Examination Seat Arrangement Method and System Based on Intelligent Examination Desks

Abstract

The present invention relates to the technical fields of intelligent education devices and examination management, and particularly to an examination seat arrangement method and system based on an intelligent examination desk. The method includes: collecting environmental data through the intelligent examination desk, and generating an environmental feature matrix in combination with implicit perception technology; dividing the examination room area based on a quantum dot distribution model, and optimizing seat allocation through reinforcement learning to generate optimized seat allocation data; using a multimodal verification module to complete candidate identity verification, binding the verification data with the optimized seat allocation data, unlocking the examination interface and loading examination tasks. The present invention effectively improves the fairness and intelligent level of examination seat allocation, realizes the preferential allocation of candidates with special needs and the dynamic management of the examination process, and has remarkable reliability and convenience.

Description

Technical Field

[0001] The present invention relates to the technical fields of intelligent education equipment and examination management, and particularly to an examination seat arrangement method and system based on an intelligent examination desk. Background Art

[0002] The reasonable arrangement of examination seats plays an important role in improving the fairness and efficiency of examinations. However, the currently widely used technologies usually rely on manual or semi-automated ranking systems, and these systems have significant defects. For example:

[0003] The prior art (Chinese invention patent, publication number: CN117132222A, title: An Examination Ranking System Based on Intelligent Desks and Chairs) mainly relies on intelligent desks and chairs and a ranking algorithm to arrange seats. Among them, a server is used to import candidate information, and a matching information between candidates and seats is generated through an automatic ranking algorithm with fixed rules. Candidate identity verification is completed through the MCU module of the desks and chairs in combination with an information reading device.

[0004] The prior art has the following defects: The existing fixed-rule ranking algorithms (such as column sorting method) cannot be intelligently adjusted according to the dynamic environmental parameters in the examination room and are difficult to adapt to changes in light, temperature, humidity, etc.; The perception of the environment in the prior art is limited to a small amount of static data (such as desk and chair numbers, candidate information), ignoring the impact of implicit environmental data (such as air flow, micro-vibration) on the comfort of the examination room; It is difficult for the prior art to achieve preferential care for candidates with special needs. For example, candidates who need specific seats due to physical conditions cannot have their seat allocations dynamically adjusted; Conflict detection and allocation optimization are relatively mechanized, and adaptive optimization technology is not introduced, easily resulting in low resource utilization. Summary of the Invention

[0005] In view of the above-mentioned many problems existing in the prior art, the present invention provides an examination seat arrangement method and system based on an intelligent examination desk. The present invention collects explicit and implicit environmental data, extracts environmental features by using a spatio-temporal convolutional neural network; divides the examination room area in combination with a quantum dot distribution model, further optimizes seat allocation by a reinforcement learning algorithm, and realizes identity verification and task loading through an intelligent examination desk. The final effect is to achieve dynamic environmental adaptation, special needs care, and intelligent management of the entire examination process.

[0006] An examination seat arrangement method based on an intelligent examination desk includes the following steps:

[0007] Collect environmental data of the examination room through an intelligent examination desk to generate environmental perception data; collect air flow and micro-vibration features in combination with implicit perception technology to generate implicit environmental data; integrate and process the environmental perception data and the implicit environmental data to generate an environmental feature matrix; receive and standardize the candidate information data;

[0008] Based on the environmental feature matrix and the physical layout of the examination room, a quantum dot distribution model is used to divide the examination room area and generate area suitability data; according to the area suitability data, candidates with special needs are preferentially assigned to suitable areas to generate area allocation data;

[0009] Based on the area allocation data and candidate information data, the seat status matrix is initialized, and preliminary seat allocation data is generated through a dynamic programming algorithm; conflict detection and optimization are performed on the preliminary seat allocation data, and a reinforcement learning algorithm is used to adjust the seat allocation plan to generate optimized seat allocation data;

[0010] Through the multi-modal verification module of the intelligent examination desk, biometric data of candidates is collected to complete identity verification and generate verified data; the verified data is bound to the optimized seat allocation data to complete the unlocking of the examination interface and task loading.

[0011] Preferably, the environmental data includes light intensity, humidity, temperature, and noise level, and the implicit environmental data is generated by a highly sensitive sensor configured inside the intelligent examination desk to detect air flow characteristics and micro-vibration frequency characteristics in real time.

[0012] Preferably, the environmental feature matrix performs dynamic feature extraction on environmental perception data and implicit environmental data through a spatio-temporal convolutional neural network, specifically including a joint analysis of spatial distribution and time change patterns to extract feature data of light uniformity, temperature and humidity stability, and noise change trends.

[0013] Preferably, the quantum dot distribution model uses a quantum energy simulation method to generate area suitability data through simulation calculations of quantum states of environmental suitability parameters in the examination room area. The area suitability data includes light stability values, noise interference values, and environmental temperature and humidity equilibrium values for each area.

[0014] Preferably, the area allocation data is generated through a reinforcement learning algorithm, where the allocation rule for candidates with special needs uses the area suitability score as a weight, and by calculating the comprehensive suitability scores of different candidate areas, the matching relationship between candidates with special needs and priority areas is dynamically adjusted.

[0015] Preferably, the preliminary seat allocation data is generated by jointly optimizing the area allocation data and candidate information data through a dynamic programming algorithm. The optimization process includes calculating the priority allocation sequence of seats in each area with the goal of minimizing the distance between candidates and meeting special needs.

[0016] Preferably, the optimized seat allocation data is generated through a conflict detection module and a reinforcement learning adjustment module, specifically including detecting conflict factors in the seat allocation plan and dynamically optimizing the allocation strategy according to the utilization rate of examination room resources and the priority of candidate needs.

[0017] Preferably, the multimodal verification module includes a fingerprint recognition module and a face recognition module, and the verification pass data is comprehensively generated from the matching results of fingerprint feature vectors and face feature vectors.

[0018] Preferably, the unlocking of the examination interface and the task loading include activating the examination permission of the examinee according to the verification pass data, loading the examination tasks in real time, and recording the start time, completion status, and abnormal operation information of the examination tasks.

