operation scene, a target parameter set of low-voltage insulating gloves can be obtained. The target parameter set can be subsequently applied to the design and manufacture of low-voltage insulating gloves in the target operation scene. For example, the relevant surface area of ​​the gloves can be enhanced according to the glove reinforcement area parameters, for example, it can include setting an anti-wear reinforcement structure, etc.; at the same time, the specific sizes of low-voltage insulating gloves of different size categories can also be determined according to the glove size category parameters.

[0070] In the above-mentioned method for determining the parameters of low-voltage insulating gloves, for a specific low-voltage operation scene, by collecting the operation environment parameters of the scene and the operation behavior parameters including the hand motion trajectory parameters and the hand motion state parameters, the operation parameters that can reflect the characteristics of the target operation scene can be obtained. Then, by inputting the operation parameters into the trained friction analysis model, the friction force on each area of ​​the hand during the operation of the target operation scene can be accurately analyzed by the model to obtain the corresponding friction analysis results, and then the area in the target operation scene where the low-voltage insulating gloves need to be strengthened can be determined based on the friction analysis results to obtain the corresponding glove strengthening area parameters. At the same time, by statistically analyzing the hand size data of each staff member in the target operation scene and determining the glove size category parameters of the target operation scene according to their distribution, the glove size category parameters that can match the low-voltage insulating gloves with the hand sizes of most staff members can be determined according to the size of the front-line staff in the target operation scene. Therefore, by using the target parameter set obtained according to the glove reinforcement area parameters and the glove size category parameters, low-voltage insulating gloves can be designed and produced that can adapt to the operating characteristics of the target operating scenario and can adapt to the hand size of the front-line workers who need to perform the target operation, thereby effectively ensuring the safety and efficiency of the target low-voltage operation.

[0071] In an exemplary embodiment, Figure 2 As shown, the trained friction analysis model can be obtained by following the steps below:

[0072] Step S201, obtaining a sample of operation parameters corresponding to a sample operation scene.

[0073] The sample operation scene may include different operation scenes that require wearing low-voltage insulating gloves for low-voltage live operation. The test personnel may perform corresponding operation operations in the sample operation scene to collect the operation behavior parameters and the operation environment parameters of the operation process as the operation behavior parameter samples and the operation environment parameter samples corresponding to the sample operation scene. At the same time, the flexible pressure sensors provided on the sample gloves worn by the test personnel may be used to monitor the pressure on each hand area during the operation, and then the magnitude, direction and other data of the friction force on each hand area in the scene may be analyzed to obtain the friction data samples corresponding to the scene.

[0074] In this step, operation parameter samples corresponding to multiple different sample operation scenes can be obtained and used as training data for the friction analysis model.

[0075] Step S202: input the operation behavior parameter samples and the operation environment parameter samples included in the operation parameter samples into a neural network model based on a multi-layer perceptron to obtain a friction analysis result corresponding to the sample operation scene output by the neural network model.

[0076] In this step, a pre-built neural network model based on a multi-layer perceptron can be used as the friction analysis model to be trained. The work behavior parameter samples and work environment parameter samples contained in the work parameter samples are converted into vectors and input into the model. The model processes the data and outputs the corresponding friction analysis results.

[0077] Exemplarily, the friction analysis model to be trained may include an input layer, a hidden layer, and an output layer. The input layer may be used to receive an input feature vector and transmit it to the hidden layer; the hidden layer may be a fully connected layer, which may be used to learn feature representation; and the output layer may receive the output of the hidden layer and output the friction analysis results corresponding to each hand area.

[0078] For example, taking the friction analysis model to be trained as an example including two hidden layers, assuming that the operation behavior parameter samples and the operation environment parameter samples have a total of N feature vectors, the processing process of the model on the input data can be expressed as:

[0079] First, the input layer can receive the input feature vector and pass it to the first hidden layer. The output of the input layer can be expressed as: .

[0080] Then, the first hidden layer receives the feature vector from the input layer , and process it to get the corresponding output , and then transmit it to the second hidden layer. This process can be expressed as:

[0081]

[0082] In the formula, is the weight matrix of the first hidden layer, ; is the number of neurons in the first hidden layer; is the bias vector of the first hidden layer, ; is the activation function of the first hidden layer (for example, ReLU, Sigmoid, etc.).

