Teaching environment control system based on Internet of Things

Abstract

The invention relates to the technical field of teaching environment control, in particular to a teaching environment control system based on the Internet of Things, which comprises a data acquisition unit, a parameter control unit, a data processing unit and a data processing unit, the matching module is used for matching the environment state evaluation result with a preset teaching environment optimization rule base so as to obtain a control parameter set of the environment adjusting equipment; the environment adjusting unit is used for distributing the equipment control instruction set to the corresponding environment adjusting equipment execution unit based on the Internet of Things gateway so as to realize preliminary adjustment of the teaching environment; the comfort index unit is used for acquiring a student comfort index based on the student physiological response data; and the adjusting and optimizing unit is used for dynamically correcting the control parameter set based on the student comfort index. According to the invention, an environment adjusting strategy is continuously improved through a real-time feedback mechanism, so that a control effect is gradually optimized in long-term operation, and an efficient teaching environment is formed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of teaching environment control, and particularly relates to a teaching environment control system based on Internet of Things. BACKGROUND

[0002] Traditional methods are usually single in environmental regulation, mainly relying on the adjustment of a single environmental parameter (such as temperature, humidity) to realize comfort optimization, which may ignore the comprehensive influence of factors such as light, air quality, etc., while multi-modal environmental sensors can simultaneously collect multiple parameters (such as temperature, humidity, light, carbon dioxide concentration, etc.), more comprehensively considering the optimization requirements of the teaching environment; traditional methods often lack effective feedback mechanisms, usually adjusted through periodic manual detection or feedback of certain single sensors, with a relatively lagging response; traditional methods are usually not intelligent, often relying on manual setting or timed automatic control, and cannot make flexible adjustments according to real-time data; traditional methods are usually based on fixed rules and static models for adjustment, lacking a systematic learning and continuous optimization process. SUMMARY

[0003] The technical problem to be solved by the present application is to overcome the above-mentioned shortcomings of the prior art, and to provide a teaching environment control system based on Internet of Things.

[0004] The technical scheme adopted to solve the above technical problems is: a teaching environment control system based on Internet of Things, comprising:

[0005] a data acquisition unit for acquiring environmental parameters of a teaching area based on multi-modal environmental sensors, and performing standardized processing on the environmental parameters to obtain standard environmental parameters;

[0006] a control parameter unit for inputting the standard environmental parameters into a pre-trained environmental state evaluation model to obtain an environmental state evaluation result, and matching the environmental state evaluation result with a pre-set teaching environment optimization rule library to obtain a control parameter set of environmental regulation equipment;

[0007] an environmental regulation unit for generating a device control instruction set based on the control parameter set, distributing the device control instruction set to the corresponding environmental regulation equipment execution unit based on an Internet of Things gateway, to realize preliminary regulation of the teaching environment;

[0008] a comfort index unit for acquiring student physiological response data based on a physiological signal acquisition module deployed on a student terminal, and obtaining a student comfort index based on the student physiological response data;

[0009] an adjustment optimization unit configured to dynamically modify the set of control parameters based on the student comfort index to obtain an optimal set of control parameters of the environmental adjustment device, and control the teaching environment based on the optimal set of control parameters.

[0010] Preferably, the environmental parameters include temperature distribution data, humidity gradient data, light intensity, and carbon dioxide concentration, the environmental adjustment device includes a variable frequency air conditioning cluster, an adaptive lighting array, and a fresh air regulation system, and the student physiological response data includes skin electrical response waveform, heart rate variability sequence, and eye movement trajectory features.

[0011] Preferably, the environmental state evaluation model is a deep neural network model trained based on a large amount of historical teaching environment data and corresponding teaching effect feedback data, the environmental state evaluation model performs feature extraction and pattern recognition on the standard environmental parameters to obtain a state evaluation result of the teaching environment, and the environmental state evaluation model includes an input layer, a hidden layer, and an output layer, wherein the hidden layer is configured to capture the spatiotemporal dynamic features of the environmental parameters.

