An artificial intelligence-based method for evaluating fire emergency response capabilities

Abstract

The present invention discloses an artificial intelligence-based fire emergency response capability assessment method, which uses AI algorithms to automatically analyze and calculate assessment data, eliminates the subjectivity of manual assessment, and ensures the objectivity and consistency of the assessment results; through real-time monitoring and assessment of the performance of trainees, timely feedback can be obtained and adjustments can be made during drills and actual combat, thereby improving the effectiveness of emergency response and enhancing the pertinence of subsequent training and drills for trainees; the scheme comprehensively considers multiple factors such as physiological performance, movement performance, voice communication and team collaboration, and quantitatively assesses the emergency response capabilities of individuals and teams from multiple dimensions; this comprehensive assessment can more comprehensively reflect the actual capabilities of trainees and provide a basis for personalized training; by introducing the concept of task matching, the assessment results can not only reflect individual capabilities, but also make adaptive adjustments for specific tasks and roles, which helps to optimize role allocation and improve the overall efficiency of the team.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence related technologies, and in particular to an artificial intelligence-based fire emergency response capability assessment method. Background Art

[0002] Assessing emergency response capabilities is a critical component of safety management, directly impacting the efficiency and effectiveness of emergency rescue efforts. Existing assessment methods primarily rely on manual evaluation and accumulated experience. Common evaluation methods include expert scoring, questionnaires, and case studies. While these traditional methods can reflect training personnel's capabilities to a certain extent, they suffer from the following drawbacks:

[0003] Subjectivity and inconsistency: Traditional evaluations often rely on the experience and judgment of reviewers, resulting in highly subjective evaluation results that may vary significantly between reviewers. This inconsistency not only reduces the reliability of the evaluation but may also lead to misjudgment of the trainees' true abilities.

[0004] Lack of real-time performance: Traditional methods usually conduct post-event evaluations after an incident occurs, which makes it difficult to reflect the performance of trainees in emergency situations in real time. This lag makes it impossible to use evaluation feedback to adjust tactics and strategies in an emergency.

[0005] Insufficient data utilization: Existing technologies usually only focus on a single dimension (such as physiological state or a single behavioral performance), and fail to comprehensively consider multiple factors such as physiology, psychology, and teamwork. This makes the evaluation results unable to fully reflect the true capabilities of trainees and team effectiveness.

[0006] Ignoring individual differences: There are significant differences in the performance of different trainees in emergency response, and traditional methods are difficult to dynamically adjust according to individual characteristics and specific task requirements; this leads to the potential of some trainees not being fully tapped, affecting the improvement of overall response capabilities. Summary of the Invention

[0007] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0008] Therefore, in order to solve the above technical problems, the present invention provides the following technical solutions: a fire emergency response capability assessment method based on artificial intelligence, comprising the following specific steps: S1: installing team behavior data acquisition equipment in a training site or virtual reality system, and configuring data acquisition equipment for individual trainees; S2: constructing a simulated fire emergency scenario, setting emergency tasks and team roles; S3: in the emergency scenario, collecting the trainees' physiological data, motion data and voice data in real time, collecting environmental data at the same time, and monitoring the team collaboration behavior data in real time; S4: by analyzing, processing and integrating the trainees' physiological data, motion data, voice and communication data and team collaboration data, a multi-dimensional comprehensive evaluation model is constructed through an AI algorithm, which takes into account the individual's independent performance and team collaboration; S5: combined with real-time data, the comprehensive evaluation model quantitatively evaluates the individual's emergency response capability from multiple angles, evaluates the team's overall emergency response capability, and optimizes the role allocation in future tasks based on the performance of individual roles.

[0009] As a preferred solution of the fire emergency response capability assessment method based on artificial intelligence described in the present invention, in which: in step S1, each trainee is equipped with a multimodal data acquisition device, including physiological sensors (monitoring heart rate, respiratory rate, body temperature, etc.), motion capture devices (monitoring position, movement speed, posture, etc.), voice recording equipment (collecting voice features) and environmental sensors (monitoring temperature, smoke concentration, etc. of the surrounding environment).