[0083] The second hidden layer can receive the vector from the first hidden layer , and process it to get the corresponding output , and then transmit it to the output layer. This process can be expressed as:

[0084]

[0085] In the formula, is the weight matrix of the second hidden layer, ; is the number of neurons in the second hidden layer; is the bias vector of the second hidden layer, ; is the activation function of the second hidden layer (for example, ReLU, Sigmoid, etc.).

[0086] Then, the output layer can receive the vector from the second hidden layer , and process it to obtain the friction analysis results corresponding to each hand area . The processing can be expressed as:

[0087]

[0088] in, is the weight matrix of the output layer, ; M is the number of neurons in the output layer; is the bias vector of the output layer, Optionally, the number of M can be set to be the same as the number of hand regions, and the output value of each neuron can correspond to the friction analysis result of one hand region.

[0089] Step S203, according to the difference between the friction analysis result corresponding to the sample operation scene and the friction data sample included in the operation parameter sample, the model parameters of the neural network model are adjusted using an optimization algorithm based on gradient descent to obtain a trained friction analysis model.

[0090] Among them, according to the difference between the friction analysis results output by the friction analysis model to be trained and the friction data samples corresponding to the same sample operation scene contained in the operation parameter samples, the model parameters of the model can be optimized to obtain a trained friction analysis model.

[0091] Exemplarily, in this step, the mean square error can be used as the loss function, and the difference between the friction analysis result and the friction data sample is measured according to the size of the mean square error:

[0092]

[0093] in, is the friction data sample, Friction analysis results output by the model. represents the mean square error between the friction analysis results and the friction data samples, N is the number of operating parameter samples, is the friction data sample contained in the i-th operating parameter sample, is the friction analysis result corresponding to the i-th operating parameter sample.

[0094] Based on the above loss function, the parameters of the model can be optimized and adjusted using an optimization algorithm based on gradient descent to obtain model parameters that minimize the mean square error between the friction analysis results and the friction data samples, thereby obtaining a trained friction analysis model. Exemplarily, the optimization algorithm used in this step may include, but is not limited to, a gradient descent algorithm, an adaptive moment estimation algorithm (Adaptive Moment Estimation, Adam), a root mean square propagation algorithm (Root Mean Square Propagation, Root Mean Square Propagation), and the like.

[0095] In this embodiment, by constructing a neural network model based on a multi-layer perceptron as the friction analysis model to be trained, and using the operation parameter samples corresponding to the sample operation scenes to train the model, a model that can accurately analyze the friction conditions of different low-pressure operation scenes can be obtained, and using the optimization algorithm based on gradient descent to adjust the parameters of the model is conducive to improving the training efficiency and the accuracy of the model. Therefore, using the trained friction analysis model, even when facing a target operation scene different from the sample operation scene, accurate friction analysis results can be output.

[0096] In an exemplary embodiment, Figure 3 As shown, before obtaining the operation parameters of the target operation scene according to the operation behavior parameters and the operation environment parameters of the target operation scene, the following steps are also included:

[0097] Step S301, using an inertial sensor to obtain acceleration parameters and angular velocity parameters of a plurality of first hand sampling points during an operation in a target operation scene, and obtaining hand motion state parameters according to the acceleration parameters and angular velocity parameters.

[0098] Among them, the inertial sensor (Inertial Measurement Unit, IMU) can measure the acceleration and angular velocity of the object. In this step, the inertial sensors of multiple first hand sampling points worn on the hand can be used to measure the acceleration parameters and angular velocity parameters of each first hand sampling point during the operation of the target operation scene, and the speed, acceleration and other parameters of each first hand sampling point can be calculated based on these parameters, so as to obtain the hand motion state parameters of the target operation scene. Exemplarily, the first hand sampling points may include fingertips, finger bases, palms, etc.

[0099] Step S302: using an optical tracking device to track the motion trajectories of a plurality of second hand sampling points during the operation, and obtaining hand motion trajectory parameters according to the motion trajectories.

[0100] The optical tracking device can capture the precise position of the marker point in three-dimensional space and obtain the motion trajectory of the marker point. In this step, the marker points can be set at multiple second hand sampling points on the hand, and the operation process can be tracked in all directions using multiple micro cameras, so that the motion trajectory of each second hand sampling point during the operation can be obtained, and then the hand motion trajectory parameters of the target operation scene can be obtained. Exemplarily, the second hand sampling points can include multiple different positions on the fingers and palms.

