Digital intelligent safety emergency management system and method based on AI algorithm and cloud computing

Abstract

The invention provides a digital intelligent safety emergency management system and method based on an AI algorithm and cloud computing, and the system comprises an image hidden danger recognition module which is used for recognizing the potential safety hazards in a field image based on a visual analysis technology; the assessment and early warning module is used for analyzing the hidden danger description of the potential safety hazard by using big data analysis and machine learning technologies, obtaining a safety risk assessment result and performing safety early warning; the emergency disposal module is used for providing an intelligent emergency disposal scheme according to the safety risk assessment result; and the intelligent question and answer module is used for performing intelligent question and answer in the emergency disposal process of the user. According to the digital intelligent safety emergency management system and method based on the AI algorithm and cloud computing, the information islanding effect of traditional safety emergency management is broken through, the problem of decision making difficulty is solved, the management efficiency is improved, and the auxiliary manual management process is more intelligent.

Description

Technical Field

[0001] The present invention relates to the field of security management technology, and in particular to a digital security emergency management system and method based on AI algorithms and cloud computing. Background Art

[0002] With the rapid development of society and the economy, safety and emergency management face increasingly severe challenges. Traditional safety and emergency management methods suffer from information silos, low efficiency, and difficult decision-making, making them unable to meet the needs of modern safety and emergency management. For example, chemical park management departments face complex workflows and cumbersome communication issues in managing park enterprises. The delay in identifying potential risks, inadequate routine security inspections, and incomplete emergency response plans all increase safety risks in production processes. Furthermore, the current safety and emergency management system's functional modules are complex to operate, increasing staff workload and requiring high computer skills.

[0003] In view of this, there is an urgent need for digital security emergency management systems and methods based on AI algorithms and cloud computing to at least address the above-mentioned shortcomings. Summary of the Invention

[0004] One of the purposes of the present invention is to provide a digital safety emergency management system and method based on AI algorithms and cloud computing, visually analyze safety hazards in on-site images, use AI and cloud computing to analyze the safety risk assessment results of safety hazards and issue safety warnings; in addition, it provides intelligent emergency response plans and conducts intelligent question and answer during the user's emergency response process, breaking the information island effect of traditional safety emergency management, solving the problem of decision-making difficulties, improving management efficiency, and making the auxiliary manual management process more intelligent.

[0005] The digital security emergency management system based on AI algorithms and cloud computing provided by the embodiments of the present invention includes:

[0006] Image hidden danger identification module, used to identify safety hazards in on-site images based on visual analysis technology;

[0007] The assessment and early warning module is used to analyze the potential safety hazards and their descriptions using big data analysis and machine learning technologies, obtain safety risk assessment results, and issue safety warnings;

[0008] The emergency response module is used to provide intelligent emergency response plans based on the security risk assessment results; the intelligent question and answer module is used to conduct intelligent questions and answers during the user's emergency response process.

[0009] Preferably, the assessment and early warning module uses big data analysis and machine learning technology to analyze the potential safety hazard description, obtain safety risk assessment results and issue safety early warnings, including:

[0010] Build a security risk quantitative assessment library based on historical data;

[0011] Analyze the potential safety hazard descriptions based on the security risk quantitative assessment database to obtain the security risk assessment results, which include: risk type and risk value;

[0012] If the risk value is greater than the risk value threshold corresponding to the risk type, a safety warning will be issued.

[0013] Preferably, the emergency response module provides an intelligent emergency response plan based on the security risk assessment results, including:

[0014] Match emergency plan templates based on safety risk assessment results;

[0015] Based on the emergency plan template, assist users to quickly generate emergency plans.

[0016] Preferably, the emergency response module assists users in quickly generating emergency plans based on the emergency plan template, including:

[0017] According to the parsing level of the template content tags corresponding to the template content, the template content tags are traversed in sequence, and the template content tag currently being traversed is used as the target content tag;

[0018] Determine the collection-related template content tag of the target content tag based on the association relationship between the target content tag and the on-site information collection;

[0019] Classify the target content tag and the collection-related template content tag into the same tag group, and at the same time, remove the collection-related template content tag from the template content tags to be traversed subsequently;

[0020] After all the template content tags that need to be traversed are traversed, it is determined whether the matching situation of the emergency plan template reaches the trigger value based on the multiple tag groups obtained;

[0021] If not, re-match the emergency plan template;

[0022] If so, the template content is obtained by matching the on-site information according to the grouping time sequence of the multiple tag groups, and an emergency plan is generated according to the emergency plan template that matches the template content.

