Mine lamp-based tunnel environment risk prediction method and device and computer equipment

By obtaining tunnel environment and operation data, identifying risk information and using risk prediction networks and knowledge graphs to generate response strategies, the problem of low accuracy of manual analysis is solved, and the accuracy and safety of tunnel operation risk prediction is improved.

CN118940876APending Publication Date: 2024-11-12SHENZHEN ZHONGFUNENG ELECTRIC EQUIPMENT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410695890.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-05-31
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the prior art, the accuracy of manual analysis is affected by manual experience and has poor timeliness, so it is impossible to accurately predict the risk situation of tunnel operations in the first time, resulting in a low accuracy of tunnel operations risk prediction.

Method used

By obtaining tunnel environmental data, tunnel operation data and construction personnel's operation process images, identifying environmental risk information and work content of risk hazard personnel, using risk prediction network and knowledge graph to generate tunnel risk information and response strategies, and to construction Personnel send risk warning messages.

Benefits of technology

Improve the accuracy and comprehensiveness of tunnel operation risk monitoring, avoid the inefficiency and low accuracy of manual detection, can identify the related information between multiple risks, improve the prediction accuracy and safety protection effect, and ensure the safety of construction workers. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940876A_ABST
    Figure CN118940876A_ABST
Patent Text Reader

Abstract

The invention provides a tunnel environment risk prediction method and device based on miner's lamps and computer equipment, which are applied to a tunnel operation safety management system, and the method comprises the steps: obtaining tunnel environment data, operation data of a tunnel operation instrument and operation process images of a plurality of constructors, and carrying out the prediction of the tunnel environment risk based on the data, environment risk information and the working type and the working process of each constructor are identified, so that the risk work content of each risk hidden danger person is identified; and on the basis of the environmental risk information and the risk work content of each risk hidden danger person, tunnel risk information is predicted through the risk knowledge graph, so that a tunnel risk coping strategy is generated. In the embodiment of the invention, the possibility of risk generation is avoided, so that the safety protection effect on tunnel constructors is improved, an intelligent risk safety protection system can predict the risk information of tunnel operation efficiently and precisely, and the risk prediction precision of the tunnel operation is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of information transmission and artificial intelligence technology, and in particular to a method, device and computer equipment for predicting tunnel environmental risks based on a mining lamp. Background Art

[0002] Tunnel operations are risky and difficult, and the safety management of tunnel operations is often the top priority of current tunnel operations. In order to improve the safety control effect of tunnel operations, the tunnel operation safety management system is used to detect the relevant environmental data of tunnel operations in real time, thereby providing safety protection for construction personnel. However, since the crisis occurs quickly when an emergency occurs in the tunnel, even if the construction personnel are reminded in time, they cannot leave the dangerous area in time, resulting in poor safety protection for the construction personnel. Therefore, how to predict the risks of tunnel operations is the current research summary.

[0003] Traditional technology is to manually analyze the detection data to predict whether there are risks in tunnel operations. However, since the accuracy of manual analysis is affected by manual experience and the timeliness of manual analysis is poor, it is often impossible to predict the risk of tunnel operations in the first place, resulting in low accuracy in risk prediction of tunnel operations. Summary of the invention

[0004] The main purpose of the present invention is to provide a tunnel environment risk prediction method, device and computer equipment based on a mining lamp, aiming to solve the problem in the prior art that the accuracy of manual analysis is affected by manual experience, and the timeliness of manual analysis is poor, and the risk situation of tunnel operations cannot be predicted in the first time.

[0005] To achieve the above object, the present invention provides a tunnel environmental risk prediction method based on a mining lamp, which is applied to a tunnel operation safety management system. The method comprises:

[0006] Acquire tunnel environment data, operation data of tunnel operation instruments, and operation process images of multiple construction workers, and identify environmental risk information based on the tunnel environment data and the operation data of the tunnel operation instruments;

[0007] Based on each of the operation process images, the work type of each construction worker and the work flow of each construction worker are identified, and based on the work type of each of the construction workers and the work flow of each of the construction workers, the risk work content of each risk potential personnel is identified through a risk prediction network;

[0008] Based on the environmental risk information and the risk work content of each of the risk potential personnel, predict the tunnel risk information through the risk knowledge map, and generate a tunnel risk response strategy based on the tunnel risk information;

[0009] The tunnel risk response strategy is sent to each of the construction personnel, and risk warning information corresponding to the risky work content is sent to each of the risk potential personnel.

[0010] Optionally, the identifying environmental risk information based on the tunnel environment data and the operation data of the tunnel operation instrument includes:

[0011] Identifying environmental factor parameters of various environmental factors corresponding to the tunnel environmental data, and identifying structural risk data of the tunnel operating instrument based on the operating data of the tunnel operating instrument;

[0012] Based on the environmental factor parameters of each of the environmental factors, querying the environmental factor range corresponding to the environmental factor parameters of each environmental factor and the environmental risk type corresponding to each environmental factor in the environmental risk database, and identifying the environmental risk degree corresponding to each environmental factor based on the environmental factor range corresponding to each of the environmental factors and the environmental risk type corresponding to each of the environmental factors;

[0013] The structural risk data of the tunnel operation instrument and the environmental risk degree corresponding to each environmental factor are used as environmental risk information.

[0014] Optionally, the identifying the work type of each construction worker and the work flow of each construction worker based on each of the operation process images includes:

[0015] Through the image edge recognition algorithm, the action image of each construction worker in each operation process image is identified, and each construction worker is marked to obtain the corresponding identification information of each construction worker;

[0016] The action images of the construction workers with the same personnel identification information are arranged according to the acquisition order of the operation process images to obtain the action sequence of each construction worker, and the action features of each construction worker are extracted through the feature extraction network;

[0017] In the workflow database, the workflow corresponding to each action feature is matched, and the work type corresponding to each workflow is used as the work type of each construction worker, and each workflow is used as the workflow of each construction worker.