[0101] Step S303, obtaining the operation behavior parameters according to the hand movement state parameters and the hand movement trajectory parameters.

[0102] In this step, by combining the hand motion state parameters and the hand motion trajectory parameters, it is possible to obtain the work behavior parameters that can comprehensively and accurately reflect the hand behavior in the target work scene.

[0103] In this embodiment, with respect to hand behavior in low-pressure working scenarios, inertial sensors are used to obtain hand motion state parameters, and optical tracking devices are used to obtain hand motion trajectory parameters, thereby obtaining multi-dimensional hand behavior data during the working process, better reflecting the hand behavior characteristics in the working scenario, and facilitating the subsequent use of the data to conduct a more accurate analysis of the friction conditions in the target working scenario.

[0104] In an exemplary embodiment, the operating parameter samples used to train the friction analysis model also include surface structure parameter samples and wear data samples of each surface area of ​​the low-voltage insulating glove sample in the sample operating scene; the operating parameters of the target operating scene also include surface structure parameters of each surface area of ​​the low-voltage insulating glove in the target operating scene; the friction analysis results of each hand area output by the friction analysis model include friction force analysis data and wear analysis data of the hand area.

[0105] Among them, Figure 4 As shown, after obtaining the glove reinforcement area parameters corresponding to the target working scene according to the friction analysis results of each hand area, the following may also be included:

[0106] Step S401, determining a target reinforcement area of ​​the low-voltage insulating gloves in the target operation scene according to the glove reinforcement area parameters corresponding to the target operation scene.

[0107] Step S402, when the friction analysis data and wear analysis data corresponding to the target reinforcement area do not meet the preset conditions, the friction analysis model is used to iteratively optimize the surface structure parameters of the target reinforcement area until the target surface structure parameters that make the friction analysis data and wear analysis data of the target reinforcement area meet the preset conditions are obtained and the iteration is stopped.

[0108] According to the glove reinforcement area parameters and glove size category parameters, a target parameter set of low-voltage insulating gloves applied to the target operation scenario is obtained, which may also include:

[0109] Step S403, obtaining a target parameter set according to the glove reinforcement area parameters, the glove size category parameters and the target surface structure parameters of the target reinforcement area.

[0110] Among them, since the friction force exerted on the hand area is usually correlated with the wear condition of the corresponding area of ​​the low-voltage insulating gloves, the trained friction analysis model can be used in this embodiment to simultaneously analyze the friction force exerted on each hand area and the wear condition of each area on the surface of the low-voltage insulating gloves.

[0111] Specifically, the trained friction analysis model used in this embodiment can receive the hand motion trajectory parameters, hand motion state parameters and surface structure parameters of each surface area of ​​the low-voltage insulating gloves contained in the operation parameter sample as input data, and output the friction analysis results corresponding to each hand area by processing these data. Among them, the friction analysis results may include the friction analysis data of the hand area and the wear analysis data of the glove surface area corresponding to the hand area. Exemplarily, the surface structure parameters of the surface area may include the roughness, hardness, etc. of the surface area on the glove, and the wear analysis data may include a numerical value for the degree of wear on the glove surface (for example, its value range may be 0 to 100%, the smaller the value, the lower the degree of wear, and the larger the value, the higher the degree of wear).

[0112] The model can be trained using operating parameter samples including operating behavior parameter samples, operating environment parameter samples and friction data samples in sample operating scenes, as well as surface structure parameter samples and wear data samples of each surface area of ​​low-voltage insulating gloves samples.

[0113] Exemplarily, the friction analysis model can be a multi-task learning model based on a multi-layer perceptron, which may include an input layer, a hidden layer, and an output layer. Since there is a correlation between friction and wear, the same input layer and a shared hidden layer can be used to process the two tasks when constructing the model, the output layer receives the data of the input model, and the first few hidden layers perform preliminary feature extraction. Then, branches including hidden layers and output layers can be constructed for the two tasks respectively. The hidden layer in one branch can further learn features related to friction analysis based on the preliminary features extracted by the shared hidden layer and transmit them to the output layer of the branch, and the output layer can output friction analysis data of each hand area; the hidden layer in another branch can further learn features related to wear analysis based on the preliminary features extracted by the shared hidden layer and transmit them to the output layer of the branch, and the output layer can output wear analysis data of the glove surface area corresponding to each hand area.

