Rescue training efficiency evaluation system and optimization method thereof

Abstract

The invention discloses a rescue training efficiency evaluation system and an optimization method thereof, and belongs to the technical field of efficiency evaluation, the rescue training efficiency evaluation system comprises a data acquisition module used for collecting performance data and situation data of rescue personnel in simulated training; the fuzzy logic processing module is connected to the data acquisition module and is used for fuzzifying the performance data and establishing a fuzzy rule base; according to the method, a fuzzy logic theory is adopted, specific performance data of ambulance personnel in simulation training is converted into a fuzzy set, accurate numerical values are mapped to a fuzzy concept, a fuzzy membership function is defined, a system constructs the fuzzy set for each evaluation index, and therefore the data are allowed to cross traditional classification boundaries, and the accuracy of the ambulance personnel is improved. And the uncertainty and continuity of the performance of the ambulance personnel can be better captured.

Description

Technical Field

[0001] The present invention relates to the technical field of performance evaluation, and specifically to an ambulance training performance evaluation system and its optimization method. Background Art

[0002] Ambulance training performance evaluation refers to a systematic evaluation process of the skills, knowledge, behaviors, and overall performance of ambulance personnel after receiving training. The purpose of the evaluation is to ensure that ambulance personnel can meet the specified ambulance standards and effectively perform ambulance tasks in actual emergency situations.

[0003] Most of the existing ambulance training performance evaluation systems rely on traditional statistical methods or simple scoring systems for evaluation, and cannot comprehensively and deeply capture the complexity and dynamics in ambulance training. Ambulance training not only involves the mastery of skills, but also includes multi-dimensional abilities such as decision-making ability, teamwork, and stress management, which are difficult to comprehensively cover by simple statistical methods.

[0004] At the same time, the evaluation indicators are usually static, which means they are evaluated based on preset standards and rules. However, the behaviors and performances of ambulance personnel change over time, situations, and experience, and static evaluation indicators cannot adapt to these changes, resulting in the evaluation results not matching the actual abilities of ambulance personnel. When the performance of an ambulance personnel in a simulated emergency situation may vary due to nervousness or lack of experience, static evaluation indicators cannot reflect this difference. Therefore, an ambulance training performance evaluation system and its optimization method are proposed.

[0005] The above information disclosed in this background art is only used to increase the understanding of the background art of the present invention. Therefore, it may include prior art that is not known to those of ordinary skill in the art. Summary of the Invention

[0006] The present invention aims to solve at least one of the technical problems existing in the prior art. For this reason, an object of the present invention is to propose an ambulance training performance evaluation system and its optimization method.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An ambulance training performance evaluation system, comprising:

[0009] A data acquisition module, configured to collect the performance data and scenario data of ambulance personnel in simulated training;

[0010] A fuzzy logic processing module, connected to the data acquisition module, configured to fuzzify the performance data and establish a fuzzy rule base;

[0011] An online learning module, connected to a fuzzy logic processing module, for training a model in real time to adapt to the behavioral changes of ambulance personnel;

[0012] A weight adjustment module, connected to the online learning module, for dynamically adjusting the weights of evaluation metrics according to the evaluation results of the fuzzy logic processing module and the output of the online learning module;

[0013] An evaluation output module, connected to the weight adjustment module, for outputting the final evaluation result of ambulance training effectiveness.

[0014] As a further optimization scheme of the present invention, the data acquisition module includes a video monitoring unit, an audio acquisition unit, a data synchronization and integration unit, and a data preprocessing unit;

[0015] Among them, the video monitoring unit includes a high-definition camera and an image processing system; the audio acquisition unit includes a microphone array and a sound analysis software; the data synchronization and integration unit includes a data synchronizer and a data integrator.

[0016] As a further optimization scheme of the present invention, the fuzzy logic processing module includes a data input interface unit, a fuzzification unit, a rule base establishment unit, a fuzzy inference engine unit, a defuzzification unit, and a result output unit;

[0017] Among them, the data input interface unit includes a data receiver and a data formatter; the fuzzification unit includes a fuzzification processor and a membership function library; the rule base establishment unit includes a rule editor and a rule memory; the fuzzy inference engine unit includes an inference mechanism and a conflict resolver; the defuzzification unit includes a defuzzification processor and a defuzzification method library; the result output unit includes an output converter and a result transmitter.

