User operation risk early warning methods, devices, computer equipment and storage media

Abstract

This application relates to a user operation risk early warning method, apparatus, computer equipment, and storage medium. The method includes: a server acquiring physiological signal data and operation data of a user to be assessed; inputting the physiological signal data into a pre-constructed hazard risk assessment model to obtain a hazard risk assessment result for the user to be assessed; inputting the operation data into a pre-constructed posture risk assessment model to obtain a posture risk assessment result for the user to be assessed; then, obtaining a risk assessment result for the user to be assessed based on the hazard risk assessment result and the posture risk assessment result; finally, obtaining user operation risk early warning information for the user to be assessed based on the risk assessment result and returning it to the user's terminal for user operation risk early warning. This method achieves objectivity in risk assessment while also enhancing the accuracy and reliability of risk assessment.

Description

Technical Field

[0001] This application relates to the field of personal risk assessment technology, and in particular to a user operation risk early warning method, device, computer equipment, computer-readable storage medium and computer program product. Background Technology

[0002] In modern industrial production and on-site operations, personal safety is always a crucial issue. In the past, the assessment of personal risks mainly relied on experience or simple safety rules. This method allows for quick decision-making, low implementation costs, and high flexibility. However, the results obtained by this method are relatively crude, have extremely limited application scope, and also suffer from problems such as strong subjectivity and insufficient accuracy. Summary of the Invention

[0003] Therefore, it is necessary to provide a user operation risk early warning method, device, computer equipment, computer-readable storage medium, and computer program product that can improve the objectivity and accuracy of judgment in addressing the above-mentioned technical problems.

[0004] Firstly, this application provides a user operation risk early warning method, including:

[0005] Acquire physiological signal data of the user to be identified, and acquire the user's work data;

[0006] Physiological signal data is input into a pre-built hazard risk assessment model to obtain the hazard risk assessment results for the user to be judged; and work data is input into a pre-built posture risk assessment model to obtain the posture risk assessment results for the user to be judged.

[0007] Based on the hazard risk assessment results and the posture risk assessment results, the risk assessment results for the users to be assessed are obtained;

[0008] Based on the risk assessment results, user operation risk warning information for the user to be assessed is obtained and returned to the user's terminal for user operation risk warning.

[0009] In one embodiment, acquiring the physiological signal data of the user to be identified includes:

[0010] Obtain the raw physiological signal data of the user to be identified; the raw physiological signal data includes first raw physiological signal data and second raw physiological signal data; the first raw physiological signal data is disturbed raw physiological signal data; the second raw physiological signal data is undisturbed raw physiological signal data;

[0011] The first original physiological signal data and a pre-constructed random matrix are multiplied to obtain the transformed first original physiological signal data;

[0012] Physiological signal data is obtained based on the transformed first and second original physiological signal data.

[0013] In one embodiment, the transformed first original physiological signal data includes third original physiological signal data, fourth original physiological signal data, and fifth original physiological signal data; wherein, the third original physiological signal data is original physiological signal data subject to electromechanical interference, the fourth original physiological signal data is original physiological signal data subject to motion artifact interference, and the fifth original physiological signal data is original physiological signal data undisturbed.

[0014] Based on the transformed first and second original physiological signal data, physiological signal data is obtained, including:

[0015] The third raw physiological signal data is filtered using a preset band-stop filter to obtain filtered third raw physiological signal data, and the fourth raw physiological signal data is filtered using a preset low-pass filter to obtain filtered fourth raw physiological signal data.

[0016] The second raw physiological signal data, the filtered third raw physiological signal data, the filtered fourth raw physiological signal data, and the fifth raw physiological signal data are summed to obtain the physiological signal data to be processed.

[0017] The physiological signal data to be processed is denoised and normalized to obtain the physiological signal data.

[0018] In one exemplary embodiment, the job data includes job video data and acceleration data;

[0019] Obtain the job data of the user to be judged, including:

[0020] The working video data is downsampled, normalized, and denoised to obtain the processed working video data. The acceleration data is denoised and normalized to obtain the processed acceleration data.

[0021] The corresponding working video feature vector is obtained based on the processed working video data, and the corresponding acceleration feature vector is obtained based on the processed acceleration data.

[0022] Obtain the first weight corresponding to the feature vector of the working video, and obtain the second weight corresponding to the acceleration feature vector;

[0023] Based on the first weight and the second weight, the work video feature vector and the acceleration feature vector are weighted and summed to obtain the work data feature vector of the user to be judged.

[0024] Inputting the operational data into a pre-built attitude risk assessment model yields the attitude risk assessment results for the user to be assessed, including:

[0025] The operation data feature vector is input into a pre-built posture risk assessment model to obtain a higher-order feature vector corresponding to the operation data feature vector, and the posture risk assessment result of the user to be judged is obtained based on the higher-order feature vector; the higher-order feature vector is used to distinguish different posture information of the user to be judged.

[0026] In one embodiment, based on the hazard risk assessment results and the posture risk assessment results, the risk assessment results for the user to be assessed are obtained, including:

[0027] Obtain the third weight corresponding to the hazard risk assessment results, and obtain the fourth weight corresponding to the attitude risk assessment results;

[0028] By using the third and fourth weights, the risk assessment results of hidden dangers and the risk assessment results of posture are weighted to obtain the risk assessment results of the user to be judged.