[0114] It is understandable that by inputting the operating parameters of the target operating scenario into the trained friction analysis model, the friction analysis results and wear analysis data output by the model can be obtained. Then, using the friction analysis results, the glove reinforcement area parameters corresponding to the target operating scenario can be further obtained. Among them, the glove reinforcement area parameters may include information indicating the glove reinforcement area that needs to be reinforced on the low-voltage insulating gloves, and the glove reinforcement area corresponds to the hand area that is subject to greater friction.

[0115] Based on this, in step S401, the target reinforcement area where the surface of the low-voltage insulating gloves needs to be reinforced in the target operation scenario can be determined according to the glove reinforcement area parameters.

[0116] Then, in step S402, the friction analysis data and wear analysis data corresponding to the target enhanced area can be analyzed to determine whether they meet the corresponding preset conditions. For example, in order to ensure the safety of low-voltage live working, low-voltage insulating gloves need to have certain anti-slip and anti-wear properties. Based on this, the friction threshold and the wear threshold can be set respectively. When the friction analysis data of the target enhanced area indicates that the corresponding friction is not less than the friction threshold, and the wear analysis data indicates that the corresponding wear degree is not greater than the wear threshold, it can be considered that the friction analysis data and the wear analysis data meet the preset conditions.

[0117] When it is determined that the friction analysis data and the wear analysis data do not meet the preset conditions, the surface structure parameters corresponding to the target reinforcement area can be adjusted, and the trained friction analysis model can be used to analyze the friction and wear conditions in the target operation scene again according to the adjusted surface structure parameters and the remaining data in the operation parameters of the target operation scene. When the friction analysis data and the wear analysis data in the friction analysis results output by the model meet the preset conditions, the adjusted surface structure parameters of the target reinforcement area can be used as the target surface structure parameters of the area.

[0118] Then, in step S403, a target parameter set of the low-voltage insulating gloves can be obtained according to the glove reinforcement area parameters, the glove size category parameters and the target surface structure parameters of the target reinforcement area. Based on the target parameter set, in the subsequent design and manufacture of low-voltage insulating gloves for target working scenarios, more targeted enhancement processing can be performed on the relevant surface areas of the gloves according to the target surface structure parameters of the target reinforcement area.

[0119] In this embodiment, in view of the fact that the friction force on the hand area is associated with the wear condition of the corresponding surface area on the low-voltage insulating gloves, the trained friction analysis model is used to simultaneously analyze the friction force on the hand area and the wear condition of the glove surface in the target operation scene, so that data that can reflect the characteristics of low-voltage operation in the target operation scene can be obtained more accurately. After determining the target reinforced area of ​​the low-voltage insulating gloves according to the glove reinforced area parameters, the surface structure parameters of the target reinforced area whose friction analysis data and wear analysis data do not meet the preset conditions are adjusted, and then the friction analysis model is used to perform friction analysis and wear analysis again according to the adjusted surface structure parameters, so that the anti-slip performance of the gloves can be considered while strengthening the wear resistance of the target reinforced area, and the target surface structure parameters that can simultaneously meet the wear resistance requirements and anti-slip requirements of low-voltage operation can be obtained. Therefore, the target parameter set is obtained according to the glove reinforced area parameters, the glove size category parameters and the target surface structure parameters, which can be conducive to designing and manufacturing low-voltage insulating gloves with higher safety in the target operation scene.

[0120] In an exemplary embodiment, the surface structure parameters of the surface region may include protrusion structure parameters of the surface region, and / or sandblasting strengthening structure parameters.

[0121] The strengthening treatment of the glove surface may include one or more treatments such as providing a protruding structure on the glove surface, sandblasting the glove surface, etc. Based on this, the surface structure parameters of each surface area of ​​the glove may correspondingly include one or more of the protruding structure parameters and the sandblasting strengthening structure parameters.