[0019] A system for implementing the examination seat arrangement method based on the intelligent examination desk includes:

[0020] An environmental sensing module for collecting environmental data;

[0021] An implicit perception module for collecting air flow and micro-vibration characteristics;

[0022] An environmental feature analysis module for integrating environmental perception data and implicit environmental data and generating an environmental feature matrix;

[0023] An examinee information management module for receiving and standardizing examinee information data;

[0024] A region division module for dividing the examination room area based on the environmental feature matrix and the physical layout of the examination room using a quantum dot distribution model and generating region suitability data;

[0025] A seat arrangement module for generating region allocation data based on the region suitability data and initializing the seat status matrix, generating preliminary seat allocation data through a dynamic programming algorithm, and optimizing and generating optimized seat allocation data through a reinforcement learning algorithm;

[0026] A multimodal verification module for collecting biometric data of examinees and generating verification pass data;

[0027] An execution module for binding the verification pass data with the optimized seat allocation data and completing the unlocking of the examination interface and the task loading.

[0028] Compared with the prior art, the advantages and beneficial effects of the present invention are as follows:

[0029] The present invention combines explicit and implicit environmental data (such as light, air flow, etc.), generates an environmental feature matrix through a spatio-temporal convolutional neural network, and comprehensively optimizes the environmental suitability of seat arrangement;

[0030] By means of quantum state simulation and reinforcement learning technology, the present invention effectively improves the accuracy of the matching between examinees and seats, especially the priority allocation and optimization for examinees with special needs;

[0031] In the present invention, the multi-modal verification technology (such as the combination of fingerprint and face recognition) improves the security and accuracy of identity verification, ensuring the seamless connection of the process of binding candidates to seats;

[0032] The present invention realizes the precise management of examination permissions, and at the same time can record and analyze the execution status of examination tasks in real time, providing guarantee for the rapid response to abnormal behaviors. Brief Description of the Drawings

[0033] Figure 1 is a schematic flow chart of the method of the present invention;

[0034] Figure 2 is a schematic diagram of regional suitability division and allocation in the present invention;

[0035] Figure 3 is a schematic diagram of the generation of optimized seat allocation data in the present invention;

[0036] Figure 4 is a schematic diagram of multi-modal verification and task loading in the present invention;

[0037] Figure 5 is a block diagram of the structure of the system of the present invention. Detailed Embodiments

[0038] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the following detailed description, for the sake of explanation, many specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. However, obviously, one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts of the present disclosure.

[0039] The terms used herein are merely for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising" and the like used herein indicate the presence of the described features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components.

[0040] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0041] As Figure 1 shown, a method for arranging examination seats based on an intelligent examination desk includes the following steps:

[0042] Collect environmental data of the examination room through an intelligent examination platform to generate environmental perception data; collect air flow and micro-vibration characteristics by combining implicit perception technology to generate implicit environmental data; integrate and process the environmental perception data and implicit environmental data to generate an environmental feature matrix; receive and standardize the candidate information data;

[0043] The environmental sensing module equipped on the intelligent examination platform includes a light sensor, a temperature and humidity sensor, and a noise sensor, which are used to monitor the physical environment parameters in the examination room in real time. These data are directly collected by the sensors. For example, the light intensity is quantified as the illumination level, the temperature and humidity data are represented by the relative humidity and temperature values, and the noise level is recorded in the form of decibel (dB) values.

[0044] Implicit environmental data refers to characteristics that are difficult to directly capture by traditional sensors but have a significant impact on the environment, such as air flow and micro-vibration. Through highly sensitive pressure sensors and microfluid detectors built into the intelligent examination platform, the capture of air flow velocity, turbulence patterns, and micro-vibration signals caused by external vibration sources is realized.

[0045] All the collected data are integrated through a feature fusion module, combining information in the time dimension and space dimension to generate a multi-dimensional environmental perception data matrix. A spatio-temporal convolutional neural network (ST-CNN) is used to analyze these data matrices and extract key features, such as light uniformity, temperature and humidity stability, and noise distribution trends. Through convolutional operations, environmental features are represented as two-dimensional matrices, where each cell corresponds to the environmental suitability score of a specific area.

[0046] The identity information of candidates, including name, admission ticket number, and special requirement marks (such as light sensitivity, noise sensitivity, etc.), is pre-entered into the examination system. These information are read by the identity verification module when candidates log in to the intelligent examination platform.

[0047] The candidate information data are subjected to data cleaning and standardization processing to ensure unified data format, eliminate redundant information, and provide structured input for subsequent area allocation and seat arrangement. For example, special requirement marks are encoded into a specific tag set (such as "light sensitivity" is 1, "noise sensitivity" is 2).

[0048] Aggregate the processed environmental perception data and implicit environmental data by area. For example, the light, noise, and air flow characteristics around each examination platform are assigned to specific grid cells. Through area division and feature calculation, an environmental feature matrix is formed, where each row represents a specific area and each column corresponds to specific environmental features.

[0049] The environmental feature matrix is further dynamically analyzed through a neural network to capture the changing trends of environmental parameters over time, such as the fluctuation range of light intensity at different time periods.

[0050] Example: In a certain examination room, the intelligent examination desk is equipped with sensors that detect the light intensity in area A as 300 lux, the noise level as 60 dB, and the relative humidity as 50%. At the same time, the air velocity sensor records that the air flow in this area is relatively uniform, and the vibration sensor detects a low micro-vibration level. Combining with the implicit environmental data generated by the implicit perception technology, area A is marked as a highly suitable area.

[0051] Dynamic adaptation: A light-sensitive candidate is assigned to area A, and their special needs can be met. At the same time, the system dynamically updates the environmental feature matrix according to real-time changes. If the light intensity in area A increases to 500 lux (exceeding the suitable threshold), the system will reduce its suitability score and trigger a reallocation process.

[0052] Preferably, the environmental data includes light intensity, humidity, temperature, and noise level. The implicit environmental data is generated by highly sensitive sensors configured inside the intelligent examination desk to detect the air flow characteristics and micro-vibration frequency characteristics in real time.

[0053] The light sensor is arranged on the surface or top of the examination desk to capture the illumination intensity of the surrounding environment. The sensor quantifies the illumination intensity into a numerical signal and can record the uniformity and stability of the light in real time. These data are of great significance for the area adaptation of light-sensitive candidates (such as myopic or photophobic candidates).

[0054] The humidity and temperature sensors are installed near the examination desk to sense the local microclimate conditions in the examination room. The sensors measure the water vapor content and temperature changes in the air and transmit the data to the processing unit to generate the local humidity and temperature distribution characteristics of the examination room.