[0012] Preferably, the environmental state evaluation result is matched with a preset teaching environment optimization rule library to obtain a set of control parameters of the environmental adjustment device, including:

[0013] comparing the environmental state evaluation result with a corresponding threshold in the teaching environment optimization rule library;

[0014] if the environmental state evaluation result exceeds the corresponding threshold, extracting corresponding initial control parameters of the environmental adjustment device from the teaching environment optimization rule library;

[0015] performing conflict detection and resolution processing on the initial control parameters to obtain a set of control parameters of the environmental adjustment device.

[0016] Preferably, the conflict detection and resolution processing on the initial control parameters to obtain a set of control parameters of the environmental adjustment device includes:

[0017] constructing a conflict relationship graph of the initial control parameters, wherein the nodes of the conflict relationship graph represent the initial control parameters, and the edges of the conflict relationship graph represent the conflict relationships between the initial control parameters;

[0018] performing traversal and resolution on the conflict relationship graph based on a preset conflict resolution strategy to obtain the set of control parameters after conflict resolution, wherein the conflict resolution strategy includes a priority sorting rule and a parameter compromise calculation method.

[0019] Preferably, the student comfort index is obtained based on the student physiological response data, including:

[0020] preprocessing the student physiological response data to obtain standardized physiological feature data, wherein the preprocessing comprises denoising, filtering and feature extraction operations;

[0021] inputting the standardized physiological feature data into a pre-trained student comfort prediction model, and performing comfort prediction on the standardized physiological feature data based on the student comfort prediction model to obtain the student comfort index.

[0022] Preferably, the student comfort prediction model is trained based on a large amount of student physiological response data and corresponding subjective comfort evaluation data, and the student comfort prediction model adopts a cross-validation method for parameter optimization during the training process. The student comfort prediction model includes a data input layer, a fully connected layer and a prediction output layer. The data input layer is used to receive standardized physiological feature data, the fully connected layer is used to extract deep features of the physiological feature data, combine different physiological feature data in a nonlinear manner, and map to the final output, and the prediction output layer is used to output the student comfort index prediction result. The student comfort prediction model can dynamically adapt to the physiological feature differences of students of different ages by continuously learning the complex correlation between different physiological data and comfort, thereby improving the accuracy of comfort evaluation.

[0023] Preferably, the control parameter set is dynamically corrected based on the student comfort index to obtain an optimal control parameter set of the environmental regulation device, comprising:

[0024] obtaining an optimal control parameter adjustment range corresponding to the student comfort index based on a preset comfort control parameter mapping relationship table;

[0025] adjusting the control parameter set based on the optimal control parameter adjustment range to obtain a corrected control parameter set;

[0026] iteratively optimizing the corrected control parameter set based on a real-time feedback mechanism until the student comfort index reaches a preset student comfort threshold to obtain the optimal control parameter set;

[0027] The comfort control parameter mapping relationship table is constructed based on historical experimental data, and contains the optimal parameter range of various environmental regulation devices under different comfort levels, and is adaptively adjusted according to the actual teaching scene.

[0028] Preferably, the real-time feedback mechanism comprises:

[0029] real-time collection of actual student physiological response data after execution of the environmental regulation device;

[0030] inputting the actual student physiological response data into the student comfort prediction model to obtain a current student comfort index;

[0031] comparing the current student comfort index with the student comfort threshold value;

[0032] if the current student comfort index does not reach the student comfort threshold value, continue to modify the control parameter set until the student comfort threshold value is reached to obtain the optimal control parameter set.

[0033] Preferably, the teaching environment is controlled based on the optimal control parameter set, including:

[0034] transmitting the optimal control parameter set to the corresponding environment regulation device execution unit based on an Internet of Things communication protocol;

[0035] the environment regulation device execution unit accurately controls the variable frequency air conditioning cluster, the adaptive lighting array and the fresh air regulation system based on the received optimal control parameter set;

[0036] adjusting and optimizing the teaching environment based on the real-time feedback mechanism to ensure that the teaching environment is continuously maintained within the preset comfort range.