[0122] For example, the raised structures provided on the surface of the gloves may be provided in an array on one or more surface areas of the gloves, and the corresponding raised structure parameters may include the distribution density, size, shape, etc. of the raised structures. The shapes of the raised structures may include hemispherical, cylindrical, conical, prism-shaped, etc. The range of the size of the raised structures may be set in consideration of the comfort level of the gloves, for example, the height may be set between 0.5 and 1.5 mm to avoid affecting the flexibility and comfort level of wearing the gloves for work.

[0123] Exemplarily, the sandblasting treatment performed on the surface of the glove may be performed by spraying one or more surface areas of the glove with, for example, silicon dioxide-coated alumina particles so that the particles are evenly distributed on the corresponding surface areas, and the corresponding sandblasting strengthening structural parameters may include particle size, spraying concentration, spraying thickness, etc.

[0124] Based on this, when adjusting the surface structure parameters corresponding to the target reinforcement area, it is possible to adjust whether to set a raised structure in the target reinforcement area, the specific setting parameters of the raised structure, whether to perform sandblasting, and the specific parameters of the sandblasting to determine the best reinforcement treatment method for the target reinforcement area.

[0125] In this embodiment, for strengthening treatments such as setting a protruding structure or performing sandblasting on the glove surface, the protruding structure parameters and the sandblasting strengthening structure parameters are used as part of the surface structure parameters, so that when the surface structure parameters of the target strengthening area are adjusted, the strength and roughness of the target strengthening area on the glove surface can be adjusted by adding a protruding structure, or performing sandblasting, or a combination of the two, and the setting method of the protruding structure or the sandblasting method can be further refined and adjusted to obtain the target surface structure parameters that can achieve the best balance between the anti-slip and wear resistance of the target strengthening area.

[0126] In an exemplary embodiment, Figure 5 As shown, the hand size data of each operator in the target operation scene is counted, and the size category parameters of the low-voltage insulating gloves are obtained according to the data distribution of the hand size data, which may include:

[0127] Step S501, counting the dimensional data corresponding to each hand dimension of each operator in the target working scene, and obtaining the hand size data according to the dimensional data corresponding to each hand dimension.

[0128] The hand size data may include dimension data corresponding to each hand dimension, and the hand dimension may include finger length, palm length, palm width, palm thickness, etc. In this step, the dimensions of each hand dimension of each operator may be measured by, for example, three-dimensional scanning, etc., to collect the corresponding dimension data, and then obtain the hand size data of the target operation scene.

[0129] Step S502 , respectively counting the average value and standard deviation of the dimensional data corresponding to each hand dimension.

[0130] For hand size data containing multiple dimensional data, the corresponding dimensional data average and dimensional data standard deviation can be calculated for each hand dimension. For example, for each of the aforementioned hand dimensions, the average finger length, the average palm length, the average palm width and the average palm thickness can be obtained, and the standard deviation of the finger length, the standard deviation of the palm length, the standard deviation of the palm width and the standard deviation of the palm thickness can be obtained.

[0131] Step S503, determining the dimensional data interval corresponding to each hand dimension of each size category according to the dimensional data average value and the dimensional data standard deviation corresponding to each hand dimension.

[0132] Among them, multiple size categories that need to be divided can be preset, for example, they can include XS, S, M, L, XL, etc. Then, according to the dimensional data average value and dimensional data standard deviation corresponding to each hand dimension, each hand dimension data can be divided into dimensional data intervals corresponding to each size category.

[0133] For example, taking the hand dimension as the finger length as an example, assuming that its value range is The average finger length is , the standard deviation of finger length is , it can be divided into multiple dimensional data intervals corresponding to different size categories, for example, it may include: dimensional data interval corresponding to size category XS ), corresponding to the dimension data interval of size category S[ , corresponding to the dimension data interval of size category M[ , corresponding to the dimension data interval of size category L ( , corresponding to the dimension data interval of size category XL .

[0134] It can be understood that the division method of the dimension data interval is not unique, and the number of size categories and the division method of the interval can be adjusted according to the actual numerical range and distribution of the hand size data.

[0135] Step S504, determining the target dimension parameters of each hand dimension corresponding to each size category according to the data median of each dimensional data interval corresponding to each size category.

[0136] In order to adapt the size of the low-voltage insulating gloves corresponding to each size category to the hand dimension data in the corresponding dimension data interval, in this step, for each size category, the data median of the dimension data interval of each hand dimension can be used as the target dimension parameter of the hand dimension in the size category. That is, for each size category, the target dimension parameters corresponding to the finger length, palm length, palm width and palm thickness can be determined respectively.