[0023] The digital security emergency management system based on AI algorithms and cloud computing provided by the embodiments of the present invention also performs the following operations:

[0024] Based on the user's first action trajectory in the historical period, the first local emergency area and the management site map, predict the second local emergency area that the user is about to visit;

[0025] Generate emergency knowledge network based on emergency plan;

[0026] Based on the emergency knowledge network, the knowledge linkage value is calculated according to the knowledge association relationship between the historical local emergency area and the second local emergency area corresponding to the emergency knowledge in the emergency knowledge network;

[0027] If the knowledge linkage value is greater than or equal to a preset knowledge linkage value threshold, feature extraction is performed on the local route between the historical local emergency area and the corresponding second local emergency area to obtain local route features. The local route features include at least: the length of the local route, the risk type and risk value of other second local emergency areas along the local route, and the predicted emergency response time of other second local emergency areas along the local route.

[0028] Determine whether to associate the historical local emergency area with the corresponding second local emergency area based on a preset association determination library and local line characteristics;

[0029] The second action trajectory of the user is planned according to the positions of the associated second local emergency area and the remaining second local emergency areas in the management site map.

[0030] The digital security emergency management method based on AI algorithms and cloud computing provided by the embodiments of the present invention includes:

[0031] Identify safety hazards in on-site images based on visual analysis technology;

[0032] Utilize big data analysis and machine learning technologies to analyze potential safety hazards, obtain safety risk assessment results, and issue safety warnings;

[0033] Provide intelligent emergency response solutions based on security risk assessment results;

[0034] Provide intelligent Q&A while users are handling emergencies.

[0035] Preferably, big data analysis and machine learning technologies are used to analyze the potential safety hazards, obtain safety risk assessment results and issue safety warnings, including:

[0036] Build a security risk quantitative assessment library based on historical data;

[0037] Analyze the potential safety hazard descriptions based on the security risk quantitative assessment database to obtain the security risk assessment results, which include: risk type and risk value;

[0038] If the risk value is greater than the risk value threshold corresponding to the risk type, a safety warning will be issued.

[0039] Preferably, an intelligent emergency response plan is provided based on the security risk assessment results, including:

[0040] Match emergency plan templates based on safety risk assessment results;

[0041] Based on the emergency plan template, assist users to quickly generate emergency plans.

[0042] Preferably, based on the emergency plan template, the user is assisted in quickly generating an emergency plan, including:

[0043] According to the parsing level of the template content tags corresponding to the template content, the template content tags are traversed in sequence, and the template content tag currently being traversed is used as the target content tag;

[0044] Determine the collection-related template content tag of the target content tag based on the association relationship between the target content tag and the on-site information collection;

[0045] Classify the target content tag and the collection-related template content tag into the same tag group, and at the same time, remove the collection-related template content tag from the template content tags to be traversed subsequently;

[0046] After all the template content tags that need to be traversed are traversed, it is determined whether the matching situation of the emergency plan template reaches the trigger value based on the multiple tag groups obtained;

[0047] If not, re-match the emergency plan template;

[0048] If so, the template content is obtained by matching the on-site information according to the grouping time sequence of the multiple tag groups, and an emergency plan is generated according to the emergency plan template that matches the template content.

[0049] The digital security emergency management method based on AI algorithms and cloud computing provided in an embodiment of the present invention also includes:

[0050] Based on the user's first action trajectory in the historical period, the first local emergency area and the management site map, predict the second local emergency area that the user is about to visit;

[0051] Generate emergency knowledge network based on emergency plan;

[0052] Based on the emergency knowledge network, the knowledge linkage value is calculated according to the knowledge association relationship between the historical local emergency area and the second local emergency area corresponding to the emergency knowledge in the emergency knowledge network;

[0053] If the knowledge linkage value is greater than or equal to a preset knowledge linkage value threshold, feature extraction is performed on the local route between the historical local emergency area and the corresponding second local emergency area to obtain local route features. The local route features include at least: the length of the local route, the risk type and risk value of other second local emergency areas along the local route, and the predicted emergency response time of other second local emergency areas along the local route.