[0037] The beneficial effects of the present application are as follows: (1) The present application monitors the physiological signals and comfort index of students, and the system not only provides support for short-term learning environment adjustment, but also provides data basis for long-term health management of students, continuously monitors and optimizes the teaching environment, helps to improve the physical health and psychological state of students, and helps to improve the overall health level and learning experience of students; (2) The present application provides a scientific basis for teaching environment adjustment based on data analysis of environmental parameters and physiological signals, and through continuous collection and analysis of data, the system can continuously improve the environmental regulation strategy through the real-time feedback mechanism, thereby gradually optimizing the control effect in the long-term operation, forming an efficient teaching environment; (3) The present application collects environmental parameters and student physiological data in real time, and the system can adjust environmental control parameters in real time according to these data. This real-time feedback mechanism ensures that the teaching environment is always in the most suitable state, avoiding the decline in comfort due to external environmental changes (such as seasonal changes, changes in the number of people, etc.) or other uncontrollable factors; (4) The present application realizes the synchronous collection of multiple parameters of the teaching environment and the collaborative control of the equipment through the sensor network operating system and the Internet of Things communication technology, effectively solving the limitations of single parameter adjustment in traditional methods. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 a system flowchart of the overall system in an embodiment of the present application;

[0039] Reference signs: 1, data acquisition unit; 2, control parameter unit; 3, environment adjusting unit; 4, comfort index unit; 5, adjustment optimization unit. DETAILED DESCRIPTION

[0040] Embodiment one, as shown in the figure, the present application proposes a teaching environment control system based on Internet of Things, comprising: Figure 1

[0041] Data acquisition unit 1, for collecting the environmental parameters of the teaching area based on multi-modal environmental sensors, and standardizing the environmental parameters to obtain standard environmental parameters;

[0042] Control parameter unit 2, for inputting the standard environmental parameters into the pre-trained environmental state evaluation model to obtain the environmental state evaluation results, and matching the environmental state evaluation results with the preset teaching environment optimization rule library to obtain the control parameter set of the environmental adjusting device;

[0043] Environment adjusting unit 3, for generating device control instruction set based on the control parameter set, and distributing the device control instruction set to the corresponding environmental adjusting device execution unit based on the Internet of Things gateway to realize the preliminary adjustment of the teaching environment;

[0044] Comfort index unit 4, for obtaining student physiological response data based on the physiological signal acquisition module deployed on the student terminal, and obtaining the student comfort index based on the student physiological response data;

[0045] Adjustment optimization unit 5, for dynamically correcting the control parameter set based on the student comfort index to obtain the optimal control parameter set of the environmental adjusting device, and controlling the teaching environment based on the optimal control parameter set.

[0046] ​In the present application, the multi-modal environment sensor can simultaneously collect various environmental information such as temperature, humidity, light intensity, noise and other parameters, and different types of sensors work together to comprehensively monitor the environmental conditions of the teaching area; the standard environmental parameters refer to the environmental parameters in a unified format and range obtained by standardizing the collected environmental data, the purpose of this step is to eliminate the differences of different sensors or devices in the measurement process, so that the data remains consistent in the processing process; the environmental state evaluation result refers to the result obtained by the evaluation model, which is a state judgment of the suitability of the teaching environment; the teaching environment optimization rule library is used to guide how to optimize the teaching environment according to the environmental state evaluation result, and the rule library includes adjustment schemes for temperature, humidity, light and other aspects; the control parameter set of the environmental regulation device refers to the control parameter set generated by the system after determining how to optimize the teaching environment, these control parameters indicate how to adjust the working mode of the environmental regulation device; the device control instruction set refers to specific control instructions, including on-off, temperature adjustment, brightness adjustment and other instructions, which indicate how each environmental regulation device acts; the Internet of Things network connects different Internet of Things devices as a data transmission intermediary between devices and the central control system, and the gateway is responsible for transmitting control instructions to each environmental regulation device; the environmental regulation device execution unit refers to the device that actually executes environmental regulation, such as air conditioner, humidifier, lighting system, etc.; the physiological signal acquisition module refers to the module deployed on the student terminal device, which is used to acquire physiological data of students in real time, such as heart rate, body temperature, skin electric response, etc., through which the physiological state of students can be understood; the student physiological response data refers to the physiological state data of students obtained by the physiological signal acquisition module, which reflects the physiological response of students, such as whether they feel uncomfortable, fatigue or anxiety, etc.; the student comfort index refers to the index calculated based on the student physiological response data, which represents the comfort level of students in the current environment, and a higher comfort index usually indicates that students feel comfortable in the environment, and a lower one indicates discomfort.