[0010] As a preferred solution of the artificial intelligence-based fire emergency response capability assessment method described in the present invention, in step S1, high-definition cameras, voice analysis equipment, Internet of Things devices, etc. are installed in the training site or virtual reality system to capture interactive behaviors, command transmission, equipment use and rescue execution during the team collaboration process.

[0011] As a preferred solution of the artificial intelligence-based fire emergency response capability assessment method described in the present invention, in step S2, a virtual or physical simulation scene is designed based on real fire emergency events, covering different fire types (such as structural fires, forest fires, etc.), and setting a variety of complex conditions, including smoke, high temperature, trapped people, obstacles, etc., to be as close to the real environment as possible.

[0012] As a preferred solution of the artificial intelligence-based fire emergency response capability assessment method described in the present invention, in step S2, the system assigns specific tasks (such as fire fighting, rescue, communication, medical treatment, etc.) and corresponding team roles (such as commander, rescuer, supporter) to each trainee, and stipulates the time requirements and goals for task completion.

[0013] As a preferred solution of the fire emergency response capability assessment method based on artificial intelligence described in the present invention, in step S3, the command transmission, communication method and task execution status between team members are monitored through cameras and voice analysis equipment to collect team collaboration behavior data.

[0014] As a preferred embodiment of the fire emergency response capability assessment method based on artificial intelligence of the present invention, in step S4, the physiological performance data, movement data, voice data and team behavior data of the trainees are analyzed to calculate the individual's physiological emergency response score, movement performance score, voice data score and team building collaboration performance score in the emergency scenario;

[0015] The physiological performance data score is evaluated based on heart rate HR, respiratory rate BR, body temperature T, etc., and then the individual's physiological emergency response score is calculated. Specifically, the calculation formula for the physiological emergency response score is as follows: ;

[0016] in, is the number of data points, and is a weight adjustment parameter that controls the sensitivity to fluctuations in heart rate and respiratory rate; and is the individual's resting state baseline value; It is the time window; It represents the physiological response score, which reflects the individual's physiological adaptability under stressful environment;

[0017] The action data score is based on the trainee's movement speed v, action accuracy A, etc., and then judges the individual's action reaction and execution efficiency. Specifically, the calculation formula for the action performance score is as follows: ; and are the ideal values for standard speed and movement accuracy respectively; 、 、 and All are adjustment coefficients; It stands for Movement Performance Score, which measures the agility and movement accuracy of trainees;

[0018] Speech data scoring is evaluated using a natural language processing (NLP) algorithm, taking into account factors such as speech rate (SR), intonation (SP), and emotional fluctuation (EM). Specifically, the formula for calculating speech data scoring is as follows: ;

[0019] in, and are the optimal values for speaking speed and intonation, respectively; and is the adjustment parameter; Score the verbal communication performance, which reflects the trainee's communication ability and emotional stability under pressure;

[0020] The teamwork performance score is evaluated based on the quality of interaction between individuals and other team members (IQ), instruction execution effectiveness (EX), and task completion (TC). Specifically, the teamwork performance score is calculated as follows: ;

[0021] in, the quality of interaction with other team members; For ideal instruction execution effect; The highest degree of task completion; Reflects individual performance in teamwork and is used to assess an individual's ability to communicate, execute and complete tasks in a team.

[0022] As a preferred solution of the fire emergency response capability assessment method based on artificial intelligence of the present invention, wherein: in step S5, real-time data is input into the comprehensive assessment model to generate an individual's comprehensive emergency response capability score; specifically, the individual's comprehensive emergency response capability score The calculation formula is as follows: ;

[0023] in, 、 、 、 The weight of each dimension is dynamically adjusted according to the task type and scenario requirements; the formula value range is: ∈[0,1], The closer it is to 1, the stronger the emergency response capability of the trainee.

