An intelligent reservation method for cross-institutional laboratory resources based on the Internet of Things

Abstract

The application relates to the technical field of the Internet of Things, in particular to a cross-institutional laboratory resource intelligent reservation method based on the Internet of Things, which comprises the following steps: obtaining a laboratory access message triggered after a user completes registration authentication and obtaining laboratory whole-process management parameters; after data preprocessing, a to-be-analyzed management data set is obtained; the to-be-analyzed management data set is input into a preset laboratory intelligent management and control model, the laboratory intelligent management and control model dynamically calculates user rights and resource use management and control results according to the correlation between the data in the to-be-analyzed management data set; the user type and the resource use type are obtained, and laboratory use and right maintenance suggestions for corresponding users are generated according to the user rights and the resource use management and control results. The application has the effect of solving the problems of business process breakage and insufficient management efficiency caused by system dispersion in the existing laboratory management.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to an IoT-based method for intelligent reservation of cross-institutional laboratory resources. Background Technology

[0002] As scientific research activities become increasingly complex and sophisticated, universities, research institutes, and corporate R&D centers are placing higher demands on laboratory management. Traditional laboratory management involves a series of processes, including equipment sharing and reservation, operator training and assessment, consumable requisition, laboratory space allocation, and user account and financial settlement. These processes are often interconnected; for example, users must pass an operational assessment for a specific instrument before reserving its use and settling accounts using pre-paid accounts. Currently, this comprehensive management need is becoming increasingly common, urgently requiring efficient and standardized information technology support.

[0003] Currently, existing technical solutions for laboratory management mainly fall into two categories. The first is the traditional manual management model, which relies on paper registration, telephone appointments, and offline training. This method is inefficient, error-prone, and difficult to trace and statistically analyze. The second category uses fragmented electronic tools for management. For example, separate online forms are used for instrument reservations, another training website is used for assessments, and user accounts and payment information may be recorded in a third financial system. While these solutions partially achieve online operation, the systems are independent of each other, and data cannot be automatically transferred and verified. For instance, the reservation system cannot automatically verify whether users have completed the required training, and the financial system cannot synchronize payments to reservation records in real time, leading to a break in the business process. Manual intervention for comparison and coordination is still required, and management efficiency has not been fundamentally improved. Therefore, there is still room for improvement. Summary of the Invention

[0004] To address the issues of fragmented business processes and insufficient management efficiency caused by decentralized systems in existing laboratory management, this application provides an intelligent reservation method for cross-institutional laboratory resources based on the Internet of Things.

[0005] The above-mentioned objective of this application is achieved through the following technical solution: A smart reservation method for cross-institutional laboratory resources based on the Internet of Things (IoT), comprising: Obtain the laboratory access message triggered after the user completes registration and authentication, and obtain the laboratory full-process management parameters, wherein the laboratory full-process management parameters include user identity data, training and assessment records, resource reservation information, permission status and usage billing data; After preprocessing the user identity data, the training and assessment records, the resource reservation information, the permission status, and the usage and billing data, a dataset to be analyzed and managed is obtained. The dataset to be analyzed is input into a preset intelligent laboratory management and control model. The intelligent laboratory management and control model dynamically calculates the user permissions and resource usage management results based on the correlation between the data in the dataset to be analyzed. Obtain user type and resource usage type, and generate corresponding laboratory usage and permission maintenance suggestions for users based on the user permissions and resource usage control results.

[0006] Preferably, the step of preprocessing the user identity data, the training and assessment records, the resource reservation information, the permission status, and the usage and billing data to obtain the management dataset to be analyzed specifically includes: Based on the user identity data and the training and assessment records, generate the user's qualification level for entering the room and using the equipment; After aligning the time nodes and process nodes according to the user's entry and instrument usage qualification level, the resource reservation information and the permission status, the dataset to be analyzed and managed is obtained.

[0007] Preferably, the intelligent laboratory control model is trained using the following method: From historical management data, obtain the correlation between training completion, appointment behavior, permission status and billing consumption under different user types and resource types during continuous use, and construct an intelligent management and control trend curve based on the correlation. The control inflection point is obtained from the intelligent control trend curve, and a corresponding dynamic calculation weight is set for each control inflection point, the training completion rate, and the appointment behavior according to different user types and resource types. The initial model is iteratively trained using the dynamically calculated weights under different scenarios to obtain the intelligent laboratory management model with adaptive judgment capabilities.