[0029] In one embodiment, the risk assessment result is represented by a risk value;

[0030] Based on the risk assessment results, user operation risk warning information for the user to be assessed is obtained, including:

[0031] If the risk value exceeds the preset risk value threshold, the personnel status information of the user to be judged is determined based on physiological signal data and work data.

[0032] Based on personnel status information, determine the corresponding work order content and on-site operation risk information, and obtain corresponding safety warning information and countermeasure information according to the work order content and on-site operation risk information;

[0033] User operation risk warning information is generated based on safety warning information and response measures information.

[0034] Secondly, this application also provides a user operation risk early warning device, including:

[0035] The data acquisition module is used to acquire physiological signal data of the user to be judged, as well as the user's work data;

[0036] The assessment result acquisition module is used to input physiological signal data into a pre-built hazard risk assessment model to obtain the hazard risk assessment result of the user to be judged, and to input work data into a pre-built posture risk assessment model to obtain the posture risk assessment result of the user to be judged.

[0037] The judgment result determination module is used to obtain the risk judgment result of the user to be judged based on the hidden danger risk assessment result and the posture risk assessment result;

[0038] The early warning information determination module is used to obtain user operation risk early warning information for the user to be judged based on the risk judgment result, and return it to the terminal of the user to be judged to provide user operation risk early warning.

[0039] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0040] Acquire physiological signal data of the user to be identified, and acquire the user's work data;

[0041] Physiological signal data is input into a pre-built hazard risk assessment model to obtain the hazard risk assessment results for the user to be judged; and work data is input into a pre-built posture risk assessment model to obtain the posture risk assessment results for the user to be judged.

[0042] Based on the hazard risk assessment results and the posture risk assessment results, the risk assessment results for the users to be assessed are obtained;

[0043] Based on the risk assessment results, user operation risk warning information for the user to be assessed is obtained and returned to the user's terminal for user operation risk warning.

[0044] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0045] Acquire physiological signal data of the user to be identified, and acquire the user's work data;

[0046] Physiological signal data is input into a pre-built hazard risk assessment model to obtain the hazard risk assessment results for the user to be judged; and work data is input into a pre-built posture risk assessment model to obtain the posture risk assessment results for the user to be judged.

[0047] Based on the hazard risk assessment results and the posture risk assessment results, the risk assessment results for the users to be assessed are obtained;

[0048] Based on the risk assessment results, user operation risk warning information for the user to be assessed is obtained and returned to the user's terminal for user operation risk warning.

[0049] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0050] Acquire physiological signal data of the user to be identified, and acquire the user's work data;

[0051] Physiological signal data is input into a pre-built hazard risk assessment model to obtain the hazard risk assessment results for the user to be judged; and work data is input into a pre-built posture risk assessment model to obtain the posture risk assessment results for the user to be judged.

[0052] Based on the hazard risk assessment results and the posture risk assessment results, the risk assessment results for the users to be assessed are obtained;

[0053] Based on the risk assessment results, user operation risk warning information for the user to be assessed is obtained and returned to the user's terminal for user operation risk warning.

[0054] The aforementioned user operation risk early warning method, device, computer equipment, computer-readable storage medium, and computer program product involve a server acquiring physiological signal data and operation data of the user to be assessed. The physiological signal data is then input into a pre-constructed hazard risk assessment model to obtain a hazard risk assessment result for the user. The operation data is input into a pre-constructed posture risk assessment model to obtain a posture risk assessment result for the user. Based on the hazard risk assessment result and the posture risk assessment result, a risk assessment result for the user is obtained. Finally, user operation risk early warning information for the user is obtained based on the risk assessment result and returned to the user's terminal for user operation risk early warning. By using pre-constructed models to process the acquired data to obtain corresponding risk assessment results, and then determining the corresponding risk assessment result based on the risk assessment result, and further obtaining risk early warning information based on the risk assessment result, the use of models for data processing avoids the subjectivity of human processing. The comprehensive consideration of hazard risk and posture risk enhances the accuracy and reliability of risk assessment. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is an application environment diagram of the user operation risk warning method in one embodiment;

[0057] Figure 2 This is a flowchart illustrating a user job risk warning method in one embodiment;

[0058] Figure 3 This is a flowchart illustrating the process of obtaining risk assessment results in one embodiment;

[0059] Figure 4 This is a flowchart illustrating the process of generating risk warning information in another embodiment;

[0060] Figure 5 This is a flowchart illustrating a user operation risk warning method in another embodiment;

[0061] Figure 6 This is a schematic diagram of the structure of a power knowledge parsing tree in one embodiment;

[0062] Figure 7 This is a structural block diagram of a user operation risk warning device in one embodiment;

[0063] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] The user operation risk warning method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Server 104 obtains physiological signal data and work data of the user to be judged from terminal 102. Then, it inputs the physiological signal data into a pre-built hazard risk assessment model to obtain the hazard risk assessment result for the user to be judged, and inputs the work data into a pre-built posture risk assessment model to obtain the posture risk assessment result for the user to be judged. Based on the hazard risk assessment result and the posture risk assessment result, it obtains the risk judgment result for the user to be judged. Finally, based on the risk judgment result, it obtains the user's work risk warning information for the user to be judged and returns it to the user's terminal for user work risk warning. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Headset devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0066] In one exemplary embodiment, such as Figure 2 As shown, a user operation risk early warning method is provided, which is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S201 to S204. Wherein:

[0067] Step S201: Obtain physiological signal data of the user to be identified, and obtain the work data of the user to be identified.