[0047] In embodiment two, the present application proposes a teaching environment control system based on Internet of Things, compared with embodiment one, the present embodiment further includes that the environmental parameters include temperature distribution data, humidity gradient data, light intensity and carbon dioxide concentration, the environmental regulation device includes a variable frequency air conditioner cluster, an adaptive lighting array and a fresh air regulation system, and the student physiological response data includes skin electric response waveform, heart rate variability sequence and eye movement trajectory features.

[0048] In an optional embodiment, the environment state evaluation model is a deep neural network model trained based on a large amount of historical teaching environment data and corresponding teaching effect feedback data. The environment state evaluation model performs feature extraction and pattern recognition on the standard environment parameters to obtain the state evaluation result of the teaching environment. The environment state evaluation model includes an input layer, a hidden layer, and an output layer. The hidden layer is used to capture the spatiotemporal dynamic characteristics of the environment parameters.

[0049] It should be noted that the historical teaching environment data refers to the teaching environment related data collected in the past period of time, which includes environmental parameters such as temperature, humidity, and illumination, as well as other factors that may affect the teaching effect. The teaching effect feedback data refers to the data feedback related to the teaching effect, such as students' learning performance, learning attitude, classroom participation, and satisfaction, which can reflect the influence of the teaching environment on students' learning. Pattern recognition is used to determine the relationship between different combinations of environmental parameters and teaching effect, helping to evaluate the suitability of the teaching environment. The input layer receives the standard environment parameters as input. The output layer is used to predict the suitability of the teaching environment based on the environmental parameters.

[0050] In an optional embodiment, the environment state evaluation result is matched with a preset teaching environment optimization rule library to obtain a control parameter set of the environment adjustment device, including:

[0051] Comparing the environment state evaluation result with the corresponding threshold in the teaching environment optimization rule library;

[0052] If the environment state evaluation result exceeds the corresponding threshold, the initial control parameters of the corresponding environment adjustment device are extracted from the teaching environment optimization rule library;

[0053] The initial control parameters are subjected to conflict detection and resolution processing to obtain the control parameter set of the environment adjustment device.

[0054] It should be noted that the initial control parameters refer to the first step device adjustment parameters for the environment state extracted according to the rule library. Conflict detection refers to checking whether there is a contradiction between multiple initial control parameters, for example, the air conditioner commands one area to warm up while another area requires cooling down at the same time, which needs to be detected. Resolution processing refers to coordinating or optimizing the detected conflicts so that all control parameters can be executed simultaneously without mutual contradiction.

[0055] In an optional embodiment, the initial control parameters are subjected to conflict detection and resolution processing to obtain the control parameter set of the environment adjustment device, including:

[0056] constructing a conflict relation graph of the initial control parameters, wherein nodes of the conflict relation graph represent the initial control parameters, and edges of the conflict relation graph represent conflict relations between the initial control parameters;

[0057] performing traversal and resolution on the conflict relation graph based on a preset conflict resolution strategy to obtain a control parameter set after conflict resolution, wherein the conflict resolution strategy includes a priority sorting rule and a parameter compromise calculation method.

[0058] It should be noted that the traversal and resolution of the conflict relation graph means that by traversing all nodes (initial control parameters) and edges (conflict relations) in the conflict relation graph, each pair of conflicts is solved according to the preset conflict resolution strategy, the traversal is performed in a depth-first manner to check and handle the conflicts, and finally a control parameter set after conflict resolution is generated; the priority sorting rule means that the conflicts are solved according to the importance or priority of different control parameters, for example, the temperature of an air conditioner can be set as a high priority, and if the temperature of the air conditioner and the humidity adjustment conflict, the setting of the temperature of the air conditioner is given priority; the parameter compromise calculation method means that in the case of conflict, the conflicting parameters are adjusted by a compromise method to find a balance point, for example, when the temperature and the humidity conflict, the temperature can be adjusted to 26°C and the humidity to 50% to achieve a balance between the two.