[0024] As a preferred solution of the fire emergency response capability evaluation method based on artificial intelligence of the present invention, in step S5, in order to evaluate the overall performance of the team, a team emergency response capability report is generated; based on the individual evaluation results of each trainee, the overall team collaboration effectiveness is calculated. , the calculation formula is as follows:

[0025] ;

[0026] in, is the comprehensive score of the i-th trainee; The degree of task completion for each training personnel; To evaluate the overall team collaboration effectiveness, the team's overall task execution efficiency and coordination ability are evaluated; the formula range is: ∈[0,1], The closer it is to 1, the higher the overall collaboration efficiency of the team.

[0027] As a preferred solution of the fire emergency response capability assessment method based on artificial intelligence of the present invention, in step S5, based on the individual assessment results and team performance, the system automatically generates a role allocation optimization plan, which is based on the individual role fitness. and Task Fit™, which evaluates and determines the score of an individual's suitability for a role. Role Fit is calculated as follows: ;

[0028] in, is the match between the individual and the current task; and are the scores of individuals on motor performance and communication performance, respectively; It is the score of an individual’s suitability for a role; the system is based on each individual’s Automatically optimize role allocation based on the team's overall task requirements to ensure maximum collaborative efficiency in future tasks; Formula value range: ∈[0,1], The closer it is to 1, the more suitable the individual is for the current task role.

[0029] Beneficial effects of the present invention: 1. The present invention uses AI algorithms to automatically analyze and calculate evaluation data, eliminating the subjectivity of manual evaluation and ensuring the objectivity and consistency of evaluation results; this method improves the reliability of evaluation and provides a solid data foundation for scientific research. 2. The present invention can monitor and evaluate the performance of trainees in real time, so that timely feedback can be obtained and adjustments can be made during drills and actual combat; this real-time performance significantly improves the effectiveness of emergency response and enhances the pertinence of subsequent training and drills for trainees. 3. The present invention comprehensively considers multiple factors such as physiological performance, movement performance, voice communication and teamwork, and conducts a quantitative assessment of the emergency response capabilities of individuals and teams from multiple dimensions; this comprehensive assessment can more comprehensively reflect the true capabilities of trainees and provide a basis for personalized training. 4. By introducing the concept of task matching, the present invention's evaluation results can not only reflect individual capabilities, but also make adaptive adjustments for specific tasks and roles; this feature helps to optimize role allocation and improve the overall efficiency of the team. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0031] Figure 1 It is the overall workflow diagram of the present invention. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0033] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0034] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0035] Example 1

[0036] Reference Figure 1 , which is the first embodiment of the present invention, provides a fire emergency response capability assessment method based on artificial intelligence, including the following specific steps:

[0037] S1: Install team behavior data collection equipment in the training venue or virtual reality system, and configure data collection equipment for individual trainers;

[0038] Each trainee is equipped with multimodal data acquisition equipment, including physiological sensors (to monitor heart rate, respiratory rate, body temperature, etc.), motion capture devices (to monitor position, movement speed, posture, etc.), voice recording equipment (to collect voice features), and environmental sensors (to monitor the surrounding environment such as temperature and smoke concentration);

[0039] Install high-definition cameras, voice analysis equipment, IoT devices, etc. in training venues or virtual reality systems to capture interactive behaviors, command transmission, equipment usage, and rescue execution during team collaboration.

[0040] S2: Construct a simulated fire emergency scenario and set emergency tasks and team roles;

[0041] Design virtual or physical simulation scenarios based on real fire emergency events, covering different fire types (such as structural fires, forest fires, etc.), setting up a variety of complex conditions, including smoke, high temperatures, trapped people, obstacles, etc., to be as close to the real environment as possible;

[0042] The system assigns specific tasks (such as firefighting, rescue, communication, medical treatment, etc.) and corresponding team roles (such as commander, rescuer, supporter) to each trainee, and stipulates the time requirements and goals for task completion.

[0043] S3: In emergency scenarios, real-time collection of trainees’ physiological data, motion data, and voice data, as well as environmental data, is performed, and team collaboration behavior data is monitored in real time;

[0044] Use cameras and voice analysis equipment to monitor the transmission of instructions, communication methods and task execution among team members, and collect team collaboration behavior data.