[0068] Step S202: Input physiological signal data into a pre-built hazard risk assessment model to obtain the hazard risk assessment result of the user to be judged, and input work data into a pre-built posture risk assessment model to obtain the posture risk assessment result of the user to be judged.

[0069] Physiological signal data can be understood as measurable information generated by the internal or external physiological activities of an organism, such as a series of time-series data such as electrocardiogram, electroencephalogram, electromyogram, body temperature, pulse, and respiratory rate; work data can be understood as measurable information that reflects the user's working status in the current work scenario, including various types of measurable information.

[0070] Among them, the hazard risk assessment model disclosed in this application is not limited to a time-series network, which can be understood as a network model specifically used for processing time-series data; the hazard risk assessment result can be understood as the degree of risk of a user contracting an acute illness; the posture risk assessment model disclosed in the application is not limited to a multimodal neural network, which can be understood as a network model that comprehensively considers different types of measurable information; the posture risk assessment result can be understood as the assessment result of whether the user's current posture in the current working scenario will bring safety risks.

[0071] For example, server 104 obtains physiological signal data and work data of the user to be judged from terminal 102 via the network. It inputs the physiological signal data into a pre-built hazard risk assessment model to obtain the hazard risk assessment result for the user to be judged, and inputs the work data into a pre-built posture risk assessment model to obtain the posture risk assessment result for the user to be judged. By introducing a risk assessment model to perform risk assessment on the obtained physiological signal data and work data, the objectivity of the risk assessment results is improved, and a data foundation is laid for subsequently obtaining risk judgment results.

[0072] Step S203: Based on the hazard risk assessment results and the posture risk assessment results, obtain the risk assessment results for the user to be assessed.

[0073] Step S204: Based on the risk assessment results, obtain the user operation risk warning information of the user to be assessed, and return it to the terminal of the user to be assessed to provide the user operation risk warning.

[0074] Optionally, server 104 obtains preset weight information for the hazard risk assessment results and posture risk assessment results, and performs a weighted summation of the hazard risk assessment results and posture risk assessment results based on the corresponding weight information to obtain the risk assessment result for the user to be assessed. Further, based on the risk assessment result, it determines whether to generate user operation risk warning information. If generation is determined, the user operation risk warning information for the user to be assessed is obtained based on the previously acquired physiological signal data and operation data of the user to be assessed, and returned to the user's terminal for user operation risk warning. By obtaining the risk assessment result through weighted summation of the hazard risk assessment results and posture risk results, the accuracy of the risk assessment result is improved. Furthermore, by obtaining the corresponding user operation risk warning information based on physiological signal data and operation data under preset conditions, the adaptability of the warning information is ensured, which is conducive to timely warning and ensuring the personal safety of users.

[0075] In the aforementioned user operation risk warning method, the server acquires the physiological signal data and operation data of the user to be assessed. The physiological signal data is then input into a pre-constructed hazard risk assessment model to obtain the hazard risk assessment result for the user. The operation data is input into a pre-constructed posture risk assessment model to obtain the posture risk assessment result for the user. Based on the hazard risk assessment result and the posture risk assessment result, a risk judgment result for the user is obtained. Finally, based on the risk judgment result, user operation risk warning information for the user is obtained and returned to the user's terminal for user operation risk warning. By using pre-constructed models to process the acquired data to obtain corresponding risk assessment results, and then determining the corresponding risk judgment result based on the risk assessment result, and further obtaining risk warning information based on the risk judgment result, this model-based data processing avoids the subjectivity of human processing. The comprehensive consideration of hazard risk and posture risk enhances the accuracy and reliability of risk judgment.

[0076] In one embodiment, acquiring physiological signal data of a user to be identified includes: acquiring raw physiological signal data of the user to be identified; the raw physiological signal data includes first raw physiological signal data and second raw physiological signal data; the first raw physiological signal data is disturbed raw physiological signal data; the second raw physiological signal data is undisturbed raw physiological signal data; multiplying the first raw physiological signal data with a pre-constructed random matrix to obtain transformed first raw physiological signal data; and obtaining physiological signal data based on the transformed first raw physiological signal data and second raw physiological signal data.

[0077] The random matrix can be understood as an m*n dimension matrix A, where m is the dimension of the first raw physiological signal data collected, and n is the dimension of the pure physiological signal part that needs to be separated.

[0078] For example, suppose the first raw physiological signal data is x, and the second raw physiological signal data is s. The collected first raw signal data x is multiplied by a constructed random matrix A to obtain the transformed first raw signal data y = Ax. Then, based on y and s, the physiological signal data is obtained. Using random matrix techniques to reduce the dimensionality of the first raw physiological signal data enhances the distinction between different signals—that is, pure physiological signal data and interfered physiological signal data—improving the effectiveness and usability of the raw physiological signal data, thereby enhancing the model output performance of the risk assessment model.

[0079] In one embodiment, the transformed first original physiological signal data includes third original physiological signal data, fourth original physiological signal data, and fifth original physiological signal data; wherein, the third original physiological signal data is original physiological signal data subject to electromechanical interference, the fourth original physiological signal data is original physiological signal data subject to motion artifact interference, and the fifth original physiological signal data is original physiological signal data undisturbed.