[0055] The noise sensor is based on acoustic wave capture technology and can accurately measure the sound pressure level (decibels) at a specific location. This data helps to identify areas with low noise and provides a suitable examination environment for noise-sensitive candidates.

[0056] The intelligent examination desk is equipped with a microfluidic detection module that generates air flow characteristic data in real time by sensing the air velocity and turbulent flow pattern. The air flow characteristics are used to identify areas with relatively stable air flow, thus avoiding discomfort or interference caused to candidates by air flow changes.

[0057] The highly sensitive pressure sensor is embedded in the base of the examination desk to capture the micro-vibration signals caused by external interference sources (such as nearby mechanical vibrations or people walking). Through frequency and amplitude analysis, vibration characteristic data is generated to determine whether a certain area has good vibration isolation.

[0058] All environmental data and implicit environmental data are integrated and processed by the sensor fusion module to form a multi-dimensional environmental feature matrix, providing input for subsequent regional suitability analysis. Through the feature extraction algorithm, the data is normalized to ensure the consistency of the suitability analysis.

[0059] The configuration of multi-type sensors ensures comprehensive coverage and real-time perception of environmental features, capable of capturing key parameters such as light, temperature and humidity, noise, air flow, and vibration. These data reflect the micro-environment differences in each area of the examination room, providing an accurate data basis for seat arrangement. The introduction of implicit environmental data makes up for the implicit environmental features that are difficult to capture by traditional sensors (such as micro-flow and vibration), significantly improving the comprehensiveness of environmental perception.

[0060] The real-time updated environmental data enables the system to quickly adjust the regional suitability score when the examination room conditions change. For example, when the light suddenly increases or the noise level rises in a certain examination desk area, the system can identify the unsuitable state of this area and dynamically adjust the candidate allocation strategy to ensure that the examination environment is always in the optimal state.

[0061] The precise monitoring of air flow and micro-vibration enables the system to effectively eliminate unstable factors in the environment. For example, areas with low vibration characteristics can be preferentially allocated to candidates who are vulnerable to external interference to ensure their concentration on the examination content. The comprehensive analysis of temperature, humidity, and light data provides a customized seat arrangement plan for candidates with special needs, improving the comfort and examination experience of candidates.

[0062] In an embodiment, in a certain examination room, the light sensor records the light intensity in area A as 400 lux, the temperature and humidity sensor records the relative humidity as 45% and the temperature as 22 °C, the noise sensor records the sound pressure level as 50 dB, the air flow velocity sensor records the flow velocity stable at 0.2 m / s, and the vibration sensor detects that the vibration frequency is in a low-frequency stable state (<10 Hz).

[0063] After system analysis, area A is marked as a suitable area, suitable for light-sensitive and noise-sensitive candidates. The system allocates a light-sensitive candidate to this area and dynamically monitors the light change to ensure environmental stability.

[0064] If the light intensity in area A increases to 600 lux (exceeding the suitable threshold), the system re-adjusts the suitability score and preferentially transfers the candidate to area B with uniform light.

[0065] Preferably, the environmental feature matrix performs dynamic feature extraction on environmental perception data and implicit environmental data through a spatio-temporal convolutional neural network, specifically including jointly analyzing the spatial distribution and time variation pattern to extract feature data such as light uniformity, temperature and humidity stability, and noise change trend.

[0066] Environmental perception data (such as light intensity, humidity, temperature, and noise level) and implicit environmental data (such as air flow characteristics and micro-vibration frequency characteristics) are divided into multiple spatial grid cells, and each grid represents a small area in the examination room. Through two-dimensional convolution operations, spatial features are extracted, such as the uniform distribution of light between regions, regional differences in temperature and humidity, and the local concentration of noise.

[0067] Based on the trend of data in each spatial unit changing over time, the network captures the dynamic change patterns in the time dimension through a temporal convolutional layer. For example, the fluctuations of the noise level at different time points, the periodic changes of the light intensity, and the gradual change trends of temperature and humidity.

[0068] The spatio-temporal convolutional neural network combines spatial features with temporal features through stacked convolutional layers to form a high-dimensional feature map containing temporal dynamics and spatial distribution characteristics. This feature map is used to generate the final environmental feature matrix.

[0069] By comparing the light intensities of different spatial units, calculating the standard deviation of the light distribution, and identifying areas with high light uniformity, which are suitable for light-sensitive candidates. Analyze the variation range of temperature and humidity over time, and mark areas with small fluctuations in temperature and humidity as high-suitability areas to improve the comfort of candidates. By detecting the fluctuation patterns of the noise level (such as the frequency and amplitude of sudden noise), evaluate the noise interference degree of the area, and allocate quiet areas for noise-sensitive candidates.

[0070] Map the high-dimensional features extracted by the spatio-temporal convolutional neural network into a two-dimensional matrix, where the rows represent spatial units and the columns represent different environmental features. The value of each cell in the matrix reflects the suitability score of the area for a certain environmental feature. For example, the first column of the matrix represents the light uniformity score, and the second column represents the temperature and humidity stability score.

[0071] The dynamic feature extraction ability of the spatio-temporal convolutional neural network enables the environmental feature matrix to comprehensively reflect the dynamic environmental conditions of the examination room. For example, when the light distribution is spatially uneven and there are temporal fluctuations, the system can accurately identify and mark these areas as low-suitability areas. The environmental feature matrix provides a quantitative basis for subsequent seat allocation. For example, directly guiding the area matching of candidates through the suitability scores in the matrix, and achieving the precise docking of candidate needs and environmental conditions. When the examination room environment changes (such as fluctuations in light intensity or a sudden increase in noise), the feature matrix can be updated in real time to support the dynamic adjustment of the seat allocation plan.

[0072] Through the comprehensive scores of different environmental features in the matrix, the system can give priority to meeting the suitability requirements of candidates with special needs, while ensuring that ordinary candidates are allocated to comfortable areas, thereby enhancing the fairness of the overall examination environment.

[0073] Example: Inside a certain examination hall, a light sensor records the light intensity in different areas. The data is divided into 4 grid cells, namely areas A, B, C, and D. Among them, the light intensity uniformity score in area A is 0.8, in area B is 0.5, in area C is 0.6, and in area D is 0.7. The noise sensor records that the noise fluctuation in area B is the smallest, with a score of 0.9.