[0018] Optionally, based on the work type of each construction worker and the work flow of each construction worker, identifying the risk work content of each risk potential personnel through a risk prediction network includes:

[0019] For each construction worker, based on the work flow of the construction worker, query the prohibited work content corresponding to the work prohibited items of the work flow, and calculate the similarity between each action feature in the personnel action sequence of the construction worker and the content feature corresponding to each prohibited work content;

[0020] Filter action features greater than the similarity threshold as risk action features, and use prohibited work content greater than the similarity threshold as target prohibited work content;

[0021] Adding the content label of the target prohibited work content corresponding to the risk action feature to each of the risk work features to obtain a first risk work feature, and treating the construction personnel with the first risk work feature as risk potential personnel;

[0022] Based on the job type of the risk potential personnel, the risk job type of the risk potential personnel is identified, and the risk job type of the risk potential personnel and the first risk job characteristic of the risk potential personnel are used as the risk job content of the risk potential personnel.

[0023] Optionally, the predicting of tunnel risk information based on the environmental risk information and the risk work content of each of the risk potential personnel through a risk knowledge graph includes:

[0024] Based on the structural risk data of the tunnel operation instrument and the environmental risk degree corresponding to each environmental factor, querying the target sub-risk map of the current tunnel operation in the risk knowledge map;

[0025] For each potential risk personnel, based on the risk work type of the potential risk personnel, in the target sub-risk map, the risk branch information is screened, and based on the risk work content of the potential risk personnel, the similarity between the risk feature of each branch node in the risk branch information and the risk work content is calculated by a similarity algorithm;

[0026] The risk feature with the maximum similarity is screened as the risk feature corresponding to the risk work content, and the risk features corresponding to the risk work content of all risk potential personnel are used as tunnel risk information.

[0027] Optionally, generating a tunnel risk response strategy based on the tunnel risk information includes:

[0028] Querying the risk level of each risk feature, and sorting the risk features according to the risk level to obtain a risk feature sequence;

[0029] In the risk response database, the risk handling strategy corresponding to each risk feature is queried, and the risk handling strategies corresponding to each risk feature are sorted according to the order of the risk feature sequence to obtain the tunnel risk response strategy.

[0030] Optionally, sending risk warning information corresponding to the risk work content to each of the risk potential personnel includes:

[0031] For each potential risk person, based on the prohibited work content corresponding to the first risk work characteristic of the potential risk person, risk warning information corresponding to the potential risk person is generated through a risk warning template;

[0032] The risk warning information is converted into notification data of multiple notification types, and the notification data of each notification type is sent to the risk potential personnel through the notification channel of each characteristic type.

[0033] In addition, to achieve the above-mentioned purpose, the present invention also provides a tunnel environment risk prediction device based on a miner's lamp, and the tunnel environment risk prediction device based on a miner's lamp is applied to a tunnel operation safety management system, and the device comprises:

[0034] An acquisition module, used to acquire tunnel environment data, operation data of tunnel operation instruments, and operation process images of multiple construction workers, and identify environmental risk information based on the tunnel environment data and the operation data of the tunnel operation instruments;

[0035] an identification module, for identifying the work type of each construction worker and the work flow of each construction worker based on each of the operation process images, and identifying the risk work content of each risk potential personnel through a risk prediction network based on the work type of each of the construction workers and the work flow of each of the construction workers;

[0036] A prediction module, for predicting tunnel risk information based on the environmental risk information and the risk work content of each risk potential personnel through a risk knowledge graph, and generating a tunnel risk response strategy based on the tunnel risk information;

[0037] The sending module is used to send the tunnel risk response strategy to each of the construction personnel, and send risk warning information corresponding to the risk work content to each of the risk potential personnel.

[0038] Optionally, the acquisition module is specifically used to:

[0039] Identifying environmental factor parameters of various environmental factors corresponding to the tunnel environmental data, and identifying structural risk data of the tunnel operating instrument based on the operating data of the tunnel operating instrument;

[0040] Based on the environmental factor parameters of each of the environmental factors, querying the environmental factor range corresponding to the environmental factor parameters of each environmental factor and the environmental risk type corresponding to each environmental factor in the environmental risk database, and identifying the environmental risk degree corresponding to each environmental factor based on the environmental factor range corresponding to each of the environmental factors and the environmental risk type corresponding to each of the environmental factors;

[0041] The structural risk data of the tunnel operation instrument and the environmental risk degree corresponding to each environmental factor are used as environmental risk information.

[0042] Optionally, the identification module is specifically used to:

[0043] Through the image edge recognition algorithm, the action image of each construction worker in each operation process image is identified, and each construction worker is marked to obtain the corresponding identification information of each construction worker;

[0044] The action images of the construction workers with the same personnel identification information are arranged according to the acquisition order of the operation process images to obtain the action sequence of each construction worker, and the action features of each construction worker are extracted through the feature extraction network;

[0045] In the workflow database, the workflow corresponding to each action feature is matched, and the work type corresponding to each workflow is used as the work type of each construction worker, and each workflow is used as the workflow of each construction worker.

[0046] Optionally, the identification module is specifically used to:

[0047] For each construction worker, based on the work flow of the construction worker, query the prohibited work content corresponding to the work prohibited items of the work flow, and calculate the similarity between each action feature in the personnel action sequence of the construction worker and the content feature corresponding to each prohibited work content;

[0048] Filter action features greater than the similarity threshold as risk action features, and use prohibited work content greater than the similarity threshold as target prohibited work content;

[0049] Adding the content label of the target prohibited work content corresponding to the risk action feature to each of the risk work features to obtain a first risk work feature, and treating the construction personnel with the first risk work feature as risk potential personnel;

[0050] Based on the job type of the risk potential personnel, the risk job type of the risk potential personnel is identified, and the risk job type of the risk potential personnel and the first risk job characteristic of the risk potential personnel are used as the risk job content of the risk potential personnel.