[0080] Based on the transformed first and second original physiological signal data, physiological signal data is obtained, including:

[0081] The third raw physiological signal data is filtered using a preset band-stop filter to obtain filtered third raw physiological signal data. The fourth raw physiological signal data is filtered using a preset low-pass filter to obtain filtered fourth raw physiological signal data. The second raw physiological signal data, the filtered third raw physiological signal data, the filtered fourth raw physiological signal data, and the fifth raw physiological signal data are summed to obtain physiological signal data to be processed. The physiological signal data to be processed is then denoised and normalized to obtain physiological signal data.

[0082] Optionally, the transformed first original physiological signal data y is decomposed into two parts: one part is the interfered part, namely the third and fourth original physiological signal data x', and the other part is the pure physiological signal part, namely the fifth original physiological signal data s'. Then y = x' + s'. The interfered part x' includes x1 and x2, where x1 represents the part affected by electromechanical interference, namely the third original physiological signal data, and x2 represents the part affected by motion artifacts, namely the fourth original physiological signal data. A band-stop filter is used to separate the part affected by electromechanical interference x1 to obtain x1', and a low-pass filter is used to separate the part affected by motion artifacts x2 to obtain x2'. x1' and x2' are summed to obtain the physiological signal data x'' = x1' + x2' after removing the interference.

[0083] The interference-removed portion x1'' and the purified physiological signal portion s' are synthesized to obtain the final interference-removed physiological signal data s'' = x'' + s', resulting in the physiological signal data to be processed, s + s''. This s + s'' data is then preprocessed, including denoising and normalization, to format it into a format suitable for input to the time-series network model, i.e., the physiological signal data. By removing interference from the disturbed physiological signal data and preprocessing the resulting data, the effectiveness and usability of the physiological signal data are further improved, thereby enhancing the output performance of the risk assessment model.

[0084] In one embodiment, the job data includes job video data and acceleration data;

[0085] Obtain the job data of the user to be judged, including:

[0086] The process involves downsampling, normalizing, and denoising the work video data to obtain processed work video data, and denoising and normalizing the acceleration data to obtain processed acceleration data. Based on the processed work video data, corresponding work video feature vectors are obtained, and based on the processed acceleration data, corresponding acceleration feature vectors are obtained. A first weight corresponding to the work video feature vector and a second weight corresponding to the acceleration feature vector are obtained. Based on the first and second weights, the work video feature vector and the acceleration feature vector are weighted and summed to obtain the work data feature vector of the user to be judged.

[0087] Inputting the operational data into a pre-built attitude risk assessment model yields the attitude risk assessment results for the user to be assessed, including:

[0088] The operation data feature vector is input into a pre-built posture risk assessment model to obtain a higher-order feature vector corresponding to the operation data feature vector, and the posture risk assessment result of the user to be judged is obtained based on the higher-order feature vector; the higher-order feature vector is used to distinguish different posture information of the user to be judged.

[0089] Among them, work video data can be understood as video content recording work scenes, processes, or activities; acceleration data can be understood as the change in velocity per unit time, which is expressed as the speed and direction of change, and is used to represent the user's current motion state and information about the possible next action; higher-order feature vectors can be understood as more abstract and complex feature information extracted from the original data, and feature vectors that can better distinguish different posture information of the user; the first weight can be understood as the influence and importance of the work video feature vector; the second weight can be understood as the influence and importance of the acceleration feature vector.

[0090] For example, server 104 performs downsampling, normalization, and denoising on the work video data to obtain processed work video data, and performs denoising and normalization on the acceleration data to obtain processed acceleration data. It then uses a convolutional neural network to extract features from the processed work video data to obtain corresponding work video feature vectors, and uses frequency domain analysis to extract features from the processed acceleration data to obtain corresponding acceleration feature vectors. Next, it obtains the first weight corresponding to the work video feature vector and the second weight corresponding to the acceleration feature vector. Based on the first and second weights, it performs a weighted sum of the work video feature vector and the acceleration feature vector to obtain the work data feature vector of the user to be judged.

[0091] Taking the attitude risk assessment model as a multimodal neural network as an example, the server 104 inputs the feature vector of the operation data into the multimodal neural network, uses the hidden layer of the multimodal neural network to extract the high-order feature vector in the feature vector of the operation data, and then the output layer of the multimodal neural network performs attitude classification prediction on the high-order feature vector and outputs the corresponding attitude risk assessment result.

[0092] By preprocessing the operational data to be input into the attitude risk assessment model as described above, and by using different data processing methods for different operational data, the effectiveness and usability of various types of operational data are greatly guaranteed, thereby improving the output effect of the attitude risk assessment model.

[0093] In one exemplary embodiment, such as Figure 3 As shown, based on the hazard risk assessment results and the posture risk assessment results, the risk assessment results for the user to be assessed are obtained, including steps S301 to S302. Wherein:

[0094] Step S301: Obtain the third weight corresponding to the hazard risk assessment result and the fourth weight corresponding to the attitude risk assessment result.

[0095] Step S302: Using the third and fourth weights, the hazard risk assessment results and posture risk assessment results are weighted to obtain the risk assessment results for the user to be judged.

[0096] The third weight can be understood as the weight set by experts in the field based on the degree of influence of historical hidden danger risk assessment results on the operational risk judgment results. The fourth weight can be understood as the weight set by experts in the field based on historical posture risk assessment results on the operational risk judgment results. The setting of the above weights takes into account multiple factors.