[0074] Feature matrix generation: The spatio-temporal convolutional neural network integrates the above data to generate the following feature matrix:

[0075]

[0076] The system, based on the scores of the feature matrix, preferentially assigns light-sensitive candidates to area A and noise-sensitive candidates to area B. At the same time, it dynamically monitors the light changes. If the light intensity fluctuation in area A exceeds the threshold, the system immediately re-adjusts the matrix score and updates the allocation plan.

[0077] As Figure 2 shown, based on the environmental feature matrix and the physical layout of the examination hall, a quantum dot distribution model is used to divide the examination hall area to generate area suitability data; according to the area suitability data, candidates with special needs are preferentially assigned to suitable areas to generate area allocation data;

[0078] Preferably, the quantum dot distribution model uses a quantum energy simulation method to generate area suitability data by simulating and calculating the quantum states of environmental suitability parameters within the examination hall area. The area suitability data includes the light stability value, noise interference value, and environmental temperature and humidity balance value of each area.

[0079] The quantum energy simulation method draws on the concept of wave function in quantum physics, maps the environmental suitability parameters inside the examination hall to the eigenvalue of the quantum state, and forms quantitative data by calculating the suitability scores of various environmental factors within the area.

[0080] The fluctuation of the light intensity is regarded as the amplitude of the light wave. By calculating the consistency of the amplitude, the light stability value is obtained; the noise interference is simulated as the frequency distribution of the sound wave. The lower the noise interference value, the higher the low-frequency stability; the temperature and humidity are quantified as the average temperature and humidity deviation value within the area. The smaller the deviation, the better the balance.

[0081] Quantization of suitability parameters, quantum state formula:

[0082] ψ(x, t) = A(x)·e i(ωt-kx)

[0083] Among them, ψ(x, t) represents the comprehensive wave function representing the regional suitability; A(x) represents the amplitude of the environmental parameters in the region (such as light intensity); ω represents the change frequency in the time dimension; kx represents the wave vector in the space dimension, reflecting the spatial variation of the environmental parameters in the region. The model quantifies the suitability into a high-dimensional matrix by establishing wave functions for light, noise, temperature, and humidity respectively and combining the environmental data specific to the region.

[0084] Generate quantum state wave functions for the light, noise, temperature, and humidity of each region respectively, and calculate the regional suitability score through the superposition principle:

[0085] S = ∫ V |ψ(x, t)| 2 dx

[0086] Among them, S represents the regional suitability score; V represents the spatial volume of the target region; |ψ(x, t)| 2 represents the total suitability intensity of the regional environmental parameters. The weighted calculation of each parameter score generates the final regional suitability data.

[0087] By quantifying and dynamically simulating the environmental parameters through the quantum energy simulation method, the accuracy of the environmental suitability assessment is significantly improved. For example, the fluctuation of light intensity not only reflects the current environmental conditions but also takes into account its change trend over time. The suitability scores of different regions can intuitively reflect the environmental quality differences in the examination room, providing strong support for regional allocation.

[0088] Since the quantum state simulation can capture the changes in the spatial and time dimensions, the regional suitability data can be updated in real time to ensure that the system can quickly adjust the seat allocation plan when the environmental conditions change. For example, when the noise level suddenly increases at a certain moment, the system reduces the suitability score of that region and preferentially allocates other regions.

[0089] The generation of regional suitability data realizes the precise matching of the needs of candidates and environmental conditions. For example, candidates sensitive to light are preferentially allocated to regions with higher light stability values, and candidates sensitive to noise are allocated to regions with lower noise interference values.

[0090] Example: A certain examination room is divided into 4 regions (A, B, C, D), and the environmental parameters are as follows:

[0091] Region A: The fluctuation of light intensity is low (uniform amplitude), the noise frequency distribution is mainly low-frequency, and the deviation of temperature and humidity is small;

[0092] Region B: The light intensity is high but unstable, the noise interference frequency is high, and the temperature and humidity fluctuate greatly;

[0093] Region C: The light is relatively uniform but dim, the noise is stable and low, and the change range of temperature and humidity is moderate;

[0094] Area D: The light is uneven, the high frequency accounts for a large proportion in the noise frequency distribution, and the temperature and humidity deviation is relatively large.

[0095] Calculation of suitability score:

[0096] The quantum state wave function of the light in Area A is ψ A (x, t) = 0.8·e i(0.2t-0.1x) , and the noise wave function is ψ A_noise (x, t) = 0.98·e i(0.1t-0.05x) , and the temperature and humidity wave function is ψ A_temp (x, t) = 0.7·e i(0.3t-0.1x) . The total suitability score of Area A is:

[0097] S A = 0.4·∫ V |ψ A (x, t)| 2 dx + 0.3·∫ V |ψ A_noise (x, t)| 2 dx + 0.3·∫ V |ψ A_temp (x, t)| 2 dx

[0098] The result shows that the suitability score of Area A is 0.85. The system preferentially assigns light-sensitive and noise-sensitive candidates to Area A according to the suitability score, assigns ordinary candidates to Area C, and marks Areas B and D as low-suitability areas.

[0099] Preferably, the area allocation data is generated by a reinforcement learning algorithm, and the allocation rule for candidates with special needs uses the area suitability score as a weight. By calculating the comprehensive suitability scores of different candidate areas, the matching relationship between candidates with special needs and the priority areas is dynamically adjusted.

[0100] The reinforcement learning algorithm adopted by the present invention realizes seat allocation optimization in the form of "intelligent agent - environment interaction". The intelligent agent (Agent) observes the current environmental state (i.e., the matching situation between the area suitability score and candidates with special needs) in each allocation operation, takes actions (allocating candidates to specific areas), and obtains rewards (Reward) from the environmental feedback.

[0101] State space S: Composed of the suitability scores of each area and the special needs of candidates, such as the light uniformity score, noise interference value, temperature and humidity balance value of the area, and the demand labels of candidates (such as light-sensitive, noise-sensitive, etc.). Action space A: The operation of allocating candidates to a specific area.

[0102] Reward function:

[0103]

[0104] Among them, R represents the total reward value; w1 represents the weight coefficient, which is used to adjust the influence degree of different suitability parameters; Q i represents the suitability score of the area; D i represents the corresponding suitability parameter of the candidate's needs; Match(Q i , D i ) represents the matching degree between the area suitability and the candidate's needs.