[0137] Step S505, obtaining the size category parameters of the low-voltage insulating gloves according to the target dimension parameters corresponding to each size category.

[0138] Among them, according to the target dimension parameters of each size category corresponding to each hand dimension, the size category parameters of the low-voltage insulating gloves can be obtained. Based on the glove size category parameters, the specific sizes of low-voltage insulating gloves of different size categories that can be suitable for operators in target working scenarios can be determined in the subsequent design and manufacture of low-voltage insulating gloves.

[0139] In this embodiment, by statistically analyzing the dimensional data of various hand dimensions of each operator in the target operation scene, hand size data that more accurately and comprehensively reflects the hand structure of the operator can be obtained. The dimensional data intervals corresponding to each size category are divided according to the mean and standard deviation of these data, and the target dimensional parameters of each size category corresponding to each hand dimension are further determined, so that the representative size of each hand dimension in each size category can be determined efficiently and quickly. Subsequently, the size category parameters determined according to this process can be applied to the design and manufacturing process of low-voltage insulating gloves, so as to accurately obtain the glove size of each size category, so that low-voltage insulating gloves that are more in line with the hand structure characteristics of each operator in the target operation scene and have higher fit and comfort can be manufactured.

[0140] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0141] Based on the same inventive concept, the embodiment of the present application also provides a low-voltage insulating glove parameter determination device for implementing the above-mentioned method for determining parameters of low-voltage insulating gloves. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of one or more low-voltage insulating glove parameter determination devices provided below can refer to the limitations of the method for determining parameters of low-voltage insulating gloves above, and will not be repeated here.

[0142] In an exemplary embodiment, Figure 6 As shown, a parameter determination device 600 for a low-voltage insulating glove is provided, comprising:

[0143] An acquisition module 601 is used to acquire operation behavior parameters and operation environment parameters of a target operation scene; wherein the operation behavior parameters include hand motion trajectory parameters and hand motion state parameters;

[0144] The friction analysis module 602 is used to input the working behavior parameters and the working environment parameters into the trained friction analysis model to obtain the friction analysis results of each hand area in the target working scene output by the friction analysis model; wherein the friction analysis model is trained using working parameter samples corresponding to the sample working scene; the working parameter samples include working behavior parameter samples, working environment parameter samples and friction data samples corresponding to the sample working scene;

[0145] A first parameter determination module 603, for obtaining the glove reinforcement area parameters corresponding to the target working scene according to the friction analysis results of each hand area;

[0146] The second parameter determination module 604 is used to collect hand size data of each operator in the target working scene, and obtain the glove size category parameter corresponding to the target working scene according to the data distribution of the hand size data;

[0147] The parameter set determination module 605 is used to obtain a target parameter set of the low-voltage insulating gloves applied in the target working scenario according to the glove reinforcement area parameters and the glove size category parameters.

[0148] In an exemplary embodiment, the trained friction analysis model is trained by the following steps: obtaining the operating parameter sample corresponding to the sample operating scene; inputting the operating behavior parameter sample and the operating environment parameter sample contained in the operating parameter sample into a neural network model based on a multi-layer perceptron to obtain the friction analysis result corresponding to the sample operating scene output by the neural network model; according to the difference between the friction analysis result corresponding to the sample operating scene and the friction data sample contained in the operating parameter sample, adjusting the model parameters of the neural network model using a gradient descent-based optimization algorithm to obtain the trained friction analysis model.

[0149] In an exemplary embodiment, the device also includes: a state parameter acquisition module, which is used to use an inertial sensor to obtain acceleration parameters and angular velocity parameters of multiple first hand sampling points during the operation process of the target operation scene, and obtain the hand motion state parameters according to the acceleration parameters and the angular velocity parameters; a trajectory parameter acquisition module, which is used to use an optical tracking device to track the motion trajectories of multiple second hand sampling points during the operation process, and obtain the hand motion trajectory parameters according to the motion trajectories; and a behavior parameter acquisition module, which is used to obtain the operation behavior parameters according to the hand motion state parameters and the hand motion trajectory parameters.