[0051] Optionally, the prediction module is specifically used to:

[0052] Based on the structural risk data of the tunnel operation instrument and the environmental risk degree corresponding to each environmental factor, querying the target sub-risk map of the current tunnel operation in the risk knowledge map;

[0053] For each potential risk personnel, based on the risk work type of the potential risk personnel, in the target sub-risk map, the risk branch information is screened, and based on the risk work content of the potential risk personnel, the similarity between the risk feature of each branch node in the risk branch information and the risk work content is calculated by a similarity algorithm;

[0054] The risk feature with the maximum similarity is screened as the risk feature corresponding to the risk work content, and the risk features corresponding to the risk work content of all risk potential personnel are used as tunnel risk information.

[0055] Optionally, the prediction module is specifically used to:

[0056] Querying the risk level of each risk feature, and sorting the risk features according to the risk level to obtain a risk feature sequence;

[0057] In the risk response database, the risk handling strategy corresponding to each risk feature is queried, and the risk handling strategies corresponding to each risk feature are sorted according to the order of the risk feature sequence to obtain the tunnel risk response strategy.

[0058] Optionally, the sending module is specifically used to:

[0059] For each potential risk person, based on the prohibited work content corresponding to the first risk work characteristic of the potential risk person, risk warning information corresponding to the potential risk person is generated through a risk warning template;

[0060] The risk warning information is converted into notification data of multiple notification types, and the notification data of each notification type is sent to the risk potential personnel through the notification channel of each characteristic type.

[0061] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0062] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0063] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0064] The present invention provides a tunnel environmental risk prediction method, device and computer equipment based on a mining lamp. The method is applied to a tunnel operation safety management system, and the method includes: obtaining tunnel environmental data, operating data of tunnel operation instruments, and operation process images of multiple construction personnel, and identifying environmental risk information based on the tunnel environmental data and the operation data of the tunnel operation instruments; based on each of the operation process images, identifying the work type of each construction personnel and the workflow of each construction personnel, and based on the work type of each construction personnel and the workflow of each construction personnel, identifying the risk work content of each risk potential personnel through a risk prediction network; based on the environmental risk information and the risk work content of each risk potential personnel, predicting tunnel risk information through a risk knowledge map, and generating a tunnel risk response strategy based on the tunnel risk information; sending the tunnel risk response strategy to each of the construction personnel, and sending risk warning information corresponding to the risk work content to each of the risk potential personnel. This scheme improves the accuracy and comprehensiveness of risk monitoring of tunnel operations by monitoring the risks of tunnel operations from three perspectives: tunnel environmental data, operating data of tunnel operation instruments, and image data corresponding to the operation process images of construction personnel. Then, by analyzing the environmental information corresponding to the tunnel environment data and the operating data of the tunnel operation instruments, and the risk prediction network, the risk prediction of the risk work content of the risk potential personnel is carried out on the operation process images of the construction personnel, so as to predict the tunnel risk information through the risk knowledge map, which not only avoids the inefficiency and low precision of manual detection and manual analysis, but also predicts the risk through the knowledge map, which can identify the correlation information between multiple risks and the implicit correlation information, thereby improving the accuracy and comprehensiveness of the predicted tunnel risk information. Finally, in order to avoid harm to the tunnel construction personnel, the tunnel risk response strategy is issued to prevent the occurrence of tunnel risks in time, and the risk warning is issued to each risk potential personnel to avoid the possibility of risk, thereby improving the safety protection effect of the tunnel construction personnel, so that the intelligent risk safety protection system can efficiently and accurately predict the risk information of tunnel operations, thereby improving the accuracy of risk prediction for tunnel operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0066] Figure 1 is a flow chart of a tunnel environment risk prediction method based on a mining lamp provided in an embodiment of the present invention;

[0067] Figure 2 It is a structural schematic diagram of a tunnel environment risk prediction device based on a mining lamp provided in an embodiment of the present invention;

[0068] Figure 3 An internal structure diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The tunnel environment risk prediction method based on a miner's lamp provided in an embodiment of the present invention is applied to a tunnel environment risk prediction system based on a miner's lamp. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" in the specification and claims of the present application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0070] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0071] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0072] The tunnel environment risk prediction method based on the mining lamp provided in the embodiment of the present application can be applied to the application environment of the tunnel operation safety management system. The method can be applied to the terminal, the server, or the system including the terminal and the server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. Among them, the terminal monitors the risk of tunnel operations from three angles: tunnel environment data, operation data of tunnel operation instruments, and image data corresponding to the operation process images of construction personnel, thereby improving the accuracy and comprehensiveness of risk monitoring of tunnel operations. Then, by analyzing the environmental information corresponding to the tunnel environment data and the operation data of the tunnel operation instruments, and the risk work content of the risk potential personnel who perform risk prediction on the operation process images of construction personnel through the risk prediction network, the risk information of the tunnel is predicted through the risk knowledge map, which not only avoids the inefficiency and low precision problems of manual detection and manual analysis, but also predicts risks through the knowledge map, and can identify the correlation information between multiple risks and implicit correlation information, thereby improving the accuracy and comprehensiveness of predicting tunnel risk information. Finally, in order to avoid harm to tunnel construction workers, tunnel risk response strategies are issued to promptly prevent the occurrence of tunnel risks, and risk warnings are given to personnel with potential risks to avoid the possibility of risks, thereby improving the safety protection effect on tunnel construction workers. The intelligent risk safety protection system can efficiently and accurately predict the risk information of tunnel operations, thereby improving the accuracy of risk prediction for tunnel operations.