[0054] Determine whether to associate the historical local emergency area with the corresponding second local emergency area based on a preset association determination library and local line characteristics;

[0055] The second action trajectory of the user is planned according to the positions of the associated second local emergency area and the remaining second local emergency areas in the management site map.

[0056] The beneficial effects of the present invention are:

[0057] The present invention visually analyzes safety hazards in on-site images, uses AI and cloud computing to analyze the safety risk assessment results of safety hazards and issue safety warnings; in addition, it provides intelligent emergency response plans and conducts intelligent question and answering during the user's emergency response process, breaking the information island effect of traditional safety emergency management, solving the problem of difficult decision-making, improving management efficiency, and making the auxiliary manual management process more intelligent.

[0058] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document.

[0059] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0061] Figure 1 Schematic diagram of a digital security emergency management system based on AI algorithms and cloud computing in an embodiment of the present invention;

[0062] Figure 2 This is a schematic diagram of a digital security emergency management method based on AI algorithm and cloud computing in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0064] The embodiment of the present invention provides a digital security emergency management system based on AI algorithm and cloud computing, such as Figure 1 Shown, including:

[0065] Image hidden danger identification module 1, used to identify safety hazards in on-site images based on visual analysis technology;

[0066] Assessment and early warning module 2 is used to analyze the potential safety hazards and their descriptions using big data analysis and machine learning technologies, obtain safety risk assessment results, and issue safety warnings;

[0067] The assessment and early warning module uses big data analysis and machine learning technology to analyze the potential safety hazards, obtain safety risk assessment results, and issue safety warnings, including:

[0068] Build a security risk quantitative assessment library based on historical data;

[0069] Analyze the potential safety hazard descriptions based on the security risk quantitative assessment database to obtain the security risk assessment results, which include: risk type and risk value;

[0070] If the risk value is greater than the risk value threshold corresponding to the risk type, a safety warning will be issued;

[0071] Emergency response module 3 is used to provide intelligent emergency response solutions based on the safety risk assessment results;

[0072] The emergency response module provides intelligent emergency response solutions based on the safety risk assessment results, including:

[0073] Match emergency plan templates based on safety risk assessment results;

[0074] Assist users to quickly generate emergency plans based on emergency plan templates;

[0075] The intelligent question-and-answer module 4 is used to conduct intelligent question-and-answer sessions when users are handling emergencies.

[0076] The working principle and beneficial effects of the above technical solution are:

[0077] When conducting digital safety emergency management, visual analysis of on-site images is performed to identify safety hazards. The on-site images are obtained through monitoring devices in the safety management area (for example, images of the chemical park are obtained through safety hazard monitoring robots in the chemical park). When identifying safety hazards, a normal state image set is preset for each location. If the on-site image of a certain location does not match the normal state images in the normal state image set corresponding to that location, it is determined that there is a safety hazard in the on-site image of the corresponding location.

[0078] When using big data analysis and machine learning technology to analyze the hazard description of safety hazards, first obtain the historical hazard identification record of the scene corresponding to the on-site image through big data. Based on the historical hazard identification record, quantify the risk value corresponding to the historical hazard description, and construct a safety risk quantitative assessment library by corresponding the historical hazard description, risk type and risk value one by one; machine learning how to match the hazard description with the historical hazard description, and select the risk type and risk value corresponding to the most matching historical hazard description as the safety risk assessment result; in addition, determine whether the risk value is greater than the risk value threshold corresponding to the risk type (the risk value threshold corresponding to the risk type is manually pre-set). If so, issue an early warning.

[0079] When matching an emergency plan template, the emergency case database identifies the risk event corresponding to the risk type in the security risk assessment results. The framework for emergency plan development, determined based on the emergency case, becomes the emergency plan template. Template content is automatically matched based on template content tags within the template, assisting users in quickly generating emergency plans.

[0080] After the emergency plan is generated, the user will take emergency measures according to the emergency plan. During the process, based on natural language processing technology, semantic understanding, knowledge retrieval and answer generation of user safety emergency issues are achieved.