[0105] The reinforcement learning agent establishes an initial matching scheme based on the initial area suitability score and the candidate's needs. As the environmental state changes (such as the light intensity fluctuation or noise increase in a certain area), the system recalculates the area suitability score and updates the state space. The reinforcement learning agent adjusts the matching scheme according to the new state to maximize the reward function value. Through multiple rounds of training, the agent gradually optimizes the allocation strategy to make the matching scheme tend to be globally optimal.

[0106] The comprehensive suitability score is a weighted combination of the area suitability parameter and the candidate's needs:

[0107]

[0108] Among them, S total represents the comprehensive suitability score; w i represents the weight of the suitability parameter. For example, the weight of light uniformity may be higher than the weight of noise interference; Q j represents the suitability score of a certain parameter in the area.

[0109] Through the dynamic adjustment of the reinforcement learning algorithm, candidates with special needs can be preferentially matched to areas that meet their needs. For example, candidates sensitive to light will be assigned to areas with a higher light stability value, while candidates sensitive to noise will be assigned to areas with a lower noise interference value. The introduction of the comprehensive suitability score ensures that the system comprehensively considers multiple environmental parameters during the matching process and avoids over-optimization of a single parameter.

[0110] As the real-time change of the examination room environment (such as a sudden increase in noise in a certain area), the system can quickly adjust the area suitability score and dynamically optimize the allocation scheme to ensure that candidates are always in a suitable examination environment.

[0111] After multiple rounds of training, the reinforcement learning algorithm can quickly generate an optimal allocation scheme, significantly improving the allocation efficiency, while ensuring fair consideration of the needs of different candidates.

[0112] Example: The examination room is divided into three areas (A, B, C), and the initial suitability scores of each area are:

[0113] Area A: Light uniformity is 0.8, noise interference value is 0.9, temperature and humidity balance value is 0.7;

[0114] Area B: Light uniformity is 0.7, noise interference value is 0.8, temperature and humidity balance value is 0.6;

[0115] Area C: Light uniformity is 0.6, noise interference value is 0.7, temperature and humidity balance value is 0.8.

[0116] Special requirements of candidates: Candidate X: Light-sensitive; Candidate Y: Noise-sensitive.

[0117] Reinforcement learning process:

[0118] Based on the area scores and candidate requirements, the system calculates the comprehensive suitability score:

[0119] Area A: The comprehensive score is 0.4·0.8 + 0.3·0.9 + 0.3·0.7 = 0.79;

[0120] Area B: The comprehensive score is 0.4·0.7 + 0.3·0.8 + 0.3·0.6 = 0.72;

[0121] Area C: The comprehensive score is 0.4·0.6 + 0.3·0.7 + 0.3·0.8 = 0.69.

[0122] After the light uniformity in Area A drops to 0.5 due to the fluctuation of light intensity, the system recalculates the comprehensive score, and the result is:

[0123] Area A: The comprehensive score drops to 0.4·0.5 + 0.3·0.9 + 0.3·0.7 = 0.68;

[0124] The system adjusts the allocation plan for Candidate X and transfers him from Area A to Area B.

[0125] Final plan: Candidate X is assigned to Area B with the best light uniformity; Candidate Y is assigned to Area A with the lowest noise interference value.

[0126] As Figure 4 shown, based on the area allocation data and candidate information data, initialize the seat status matrix, and generate the preliminary seat allocation data through the dynamic programming algorithm; perform conflict detection and optimization on the preliminary seat allocation data, and use the reinforcement learning algorithm to adjust the seat allocation plan to generate the optimized seat allocation data;

[0127] Preferably, the preliminary seat allocation data is generated by jointly optimizing the area allocation data and candidate information data through the dynamic programming algorithm, and the optimization process includes calculating the priority allocation sequence of seats in each area with the goal of minimizing the distance between candidates and meeting special requirements.

[0128] Dynamic Programming (DP) is a method for solving optimization problems, mainly achieved by decomposing complex problems into sub-problems and recursively solving them. In the present invention, the core of the dynamic programming algorithm lies in establishing a recurrence equation to optimize the matching scheme between candidates and seats.

[0129] Let f(i, j) represent the minimum cost of allocating the first i candidates to the first j seats, where the cost includes the distance between candidates and the penalty for not meeting special requirements.

[0130] Transition equation:

[0131]

[0132] Among them, C(i, j) represents the incremental cost of allocating the i-th candidate to the j-th seat; k represents the possible seat selection of the previous candidate; f(i - 1, k) represents the optimal allocation scheme for the first i - 1 candidates.

[0133] The distance between candidates, and the distance cost is calculated based on the physical distance between candidates:

[0134]

[0135] Among them, x i , y i represent the target seat coordinates of candidate i; x j , y j represent the target seat coordinates of candidate j. For allocations that do not meet special requirements, a penalty term is introduced:

[0136] P(i, j) = α · (1 - M(i, j))

[0137] Among them, M(i, j) represents a binary matching function indicating whether candidate i meets special requirements (1 for meeting, 0 for not meeting); α is the penalty weight coefficient.

[0138] The goal of the dynamic programming algorithm is to minimize the following total cost:

[0139]

[0140] Among them, n represents the total number of candidates, and m represents the total number of seats.

[0141] Based on the regional suitability score, the dynamic programming algorithm gives priority to seat allocations within high-suitability regions to ensure that candidates with special requirements can be preferentially allocated to the seats that best meet their needs.

[0142] The dynamic programming algorithm reduces the discomfort caused by excessive concentration or dispersion among candidates, such as noise interference or light occlusion, by minimizing the distance between candidates. The distance distribution among candidates is more uniform, improving the comfort of the overall examination environment.

[0143] The allocation priority of candidates with special needs is fully guaranteed. For example, candidates sensitive to light can be preferentially allocated to seats in areas with uniform light, and candidates sensitive to noise are preferentially allocated to low-noise areas.

[0144] The dynamic programming algorithm can quickly adjust the allocation plan when environmental parameters or candidate requirements change, ensuring the dynamic adaptability of the plan.

[0145] In an embodiment, the examination hall is divided into three areas (A, B, C), and the suitability scores of each area are as follows:

[0146] Area A: 0.85; Area B: 0.72; Area C: 0.65.