[0097] Optionally, server 104 obtains the third weight corresponding to the hazard risk assessment result and the fourth weight corresponding to the attitude risk assessment result from the data storage system. Using the third and fourth weights, it performs weighted processing on the hazard risk assessment result and the attitude risk assessment result to obtain the risk assessment result for the user to be assessed. By comprehensively considering the hazard risk assessment result and the attitude risk assessment result, the accuracy and objectivity of the risk assessment result are improved.

[0098] In one embodiment, such as Figure 4 As shown, the risk assessment result is represented by a risk value; based on the risk assessment result, user operation risk warning information for the user to be assessed is obtained, including steps S401 to S403, wherein:

[0099] Step S401: If the risk value is greater than the preset risk value threshold, determine the personnel status information of the user to be judged based on physiological signal data and work data.

[0100] Among them, status information can be understood as the situation information of users in different work environments or corresponding risk environments, including the user's own physiological information and corresponding work status information.

[0101] For example, if the server 104 determines that the risk value representing the risk judgment result is greater than the preset risk data threshold, it determines to initiate a risk warning. Furthermore, it determines the personnel status information of the user to be judged based on physiological signal data and work data, laying the data foundation for the subsequent generation of user work risk warning information.

[0102] Step S402: Determine the corresponding work order content and on-site operation risk information based on personnel status information, and obtain the corresponding safety warning information and countermeasure information according to the work order content and on-site operation risk information.

[0103] Step S403: Generate user operation risk warning information based on safety warning information and response measures information.

[0104] The work permit can be understood as basic work information, including work tasks, work location, work time, and personnel. On-site work risk information can be understood as the assessment and recording of potential hazards and risks when working in a specific work environment, including electrical shock, working height, and equipment failure. Safety warning information can be understood as reminders to workers to pay attention to potential risks during task execution, such as reminders on the operation of special equipment and the use of materials. Countermeasure information can be understood as information on ensuring a safe environment at the work site, such as whether fire-fighting facilities are complete and whether the work area is clearly marked.

[0105] Optionally, the personnel status information corresponds to the work order content and on-site operation risk information. Server 104 determines the corresponding work order content and on-site operation risk information based on the personnel status information, and obtains corresponding safety warning information and countermeasure information according to the work order content and on-site operation risk information. Finally, the safety warning information and countermeasure information are combined to generate user operation risk warning information. Generating user operation risks that match the user to be assessed based on the personnel status information helps protect the personal safety of the user to be assessed.

[0106] In one exemplary embodiment, such as Figure 5 As shown, a specific embodiment of a user operation risk warning method is provided, including steps S501 to S507, wherein:

[0107] Step S501a: Obtain the raw physiological signal data of the user to be identified:

[0108] 1. Workers wear sensors or wearable devices to collect physiological signal data in real time, forming a time series. The data includes heart rate, blood pressure, and body temperature, represented as {HR, BP, T}, where t represents a time point, HR represents heart rate, BP represents blood pressure, and T represents body temperature.

[0109] 2. Preprocess the collected physiological signal data, including denoising and normalization, and organize the data into a format suitable for input to the time series network model.

[0110] Step S502a: The raw physiological signal data is processed using random matrix techniques to obtain the processed raw physiological signal data.

[0111] Specifically, the process of removing electromechanical interference and motion artifact interference from the physiological signals of the workers using random matrix technology is as follows:

[0112] 1. Assume the collected interfered signal is x, and the actual physiological signal is s;

[0113] 2. Construct a random matrix A, which is an m×n dimension matrix that matches the collected physiological signal data, where m is the dimension of the collected signal data and n is the dimension of the pure physiological signal part to be separated.

[0114] 3. Multiply the collected disturbed signal x with the constructed random matrix A to obtain the transformed signal data y=Ax;

[0115] 4. Decompose the transformed signal data y into two parts: one part is the disturbed part x', and the other part is the pure physiological signal part s'. Then y = x' + s'. The disturbed part x' includes x1 and x2, where x1 represents the part affected by electromechanical interference and x2 represents the part affected by motion artifacts. By using filtering to separate the electromechanical interference part x1 and the motion artifact interference part x2, the physiological signal x'' with the interference removed is obtained.

[0116] 5. The interference-free part x'' and the pure physiological signal part s' are synthesized to obtain the final physiological signal s'' = x'' + s' after removing electromechanical interference.

[0117] Step S503a: The raw physiological signal data is processed using a filter to obtain physiological signal data:

[0118] Specifically, step S24, which involves separating the electromechanical interference-affected portion x1 and the motion artifact interference-affected portion x2 using filtering to obtain the physiological signal x'' with the interference removed, specifically includes:

[0119] A band-stop filter is used to separate the electromechanical interference-affected part x1 to obtain x1', and a low-pass filter is used to separate the motion artifact interference-affected part x2 to obtain x2'.

[0120] The x1' and x2' are combined to obtain the interference-removed part x'', where x'' = x1' + x2'.

[0121] Step S504a: Input the physiological signal data into the time series network to obtain the risk assessment results for the user to be assessed.

[0122] 1. Using a time series network model, potential acute disease risks are identified by learning the patterns and characteristics in time series data. These potential acute disease risks include A, B, and C.

[0123] I_disease = f(BP_t,T_t,HR_t,H,M)

[0124] Where I_disease represents the acute disease risk assessment result, f represents the acute disease risk assessment function, BP_t represents blood pressure, T_t represents body temperature, HR_t represents heart rate, H represents medical history, and M represents medication status.

[0125] Step S501b: Obtain the work data of the user to be identified; the work data includes work video data and acceleration data.