[0059] In an optional embodiment, the student comfort index is obtained based on student physiological response data, including:

[0060] The student physiological response data is preprocessed to obtain standardized physiological feature data, wherein the preprocessing includes denoising, filtering and feature extraction operations;

[0061] The standardized physiological feature data is input into a pre-trained student comfort prediction model, and the student comfort prediction model is used to predict the comfort of the standardized physiological feature data to obtain the student comfort index.

[0062] It should be noted that feature extraction refers to extracting features meaningful for analysis from original physiological response data, for example, the average value of heart rate, and the extracted features can be used to describe the physiological state of the student; the student comfort prediction model is a model specially used for predicting the comfort of the student, which receives standardized physiological feature data as input and outputs a numerical value representing the comfort, called the comfort index, and the prediction of the student comfort prediction model is based on the relationship between the physiological state of the student and the comfort thereof, for example, too fast heart rate may indicate that the student is not comfortable, and too high body temperature may affect the comfort of the student; the student comfort index refers to a quantitative index reflecting the comfort of the student, which is a numerical value output by the model, indicating the current comfort state of the student, and a higher comfort index indicates that the student feels comfortable, and a lower comfort index indicates that the student feels uncomfortable. The index can be used to guide environmental regulation, for example, if the student comfort index is low, the indoor temperature or humidity may need to be adjusted to improve the comfort of the student.

[0063] In an optional embodiment, the student comfort prediction model is trained based on a large amount of student physiological response data and corresponding subjective comfort evaluation data, the student comfort prediction model adopts a cross-validation method for parameter optimization during the training process, and the student comfort prediction model includes a data input layer, a fully connected layer, and a prediction output layer, wherein the data input layer is used to receive standardized physiological feature data, the fully connected layer is used to extract deep features of the physiological feature data, combine different physiological feature data in a nonlinear manner, and map to the final output, and the prediction output layer is used to output the prediction result of the student comfort index. The student comfort prediction model can dynamically adapt to the physiological feature differences of students of different ages by continuously learning the complex correlation between different physiological data and comfort, thereby improving the accuracy of comfort evaluation.

[0064] In an optional embodiment, the control parameter set is dynamically corrected based on the student comfort index to obtain an optimal control parameter set of the environmental regulation device, including:

[0065] Obtaining an optimal control parameter adjustment range corresponding to the student comfort index based on a preset comfort control parameter mapping relationship table;

[0066] Adjusting the control parameter set based on the optimal control parameter adjustment range to obtain a corrected control parameter set;

[0067] Iteratively optimizing the corrected control parameter set based on a real-time feedback mechanism until the student comfort index reaches a preset student comfort threshold to obtain an optimal control parameter set;

[0068] The comfort control parameter mapping relationship table is constructed based on historical experimental data, and contains the optimal parameter range of various types of environmental regulation devices under different comfort levels, and is adaptively adjusted according to actual teaching scenes.

[0069] It should be noted that the comfort control parameter mapping relationship table is a table constructed by experimental data or historical data, which contains the optimal working parameter range of various types of environmental regulation devices (such as temperature regulator, air conditioner, humidity controller, etc.) under different comfort levels. The table aims to guide how to adjust the parameters of environmental control devices according to different comfort requirements to achieve the ideal comfort level; the real-time feedback mechanism refers to the process of real-time monitoring and adjusting the environment according to the current comfort index of the students. Through continuous feedback and adjustment, the system can ensure that the adjustment of the environmental parameters meets the real-time needs of the students' comfort, and the iterative optimization refers to a repeated adjustment and optimization process. In this process, the corrected control parameter set will be continuously adjusted according to the real-time feedback of the comfort, until the preset comfort threshold is reached. The system improves the comfort of the environment through multiple cycle adjustments (each time based on the feedback of the last round for fine-tuning), until the optimal state is reached.

[0070] In an optional embodiment, the real-time feedback mechanism comprises:

[0071] Real-time collection of actual student physiological response data after the environmental regulation device is executed;

[0072] Inputting the actual student physiological response data into the student comfort prediction model to obtain the current student comfort index;

[0073] Comparing the current student comfort index with the student comfort threshold;

[0074] If the current student comfort index does not reach the student comfort threshold, continue to correct the control parameter set until the student comfort threshold is reached to obtain the optimal control parameter set.