[0147] Candidates with special needs include: Candidate X (noise-sensitive); Candidate Y (light-sensitive).

[0148] The initial state is defined as each candidate not yet being allocated a seat. For Candidate X, the system calculates the best seat selection in Area A, and the optimization formula is:

[0149]

[0150] The result shows that the optimal seat in Area A is located in the central position. For Candidate Y, the system preferentially selects a seat in Area B based on the light stability value. Final allocation plan: Candidate X is allocated to the central seat in Area A; Candidate Y is allocated to the seat with the highest light stability value in Area B.

[0151] Preferably, the optimized seat allocation data is generated by a conflict detection module and a reinforcement learning adjustment module, specifically including detecting conflict factors in the seat allocation plan and dynamically optimizing the allocation strategy according to the utilization rate of examination hall resources and the priority of candidate requirements.

[0152] In the present invention, the optimized seat allocation data is generated by a conflict detection module and a reinforcement learning adjustment module. The conflict detection module is used to identify potential conflict factors in the preliminary seat allocation plan, mainly including physical conflicts (such as multiple candidates being assigned to the same seat or the distance between adjacent seats being too small), demand conflicts (such as candidates with special needs not being assigned to areas that meet their needs), and resource conflicts (such as over-concentration or significant shortage of regional resource utilization). The conflict detection module quickly identifies problems based on the logical analysis of the allocation matrix. For example, by calculating whether each seat is assigned to multiple candidates at the same time, if the allocation mark of a certain seat exceeds 1, it is marked as a conflict. In addition, by checking whether the allocation matrix meets the matching rules of candidates with special needs and environmental suitability parameters, the existence of demand conflicts can be judged. After detecting conflicts, the reinforcement learning adjustment module adjusts the seat allocation through a dynamic optimization strategy, giving priority to resolving high-priority conflicts, and dynamically optimizing the allocation strategy according to the examination room resource utilization rate and candidate demand priority.

[0153] The reinforcement learning adjustment module takes an intelligent agent as the core and continuously optimizes the seat allocation plan through iterative interaction with the environment. The system models the current seat allocation state as a state space, including resource utilization rate, candidate demand satisfaction rate, and the number of conflicts. The action space includes operations such as reallocating seats and adjusting regional priorities. The reward function comprehensively considers the examination room resource utilization rate, candidate demand satisfaction degree, and conflict resolution efficiency. Specifically, the reward value is equal to the weighted sum of the resource utilization rate and the demand satisfaction rate minus the penalty term of the number of conflicts. During the optimization process, the reinforcement learning module dynamically adjusts the allocation strategy based on the feedback of the reward function, and realizes the minimization of conflicts and the maximization of resource utilization through iterative calculation.

[0154] The optimization process starts from the input of the initial allocation plan. First, the conflict detection module analyzes the plan and marks the conflict areas. Based on the marking results, the reinforcement learning module preferentially adjusts the allocation plan for areas with more conflicts according to the reward function. For example, by reallocating candidates with special needs to more suitable areas or adjusting the distribution of ordinary candidates in resource-rich areas, the overall plan is optimized. After multiple rounds of iteration, the number of conflicts gradually decreases, and the allocation plan tends to be optimal until all conflicts are resolved or the number of conflicts drops to an acceptable range.

[0155] The effects of the present invention are reflected in multiple aspects. Firstly, through the precise analysis of the conflict detection module and the dynamic adjustment of reinforcement learning, the system can efficiently solve the conflict problems in seat allocation and ensure the rationality of the allocation plan. For example, when multiple light-sensitive candidates are concentrated in the same area, resulting in conflicts, the system can identify and timely adjust the allocation plan, reallocating some candidates to other areas with uniform light. Secondly, the present invention significantly improves the utilization rate of examination room resources. By dynamically adjusting, the resources in the low-utilization areas are rationally allocated to ordinary candidates, avoiding resource waste, and at the same time meeting the priority use requirements of high-demand areas. In addition, the optimization strategy of reinforcement learning ensures the fairness and rationality of the allocation. The priority of candidates with special needs is fully guaranteed, while the allocation of ordinary candidates takes into account the resource balance and the optimization of the overall examination room environment.

[0156] For example, in the actual application of a certain examination room, the initial allocation plan assigns 5 ordinary candidates to area A, 3 light-sensitive candidates to area B, and 2 noise-sensitive candidates to area C. However, due to the fluctuation of the light stability score in area B, the needs of some light-sensitive candidates are not met. The conflict detection module marks area B as a conflict area, and the reinforcement learning module adjusts the plan according to the reward function, reallocating some light-sensitive candidates to area A with a higher light stability value, and at the same time adjusting the distribution of ordinary candidates to ensure the maximization of resource utilization. The final allocation plan meets the requirements of all candidates with special needs, and at the same time realizes the balanced distribution and efficient utilization of examination room resources. Through the above methods, the present invention significantly improves the scientificity, flexibility, and accuracy of the examination seat arrangement.

[0157] Through the multi-modal verification module of the intelligent examination desk, biometric data of candidates is collected, identity verification is completed, and verified data is generated; the verified data is bound to the optimized seat allocation data to complete the unlocking and task loading of the examination interface.

[0158] Preferably, the multi-modal verification module includes a fingerprint recognition module and a face recognition module, and the verified data is comprehensively generated by the matching results of the fingerprint feature vector and the face feature vector.

[0159] Fingerprint recognition module: Candidates input fingerprint data on the intelligent examination desk, and the fingerprint image is captured by a high-resolution fingerprint sensor, and the fingerprint feature vector (such as bifurcation points, endpoints, etc.) is extracted. The extracted feature data is matched with the fingerprint template pre-stored in the system, and if the match is successful, part of the verification result is generated.

[0160] The face recognition module uses the camera of the intelligent examination platform to capture the examinee's face image and uses a deep learning model (such as convolutional neural network, CNN) to extract the face feature vector, including facial key points (such as the relative positions of eyes, nose, and mouth) and texture features. The extracted feature vector is matched with the face template stored in the database to generate a matching result.