[0045] S4: By analyzing, processing, and integrating trainees’ physiological data, movement data, voice and communication data, and team collaboration data, a multi-dimensional comprehensive evaluation model is constructed using AI algorithms. This model considers both individual independent performance and team collaboration.

[0046] Analyze the trainees' physiological performance data, movement data, voice data, and team behavior data to calculate individual physiological emergency response scores, movement performance scores, voice data scores, and team-building collaboration performance scores in emergency scenarios;

[0047] The physiological performance data score is evaluated based on heart rate HR, respiratory rate BR, body temperature T, etc., and then the individual's physiological emergency response score is calculated. Specifically, the calculation formula for the physiological emergency response score is as follows:

[0048] ;

[0049] in, is the number of data points, and is a weight adjustment parameter that controls the sensitivity to fluctuations in heart rate and respiratory rate; and is the individual's resting state baseline value; It is the time window; It represents the physiological response score, which reflects the individual's physiological adaptability under stressful environment;

[0050] The action data score is based on the trainee's movement speed v, action accuracy A, etc., and then judges the individual's action reaction and execution efficiency. Specifically, the calculation formula for the action performance score is as follows: ; and are the ideal values for standard speed and movement accuracy respectively; 、 、 and All are adjustment coefficients; It stands for Movement Performance Score, which measures the agility and movement accuracy of trainees;

[0051] Speech data scoring is evaluated using a natural language processing (NLP) algorithm, taking into account factors such as speech rate (SR), intonation (SP), and emotional fluctuation (EM). Specifically, the formula for calculating speech data scoring is as follows: ;

[0052] in, and are the optimal values for speaking speed and intonation, respectively; and is the adjustment parameter; Score the verbal communication performance, which reflects the trainee's communication ability and emotional stability under pressure;

[0053] The teamwork performance score is evaluated based on the quality of interaction between individuals and other team members (IQ), instruction execution effectiveness (EX), and task completion (TC). Specifically, the teamwork performance score is calculated as follows: ;

[0054] in, the quality of interaction with other team members; For ideal instruction execution effect; The highest degree of task completion; Reflects individual performance in teamwork and is used to assess an individual's ability to communicate, execute and complete tasks in a team.

[0055] S5: Combined with real-time data, the comprehensive assessment model quantitatively evaluates the emergency response capabilities of individuals from multiple perspectives, assesses the emergency response capabilities of the team as a whole, and optimizes role allocation in future tasks based on the performance of individual roles;

[0056] Input the real-time data into the comprehensive evaluation model to generate the individual's comprehensive emergency response capability score; specifically, the individual's comprehensive emergency response capability score The calculation formula is as follows:

[0057] ;

[0058] in, 、 、 、 The weight of each dimension is dynamically adjusted according to the needs of the task type and scenario;

[0059] Formula value range: ∈[0,1], The closer it is to 1, the stronger the emergency response capability of the trainee is;

[0060] To evaluate the team's overall performance, generate a report on the team's emergency response capabilities; calculate the team's overall collaborative effectiveness based on the individual evaluation results of each trainer , the calculation formula is as follows: ;

[0061] in, is the comprehensive score of the i-th trainee; The degree of task completion for each training personnel; To evaluate the overall team collaboration effectiveness, evaluate the team's overall task execution efficiency and coordination ability;

[0062] Formula value range: ∈[0,1], The closer it is to 1, the higher the overall collaboration efficiency of the team;

[0063] Based on individual assessment results and team performance, the system automatically generates a role allocation optimization plan based on individual role fitness. and Task Fit™, which evaluates and determines the score of an individual's suitability for a role. Role Fit is calculated as follows: ;

[0064] in, is the match between the individual and the current task; and are the scores of individuals on motor performance and communication performance, respectively; It is the score of an individual’s suitability for a role; the system is based on each individual’s Automatically optimize role allocation based on the team's overall task requirements to ensure maximum collaboration efficiency in future tasks;

[0065] Formula value range: ∈[0,1], The closer it is to 1, the more suitable the individual is for the current task role.