[0081] The present invention visually analyzes safety hazards in on-site images, uses AI and cloud computing to analyze the safety risk assessment results of safety hazards and issue safety warnings; in addition, it provides intelligent emergency response plans and conducts intelligent question and answering during the user's emergency response process, breaking the information island effect of traditional safety emergency management, solving the problem of difficult decision-making, improving management efficiency, and making the auxiliary manual management process more intelligent.

[0082] In one embodiment, based on the emergency plan template, the user is assisted in quickly generating an emergency plan, including:

[0083] According to the parsing level of the template content tags corresponding to the template content, the template content tags are traversed in sequence, and the template content tag currently being traversed is used as the target content tag;

[0084] Determine the collection-related template content tag of the target content tag based on the association relationship between the target content tag and the on-site information collection;

[0085] Classify the target content tag and the collection-related template content tag into the same tag group, and at the same time, remove the collection-related template content tag from the template content tags to be traversed subsequently;

[0086] After all the template content tags that need to be traversed are traversed, it is determined whether the matching situation of the emergency plan template reaches the trigger value based on the multiple tag groups obtained;

[0087] If not, re-match the emergency plan template;

[0088] If so, the template content is obtained by matching the on-site information according to the grouping time sequence of the multiple tag groups, and an emergency plan is generated according to the emergency plan template that matches the template content.

[0089] The working principle and beneficial effects of the above technical solution are:

[0090] The parsing hierarchy of template content is: parse the template content of which template content tag first, then parse the template content of which template content tag, and finally output the emergency plan. Traverse the template content tags in sequence and use the template content tag currently being traversed as the target content tag.

[0091] However, the template content of the template content tags that need to be matched and obtained are obtained in different ways. The template content of the template content tag traversed first and the template content of the template content tag traversed later may be obtained through the same information collection node. For example: the template content of the tth template content tag and the template content of the t+5th template content tag can both be obtained through the chemical pipeline sensor node, but according to the conventional order, that is, the parsing level, to obtain the template content, the system needs to access the chemical pipeline sensor node twice, which greatly reduces the matching efficiency of the template content.

[0092] Therefore, the present invention introduces a field information collection association relationship, which is: which type of field information and which type of field information can be collected at the same node, which type of field information can be collected at the child node of which type of field information collection node, etc., and determines the collection-associated template content tag of the target content tag. The template content of the target content tag and the template content of the collection-associated template content tag are associated in the field information collection association relationship. The target content tag and the collection-associated template content tag are divided into the same tag group, and the template content corresponding to the same tag group is obtained within the same period of time.

[0093] In addition, there are situations where the template content tag cannot be matched to the corresponding template content. Therefore, after determining the tag group, the corresponding template content is not obtained first. After the traversal task is completed, the trigger condition of the emergency plan template output is determined, and then the template content is matched:

[0094] Specifically, the next template content label is traversed until the traversal of the template content label is completed, and it is determined whether the matching situation of the emergency plan template reaches the trigger value. When determining whether the touch value is reached, the sum of the preset weights corresponding to the template content labels in the multiple label groups is calculated. The larger the sum of the weights, the more comprehensive the corresponding input template basis and the more accurate and appropriate the result (emergency plan) output by the emergency plan template; the trigger value is a preset value, such as: 0.9; when the sum of the weights does not reach the trigger value, it means that the template input content is incomplete, and the emergency plan template is obtained again; when the sum of the weights reaches the trigger value, it means that the input basis meets the trigger condition for the emergency plan template to output the emergency plan, and the template content is obtained by matching the on-site information according to the grouping sequence of the corresponding multiple label groups, which greatly improves the input efficiency of the template content.

[0095] The embodiment of the present invention provides a digital security emergency management method based on AI algorithms and cloud computing, and also performs the following operations:

[0096] Based on the user's first action trajectory in the historical period, the first local emergency area and the management site map, predict the second local emergency area that the user is about to visit;

[0097] Generate emergency knowledge network based on emergency plan;

[0098] Based on the emergency knowledge network, the knowledge linkage value is calculated according to the knowledge association relationship between the historical local emergency area and the second local emergency area corresponding to the emergency knowledge in the emergency knowledge network;

[0099] If the knowledge linkage value is greater than or equal to a preset knowledge linkage value threshold, feature extraction is performed on the local route between the historical local emergency area and the corresponding second local emergency area to obtain local route features. The local route features include at least: the length of the local route, the risk type and risk value of other second local emergency areas along the local route, and the predicted emergency response time of other second local emergency areas along the local route.