[0161] Comprehensive verification: conduct a comprehensive analysis of the matching results of the fingerprint feature vector and the face feature vector, and generate the final verification pass data through a weighted fusion strategy. The fusion strategy calculation formula is:

[0162] V=α·F 指纹 +β·F 人脸

[0163] Where V represents the comprehensive matching score; F 指纹 represents the fingerprint matching score; F 人脸 Represents the face matching score; α and β represent the weight coefficients of fingerprint and face respectively, which are dynamically adjusted according to the scene requirements.

[0164] After the verification is passed, the system binds the candidate's verification data with their optimized seat allocation data and generates a unique identifier (such as verification binding ID). This identifier contains the candidate's identity authentication information and their seat allocation results, which serves as the basis for unlocking the test interface and loading the test tasks.

[0165] The binding data is transmitted to the management system of the smart examination platform through the local area network. After the candidate logs in, the system unlocks the corresponding examination interface based on the binding data and loads the candidate's examination task. The examination task loading includes the presentation of the task content and the monitoring settings related to the candidate's seat.

[0166] The multimodal fusion verification of fingerprints and faces avoids the misidentification or forgery problems that may occur in a single verification method. Even if the fingerprint image is partially missing or the face is affected by lighting conditions, multimodal fusion can still provide high accuracy. The joint verification of fingerprints and faces improves verification security and reduces the risk of identity fraud during the examination process.

[0167] The fingerprint and face feature extraction and matching adopt efficient algorithms to ensure that the verification process is completed quickly (usually within 1 second). The generation and transmission of binding data is completed through the local area network, which has high real-time performance. The binding of verification data and seat allocation data realizes a one-to-one correspondence, which facilitates the subsequent unlocking of the test interface and loading of tasks.

[0168] Verification ensures that candidates can only access their corresponding test interfaces and tasks through data binding, preventing task loading errors or interface confusion. The system records the time and results of each verification, which is convenient for test center management and subsequent tracing.

[0169] Example: In a certain exam, a multi-modal verification module of an intelligent exam desk is equipped in the examination room. After candidate A sits at the designated seat, he places his finger on the fingerprint recognition sensor and faces the camera for face collection at the same time. The fingerprint feature vector collected by the fingerprint sensor is [0.8, 0.4, 0.6, 0.9], and the feature vector extracted by the face recognition model is [0.7, 0.5, 0.8, 0.6]. The system calculates the matching scores of the fingerprint and the face respectively:

[0170] F 指纹 = 0.8·0.7 + 0.4·0.5 + 0.6·0.8 + 0.9·0.6 = 1.74

[0171] F 人脸 = 0.7·0.8 + 0.5·0.6 + 0.8·0.9 + 0.6·0.7 = 1.90

[0172] Calculate the comprehensive matching score through the comprehensive verification strategy:

[0173] V = 0.6·1.74 + 0.4·1.90 = 1.804

[0174] If the comprehensive score V > 1.5 is the passing condition, the identity verification of candidate A passes. The system binds the verified data with the seat allocation data (seat 3 in area B) of candidate A to generate a unique identifier ID-A3.

[0175] The bound data is transmitted to the exam desk management system through the local area network, unlocks the exam interface of seat 3 in area B, and loads the corresponding exam tasks. At the same time, the system records the verification time and bound data of candidate A to ensure the full traceability of the exam management process.

[0176] Preferably, the unlocking and task loading of the exam interface include activating the candidate's exam permission according to the verified data, loading the exam tasks in real time, and recording the start time, completion status and abnormal operation information of the exam tasks.

[0177] After the verified data is transmitted to the task management module of the intelligent exam desk, the system automatically matches the verification data with the candidate information database to confirm the candidate's identity and corresponding exam permissions. The core of exam permission activation lies in the uniqueness and consistency of the verification data. For example, the bound verification data must be consistent with the seat allocation data, and only the candidates who pass the verification can enter the exam interface. The system creates a dedicated session key (SessionKey) for the candidate based on the permission activation status. This key is used to protect the transmission security of the exam task data and prevent unauthorized access.

[0178] After the permission is activated, the task management system extracts the corresponding exam content from the task database according to the candidate information and loads it onto the intelligent exam desk through the local area network. The loading process includes the initialization of test questions, exam rules, timers, and interactive interfaces to ensure that the exam tasks are presented completely and correctly. The task loading triggers the real-time monitoring module simultaneously. This module is responsible for recording the operation behaviors of candidates during the exam, such as page switching, answering progress, and whether there are abnormal operations (such as abnormal exit from the interface).

[0179] The system records the start time of the exam task in real-time during task loading to ensure that the time point when the candidate starts answering questions can be accurately tracked. During the task execution, the system continuously monitors the task completion status, including information such as the answering completion rate and submission time. Once the exam task ends, the system automatically generates a task completion status report and stores it in the exam data log. If an abnormal operation occurs to the candidate during the task execution (such as attempting to switch the task interface or unauthorized access to other function modules), the system immediately captures and records the abnormal information, including the time when the abnormality occurred, the specific operation description, and the impact assessment.

[0180] The unlocking of the exam interface strictly depends on the authentication result to ensure that each candidate can only access the exam task bound to them. The rigor of permission management effectively prevents the problems of incorrect assignment of exam tasks and unauthorized access.

[0181] The system can load the task immediately after verification, avoiding the delay problem of traditional exam task loading. At the same time, through the integrity check of task loading, it ensures the accuracy and stability of test questions and interfaces.

[0182] The system comprehensively records key operations (such as start time, completion status, abnormal information, etc.) during the task execution, providing a strong guarantee for the security and fairness of the exam process. In particular, the immediate capture and recording of abnormal operations help managers quickly troubleshoot problems and take corresponding measures.

[0183] The activation of the exam permission and task loading are protected by an encryption mechanism throughout the process to ensure the security of exam data transmission and avoid security risks caused by data leakage or tampering.

[0184] Example: In an exam based on an intelligent exam desk, after candidate A completed identity verification through the multi-modal verification module, the verification passed data generated by the system was bound with seat allocation information (Seat 3, Area B). When the verification passed data was transmitted to the task management system, the system activated the exam permission based on candidate A's identity information and created a session key to protect the loading process of task data. Subsequently, the system extracted candidate A's exam content from the task database, including questions, timer rules, and exam interface configurations, and presented them on the touch screen of the intelligent exam desk after the task loading was completed. When the exam started, the system recorded the task start time as 10:00:00 and simultaneously monitored candidate A's operation behavior in real time in the background.