[0126] Step S502b: Perform data preprocessing on the working video data and acceleration data, and obtain the working video feature vector corresponding to the preprocessed working video data and the acceleration feature vector corresponding to the preprocessed acceleration data.

[0127] Step S503b: Based on the first weight corresponding to the working video feature vector and the second weight corresponding to the acceleration feature vector, the working video feature vector and the acceleration feature vector are weighted and summed to obtain the working data feature vector.

[0128] Step S504b: Input the task feature vector into the multimodal neural network to obtain the posture risk judgment result of the user to be judged.

[0129] 1. Utilize the hidden layers of a multimodal neural network to extract high-order features from the input data;

[0130] 2. Utilize the output layer of a multimodal neural network to perform pose classification prediction on high-order features in the input data and output risk assessment results.

[0131] I_posture = g(S,F,A)

[0132] Where I_posture represents the evaluation result of the worker's posture, g represents the worker's posture evaluation function, S represents posture stability, F represents movement frequency, and A represents movement amplitude;

[0133] Step S505: Obtain the third weight corresponding to the hazard risk assessment result, and obtain the fourth weight corresponding to the attitude risk assessment result.

[0134] Based on expert experience and domain knowledge, the weight of acute disease risk is determined as w_disease and the weight of worker posture is determined as w_posture;

[0135] Step S506: Using the third weight and the fourth weight, the hazard risk assessment result and the posture risk assessment result are weighted to obtain the risk assessment result for the user to be judged.

[0136] Risk = w_disease*I_disease + w_posture*I_posture

[0137] Risk represents the overall risk assessment results.

[0138] Step S507: If the risk value represented by the risk judgment result is greater than the preset risk value threshold, combine physiological signal data, operation data and preset power knowledge safety parsing tree to obtain user operation risk warning information, and return it to the terminal of the user to be judged to give user operation risk warning.

[0139] Electricity knowledge safety analysis tree such as Figure 5 As shown, see Figure 5 Step S507 specifically includes:

[0140] The work order includes the work task, work location, work time, and personnel. The on-site work risks include electrical shock and working height. The personnel status information includes health status and safety early warning measures for each on-site work risk to construct a power safety knowledge analysis tree.

[0141] For example, a work order might include the work task, and corresponding measures: ensuring staff clearly understand the specific requirements and steps of the work task, as well as the corresponding safe operating procedures. Safety warnings: reminding staff of potential risks during task execution, such as the operation of special equipment and the use of materials.

[0142] Work location and response measures: Ensure a safe environment at the work location, such as the completeness of fire-fighting facilities and clear signage of the work area. Safety warnings: Remind workers to be aware of potential safety hazards at the work location, such as slippery ground, high temperature and high pressure areas, etc.

[0143] Work hours and corresponding measures: Work hours should be arranged reasonably to avoid fatigue and overtime work. Safety warnings: Remind workers to be aware of the physical and mental stress that may result from prolonged work.

[0144] On-site operational risks include electric shock. Countermeasures include using insulated tools and wearing insulated gloves to ensure safe operation. Safety warnings include reminding workers to be aware of safe distances around high-voltage equipment and to adhere to operating procedures.

[0145] Equipment malfunction and corresponding measures: Regularly check equipment status and promptly maintain and repair any problematic equipment. Safety warnings: Remind staff to pay attention to abnormal sounds, vibrations, and other signs during equipment operation.

[0146] Working height and corresponding countermeasures: Wear safety belts and use appropriate climbing tools to ensure the personal safety of workers. Safety warning: Remind workers of the potential risk of falls while working at heights.

[0147] Compared with the prior art, this application has the following advantages:

[0148] 1. The introduction of models avoids the subjectivity of risk judgment based on experience, and enhances the objectivity of risk assessment results.

[0149] 2. By comprehensively considering the results of hidden danger risk assessment and attitude risk assessment, the accuracy of the final risk assessment results is enhanced.

[0150] 3. Based on the risk assessment results, determine whether to initiate a risk warning, and determine the corresponding personnel status information based on physiological signal data and work data. Based on the personnel status information, determine the corresponding safety warning information and response measures information. Combine the above safety warning information and response measures information to generate corresponding user work risk warning information, ensuring the availability of the generated warning information, which helps users stay away from or deal with potential risks and protects the personal safety of users.

[0151] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0152] Based on the same inventive concept, this application also provides a user operation risk warning device for implementing the user operation risk warning method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more user operation risk warning device embodiments provided below can be found in the limitations of the user operation risk warning method described above, and will not be repeated here.

[0153] In one exemplary embodiment, such as Figure 7 As shown, a user operation risk early warning device is provided, including: a data acquisition module 701, an evaluation result acquisition module 702, a judgment result determination module 703, and an early warning information determination module 703, wherein:

[0154] The data acquisition module 701 is used to acquire physiological signal data of the user to be judged and to acquire the work data of the user to be judged;

[0155] The assessment result acquisition module 702 is used to input physiological signal data into a pre-built hazard risk assessment model to obtain the hazard risk assessment result of the user to be judged, and to input work data into a pre-built posture risk assessment model to obtain the posture risk assessment result of the user to be judged;

[0156] The judgment result determination module 703 is used to obtain the risk judgment result of the user to be judged based on the hidden danger risk assessment result and the posture risk assessment result;

[0157] The early warning information determination module 704 is used to obtain user operation risk early warning information for the user to be judged based on the risk judgment result, and return it to the terminal of the user to be judged for user operation risk early warning.