[0073] In one embodiment, Figure 1 As shown, a tunnel environment risk prediction method based on a mining lamp is provided, and the method is applied to a terminal as an example for explanation, including the following steps:

[0074] Step S101, acquiring tunnel environment data, operation data of tunnel operation equipment, and operation process images of multiple construction workers, and identifying environmental risk information based on the tunnel environment data and operation data of tunnel operation equipment.

[0075] In this embodiment, the terminal collects the environmental data of the tunnel through equipment equipped with sensor devices such as environmental detection equipment set in the tunnel, head-mounted mining lamp equipment set on the head of the construction individual, and combined with the sensor devices arranged in the tunnel construction area. Among them, the environmental detection equipment includes air content detection equipment, air humidity detection equipment, and temperature detection equipment, etc., wherein the environmental data collected by the air content detection equipment includes air element content, air dust concentration content, etc., the environmental data collected by the air humidity detection equipment is air humidity data, and the environmental data collected by the temperature detection equipment is tunnel environmental temperature, etc. Then, the terminal collects the operation data of the tunnel operation instrument through the instrument detection equipment set in the tunnel operation instrument, wherein the operation data is used to characterize the operation state of the tunnel operation instrument and the structural state of the tunnel operation instrument, and the tunnel operation instrument is an instrument for tunnel mining, transportation, support, lighting, etc. After that, the terminal collects the operation process images of different construction personnel in the tunnel in the working state through the camera equipment set at various positions in the tunnel. Finally, the terminal identifies environmental risk information based on the tunnel environment data and the operation data of the tunnel operation instrument. The environmental risk information is the risk information of the risks in the current tunnel environment, and includes the structural risk data of the tunnel operation equipment and the environmental risk degree corresponding to each environmental factor. The specific identification process will be described in detail later.

[0076] Step S102, based on each operation process image, identify the work type of each construction worker and the work flow of each construction worker, and based on the work type of each construction worker and the work flow of each construction worker, identify the risk work content of each risk potential personnel through the risk prediction network.

[0077] In this embodiment, the terminal identifies the work type and workflow of each construction worker based on each operation process image, and identifies the risk work content of each risk potential worker based on the work type and workflow of each construction worker through the risk prediction network. The risk prediction network is a neural network based on a combination of a convolutional neural network and a similarity algorithm, and the specific prediction process will be described in detail later.

[0078] Step S103, based on the environmental risk information and the risk work content of each risk potential personnel, the tunnel risk information is predicted through the risk knowledge map, and based on the tunnel risk information, a tunnel risk response strategy is generated.

[0079] In this embodiment, the terminal predicts tunnel risk information through a risk knowledge graph based on environmental risk information and the risk work content of each risk potential personnel, and generates a tunnel risk response strategy based on the tunnel risk information. Among them, the risk knowledge graph includes a plurality of sub-knowledge graphs corresponding to different environmental risk information, each sub-knowledge graph contains risk characteristics with different associated information, and the risk knowledge graph is a knowledge graph constructed by the personnel who have worked based on historical risk data, the Internet, and expert experience, the environmental risk information, the associated information between the environmental risk information, the types of risk work, the risk work content of each risk work type, and the associated information between the risk work contents. The risk knowledge graph is preset in the terminal.

[0080] Step S104, sending the tunnel risk response strategy to each construction worker, and sending risk warning information corresponding to the risk work content to each risk potential personnel.

[0081] In this embodiment, the terminal sends the tunnel risk response strategy to the control center and each construction personnel, and sends risk warning information corresponding to the risk work content to each risk potential personnel.

[0082] Based on the above scheme, the risk monitoring of tunnel operations is carried out from three perspectives: tunnel environment data, operation data of tunnel operation instruments, and image data corresponding to the operation process images of construction personnel, which improves the accuracy and comprehensiveness of risk monitoring of tunnel operations. Then, by analyzing the environmental information corresponding to the tunnel environment data and the operation data of tunnel operation instruments, and the risk work content of risk potential personnel through risk prediction of the operation process images of construction personnel through the risk prediction network, the risk information of tunnels is predicted through the risk knowledge map, which not only avoids the inefficiency and low precision of manual detection and manual analysis, but also predicts risks through the knowledge map, which can identify the correlation information and implicit correlation information between multiple risks, thereby improving the accuracy and comprehensiveness of predicting tunnel risk information. Finally, in order to avoid harm to tunnel construction personnel, tunnel risk response strategies are issued to prevent the occurrence of tunnel risks in time, and risk warnings are issued to various risk potential personnel to avoid the possibility of risk, thereby improving the safety protection effect of tunnel construction personnel, so that the intelligent risk safety protection system can efficiently and accurately predict the risk information of tunnel operations, thereby improving the accuracy of risk prediction of tunnel operations.

[0083] Optionally, environmental risk information is identified based on tunnel environmental data and operating data of tunnel operating instruments, including: identifying environmental factor parameters of each environmental factor corresponding to the tunnel environmental data, and identifying structural risk data of the tunnel operating instruments based on the operating data of the tunnel operating instruments; based on the environmental factor parameters of each environmental factor, querying the environmental factor range corresponding to the environmental factor parameters of each environmental factor and the environmental risk type corresponding to each environmental factor in an environmental risk database, and identifying the environmental risk degree corresponding to each environmental factor based on the environmental factor range corresponding to each environmental factor and the environmental risk type corresponding to each environmental factor; and using the structural risk data of the tunnel operating instruments and the environmental risk degree corresponding to each environmental factor as environmental risk information.