[0075] It should be noted that the real-time collection of the actual physiological response data of the students after the execution of the environmental adjustment device refers to the real-time collection of the physiological data (such as body temperature, heart rate, skin temperature, and respiratory rate) of the students by the sensors or monitoring devices after the adjustment of the environmental control system. These physiological response data can reflect whether the students feel comfortable in the adjusted environment and whether the adjustment of the environment has the expected impact on the comfort of the students. The current student comfort index refers to a numerical value calculated by the student comfort prediction model, which is used to represent the current comfort state of the students. The optimal control parameter set refers to the best environmental control parameter configuration finally obtained after multiple rounds of adjustment and optimization. By continuously correcting the control parameter set, the system finally finds the parameter combination that can maximize the comfort of the students. When the student comfort index reaches the preset comfort threshold, the system considers that the current control parameter set has reached the optimum.

[0076] In an optional embodiment, the teaching environment is controlled based on the optimal control parameter set, including:

[0077] The optimal control parameter set is transmitted to the corresponding environmental adjustment device execution unit based on the Internet of Things communication protocol;

[0078] The environmental adjustment device execution unit accurately controls the variable frequency air conditioning cluster, the adaptive lighting array, and the fresh air regulation system based on the received optimal control parameter set;

[0079] The teaching environment is adjusted and optimized based on the real-time feedback mechanism to ensure that the teaching environment is continuously maintained within the preset comfort range.

[0080] It should be noted that accurate control refers to the ability of the environmental adjustment device to accurately adjust the working state of each device based on the received optimal control parameter set to ensure that the environment is continuously adjusted to the preset comfort range. Adjustment and optimization refer to the optimization of the state of the environment based on real-time feedback and adjustment of the control parameters. For example, factors such as temperature, humidity, and air circulation need to be continuously adjusted to maintain the best learning environment at different time periods or seasons. During the adjustment and optimization process, the system will automatically correct each control parameter based on real-time data to ensure that the environment is continuously within the predetermined comfort range.

[0081] The embodiments of the present application are described in detail above in combination with the drawings, but the present application is not limited thereto. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the purpose of the present application.

Claims

1. A teaching environment control system based on the Internet of Things, characterized in that, include: The data acquisition unit (1) is used to collect environmental parameters of the teaching area based on multimodal environmental sensors, and to standardize the environmental parameters to obtain standard environmental parameters. The control parameter unit (2) is used to input the standard environmental parameters into the pre-trained environmental state assessment model to obtain the environmental state assessment result, and to match the environmental state assessment result with the preset teaching environment optimization rule library to obtain the control parameter set of the environmental adjustment equipment. The environmental adjustment unit (3) is used to generate a set of equipment control instructions based on the set of control parameters, and distribute the set of equipment control instructions to the corresponding environmental adjustment equipment execution unit based on the Internet of Things gateway, so as to achieve the initial adjustment of the teaching environment; The comfort index unit (4) is used to obtain student physiological response data based on the physiological signal acquisition module deployed on the student terminal, and to obtain the student comfort index based on the student physiological response data. The adjustment and optimization unit (5) is used to dynamically modify the control parameter set based on the student comfort index to obtain the optimal control parameter set of the environmental adjustment equipment, and to control the teaching environment based on the optimal control parameter set.

2. The teaching environment control system based on the Internet of Things according to claim 1, characterized in that, The environmental parameters include temperature distribution data, humidity gradient data, light intensity, and carbon dioxide concentration. The environmental control equipment includes variable frequency air conditioning clusters, adaptive lighting arrays, and fresh air control systems. The student's physiological response data includes skin conductance waveforms, heart rate variability sequences, and eye movement trajectory characteristics.

3. The teaching environment control system based on the Internet of Things according to claim 2, characterized in that, The environmental state assessment model is a deep neural network model trained based on a large amount of historical teaching environment data and corresponding teaching effect feedback data. The environmental state assessment model performs feature extraction and pattern recognition on the standard environmental parameters to obtain the state assessment result of the teaching environment. The environmental state assessment model includes an input layer, a hidden layer and an output layer, wherein the hidden layer is used to capture the spatiotemporal dynamic features of the environmental parameters.