[0018] As a further optimization scheme of the present invention, the online learning module includes a data preprocessing unit, a model training unit, and a model update and optimization unit;

[0019] Among them, the data preprocessing unit includes a data cleaner and a feature extractor; the model training unit includes a learning algorithm library and a model trainer; the model update and optimization unit includes an incremental learner and an optimizer.

[0020] As a further optimization scheme of the present invention, the weight adjustment module includes a weight calculation unit, a weight optimization unit, and a weight storage and management unit;

[0021] Among them, the weight calculation unit includes a weight initializer and a dynamic weight adjustment algorithm; the weight optimization unit includes an optimization algorithm and a performance monitor; the weight storage and management unit includes a weight memory and a weight manager.

[0022] An optimization method for an ambulance training effectiveness evaluation system, comprising the following steps:

[0023] Step 1: Determine evaluation indicators and set initial weights;

[0024] Step 2: Collect performance data and scenario data during ambulance simulation training;

[0025] Step 3: Use a fuzzy logic system to process performance data and establish a rule base;

[0026] Step 4: Apply an online learning mechanism to train the model in real time;

[0027] Step 5: Dynamically adjust the weights of evaluation indicators according to the model output;

[0028] Step 6: Verify the effectiveness of weight adjustment and optimize it;

[0029] Step 7: Integrate the system and conduct a test run, collect user feedback and make iterative improvements.

[0030] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0031] The present invention adopts the fuzzy logic theory, converts the specific performance data of ambulance personnel in simulation training into fuzzy sets, which involves mapping precise numerical values to fuzzy concepts. By defining fuzzy membership functions, the system constructs fuzzy sets for each evaluation indicator, thereby allowing data to cross traditional classification boundaries and better capturing the uncertainty and continuity of the performance of ambulance personnel.

[0032] The present invention utilizes a fuzzy inference mechanism, which can process and analyze fuzzy data, thereby obtaining evaluation results that are closer to the actual situation and reducing information loss caused by data discretization in traditional evaluation methods.

[0033] The dynamic fuzzy rule base in the present invention can automatically adjust fuzzy rules according to the real-time performance and behavioral changes of ambulance personnel during training. It evolves continuously as training progresses. The system learns the optimal fuzzy rule configuration to improve the accuracy and adaptability of evaluation, and ensures that the evaluation results are more fair and effective according to the complexity and diversity of ambulance training.

[0034] The above summary is only for the purpose of the specification and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a block diagram of the module of the ambulance training efficiency evaluation system of the present invention;

[0036] Figure 2It is a flowchart of an optimization method for an ambulance training effectiveness evaluation system of the present invention. Detailed implementation manner

[0037] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0038] As shown in the appendix Figure 1 The ambulance training effectiveness evaluation system includes:

[0039] A data acquisition module for collecting the performance data and scenario data of ambulance personnel during simulated training;

[0040] A fuzzy logic processing module connected to the data acquisition module for fuzzifying the performance data and establishing a fuzzy rule base;

[0041] An online learning module connected to the fuzzy logic processing module for training the model in real time to adapt to the behavior changes of ambulance personnel;

[0042] A weight adjustment module connected to the online learning module for dynamically adjusting the weights of evaluation indicators according to the evaluation results of the fuzzy logic processing module and the output of the online learning module;

[0043] An evaluation output module connected to the weight adjustment module for outputting the final ambulance training effectiveness evaluation result.

[0044] The data acquisition module includes a video monitoring unit, an audio acquisition unit, a data synchronization and integration unit, and a data preprocessing unit;

[0045] Among them, the video monitoring unit includes a high-definition camera and an image processing system; the audio acquisition unit includes a microphone array and voice analysis software; the data synchronization and integration unit includes a data synchronizer and a data integrator.