[0084] In this embodiment, the terminal identifies the environmental factor parameters of each environmental factor corresponding to the tunnel environmental data, and identifies the structural risk data of the tunnel operating instrument based on the operating data of the tunnel operating instrument. Specifically, the terminal divides the tunnel environmental data into environmental data corresponding to different environmental factors, and identifies the data value corresponding to each environmental data, such as the value of toxic gas content, the value of carbon dioxide content, the value of air dust concentration, the value of air humidity, and the value of tunnel temperature. Then, the terminal splits the operating data of the tunnel operating instrument into structural operating data of different operating structures, and identifies the data value corresponding to each structural operating data. After that, the terminal screens abnormal data values ​​as the structural risk data of the tunnel operating instrument. For example, the mining speed of the mining equipment, the mining amount per unit time, the vibration amplitude of the mining equipment, and the unit fuel consumption of the mining equipment, etc., wherein the terminal regards the data value greater than the normal data range as the abnormal data value.

[0085] Based on the environmental factor parameters of each environmental factor, the terminal queries the environmental factor range corresponding to the environmental factor parameters of each environmental factor and the environmental risk type corresponding to each environmental factor in the environmental risk database, and identifies the environmental risk degree corresponding to each environmental factor based on the environmental factor range corresponding to each environmental factor and the environmental risk type corresponding to each environmental factor. Specifically, each environmental risk degree corresponds to an environmental factor range, and the terminal determines the environmental risk degree corresponding to each environmental factor by identifying the environmental factor range corresponding to each environmental factor. Finally, the terminal uses the structural risk data of the tunnel operation instrument and the environmental risk degree corresponding to each environmental factor as environmental risk information.

[0086] Based on the above scheme, the accuracy and comprehensiveness of identifying environmental risk information are improved by comprehensively analyzing the environmental risk levels of various environmental factors and the structural risk data of tunnel operation instruments.

[0087] Optionally, based on each operation process image, the work type and workflow of each construction worker are identified, including: identifying the personnel action image of each construction worker in each operation process image through an image edge recognition algorithm, and performing personnel marking processing on each construction worker to obtain the personnel identification information corresponding to each construction worker; arranging the personnel action images of construction workers with the same personnel identification information in the order of acquisition of the operation process images to obtain the personnel action sequence of each construction worker, and extracting each action feature of each construction worker through a feature extraction network; matching the workflow corresponding to each action feature in the workflow database, and using the work type corresponding to each workflow as the work type of each construction worker, and using each workflow as the workflow of each construction worker.

[0088] In this embodiment, the terminal uses an image edge recognition algorithm to identify the action image of each construction worker in each operation process image, and performs personnel marking processing on each construction worker to obtain the personnel identification information corresponding to each construction worker. The image edge recognition algorithm can be, but is not limited to, each image-edge detection algorithm in Matlab.

[0089] Then, the terminal arranges the action images of the construction workers with the same personnel identification information according to the acquisition order of the operation process images to obtain the action sequence of each construction worker, and extracts the action features of each construction worker through the feature extraction network. The feature extraction network is an image feature extraction network, which can be, but is not limited to, a BP (Back Propagation) neural network, a Hopfiled neural network, or a LVQ neural network.

[0090] Finally, in the workflow database, the terminal matches the workflow corresponding to each action feature, and uses the work type corresponding to each workflow as the work type of each construction worker, and uses each workflow as the workflow of each construction worker. Among them, the work type is the work type corresponding to each business type in the tunnel operation, including tunnel transportation management work type, tunnel mining supervision work type, tunnel equipment monitoring work type, and mineral collection work type, etc.

[0091] The method of matching workflows is that the terminal queries the workflow action features corresponding to each workflow in the workflow database, and calculates the similarity between each workflow action feature and the action feature through a similarity recognition algorithm, and uses the workflow action features corresponding to the similarity greater than the similarity threshold as the target workflow action feature, and the terminal selects the workflow containing the most target workflow action features as the workflow corresponding to the action feature. The similarity algorithm can be, but is not limited to, a Mahalanobis distance algorithm, a Euclidean distance algorithm, and a cosine similarity algorithm.

[0092] Based on the above scheme, by extracting the action features of each construction worker and matching the workflow corresponding to each action feature, the accuracy of identifying the workflow corresponding to each action feature is improved.

[0093] Optionally, based on the work type of each construction worker and the workflow of each construction worker, the risk work content of each risk potential personnel is identified through a risk prediction network, including: for each construction worker, based on the workflow of the construction worker, querying the prohibited work content corresponding to the work prohibited items of the workflow, and calculating the similarity between each action feature in the construction worker's personnel action sequence and the content feature corresponding to each prohibited work content; screening action features greater than the similarity threshold as risk action features, and taking the prohibited work content greater than the similarity threshold as the target prohibited work content; adding the content label of the target prohibited work content corresponding to the risk action feature to each risk work feature to obtain a first risk work feature, and taking the construction worker containing the first risk work feature as a risk potential personnel; based on the work type of the risk potential personnel, identifying the risk work type of the risk potential personnel, and taking the risk work type of the risk potential personnel and the first risk work feature of the risk potential personnel as the risk work content of the risk potential personnel.

[0094] In this embodiment, the terminal queries the prohibited work content corresponding to the prohibited work items of the work process for each construction worker based on the work process of the construction worker, and calculates the similarity between each action feature in the personnel action sequence of the construction worker and the content feature corresponding to each prohibited work content. Among them, the prohibited work content is the safety prohibited operation items of each type of work. The construction worker presets the personnel operation action features corresponding to the safety prohibited operation items of each type of work in the terminal, and obtains the prohibited work content corresponding to the work prohibited items of each work process. Among them, the above similarity algorithm is the same as the similarity algorithm described above.