[0150] In an exemplary embodiment, the operating parameter samples used to train the friction analysis model also include surface structure parameter samples and wear data samples of each surface area of ​​the low-voltage insulating glove sample in the sample operating scene; the operating parameters of the target operating scene also include surface structure parameters of each surface area of ​​the low-voltage insulating glove in the target operating scene; the friction analysis results of each hand area output by the friction analysis model include friction analysis data and wear analysis data of the hand area; the device also includes: a reinforcement area determination module for determining the target operating scene according to the glove reinforcement area parameters corresponding to the target operating scene. The target reinforced area of ​​the low-voltage insulating gloves; a structural parameter optimization module, used to use the friction analysis model to iteratively optimize the surface structural parameters of the target reinforced area when the friction analysis data and the wear analysis data corresponding to the target reinforced area do not meet the preset conditions, and stop iteration after obtaining the target surface structural parameters that make the friction analysis data and the wear analysis data of the target reinforced area meet the preset conditions; the parameter set determination module 605 is also used to: obtain the target parameter set according to the glove reinforced area parameters, the glove size category parameters and the target surface structural parameters of the target reinforced area.

[0151] In an exemplary embodiment, the surface structure parameters of the surface region include protrusion structure parameters of the surface region, and / or sandblasting strengthening structure parameters.

[0152] In an exemplary embodiment, the second parameter determination module 604 is also used to: count the dimensional data corresponding to each hand dimension of each operator in the target work scene, and obtain the hand size data according to the dimensional data corresponding to each hand dimension; wherein the hand dimensions include finger length, palm length, palm width and palm thickness; respectively count the average value of the dimensional data and the standard deviation of the dimensional data corresponding to each hand dimension; determine the dimensional data interval corresponding to each hand dimension for each size category according to the average value of the dimensional data and the standard deviation of the dimensional data corresponding to each hand dimension; determine the target dimensional parameters corresponding to each hand dimension for each size category according to the data median of each dimensional data interval corresponding to each size category; and obtain the size category parameters of the low-voltage insulating gloves according to each target dimensional parameter corresponding to each size category.

[0153] Each module in the above-mentioned low-voltage insulating glove parameter determination device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0154] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as the operation behavior parameters, the operation environment parameters, and the hand size data of each operator of the target operation scene. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for determining parameters of a low-voltage insulating glove is implemented.

[0155] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0156] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0157] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0158] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0159] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0160] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0161] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0162] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining parameters of low-voltage insulating gloves, characterized in that: The method comprises: According to the working behavior parameters of the target working scene, the working environment parameters, and the surface structure parameters of each surface area of ​​the low-voltage insulating gloves, the working parameters of the target working scene are obtained; wherein the working behavior parameters include hand motion trajectory parameters and hand motion state parameters; The operating parameters are input into a trained friction analysis model to obtain friction analysis results corresponding to each hand area in the target operating scene output by the friction analysis model; wherein the friction analysis model is trained using operating parameter samples corresponding to sample operating scenes; the operating parameter samples include operating behavior parameter samples, operating environment parameter samples, friction data samples corresponding to the sample operating scenes, and surface structure parameter samples and wear data samples of each surface area of ​​the low-voltage insulating glove sample in the sample operating scenes; the friction analysis results of each hand area include friction force analysis data and wear analysis data of the hand area; According to the friction analysis results of each of the hand regions, obtaining glove reinforcement region parameters corresponding to the target working scenario; Determining a target reinforcement area of ​​the low-voltage insulating gloves in the target operation scene according to the glove reinforcement area parameters corresponding to the target operation scene; In the case where the friction analysis data and the wear analysis data corresponding to the target reinforcement area do not meet the preset conditions, the surface structure parameters of the target reinforcement area are iteratively optimized using the friction analysis model until the target surface structure parameters that make the friction analysis data and the wear analysis data of the target reinforcement area meet the preset conditions are obtained and then the iteration is stopped; Collecting hand size data of each operator in the target working scene, and obtaining glove size category parameters corresponding to the target working scene according to data distribution of the hand size data; According to the glove reinforcement area parameters, the glove size category parameters and the target surface structure parameters of the target reinforcement area, a target parameter set of the low-voltage insulating gloves applied in the target working scenario is obtained.