[0046] Specifically, in the video monitoring unit, the high-definition camera is installed in the training ground for recording the operation process and scenes of ambulance personnel. The image processing system performs real-time analysis on the images captured by the camera to identify the actions and scene changes of ambulance personnel.

[0047] In the audio acquisition unit, the microphone array is distributed in the training ground for capturing the conversations and on-site sounds of ambulance personnel. The voice analysis software analyzes the voice commands and communication effects of ambulance personnel.

[0048] In the data synchronization and integration unit, a data synchronizer is used to ensure the timestamp synchronization of all sensors and monitoring devices. A data integrator integrates data from different sources to form a unified data stream for subsequent processing.

[0049] In the data preprocessing unit, a data cleaning tool removes invalid and incorrect data to ensure data quality. A data compression algorithm compresses the data to reduce the storage and transmission burden.

[0050] Furthermore, the min-max normalization formula is used:

[0051]

[0052] The fuzzy logic processing module includes a data input interface unit, a fuzzification unit, a rule base establishment unit, a fuzzy inference engine unit, a defuzzification unit, and a result output unit;

[0053] Among them, the data input interface unit includes a data receiver and a data formatter; the fuzzification unit includes a fuzzification processor and a membership function library; the rule base establishment unit includes a rule editor and a rule memory; the fuzzy inference engine unit includes an inference mechanism and a conflict resolver; the defuzzification unit includes a defuzzification processor and a defuzzification method library; the result output unit includes an output converter and a result transmitter.

[0054] Specifically, in the data input interface unit, the data receiver receives the performance data transmitted from the data acquisition module. The data formatter converts the received data into a format that the fuzzy logic processing module can recognize.

[0055] In the fuzzification unit, the fuzzification processor converts the precise input data into a fuzzy set. The membership function library stores the membership functions of different fuzzy sets for data fuzzification processing.

[0056] In the rule base establishment unit, the rule editor allows the algorithm to automatically create and modify fuzzy rules. The rule memory stores the established fuzzy rules.

[0057] In the fuzzy inference engine unit, the inference mechanism performs fuzzy logic inference based on the fuzzy rule base, processes the fuzzy input, and generates a fuzzy output. The conflict resolver decides which rules to execute first when multiple rules are triggered simultaneously.

[0058] In the defuzzification unit, the defuzzification processor converts the result of the fuzzy inference back into an exact output value. The defuzzification method library contains different defuzzification methods.

[0059] In the result output unit, the output converter converts the defuzzified result into a format that the evaluation system can use. The result transmitter transmits the processing result to other modules of the system.

[0060] More specifically, fuzzy sets and rules are defined. The response time and action accuracy of rescue personnel are used as input variables that need to be fuzzily processed. Fuzzy sets are defined for each input variable, defined as "fast", "medium", "slow" or "high", "medium", "low". Fuzzy inference rules are established, that is, "when the response time is fast and the action accuracy is high, the performance evaluation is excellent".

[0061] Fuzzification: Map the precise input data into the corresponding fuzzy sets, and use the membership function to determine the degree to which each data point belongs to each fuzzy set.

[0062] For each input data, apply the fuzzy rules to determine the rules that need to be activated. Take the minimum of the activated rules as the output of the rules, aggregate the outputs of all activated rules to form the total fuzzy output, and calculate the specific value according to the defuzzification method by the center average method as the final output of the fuzzy logic processing.

[0063] Compare the defuzzified result with the actual situation, and according to the verification result, adjust the definition of the fuzzy sets and the fuzzy rules. Integrate the output result of the fuzzy logic processing module into the entire rescue training performance evaluation system, and provide feedback to the rescue personnel according to the result of the fuzzy logic processing.

[0064] Furthermore, the formula for mapping the crisp value to the fuzzy set using the Gaussian membership function is:

[0065]

[0066] where μ is the mean of the Gaussian function and σ is the standard deviation.

[0067] In the fuzzy rules, use the if-then form, if x is A, then y is B; where A and B are fuzzy sets.

[0068] Minimum operation in the Mamdani inference method:

[0069] Activation intensity = min(μ A (x), μ B (y))

[0070] where μ A and μ B are membership functions.