[0095] The terminal screens the action features greater than the similarity threshold as risk action features, and uses the prohibited work content greater than the similarity threshold as the target prohibited work content. Then, the terminal adds the content label of the target prohibited work content corresponding to the risk action feature to each risk work feature to obtain the first risk work feature, and uses the construction personnel containing the first risk work feature as the risk potential personnel; based on the work type of the risk potential personnel, the risk work type of the risk potential personnel is identified, and the risk work type of the risk potential personnel and the first risk work feature of the risk potential personnel are used as the risk work content of the risk potential personnel. Among them, each work type corresponds to multiple risk work types, and each risk work type corresponds to multiple prohibited work contents. The terminal obtains the risk work type of the risk potential personnel by identifying the risk work type that is both the target prohibited work content and the risk work type corresponding to the work type of the construction personnel.

[0096] Based on the above scheme, the risk features corresponding to the action features are identified through similarity recognition, thereby improving the accuracy of identifying risk features.

[0097] Optionally, based on environmental risk information and the risk work content of each risk potential personnel, tunnel risk information is predicted through a risk knowledge graph, including: based on the structural risk data of tunnel operation instruments and the environmental risk degree corresponding to each environmental factor, querying the target sub-risk graph of the current tunnel operation in the risk knowledge graph; for each risk potential personnel, based on the risk work type of the risk potential personnel, screening the risk branch information in the target sub-risk graph, and based on the risk work content of the risk potential personnel, calculating the similarity between the risk characteristics of each branch node in the risk branch information and the risk work content through a similarity algorithm; screening the risk characteristics with the maximum similarity as the risk characteristics corresponding to the risk work content, and taking the risk characteristics corresponding to the risk work content of all risk potential personnel as tunnel risk information.

[0098] In this embodiment, the terminal queries the target sub-risk map of the current tunnel operation in the risk knowledge map based on the structural risk data of the tunnel operation instrument and the environmental risk degree corresponding to each environmental factor. Each target sub-risk map corresponds to an environmental risk range, which includes the environmental risk degree range corresponding to each environmental factor and the data range corresponding to the structural risk data.

[0099] Then, for each risk potential personnel, the terminal selects the risk branch information in the target sub-risk map based on the risk work type of the risk potential personnel, and calculates the similarity between the risk characteristics of each branch node in the risk branch information and the risk work content based on the risk potential personnel's risk work content through a similarity algorithm. Finally, the terminal selects the risk characteristics with the maximum similarity as the risk characteristics corresponding to the risk work content, and uses the risk characteristics corresponding to the risk work content of all risk potential personnel as the tunnel risk information. Among them, each risk branch information corresponds to a risk work type.

[0100] Based on the above scheme, by identifying the structural risk data of tunnel operation instruments and the target sub-risk map corresponding to the environmental risk degree of each environmental factor, and based on the risk branch information corresponding to the risk work type of each risk-prone personnel, the risk characteristics corresponding to the risk work content of each risk-prone personnel are calculated, thereby improving the accuracy of determining tunnel risk information.

[0101] Optionally, a tunnel risk response strategy is generated based on the tunnel risk information, including: querying the risk level of each risk feature, and sorting the risk features according to the risk level to obtain a risk feature sequence; in the risk response database, querying the risk handling strategy corresponding to each risk feature, and sorting the risk handling strategies corresponding to each risk feature in the order of the risk feature sequence to obtain the tunnel risk response strategy.

[0102] In this embodiment, the terminal queries the risk level of each risk feature, and sorts each risk feature according to the risk level to obtain a risk feature sequence. Among them, the knowledge graph contains the risk level identifier corresponding to each risk feature, and the terminal obtains the risk level corresponding to each risk feature by querying the risk level identifier of each risk feature. In the risk response database, the terminal queries the risk handling strategy corresponding to each risk feature, and sorts the risk handling strategies corresponding to each risk feature in the order of the risk feature sequence to obtain the tunnel risk response strategy. Among them, each risk feature corresponds to a risk point, such as aging equipment and construction personnel still controlling the saturated operation of the equipment, excessive dust concentration in the air and construction personnel's operation is prone to sparks, etc.

[0103] Based on the above scheme, risks are handled according to risk levels, thereby improving the priority of handling high-risk risk features, thereby avoiding the problem of tunnel risk outbreaks caused by untimely handling of high-risk risk features.

[0104] Optionally, risk warning information corresponding to the risky work content is sent to each risk potential person, including: for each risk potential person, based on the prohibited work content corresponding to the first risk work characteristic of the risk potential person, generating risk warning information corresponding to the risk potential person through a risk warning template; converting the risk warning information into notification data of multiple notification types, and sending the notification data of each notification type to the risk potential person through the notification channel of each characteristic type.

[0105] In this embodiment, the terminal generates risk warning information corresponding to each risk potential personnel based on the prohibited work content corresponding to the first risk work feature of the risk potential personnel through the risk warning template. Finally, the terminal converts the risk warning information into notification data of multiple notification types, and sends the notification data of each notification type to the risk potential personnel through the notification channels of each feature type. The risk warning template is a template preset in the terminal by the construction personnel. The terminal obtains the risk warning information corresponding to the risk potential personnel by filling the prohibited matters corresponding to the prohibited work content and the risk information corresponding to the prohibited matters into the risk warning template.

[0106] Based on the above scheme, the risk warning information corresponding to each risk potential personnel is generated by filling in the template, which improves the efficiency of generating risk warning information. Thus, the efficiency of risk warning for risk potential personnel is improved.

[0107] 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.