[0100] Determine whether to associate the historical local emergency area with the corresponding second local emergency area based on a preset association determination library and local line characteristics;

[0101] The second action trajectory of the user is planned according to the positions of the associated second local emergency area and the remaining second local emergency areas in the management site map.

[0102] The working principle and beneficial effects of the above technical solution are:

[0103] The first action trajectory in the historical period is the action trajectory of the user in the management site map in the past period of time (for example, 5 minutes). The first local emergency area is all local risk areas that require emergency management circled on the management site map. When predicting the second local emergency area, the relationship between the route distance and time between the user and each first local emergency area is calculated. If the relationship meets the preset proximity relationship (for example, the route distance becomes shorter as time increases), the corresponding first local emergency area will be used as the second local emergency area.

[0104] The emergency knowledge network is an emergency knowledge graph related to the emergency plan. The knowledge association relationship is: the graph relationship between the local emergency knowledge network corresponding to the historical local emergency area and the second local emergency area in the emergency knowledge network. For example, the A graph node in the local emergency knowledge network corresponding to the emergency knowledge of the historical local emergency area can be connected to the E graph node in the local emergency knowledge gateway connection corresponding to the emergency knowledge of the second local emergency area through the B, C, D graph nodes and a, b, c, d node dependencies. The knowledge linkage value is calculated based on the knowledge association relationship. For example, the fewer graph levels spanned by the A, B, C, D, and E graph nodes and the more node dependencies, the higher the corresponding knowledge linkage value.

[0105] If the knowledge linkage value is greater than or equal to the preset knowledge linkage value threshold (the preset knowledge linkage value threshold is manually pre-set), the local line characteristics of the local line between the historical local emergency area and the corresponding second local emergency area are extracted. The local line characteristics include at least: the length of the local line, the risk type and risk value of other second local emergency areas along the local line, and the predicted emergency processing time of other second local emergency areas along the local line. The preset association judgment library stores multiple local line characteristics that need to be judged for association, such as: the length of the local line is less than 100 meters, the preset type weight of the risk type of other second local emergency areas along the local line is less than the sum of the preset type weights of the historical local emergency area and the corresponding second local emergency area, and the predicted emergency processing time of other second local emergency areas along the local line is greater than 2 hours.

[0106] After the historical local emergency area and the corresponding second local emergency area are associated, when the second action trajectory is subsequently planned, the system will plan an action trajectory that follows the first action trajectory to the corresponding second local emergency area. During the emergency handling process, users can dynamically plan routes based on the line distance of the local emergency area and the knowledge association relationship obtained in real time, helping users to better understand and apply emergency knowledge, reducing the user's subjective thinking time and improving emergency handling efficiency.

[0107] The embodiment of the present invention provides a digital security emergency management method based on AI algorithm and cloud computing, such as Figure 2 Shown, including:

[0108] Step 1: Identify safety hazards in on-site images based on visual analysis technology;

[0109] Step 2: Utilize big data analysis and machine learning technologies to analyze the potential safety hazards, obtain safety risk assessment results, and issue safety warnings;

[0110] Step 3: Provide intelligent emergency response plans based on the security risk assessment results;

[0111] Step 4: Conduct intelligent Q&A while the user is handling the emergency.

[0112] In one embodiment, big data analysis and machine learning technologies are used to analyze the potential safety hazard descriptions, obtain safety risk assessment results, and issue safety warnings, including:

[0113] Build a security risk quantitative assessment library based on historical data;

[0114] Analyze the potential safety hazard descriptions based on the security risk quantitative assessment database to obtain the security risk assessment results, which include: risk type and risk value;

[0115] If the risk value is greater than the risk value threshold corresponding to the risk type, a safety warning will be issued.

[0116] In one embodiment, an intelligent emergency response plan is provided based on the security risk assessment results, including:

[0117] Match emergency plan templates based on safety risk assessment results;

[0118] Based on the emergency plan template, assist users to quickly generate emergency plans.