[0066] In this embodiment, by accurately assessing the capabilities of individuals and teams, a scientific basis is provided for optimizing resource allocation and task distribution, enabling faster and more effective rescue operations in emergency situations. This assessment method provides new insights into the training and education of trainees, and data-driven training strategies enable trainees to rapidly improve their emergency response capabilities in real-world scenarios. This embodiment, through comprehensive assessment capabilities, helps to promptly identify potential safety hazards, improve the overall level of safety management, and provide protection for public safety.

[0067] The present invention forms a new evaluation model through the integration and innovation of multiple advanced technologies; key steps such as real-time data collection, dynamic feedback adjustment, comprehensive data analysis and personalized role matching give this method obvious technical advantages in improving emergency response capabilities.

[0068] Example 2

[0069] This is the second embodiment of the present invention. This embodiment differs from the first embodiment in that, to verify the effectiveness of the AI-based fire emergency response capability assessment method, an emergency response capability assessment experiment was designed. This experiment aims to quantitatively evaluate the performance of trainees in emergency situations through AI and a multi-dimensional assessment model. To achieve this goal, this embodiment sets up a fire emergency scenario in a virtual reality training field or a physical simulation scenario. Fire types (e.g., structure fires, forest fires) are set, and complex elements such as smoke, high temperatures, obstacles, and trapped personnel are added to simulate the complexity of a real-world environment.

[0070] Data acquisition equipment configuration: Each trainee is equipped with multimodal data acquisition equipment, including:

[0071] Physiological sensors: monitor heart rate (HR), respiratory rate (BR), body temperature and other indicators.

[0072] Motion capture device: monitors position, movement speed, posture and other data.

[0073] Voice recording equipment: collects voice characteristics (such as speaking speed, intonation, emotion, etc.).

[0074] Environmental sensors: monitor environmental data such as temperature and smoke concentration.

[0075] Team tasks and role allocation: The system assigns specific tasks (firefighting, rescue, communication, medical care, etc.) and corresponding roles (commander, rescuer, supporter, etc.) to each trainee, and stipulates the time requirements and goals for task completion.

[0076] Trained personnel enter the field and perform designated emergency tasks. During this process, physiological data, motion data, voice data, and team collaboration data are collected in real time. High-definition cameras and voice analysis equipment are used to record the transmission of instructions and the execution of tasks.

[0077] Data processing and analysis;

[0078] Use AI algorithms to process and analyze the collected data and build a multi-dimensional comprehensive evaluation model.

[0079] Calculate individual physiological response scores, action performance scores, voice communication scores, and teamwork performance scores to obtain a comprehensive score for each trainee's emergency response ability. ;

[0080] Calculate the overall collaboration efficiency of the team ;

[0081] Role optimization; based on individual role adaptability Optimize role allocation based on task matching;

[0082] The details of the experiment are shown in the following table:

[0083]

[0084] By analyzing the data in the table, we can know that:

[0085] 1. Individual performance analysis:

[0086] In terms of comprehensive scores, trainee No. 9 had the highest comprehensive score of 0.903, while trainee No. 6 had the lowest comprehensive score of 0.790. This indicates that there are significant differences in the performance of different individuals in task execution.

[0087] Trainees with high comprehensive scores (such as numbers 3, 7, 9, and 12) scored high in motor performance, language communication, and physiological performance, especially in teamwork scores, where they performed particularly well, indicating that they were able to effectively cooperate with the team during task execution.

[0088] The trainers with low scores (such as No. 6 and 4) scored below 0.8 in terms of movement performance, language communication and physiological performance, indicating that they may have inefficiencies or communication barriers during task execution, affecting the overall team collaboration effectiveness.

[0089] 2. Comparison of task completion:

[0090] The highest task completion score was 0.96, and the lowest was 0.81, indicating significant differences in task completion efficiency between individuals. Person 9 had the highest task completion score, consistent with his high overall score, indicating that he not only performed well but also completed the task more efficiently.