[0108] Based on the same inventive concept, the embodiment of the present application also provides a tunnel environment risk prediction device based on a miner's lamp for implementing the tunnel environment risk prediction method based on a miner's lamp. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the tunnel environment risk prediction device based on a miner's lamp provided below can refer to the limitations of the tunnel environment risk prediction method based on a miner's lamp above, and will not be repeated here.

[0109] Further references Figure 2 , as a response to the above Figure 1 The present application provides an embodiment of a tunnel environment risk prediction device 200 based on a miner's lamp, and the tunnel environment risk prediction device based on a miner's lamp is applied to a tunnel dispatching system. The device includes an acquisition module 210, an identification module 220, a prediction module 230 and a sending module 240, wherein:

[0110] An acquisition module 210 is used to acquire tunnel environment data, operation data of tunnel operation instruments, and operation process images of multiple construction workers, and identify environmental risk information based on the tunnel environment data and the operation data of the tunnel operation instruments;

[0111] The identification module 220 is used to identify the work type of each construction worker and the work flow of each construction worker based on each of the operation process images, and identify the risk work content of each risk potential personnel through a risk prediction network based on the work type of each of the construction workers and the work flow of each of the construction workers;

[0112] A prediction module 230 is used to predict tunnel risk information based on the environmental risk information and the risk work content of each risk potential personnel through a risk knowledge graph, and generate a tunnel risk response strategy based on the tunnel risk information;

[0113] The sending module 240 is used to send the tunnel risk response strategy to each of the construction personnel, and send risk warning information corresponding to the risk work content to each of the risk potential personnel.

[0114] Optionally, the acquisition module 210 is specifically configured to:

[0115] Identifying environmental factor parameters of various environmental factors corresponding to the tunnel environmental data, and identifying structural risk data of the tunnel operating instrument based on the operating data of the tunnel operating instrument;

[0116] Based on the environmental factor parameters of each of the environmental factors, querying the environmental factor range corresponding to the environmental factor parameters of each environmental factor and the environmental risk type corresponding to each environmental factor in the environmental risk database, and identifying the environmental risk degree corresponding to each environmental factor based on the environmental factor range corresponding to each of the environmental factors and the environmental risk type corresponding to each of the environmental factors;

[0117] The structural risk data of the tunnel operation instrument and the environmental risk degree corresponding to each environmental factor are used as environmental risk information.

[0118] Optionally, the identification module 220 is specifically configured to:

[0119] Through the image edge recognition algorithm, the action image of each construction worker in each operation process image is identified, and each construction worker is marked to obtain the corresponding identification information of each construction worker;

[0120] The action images of the construction workers with the same personnel identification information are arranged according to the acquisition order of the operation process images to obtain the action sequence of each construction worker, and the action features of each construction worker are extracted through the feature extraction network;

[0121] In the workflow database, the workflow corresponding to each action feature is matched, and the work type corresponding to each workflow is used as the work type of each construction worker, and each workflow is used as the workflow of each construction worker.

[0122] Optionally, the identification module 220 is specifically configured to:

[0123] For each construction worker, based on the work flow of the construction worker, query the prohibited work content corresponding to the work prohibited items of the work flow, and calculate the similarity between each action feature in the personnel action sequence of the construction worker and the content feature corresponding to each prohibited work content;

[0124] Filter action features greater than the similarity threshold as risk action features, and use prohibited work content greater than the similarity threshold as target prohibited work content;

[0125] Adding the content label of the target prohibited work content corresponding to the risk action feature to each of the risk work features to obtain a first risk work feature, and treating the construction personnel with the first risk work feature as risk potential personnel;

[0126] Based on the job type of the risk potential personnel, the risk job type of the risk potential personnel is identified, and the risk job type of the risk potential personnel and the first risk job characteristic of the risk potential personnel are used as the risk job content of the risk potential personnel.

[0127] Optionally, the prediction module 230 is specifically configured to:

[0128] Based on the structural risk data of the tunnel operation instrument and the environmental risk degree corresponding to each environmental factor, querying the target sub-risk map of the current tunnel operation in the risk knowledge map;

[0129] For each potential risk personnel, based on the risk work type of the potential risk personnel, in the target sub-risk map, the risk branch information is screened, and based on the risk work content of the potential risk personnel, the similarity between the risk feature of each branch node in the risk branch information and the risk work content is calculated by a similarity algorithm;

[0130] The risk feature with the maximum similarity is screened as the risk feature corresponding to the risk work content, and the risk features corresponding to the risk work content of all risk potential personnel are used as tunnel risk information.

[0131] Optionally, the prediction module 230 is specifically configured to:

[0132] Querying the risk level of each risk feature, and sorting the risk features according to the risk level to obtain a risk feature sequence;

[0133] In the risk response database, the risk handling strategy corresponding to each risk feature is queried, and the risk handling strategies corresponding to each risk feature are sorted according to the order of the risk feature sequence to obtain the tunnel risk response strategy.

[0134] Optionally, the sending module 240 is specifically configured to:

[0135] For each potential risk person, based on the prohibited work content corresponding to the first risk work characteristic of the potential risk person, risk warning information corresponding to the potential risk person is generated through a risk warning template;

[0136] The risk warning information is converted into notification data of multiple notification types, and the notification data of each notification type is sent to the risk potential personnel through the notification channel of each characteristic type.

[0137] Each module in the above-mentioned tunnel environment risk prediction device based on mining lamp can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0138] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a tunnel environment risk prediction method based on a mining lamp is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0139] Those skilled in the art will understand that Figure 3 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.

[0140] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0141] 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 of any one of the methods in the first aspect are implemented.

[0142] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0143] 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.

[0144] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods 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 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), magnetoresistive 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, etc., but are not limited to this.

[0145] The technical features of the above embodiments may be arbitrarily combined. 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 specification.