4. The teaching environment control system based on the Internet of Things according to claim 3, characterized in that, The environmental condition assessment results are matched with a pre-set teaching environment optimization rule base to obtain a set of control parameters for the environmental control equipment, including: The environmental status assessment results are compared with the corresponding thresholds in the teaching environment optimization rule base; If the environmental status assessment result exceeds the corresponding threshold, the initial control parameters of the corresponding environmental adjustment equipment are extracted from the teaching environment optimization rule base. The initial control parameters are subjected to conflict detection and resolution to obtain the control parameter set of the environmental control equipment.

5. A teaching environment control system based on the Internet of Things according to claim 4, characterized in that, The initial control parameters are subjected to conflict detection and resolution processing to obtain the control parameter set of the environmental control equipment, including: Construct a conflict relationship graph of the initial control parameters, wherein the nodes of the conflict relationship graph represent the initial control parameters, and the edges of the conflict relationship graph represent the conflict relationships between the initial control parameters; The conflict relationship graph is traversed and resolved based on a preset conflict resolution strategy to obtain the set of control parameters after conflict resolution. The conflict resolution strategy includes priority sorting rules and parameter trade-off calculation methods.

6. A teaching environment control system based on the Internet of Things according to claim 5, characterized in that, The student comfort index is obtained based on the student physiological response data, including: The student physiological response data is preprocessed to obtain standardized physiological feature data, wherein the preprocessing includes noise reduction, filtering and feature extraction operations; The standardized physiological characteristic data is input into a pre-trained student comfort prediction model, and the student comfort index is obtained by predicting the comfort level of the standardized physiological characteristic data based on the student comfort prediction model.

7. A teaching environment control system based on the Internet of Things according to claim 6, characterized in that, The student comfort prediction model is trained based on a large amount of student physiological response data and corresponding subjective comfort evaluation data. During training, the model employs cross-validation for parameter optimization. The model comprises a data input layer, a fully connected layer, and a prediction output layer. The data input layer receives standardized physiological feature data. The fully connected layer performs deep feature extraction on the physiological feature data, non-linearly combines different physiological feature data, and maps them to the final output. The prediction output layer outputs the predicted student comfort index. By continuously learning the complex correlation between different physiological data and comfort, the student comfort prediction model can dynamically adapt to the physiological differences among students of different age groups, improving the accuracy of comfort assessment.

8. A teaching environment control system based on the Internet of Things according to claim 7, characterized in that, The control parameter set is dynamically adjusted based on the student comfort index to obtain the optimal control parameter set for the environmental control equipment, including: The optimal control parameter adjustment range corresponding to the student comfort index is obtained based on the preset comfort control parameter mapping table. The control parameter set is adjusted based on the optimal control parameter adjustment range to obtain a corrected control parameter set; The modified control parameter set is iteratively optimized based on a real-time feedback mechanism until the student comfort index reaches the preset student comfort threshold, so as to obtain the optimal control parameter set. The comfort control parameter mapping table is constructed based on historical experimental data, containing the optimal parameter ranges of various environmental adjustment devices under different comfort levels, and is adaptively adjusted according to actual teaching scenarios.

9. A teaching environment control system based on the Internet of Things according to claim 8, characterized in that, The real-time feedback mechanism includes: Real-time collection of actual student physiological response data after the environmental regulation equipment is activated; The actual student physiological response data is input into the student comfort prediction model to obtain the current student comfort index. Compare the current student comfort index with the student comfort threshold; If the current student comfort index does not reach the student comfort threshold, the control parameter set is further modified until the student comfort threshold is reached to obtain the optimal control parameter set.

10. A teaching environment control system based on the Internet of Things according to claim 9, characterized in that, Controlling the teaching environment based on the aforementioned optimal set of control parameters includes: The optimal control parameter set is transmitted to the corresponding environmental control device execution unit based on the Internet of Things communication protocol; The environmental control equipment execution unit performs precise control on the variable frequency air conditioning cluster, adaptive lighting array, and fresh air control system based on the received optimal control parameter set; The teaching environment is adjusted and optimized based on the real-time feedback mechanism to ensure that the teaching environment is continuously maintained within a preset comfort range.

Images