[0091] Trainees with lower task completion (such as No. 6) also performed poorly in the comprehensive score, which further verified their shortcomings in actual task execution.

[0092] 3. The relationship between the scoring indicators:

[0093] The data shows a strong correlation between teamwork scores and overall scores. For example, candidates No. 3 and No. 9 had high teamwork scores (0.95 and 0.94, respectively) and also high overall scores (0.895 and 0.903, respectively), indicating that teamwork is an important factor in improving overall performance.

[0094] The motor performance score and language communication score also have a significant impact on the overall score. Individuals with high scores usually have excellent performance in these two indicators (for example, No. 7 has a motor score of 0.88 and a language score of 0.88).

[0095] In the experiment, the present invention was able to accurately identify the strengths and weaknesses of trainees in emergency tasks through multimodal data collection and comprehensive scoring models. For example, trainee No. 9 performed well in multiple scores, and the system can recommend him to play a key role in future tasks, such as commander or rescuer. This data-based role optimization allocation can significantly improve the task completion efficiency of the entire team. Existing training systems usually rely on subjective evaluation or a single data source (such as action scores or physiological indicators), which cannot fully reflect the emergency response capabilities of individuals. The present invention uses a comprehensive scoring model, combined with multi-dimensional data such as action, language, and physiology, to more finely evaluate the performance of individuals and teams, which helps to improve training effects and actual combat performance.

[0096] For individuals with low overall scores (such as those with scores 6 and 4), the system can provide specific improvement suggestions (such as enhanced performance training or verbal communication training) to enhance their task execution capabilities. This personalized feedback mechanism is relatively rare in existing technologies; conventional training systems are unable to provide such detailed data analysis and optimization suggestions. Traditional role assignments are often based on experience or fixed divisions of labor, but this invention uses a data-driven approach to dynamically adjust role assignments, enabling better adaptation to diverse task requirements. This intelligent role optimization can significantly improve a team's efficiency in completing tasks in complex environments.

[0097] The present invention can dynamically evaluate the physiological state and behavioral performance of trainees through real-time monitoring of multimodal data. For example, if a trainee's heart rate is found to be too high and their performance score has decreased during training (such as the heart rate of trainee No. 6 is 87 and the performance score is only 0.79), the system can suggest pausing the task to prevent excessive physical fatigue. This real-time emergency response adjustment function is an advantage that existing technologies cannot provide. The system can provide real-time feedback on the performance of trainees during the execution of tasks and dynamically adjust their training load and task allocation. This flexible training and task management mechanism is not common in existing training systems and provides significant innovation and practical value.