[0146] 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 tunnel environment risk prediction method based on mining lamps, applied to tunnel operation safety management system, characterized in that: The method comprises: Acquire tunnel environment data, operation data of tunnel operation instruments, and operation process images of multiple construction workers, and identify environmental risk information based on the tunnel environment data and the operation data of the tunnel operation instruments; Based on each of the operation process images, the work type of each construction worker and the work flow of each construction worker are identified, and based on the work type of each of the construction workers and the work flow of each of the construction workers, the risk work content of each risk potential personnel is identified through a risk prediction network; Based on the environmental risk information and the risk work content of each of the risk potential personnel, predict the tunnel risk information through the risk knowledge map, and generate a tunnel risk response strategy based on the tunnel risk information; The tunnel risk response strategy is sent to each of the construction personnel, and risk warning information corresponding to the risky work content is sent to each of the risk potential personnel.

2. The method according to claim 1, characterized in that: The identifying of environmental risk information based on the tunnel environment data and the operation data of the tunnel operation instrument includes: Identifying environmental factor parameters of various environmental factors corresponding to the tunnel environmental data, and identifying structural risk data of the tunnel operating instrument based on the operating data of the tunnel operating instrument; Based on the environmental factor parameters of each of the environmental factors, querying the environmental factor range corresponding to the environmental factor parameters of each environmental factor and the environmental risk type corresponding to each environmental factor in the environmental risk database, and identifying the environmental risk degree corresponding to each environmental factor based on the environmental factor range corresponding to each of the environmental factors and the environmental risk type corresponding to each of the environmental factors; The structural risk data of the tunnel operation instrument and the environmental risk degree corresponding to each environmental factor are used as environmental risk information.

3. The method according to claim 1, characterized in that The identifying the work type of each construction worker and the work flow of each construction worker based on each of the operation process images includes: Through the image edge recognition algorithm, the action image of each construction worker in each operation process image is identified, and each construction worker is marked to obtain the corresponding identification information of each construction worker; The action images of the construction workers with the same personnel identification information are arranged according to the acquisition order of the operation process images to obtain the action sequence of each construction worker, and the action features of each construction worker are extracted through the feature extraction network; In the workflow database, the workflow corresponding to each action feature is matched, and the work type corresponding to each workflow is used as the work type of each construction worker, and each workflow is used as the workflow of each construction worker.

4. The method according to claim 3, characterized in that Based on the work type and work flow of each construction worker, the risk work content of each risk potential worker is identified through a risk prediction network, including: For each construction worker, based on the work flow of the construction worker, query the prohibited work content corresponding to the work prohibited items of the work flow, and calculate the similarity between each action feature in the personnel action sequence of the construction worker and the content feature corresponding to each prohibited work content; Filter action features greater than the similarity threshold as risk action features, and use prohibited work content greater than the similarity threshold as target prohibited work content; Adding the content label of the target prohibited work content corresponding to the risk action feature to each of the risk work features to obtain a first risk work feature, and treating the construction personnel with the first risk work feature as risk potential personnel; Based on the job type of the risk potential personnel, the risk job type of the risk potential personnel is identified, and the risk job type of the risk potential personnel and the first risk job characteristic of the risk potential personnel are used as the risk job content of the risk potential personnel.

5. The method according to claim 4, characterized in that The method of predicting tunnel risk information based on the environmental risk information and the risk work content of each risk potential personnel through a risk knowledge graph includes: Based on the structural risk data of the tunnel operation instrument and the environmental risk degree corresponding to each environmental factor, querying the target sub-risk map of the current tunnel operation in the risk knowledge map; For each potential risk personnel, based on the risk work type of the potential risk personnel, in the target sub-risk map, the risk branch information is screened, and based on the risk work content of the potential risk personnel, the similarity between the risk feature of each branch node in the risk branch information and the risk work content is calculated by a similarity algorithm; The risk feature with the maximum similarity is screened as the risk feature corresponding to the risk work content, and the risk features corresponding to the risk work content of all risk potential personnel are used as tunnel risk information.

6. The method according to claim 5, characterized in that The generating a tunnel risk response strategy based on the tunnel risk information includes: Querying the risk level of each risk feature, and sorting the risk features according to the risk level to obtain a risk feature sequence; In the risk response database, the risk handling strategy corresponding to each risk feature is queried, and the risk handling strategies corresponding to each risk feature are sorted according to the order of the risk feature sequence to obtain the tunnel risk response strategy.

7. The method according to claim 5, characterized in that The sending of risk warning information corresponding to the risk work content to each of the risk potential personnel includes: For each potential risk person, based on the prohibited work content corresponding to the first risk work characteristic of the potential risk person, risk warning information corresponding to the potential risk person is generated through a risk warning template; The risk warning information is converted into notification data of multiple notification types, and the notification data of each notification type is sent to the risk potential personnel through the notification channel of each characteristic type.

8. A tunnel environment risk prediction device based on a mining lamp, applied to a tunnel operation safety management system, characterized in that: The device comprises: An acquisition module, used to acquire tunnel environment data, operation data of tunnel operation instruments, and operation process images of multiple construction workers, and identify environmental risk information based on the tunnel environment data and the operation data of the tunnel operation instruments; an identification module, for identifying the work type of each construction worker and the work flow of each construction worker based on each of the operation process images, and identifying the risk work content of each risk potential personnel through a risk prediction network based on the work type of each of the construction workers and the work flow of each of the construction workers; A prediction module, for predicting tunnel risk information based on the environmental risk information and the risk work content of each risk potential personnel through a risk knowledge graph, and generating a tunnel risk response strategy based on the tunnel risk information; The sending module is used to send the tunnel risk response strategy to each of the construction personnel, and send risk warning information corresponding to the risk work content to each of the risk potential personnel.

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

10. 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 7 are implemented.