2. The method according to claim 1, characterized in that The trained friction analysis model is obtained by training through the following steps: Obtaining the operation parameter sample corresponding to the sample operation scene; Inputting the operation behavior parameter sample and the operation environment parameter sample included in the operation parameter sample into a neural network model based on a multi-layer perceptron to obtain a friction analysis result corresponding to the sample operation scene output by the neural network model; According to the difference between the friction analysis result corresponding to the sample operation scene and the friction data sample included in the operation parameter sample, the model parameters of the neural network model are adjusted using a gradient descent-based optimization algorithm to obtain the trained friction analysis model.

3. The method according to claim 1, characterized in that Before obtaining the operation parameters of the target operation scene according to the operation behavior parameters and the operation environment parameters of the target operation scene, the method further includes: Using an inertial sensor to obtain acceleration parameters and angular velocity parameters of a plurality of first hand sampling points during an operation in the target operation scene, and obtaining the hand motion state parameters according to the acceleration parameters and the angular velocity parameters; Tracking the motion trajectories of a plurality of second hand sampling points during the operation using an optical tracking device, and obtaining the hand motion trajectory parameters according to the motion trajectories; The operation behavior parameter is obtained according to the hand movement state parameter and the hand movement trajectory parameter.

4. The method according to claim 1, characterized in that: The surface structure parameters of the surface area include protrusion structure parameters of the surface area and / or sandblasting strengthening structure parameters.

5. The method according to any one of claims 1 to 4, characterized in that: The statistically collecting the hand size data of each operator in the target operation scene and obtaining the size category parameters of the low-voltage insulating gloves according to the data distribution of the hand size data include: Counting the dimensional data corresponding to each hand dimension of each operator in the target working scene, and obtaining the hand size data according to the dimensional data corresponding to each hand dimension; wherein the hand dimensions include finger length, palm length, palm width and palm thickness; Counting respectively the average value and standard deviation of the dimension data corresponding to each hand dimension; Determine, according to the dimensional data average value and the dimensional data standard deviation corresponding to each hand dimension, the dimensional data interval corresponding to each hand dimension of each size category; Determining target dimension parameters of each hand dimension corresponding to each size category according to the data median of each dimension data interval corresponding to each size category; The size category parameters of the low-voltage insulating gloves are obtained according to the target dimension parameters corresponding to the size categories.

6. A parameter determination device for low-voltage insulating gloves, characterized in that: The device comprises: An acquisition module, used to obtain the operation parameters of the target operation scene according to the operation behavior parameters of the target operation scene, the operation environment parameters, and the surface structure parameters of each surface area of ​​the low-voltage insulating gloves; wherein the operation behavior parameters include hand motion trajectory parameters and hand motion state parameters; A friction analysis module, used for inputting the work behavior parameters and the work environment parameters into a trained friction analysis model, and obtaining the friction analysis results of each hand area in the target work scene output by the friction analysis model; wherein the friction analysis model is trained using work parameter samples corresponding to sample work scenes; the work parameter samples include work behavior parameter samples, work environment parameter samples, friction data samples corresponding to the sample work scenes, and surface structure parameter samples and wear data samples of each surface area of ​​the low-voltage insulating glove sample in the sample work scenes; the friction analysis results of each hand area include friction force analysis data and wear analysis data of the hand area; A first parameter determination module, configured to obtain the glove reinforcement area parameters corresponding to the target working scene according to the friction analysis results of each of the hand areas; A reinforcement area determination module, used to determine a target reinforcement area of ​​the low-voltage insulating gloves in the target operation scene according to the glove reinforcement area parameters corresponding to the target operation scene; a structural parameter optimization module, for iteratively optimizing the surface structural parameters of the target reinforcement area using the friction analysis model when the friction analysis data and the wear analysis data corresponding to the target reinforcement area do not meet the preset conditions, until the target surface structural parameters are obtained so that the friction analysis data and the wear analysis data of the target reinforcement area meet the preset conditions and then the iteration is stopped; A second parameter determination module is used to collect hand size data of each operator in the target working scene, and obtain glove size category parameters corresponding to the target working scene according to data distribution of the hand size data; The parameter set determination module is used to obtain a target parameter set of the low-voltage insulating gloves applied in the target working scene according to the glove reinforcement area parameters, the glove size category parameters and the target surface structure parameters of the target reinforcement area.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images