[0119] In one embodiment, based on the emergency plan template, the user is assisted in quickly generating an emergency plan, including:

[0120] According to the parsing level of the template content tags corresponding to the template content, the template content tags are traversed in sequence, and the template content tag currently being traversed is used as the target content tag;

[0121] Determine the collection-related template content tag of the target content tag based on the association relationship between the target content tag and the on-site information collection;

[0122] Classify the target content tag and the collection-related template content tag into the same tag group, and at the same time, remove the collection-related template content tag from the template content tags to be traversed subsequently;

[0123] After all the template content tags that need to be traversed are traversed, it is determined whether the matching situation of the emergency plan template reaches the trigger value based on the multiple tag groups obtained;

[0124] If not, re-match the emergency plan template;

[0125] If so, the template content is obtained by matching the on-site information according to the grouping time sequence of the multiple tag groups, and an emergency plan is generated according to the emergency plan template that matches the template content.

[0126] The present invention provides a digital security emergency management method based on AI algorithms and cloud computing, which also includes:

[0127] Based on the user's first action trajectory in the historical period, the first local emergency area and the management site map, predict the second local emergency area that the user is about to visit;

[0128] Generate emergency knowledge network based on emergency plan;

[0129] Based on the emergency knowledge network, the knowledge linkage value is calculated according to the knowledge association relationship between the historical local emergency area and the second local emergency area corresponding to the emergency knowledge in the emergency knowledge network;

[0130] If the knowledge linkage value is greater than or equal to a preset knowledge linkage value threshold, feature extraction is performed on the local route between the historical local emergency area and the corresponding second local emergency area to obtain local route features. The local route features include at least: the length of the local route, the risk type and risk value of other second local emergency areas along the local route, and the predicted emergency response time of other second local emergency areas along the local route.

[0131] Determine whether to associate the historical local emergency area with the corresponding second local emergency area based on a preset association determination library and local line characteristics;

[0132] The second action trajectory of the user is planned according to the positions of the associated second local emergency area and the remaining second local emergency areas in the management site map.

[0133] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A digital security emergency management system based on AI algorithms and cloud computing, characterized by: include: Image hidden danger identification module, used to identify safety hazards in on-site images based on visual analysis technology; The assessment and early warning module is used to analyze the potential safety hazards and their descriptions using big data analysis and machine learning technologies, obtain safety risk assessment results, and issue safety warnings; Emergency response module, used to provide intelligent emergency response solutions based on security risk assessment results; The intelligent question-and-answer module is used to conduct intelligent question-and-answer sessions when users are handling emergencies.

2. The digital security emergency management system based on AI algorithm and cloud computing as claimed in claim 1 is characterized in that: The assessment and early warning module uses big data analysis and machine learning technology to analyze potential safety hazards, obtain safety risk assessment results, and issue safety warnings, including: Build a security risk quantitative assessment library based on historical data; Analyze the potential safety hazard descriptions based on the security risk quantitative assessment database to obtain the security risk assessment results, which include: risk type and risk value; If the risk value is greater than the risk value threshold corresponding to the risk type, a safety warning will be issued.

3. The digital security emergency management system based on AI algorithm and cloud computing as claimed in claim 1 is characterized in that: The emergency response module provides intelligent emergency response solutions based on the safety risk assessment results, including: Match emergency plan templates based on safety risk assessment results; Based on the emergency plan template, assist users to quickly generate emergency plans.

4. The digital security emergency management system based on AI algorithm and cloud computing as claimed in claim 3 is characterized by: The emergency response module helps users quickly generate emergency plans based on the emergency plan template, including: According to the parsing level of the template content tags corresponding to the template content, the template content tags are traversed in sequence, and the template content tag currently being traversed is used as the target content tag; Determine the collection-related template content tag of the target content tag based on the association relationship between the target content tag and the on-site information collection; Classify the target content tag and the collection-related template content tag into the same tag group, and at the same time, remove the collection-related template content tag from the template content tags to be traversed subsequently; After all the template content tags that need to be traversed are traversed, it is determined whether the matching situation of the emergency plan template reaches the trigger value based on the multiple tag groups obtained; If not, re-match the emergency plan template; If so, the template content is obtained by matching the on-site information according to the grouping time sequence of the multiple tag groups, and an emergency plan is generated according to the emergency plan template that matches the template content.