[0158] In one embodiment, the data acquisition module 701 further includes:

[0159] The acquisition submodule is used to acquire the original physiological signal data of the user to be identified; the original physiological signal data includes first original physiological signal data and second original physiological signal data; the first original physiological signal data is the original physiological signal data that has been interfered with; the second original physiological signal data is the original physiological signal data that has not been interfered with.

[0160] The multiplication submodule is used to multiply the first original physiological signal data and a pre-constructed random matrix to obtain the transformed first original physiological signal data.

[0161] The physiological signal data acquisition submodule is used to obtain physiological signal data based on the transformed first and second original physiological signal data.

[0162] In one embodiment, the transformed first original physiological signal data includes third original physiological signal data, fourth original physiological signal data, and fifth original physiological signal data; wherein, the third original physiological signal data is original physiological signal data subject to electromechanical interference, the fourth original physiological signal data is original physiological signal data subject to motion artifact interference, and the fifth original physiological signal data is original physiological signal data undisturbed.

[0163] The physiological signal data acquisition submodule is also used to filter the third raw physiological signal data using a preset band-stop filter to obtain filtered third raw physiological signal data, and to filter the fourth raw physiological signal data using a preset low-pass filter to obtain filtered fourth raw physiological signal data; to sum the second raw physiological signal data, the filtered third raw physiological signal data, the filtered fourth raw physiological signal data, and the fifth raw physiological signal data to obtain physiological signal data to be processed; and to perform denoising and normalization processing on the physiological signal data to be processed to obtain physiological signal data.

[0164] In an exemplary embodiment, the job data includes job video data and acceleration data; the data acquisition module 701 is further configured to perform downsampling, normalization, and denoising processing on the job video data to obtain processed job video data, and to perform denoising and normalization processing on the acceleration data to obtain processed acceleration data; to obtain a corresponding job video feature vector based on the processed job video data, and to obtain a corresponding acceleration feature vector based on the processed acceleration data; to obtain a first weight corresponding to the job video feature vector, and to obtain a second weight corresponding to the acceleration feature vector; and to perform a weighted summation of the job video feature vector and the acceleration feature vector based on the first weight and the second weight to obtain the job data feature vector of the user to be identified.

[0165] The evaluation result acquisition module 702 is also used to input the operation data feature vector into the pre-built posture risk assessment model to obtain the higher-order feature vector corresponding to the operation data feature vector, and obtain the posture risk assessment result of the user to be judged based on the higher-order feature vector; the higher-order feature vector is used to distinguish the different posture information of the user to be judged.

[0166] In one embodiment, the discrimination result determination module 703 is further configured to obtain the third weight corresponding to the hidden danger risk assessment result and the fourth weight corresponding to the attitude risk assessment result; and to use the third weight and the fourth weight to perform weighted processing on the hidden danger risk assessment result and the attitude risk assessment result to obtain the risk discrimination result of the user to be judged.

[0167] In one embodiment, the risk assessment result is represented by a risk value; the early warning information determination module 704 is further configured to determine the personnel status information of the user to be assessed based on physiological signal data and work data when the risk value is greater than a preset risk value threshold; determine the corresponding work order content and on-site work risk information based on the personnel status information, and obtain the corresponding safety early warning information and countermeasure information based on the work order content and on-site work risk information; and generate user work risk early warning information based on the safety early warning information and countermeasure information.

[0168] Each module in the aforementioned user operation risk early warning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0169] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores physiological signal data and operational data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a user operational risk warning method.

[0170] Technicians can understand. Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0171] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the user operation risk warning method of the above embodiment.

[0172] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the user job risk warning method of the above embodiment.

[0173] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the user job risk warning method of the above embodiment.

[0174] 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, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0175] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0176] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0177] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A user operation risk early warning method, characterized in that, The method includes: Obtain the raw physiological signal data of the user to be identified; the raw physiological signal data includes first raw physiological signal data and second raw physiological signal data; the first raw physiological signal data is disturbed raw physiological signal data; the second raw physiological signal data is undisturbed raw physiological signal data; The first original physiological signal data and a pre-constructed random matrix are multiplied to obtain the transformed first original physiological signal data; the transformed first original physiological signal data includes third original physiological signal data, fourth original physiological signal data and fifth original physiological signal data; wherein, the third original physiological signal data is original physiological signal data subject to electromechanical interference, the fourth original physiological signal data is original physiological signal data subject to motion artifact interference, and the fifth original physiological signal data is original physiological signal data unaffected by interference; The third raw physiological signal data is filtered using a preset band-stop filter to obtain filtered third raw physiological signal data, and the fourth raw physiological signal data is filtered using a preset low-pass filter to obtain filtered fourth raw physiological signal data. The second raw physiological signal data, the filtered third raw physiological signal data, the filtered fourth raw physiological signal data, and the fifth raw physiological signal data are summed to obtain physiological signal data to be processed. The physiological signal data to be processed is then denoised and normalized to obtain the physiological signal data of the user to be identified, and the user's work data is acquired. The physiological signal data is input into a pre-built hazard risk assessment model to obtain the hazard risk assessment result of the user to be judged, and the operation data is input into a pre-built posture risk assessment model to obtain the posture risk assessment result of the user to be judged. Based on the hazard risk assessment results and the posture risk assessment results, the risk assessment results for the user to be assessed are obtained; Based on the risk assessment results, user operation risk warning information for the user to be assessed is obtained and returned to the terminal of the user to be assessed for user operation risk warning.