[0098] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A fire emergency response capability assessment method based on artificial intelligence, characterized by: The following specific steps are included: S1: Install team behavior data collection equipment in the training venue or virtual reality system, and configure data collection equipment for individual trainers; S2: Construct a simulated fire emergency scenario and set emergency tasks and team roles; S3: In emergency scenarios, real-time collection of trainees’ physiological data, motion data, and voice data, as well as environmental data, is performed, and team collaboration behavior data is monitored in real time; S4: By analyzing, processing, and integrating trainees’ physiological data, movement data, voice and communication data, and team collaboration data, a multi-dimensional comprehensive evaluation model is constructed using AI algorithms. This model considers both individual independent performance and team collaboration. S5: Combined with real-time data, the comprehensive assessment model quantitatively evaluates the emergency response capabilities of individuals from multiple perspectives, assesses the emergency response capabilities of the team as a whole, and optimizes role allocation in future tasks based on the performance of individual roles; In step S1, each trainee is equipped with a multimodal data acquisition device, including a physiological sensor, a motion capture device, a voice recording device, and an environmental sensor; In step S1, high-definition cameras, voice analysis equipment, and Internet of Things devices are installed in the training venue or virtual reality system to capture the interactive behavior, command transmission, equipment use, and rescue execution during the team collaboration process; In step S2, based on real fire emergency events, virtual or physical simulation scenarios are designed, covering different fire types and setting up a variety of complex conditions, including smoke, high temperature, trapped people, and obstacles, to be close to the real environment; In step S4, the trainees' physiological performance data, movement data, voice data, and team behavior data are analyzed to calculate the individual's physiological emergency response score, movement performance score, voice data score, and team collaboration performance score in the emergency scenario; The physiological performance data score is evaluated based on heart rate HR, respiratory rate BR, and body temperature T, and then the individual's physiological emergency response score is calculated. Specifically, the calculation formula for the physiological emergency response score is as follows: ; in, is the number of data points, and is a weight adjustment parameter that controls the sensitivity to fluctuations in heart rate and respiratory rate; and is the individual's resting state baseline value; It is the time window; It represents the physiological response score, which reflects the individual's physiological adaptability under stressful environment; The action data score is based on the trainee's movement speed v and action accuracy A, and then judges the individual's action reaction and execution efficiency. Specifically, the calculation formula for the action performance score is as follows: ; and are the ideal values for standard speed and movement accuracy respectively; 、 、 and All are adjustment coefficients; It stands for Movement Performance Score, which measures the agility and movement accuracy of trainees; The speech data score is evaluated using a natural language processing algorithm, which takes into account speech rate (SR), intonation (SP), and emotional fluctuation (EM). Specifically, the formula for calculating the speech data score is as follows: ; in, and are the optimal values for speaking speed and intonation, respectively; and To adjust the parameters; Score the verbal communication performance, which reflects the trainee's communication ability and emotional stability under pressure; The teamwork performance score is evaluated based on the quality of interaction (IQ) between individuals and other team members, the effectiveness of instruction execution (EX), and the degree of task completion (TC). Specifically, the teamwork performance score is calculated as follows: ; in, the quality of interaction with other team members; For ideal instruction execution effect; The highest degree of task completion; Reflects individual performance in teamwork and is used to assess an individual's ability to communicate, execute, and complete tasks within a team; In step S5, the real-time data is input into the comprehensive evaluation model to generate the individual's comprehensive emergency response capability score; specifically, the individual's comprehensive emergency response capability score The calculation formula is as follows: ; in, 、 、 、 The weight of each dimension is dynamically adjusted according to the needs of the task type and scenario; Formula value range: ∈[0,1], The closer it is to 1, the stronger the emergency response capability of the trainee.

2. The fire emergency response capability assessment method based on artificial intelligence according to claim 1, characterized in that: In step S2, the system assigns specific tasks and corresponding team roles to each trainee, and specifies the time requirements and goals for task completion.

3. The fire emergency response capability assessment method based on artificial intelligence according to claim 2, characterized in that: In step S3, the instruction transmission, communication methods and task execution status between team members are monitored through cameras and voice analysis equipment to collect team collaboration behavior data.

4. The fire emergency response capability assessment method based on artificial intelligence according to claim 3, characterized in that: In step S5, in order to evaluate the overall performance of the team, a report on the team's emergency response capability is generated; based on the individual evaluation results of each trainer, the overall team collaboration effectiveness is calculated. , the calculation formula is as follows: ； in, is the comprehensive score of the i-th trainee; The degree of task completion for each training personnel; To evaluate the overall team collaboration effectiveness, evaluate the team's overall task execution efficiency and coordination ability; Formula value range: ∈[0,1], The closer it is to 1, the higher the overall collaboration efficiency of the team.

5. The fire emergency response capability assessment method based on artificial intelligence according to claim 4, characterized in that: In step S5, based on the individual evaluation results and team performance, the system automatically generates a role allocation optimization plan based on the individual role fitness. and Task Fit™, which evaluates and determines the score of an individual's suitability for a role. Role Fit is calculated as follows: ； in, is the match between the individual and the current task; and are the scores of individuals on motor performance and communication performance, respectively; It is the score of an individual’s suitability for a role; the system is based on each individual’s Automatically optimize role allocation based on the team's overall task requirements to ensure maximum collaboration efficiency in future tasks; Formula value range: ∈[0,1], The closer it is to 1, the more suitable the individual is for the current task role.

Images