5. The digital security emergency management system based on AI algorithm and cloud computing as claimed in claim 1 is characterized in that: Also perform the following operations: Based on the user's first action trajectory in the historical period, the first local emergency area and the management site map, predict the second local emergency area that the user is about to visit; Generate emergency knowledge network based on emergency plan; Based on the emergency knowledge network, the knowledge linkage value is calculated according to the knowledge association relationship between the historical local emergency area and the second local emergency area corresponding to the emergency knowledge in the emergency knowledge network; If the knowledge linkage value is greater than or equal to a preset knowledge linkage value threshold, feature extraction is performed on the local route between the historical local emergency area and the corresponding second local emergency area to obtain local route features. The local route features include at least: the length of the local route, the risk type and risk value of other second local emergency areas along the local route, and the predicted emergency response time of other second local emergency areas along the local route. Determine whether to associate the historical local emergency area with the corresponding second local emergency area based on a preset association determination library and local line characteristics; The second action trajectory of the user is planned according to the positions of the associated second local emergency area and the remaining second local emergency areas in the management site map.

6. A digital security emergency management method based on AI algorithms and cloud computing, characterized by: include: Identify safety hazards in on-site images based on visual analysis technology; Utilize big data analysis and machine learning technologies to analyze potential safety hazards, obtain safety risk assessment results, and issue safety warnings; Provide intelligent emergency response solutions based on security risk assessment results; Provide intelligent Q&A while users are handling emergencies.

7. The digital security emergency management method based on AI algorithm and cloud computing according to claim 6 is characterized in that: Utilize big data analysis and machine learning technologies to analyze potential safety hazards, obtain safety risk assessment results, and issue safety warnings, including: Build a security risk quantitative assessment library based on historical data; Analyze the potential safety hazard descriptions based on the security risk quantitative assessment database to obtain the security risk assessment results, which include: risk type and risk value; If the risk value is greater than the risk value threshold corresponding to the risk type, a safety warning will be issued.

8. The digital security emergency management method based on AI algorithm and cloud computing according to claim 6 is characterized in that: Provide intelligent emergency response solutions based on the security risk assessment results, including: Match emergency plan templates based on safety risk assessment results; Based on the emergency plan template, assist users to quickly generate emergency plans.

9. The digital security emergency management method based on AI algorithm and cloud computing according to claim 8, characterized in that: Based on the emergency plan template, users can quickly generate emergency plans, including: According to the parsing level of the template content tags corresponding to the template content, the template content tags are traversed in sequence, and the template content tag currently being traversed is used as the target content tag; Determine the collection-related template content tag of the target content tag based on the association relationship between the target content tag and the on-site information collection; Classify the target content tag and the collection-related template content tag into the same tag group, and at the same time, remove the collection-related template content tag from the template content tags to be traversed subsequently; After all the template content tags that need to be traversed are traversed, it is determined whether the matching situation of the emergency plan template reaches the trigger value based on the multiple tag groups obtained; If not, re-match the emergency plan template; If so, the template content is obtained by matching the on-site information according to the grouping time sequence of the multiple tag groups, and an emergency plan is generated according to the emergency plan template that matches the template content.

10. The digital security emergency management method based on AI algorithm and cloud computing according to claim 6, characterized in that: Also includes: Based on the user's first action trajectory in the historical period, the first local emergency area and the management site map, predict the second local emergency area that the user is about to visit; Generate emergency knowledge network based on emergency plan; Based on the emergency knowledge network, the knowledge linkage value is calculated according to the knowledge association relationship between the historical local emergency area and the second local emergency area corresponding to the emergency knowledge in the emergency knowledge network; If the knowledge linkage value is greater than or equal to a preset knowledge linkage value threshold, feature extraction is performed on the local route between the historical local emergency area and the corresponding second local emergency area to obtain local route features. The local route features include at least: the length of the local route, the risk type and risk value of other second local emergency areas along the local route, and the predicted emergency response time of other second local emergency areas along the local route. Determine whether to associate the historical local emergency area with the corresponding second local emergency area based on a preset association determination library and local line characteristics; The second action trajectory of the user is planned according to the positions of the associated second local emergency area and the remaining second local emergency areas in the management site map.

Images