2. The method according to claim 1, characterized in that, The operational data includes operational video data and acceleration data; The step of obtaining the job data of the user to be identified includes: The working video data is downsampled, normalized, and denoised to obtain processed working video data; the acceleration data is denoised and normalized to obtain processed acceleration data. Based on the processed working video data, obtain the corresponding working video feature vector, and based on the processed acceleration data, obtain the corresponding acceleration feature vector; Obtain the first weight corresponding to the working video feature vector, and obtain the second weight corresponding to the acceleration feature vector; Based on the first weight and the second weight, the work video feature vector and the acceleration feature vector are weighted and summed to obtain the work data feature vector of the user to be judged. The operation data is input into a pre-built attitude risk assessment model to obtain the attitude risk assessment results for the user to be judged, including: The operation data feature vector is input into a pre-constructed posture risk assessment model to obtain a higher-order feature vector corresponding to the operation data feature vector, and the posture risk assessment result of the user to be judged is obtained based on the higher-order feature vector; the higher-order feature vector is used to distinguish the different posture information of the user to be judged.

3. The method according to claim 1, characterized in that, The step of obtaining the risk assessment result for the user to be assessed based on the hazard risk assessment result and the posture risk assessment result includes: Obtain the third weight corresponding to the hidden danger risk assessment result, and obtain the fourth weight corresponding to the attitude risk assessment result; Using the third and fourth weights, the risk assessment results and the attitude risk assessment results are weighted to obtain the risk assessment results for the user to be judged.

4. The method according to claim 1, characterized in that, The risk assessment result is represented by a risk value; The process of obtaining user operation risk warning information for the user to be assessed based on the risk assessment result includes: If the risk value is greater than a preset risk value threshold, the personnel status information of the user to be identified is determined based on the physiological signal data and the work data. Based on the personnel status information, the corresponding work order content and on-site operation risk information are determined, and corresponding safety warning information and countermeasure information are obtained according to the work order content and the on-site operation risk information. User operation risk warning information is generated based on the safety warning information and the countermeasure information.

5. A user operation risk early warning device, characterized in that, The device includes: The data acquisition module is used to acquire the raw physiological signal data of the user to be identified. The raw physiological signal data includes first raw physiological signal data and second raw physiological signal data. The first raw physiological signal data is disturbed raw physiological signal data; the second raw physiological signal data is undisturbed raw physiological signal data. The first raw physiological signal data is multiplied by a pre-constructed random matrix to obtain transformed first raw physiological signal data. The transformed first raw physiological signal data includes third, fourth, and fifth raw physiological signal data. The third raw physiological signal data is subject to electromechanical interference, and the fourth raw physiological signal data is subject to motion artifact interference. The process involves: first, obtaining raw physiological signal data; second, obtaining raw physiological signal data; and third, obtaining raw physiological signal data undisturbed by interference; third, obtaining raw physiological signal data filtered using a preset band-stop filter; fourth, obtaining raw physiological signal data filtered using a preset low-pass filter; summing the raw physiological signal data, the filtered raw physiological signal data, the filtered raw physiological signal data, and the raw physiological signal data, to obtain physiological signal data to be processed; and finally, denoising and normalizing the physiological signal data to be processed to obtain the physiological signal data of the user to be identified, and acquiring the user's work data. The assessment result acquisition module is used to input the physiological signal data into a pre-built hazard risk assessment model to obtain the hazard risk assessment result of the user to be judged, and to input the operation data into a pre-built posture risk assessment model to obtain the posture risk assessment result of the user to be judged; The judgment result determination module is used to obtain the risk judgment result of the user to be judged based on the hidden danger risk assessment result and the posture risk assessment result; The early warning information determination module is used to obtain user operation risk early warning information of the user to be judged based on the risk judgment result, and return it to the terminal of the user to be judged for user operation risk early warning.

6. The apparatus according to claim 5, characterized in that, The operational data includes operational video data and acceleration data, and the device further includes: The data acquisition module is further configured to perform downsampling, normalization, and denoising on the work video data to obtain processed work video data, and to perform denoising and normalization on the acceleration data to obtain processed acceleration data; acquire corresponding work video feature vectors based on the processed work video data, and acquire corresponding acceleration feature vectors based on the processed acceleration data; acquire a first weight corresponding to the work video feature vectors, and acquire a second weight corresponding to the acceleration feature vectors; and perform a weighted summation of the work video feature vectors and the acceleration feature vectors based on the first weights and the second weights to obtain the work data feature vector of the user to be identified. The evaluation result acquisition module is further configured to input the operation data feature vector into a pre-constructed posture risk assessment model to obtain a higher-order feature vector corresponding to the operation data feature vector, and obtain the posture risk assessment result of the user to be judged based on the higher-order feature vector; the higher-order feature vector is used to distinguish the different posture information of the user to be judged.

7. The apparatus according to claim 5, characterized in that, The device further includes: The discrimination result determination module is further configured to obtain the third weight corresponding to the hidden danger risk assessment result and the fourth weight corresponding to the posture risk assessment result; and to use the third weight and the fourth weight to perform weighted processing on the hidden danger risk assessment result and the posture risk assessment result to obtain the risk discrimination result of the user to be judged.

8. 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, it implements the steps of the method according to any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images