[0185] During the exam, candidate A attempted to switch the task interface. The system identified this operation as an abnormal behavior and recorded detailed information, including the abnormal occurrence time 10:15:32, the operation description "attempt to enter an unauthorized module", and the preliminary assessment "did not affect the current exam task". After the task ended, the system automatically recorded the exam completion time as 11:30:00 and generated a task completion status report, including candidate A's answer completion rate of 100%, the submission time of 11:29:45, and no major abnormalities affecting.

[0186] As Figure 5 shown, a system for implementing the seat arrangement method for the intelligent exam desk-based exam includes:

[0187] An environmental sensing module for collecting environmental data;

[0188] An implicit sensing module for collecting air flow and micro-vibration characteristics;

[0189] An environmental feature analysis module for integrating environmental perception data and implicit environmental data and generating an environmental feature matrix;

[0190] A candidate information management module for receiving and standardizing candidate information data;

[0191] A region division module for dividing the exam room area using a quantum dot distribution model based on the environmental feature matrix and the physical layout of the exam room and generating region suitability data;

[0192] A seat arrangement module for generating region allocation data based on the region suitability data and initializing the seat status matrix, generating preliminary seat allocation data through a dynamic programming algorithm, and optimizing and generating optimized seat allocation data through a reinforcement learning algorithm;

[0193] A multi-modal verification module for collecting biometric data of candidates and generating verification passed data;

[0194] An execution module for binding the verified data with the optimized seat allocation data and completing the unlocking of the examination interface and the loading of tasks.

[0195] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects.

[0196] The above are only the embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for arranging examination seats based on an intelligent examination desk, characterized in that It includes the following steps: Collect environmental data of the examination room through an intelligent examination platform to generate environmental perception data; combine implicit perception technology to collect air flow and micro-vibration characteristics to generate implicit environmental data; integrate and process the environmental perception data and implicit environmental data to generate an environmental feature matrix; receive and standardize the processed candidate information data; Based on the environmental feature matrix and the physical layout of the examination room, use a quantum dot distribution model to divide the examination room area to generate area suitability data; according to the area suitability data, preferentially allocate candidates with special needs to suitable areas to generate area allocation data; The environmental feature matrix performs dynamic feature extraction on the environmental perception data and implicit environmental data through a spatio-temporal convolutional neural network, specifically including jointly analyzing the spatial distribution and time variation patterns to extract feature data of light uniformity, temperature and humidity stability, and noise change trend; The quantum dot distribution model uses a quantum energy simulation method to generate area suitability data through simulation calculations of the quantum states of environmental suitability parameters within the examination room area. The area suitability data includes the light stability value, noise interference value, and environmental temperature and humidity balance value of each area; The area allocation data is generated through a reinforcement learning algorithm. The allocation rule for candidates with special needs uses the area suitability score as a weight. By calculating the comprehensive suitability scores of different candidate areas, the matching relationship between candidates with special needs and priority areas is dynamically adjusted; generate quantum state wave functions for the light, noise, temperature, and humidity of each area respectively, and calculate the area suitability score through the superposition principle: S = ∫ V |ψ(x, t)| 2 dx Among them, S represents the regional suitability score; V represents the spatial volume of the target area; |ψ(x,t)| 2 represents the total suitability intensity of the regional environmental parameters; ψ(x,t) represents the comprehensive wave function representing the regional suitability; the weighted calculation of the scores of each regional environmental parameter generates the final regional suitability data; Based on the area allocation data and candidate information data, initialize the seat status matrix, and generate preliminary seat allocation data through a dynamic programming algorithm; perform conflict detection and optimization on the preliminary seat allocation data, and use a reinforcement learning algorithm to adjust the seat allocation plan to generate optimized seat allocation data; The preliminary seat allocation data is generated by jointly optimizing the area allocation data and candidate information data through a dynamic programming algorithm. The optimization process includes taking the minimization of the distance between candidates and the satisfaction of special needs as the goal, and calculating the priority allocation sequence of seats in each area; Through the multi-modal verification module of the intelligent examination platform, collect the biometric data of the candidate, complete the identity verification, and generate verification passed data; bind the verification passed data with the optimized seat allocation data to complete the unlocking and task loading of the examination interface.

2. The examination seat arrangement method based on an intelligent examination desk according to claim 1, wherein The environmental data includes light intensity, humidity, temperature, and noise level. The implicit environmental data is generated by a highly sensitive sensor configured within the intelligent examination platform to detect air flow characteristics and micro-vibration frequency characteristics in real time.

3. The examination seat arrangement method based on an intelligent examination desk according to claim 1, wherein The optimized seat allocation data is generated by a conflict detection module and a reinforcement learning adjustment module, specifically including detecting conflict factors in the seat allocation plan, and dynamically optimizing the allocation strategy according to the utilization rate of examination room resources and the priority of candidate needs.

4. The examination seat arrangement method based on an intelligent examination desk according to claim 1, wherein The multi-modal verification module includes a fingerprint recognition module and a face recognition module. The verification passed data is comprehensively generated from the matching results of the fingerprint feature vector and the face feature vector.

5. The examination seat arrangement method based on an intelligent examination desk according to claim 1, characterized in that The examination interface unlocking and task loading include activating the examination permissions of candidates based on the verified data, loading the examination tasks in real time, and recording the start time, completion status, and abnormal operation information of the examination tasks.

6. A system for implementing the examination seat arrangement method based on an intelligent examination desk according to any one of claims 1-5, characterized in that, It includes: An environmental sensing module for collecting environmental data; An implicit perception module for collecting air flow and micro-vibration characteristics; An environmental feature analysis module for integrating environmental perception data and implicit environmental data and generating an environmental feature matrix; A candidate information management module for receiving and standardizing candidate information data; A region division module for dividing the examination room area based on the environmental feature matrix and the physical layout of the examination room using a quantum dot distribution model and generating region suitability data; A seat arrangement module for generating region allocation data based on the region suitability data and initializing the seat status matrix, generating preliminary seat allocation data through a dynamic programming algorithm, and optimizing and generating optimized seat allocation data through a reinforcement learning algorithm; A multi-modal verification module for collecting biometric data of candidates and generating verified data; An execution module for binding the verified data with the optimized seat allocation data and completing the examination interface unlocking and task loading.

Images