[0071] The formula used to calculate the centroid of the fuzzy set in the center average method is:

[0072]

[0073] where u i is the membership degree, x iis an element of the fuzzy set.

[0074] The online learning module includes a data preprocessing unit, a model training unit, and a model updating and optimizing unit;

[0075] Among them, the data preprocessing unit includes a data cleaner and a feature extractor; the model training unit includes a learning algorithm library and a model trainer; the model updating and optimizing unit includes an incremental learner and an optimizer.

[0076] Specifically, in the data preprocessing unit, the data cleaner removes noise and irrelevant data. The feature extractor extracts useful features from the original data.

[0077] In the model training unit, the learning algorithm library contains learning algorithms for training the model. The model trainer uses the collected data and the selected algorithm to train the model.

[0078] The supervised learning algorithms include decision tree, support vector machine, random forest, neural network, gradient boosting machine, unsupervised learning algorithm, K-means clustering, hierarchical clustering, semi-supervised learning algorithm, autoencoder, image label propagation;

[0079] The specific steps are as follows: implement a class for each algorithm, this class inherits from the LearningAlgorithm interface, create an algorithm library management class for storing algorithm instances and providing methods for selecting and configuring algorithms, and use the algorithm library to select, configure and train the model.

[0080] In the model updating and optimizing unit, the incremental learner updates the model based on the original model using new data, and the optimizer uses gradient descent to adjust the model parameters.

[0081] More specifically, receive real-time training data, clean the data, remove noise and outliers, standardize the data format, use 70%-80% of the data in the dataset for training, and the remaining for testing, and use RandomForestClassifier in the scikit-learn library.

[0082] Subsequently, use the training set data to train the random forest model. During the model training process, each tree is constructed on a randomly sampled subset of data and a subset of features, and deploy the trained model to the ambulance training effectiveness evaluation system.

[0083] Furthermore, the information gain formula used in decision tree construction is:

[0084]

[0085] Among them, IG is the information gain, D is the dataset, a is the attribute, D v is a value of the attribute a.

[0086] The online gradient descent update formula is used in incremental learning:

[0087]

[0088] where θ is the model parameter, α is the learning rate, and J(θ) is the loss function.

[0089] The weight adjustment module includes a weight calculation unit, a weight optimization unit, and a weight storage and management unit;

[0090] Among them, the weight calculation unit includes a weight initializer and a dynamic weight adjustment algorithm; the weight optimization unit includes an optimization algorithm and a performance monitor; the weight storage and management unit includes a weight memory and a weight manager;

[0091] Specifically, in the weight calculation unit, the weight initializer assigns initial weights to each evaluation metric. The dynamic weight adjustment algorithm dynamically calculates and adjusts the weights according to real-time data and evaluation results.

[0092] In the weight optimization unit, the particle swarm optimization method is used to optimize the weight assignment, and the performance monitor monitors the evaluation performance after the weight adjustment.

[0093] In the weight storage and management unit, the weight memory stores the current and historical weight assignment situations. The weight manager manages the versions and updates of the weights.

[0094] Specifically, initial weights are assigned to each evaluation metric, the latest evaluation results are received from the fuzzy logic processing module and the online learning module, the performance of each evaluation metric is analyzed, those metrics that have a greater impact on the training efficiency are identified, and the adjustment requirements for the weights of each metric are calculated. The weights of the metrics are adjusted according to the suggestions output by the predefined rules, and the weights of each evaluation metric are dynamically updated. Whether the adjusted weights are reasonable and whether the evaluation accuracy is improved is verified through simulation tests. According to the verification results, the weights are adjusted. The adjusted weights are output to the evaluation output module for the final efficiency evaluation calculation.

[0095] Furthermore, in dynamic weight adjustment, the update formula of the recursive least squares method is used:

[0096]

[0097] where P is the covariance matrix and z is the observation vector.

[0098] Embodiment 2

[0099] As shown in the attached Figure 2 The optimization method of the ambulance training efficiency evaluation system includes the following steps:

[0100] Step 1: Determine evaluation metrics and set initial weights;

[0101] Step 2: Collect performance data and scenario data during ambulance simulation training;

[0102] Step 3: Process the performance data using a fuzzy logic system and establish a rule base;

[0103] Step 4: Apply an online learning mechanism to train the model in real time;

[0104] Step 5: Dynamically adjust the weights of the evaluation metrics according to the model output;

[0105] Step 6: Verify the effectiveness of the weight adjustment and optimize it;

[0106] Step 7: Integrate the system and conduct a test run, collect user feedback and make iterative improvements.

[0107] Any process or method description represented in the flowchart or described in other ways herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process. And the scope of the preferred embodiments of the present invention includes additional implementations, where functions may be performed in an order different from that shown or discussed, including performing functions in substantially simultaneous manners or in reverse order according to the functions involved, which should be understood by those skilled in the technical field to which the embodiments of the present invention belong.

[0108] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatuses, or devices.

[0109] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0110] Those of ordinary skill in the art can understand that all or part of the steps carried out in the method of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0111] In addition, each functional unit in various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0112] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. An ambulance training effectiveness evaluation system, characterized in that, Including: A data acquisition module, which is used to collect the performance data and scenario data of the rescue personnel during the simulation training; A fuzzy logic processing module, connected to the data acquisition module, which is used to fuzzify the performance data and establish a fuzzy rule base; An online learning module, connected to the fuzzy logic processing module, which is used to train the model in real time to adapt to the behavior changes of the rescue personnel; A weight adjustment module, connected to the online learning module, which is used to dynamically adjust the weights of the evaluation indicators according to the evaluation results of the fuzzy logic processing module and the output of the online learning module; An evaluation output module, connected to the weight adjustment module, which is used to output the final evaluation result of the rescue training effectiveness.

2. The ambulance training effectiveness evaluation system according to claim 1, wherein: The data acquisition module includes a video monitoring unit, an audio acquisition unit, a data synchronization and integration unit, and a data preprocessing unit; Among them, the video monitoring unit includes a high-definition camera and an image processing system; the audio acquisition unit includes a microphone array and a sound analysis software; the data synchronization and integration unit includes a data synchronizer and a data integrator.

3. The ambulance training effectiveness evaluation system according to claim 1, wherein: The fuzzy logic processing module includes a data input interface unit, a fuzzification unit, a rule base establishment unit, a fuzzy inference engine unit, a defuzzification unit, and a result output unit; Among them, the data input interface unit includes a data receiver and a data formatter; the fuzzification unit includes a fuzzification processor and a membership function library; the rule base establishment unit includes a rule editor and a rule memory; the fuzzy inference engine unit includes an inference mechanism and a conflict resolver; the defuzzification unit includes a defuzzification processor and a defuzzification method library; the result output unit includes an output converter and a result transmitter.

4. The ambulance training effectiveness evaluation system according to claim 1, wherein: The online learning module includes a data preprocessing unit, a model training unit, and a model update and optimization unit; Among them, the data preprocessing unit includes a data cleaner and a feature extractor; the model training unit includes a learning algorithm library and a model trainer; the model update and optimization unit includes an incremental learner and an optimizer.

5. The ambulance training effectiveness evaluation system according to claim 1, wherein: The weight adjustment module includes a weight calculation unit, a weight optimization unit, and a weight storage and management unit; Among them, the weight calculation unit includes a weight initializer and a dynamic weight adjustment algorithm; the weight optimization unit includes an optimization algorithm and a performance monitor; the weight storage and management unit includes a weight memory and a weight manager.

6. Optimization method for the effectiveness evaluation system of ambulance training, characterized in that, Including the following steps: Step 1: Determine the evaluation indicators and set the initial weights; Step 2: Collect the performance data and scenario data during the rescue simulation training; Step 3: Use the fuzzy logic system to process the performance data and establish a rule base; Step 4: Apply the online learning mechanism to train the model in real time; Step 5: Dynamically adjust the weights of the evaluation indicators according to the model output; Step 6: Verify the effectiveness of the weight adjustment and optimize it; Step 7: Integrate the system and conduct a test run, collect user feedback and make iterative improvements.

Images