[0008] Preferably, the step of inputting the dataset to be analyzed into a preset intelligent laboratory management model, wherein the intelligent laboratory management model dynamically calculates the user permission and resource usage management results based on the correlation between the data in the dataset to be analyzed, specifically including: Input the management dataset to be analyzed into the laboratory intelligent control model; Based on the control trend curve and the control inflection point, match the calculation weights corresponding to the current user type and resource type; The user permissions and resource control results are dynamically obtained by comprehensively calculating the dataset to be analyzed and the matched calculation weights.

[0009] Preferably, the step of obtaining user type and resource usage type, and generating corresponding laboratory usage and permission maintenance suggestions for users based on the user permissions and resource usage control results, specifically includes: Retrieve the user permissions and resource management results for each user type corresponding to the resource type; If the control result is lower than the preset usage permission threshold, then the laboratory usage and maintenance suggestions are generated based on the user identity data, remaining resource types, and current training status.

[0010] Preferably, if the control result is lower than a preset usage permission threshold, then a laboratory usage and maintenance suggestion is generated based on the user identity data, remaining resource type, and current training status, specifically including: Determine whether user training is complete, whether the assessment is satisfactory, whether the usage rights are valid, and whether the account balance meets the billing conditions; If any condition is not met, the access rights to the corresponding resources will be locked, and maintenance suggestions such as time-limited training, supplementary payment, or recertification will be generated.

[0011] Preferably, it also includes reservation and automatic billing control steps: Get user-initiated requests for instrument, venue, or research service reservations, and read the user's current permission status, credit score, and account balance information; The estimated cost is calculated based on the pre-design fee rules and the reservation duration, and the account balance is compared with the estimated cost. When the comparison result shows sufficient balance, the payment will be automatically deducted and a reservation success instruction will be generated; when the comparison result shows insufficient balance, the reservation will be terminated and a balance reminder message will be triggered.

[0012] The second objective of this invention is achieved through the following technical solution: A smart reservation device for cross-institutional laboratory resources based on the Internet of Things (IoT), the device comprising: The parameter acquisition module is used to acquire the laboratory access message triggered after the user completes registration and authentication, and to acquire the laboratory full-process management parameters, wherein the laboratory full-process management parameters include user identity data, training and assessment records, resource reservation information, permission status and usage billing data; The dataset acquisition module is used to preprocess the user identity data, the training and assessment records, the resource reservation information, the permission status, and the usage and billing data to obtain the dataset to be analyzed and managed. The resource management module is used to input the dataset to be analyzed into a preset intelligent laboratory management model. The intelligent laboratory management model dynamically calculates the user permissions and resource usage management results based on the correlation between the data in the dataset to be analyzed. The suggestion generation module is used to obtain user type and resource usage type, and generate corresponding laboratory usage and permission maintenance suggestions for users based on the user permissions and resource usage control results.

[0013] The above-mentioned objective three of this application is achieved through the following technical solution: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described Internet of Things-based cross-institutional laboratory resource intelligent reservation method.

[0014] The fourth objective of this application is achieved through the following technical solution: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described IoT-based cross-institutional laboratory resource intelligent reservation method.

[0015] In summary, this application includes at least one of the following beneficial technical effects: 1. By integrating multi-dimensional end-to-end management parameters such as user identity, training, appointment, permissions, and billing, a unified dataset for analysis and management has been constructed, breaking down information barriers between traditional decentralized management systems and providing a data foundation for global intelligent decision-making and collaborative management of cross-institutional laboratory resources; 2. By introducing a laboratory intelligent management and control model trained on historical data, this model can deeply analyze the correlation between multi-source data and dynamically calculate the comprehensive user permission and resource usage management results, realizing the transformation from single, static permission judgment to multi-objective, dynamic, and refined intelligent evaluation. 3. By generating personalized suggestions for laboratory use and access control based on the control results and specific scenarios output by the intelligent model, the management mode is transformed from passive response and post-event processing to proactive early warning, early intervention and precise guidance, thereby improving the management efficiency and resource utilization efficiency of the large-scale laboratory resource sharing network. Attached Figure Description

[0016] Figure 1 This is a flowchart of an embodiment of the Internet of Things-based intelligent reservation method for cross-institutional laboratory resources in this application.

[0017] Figure 2This is a schematic diagram of a cross-institutional laboratory resource intelligent reservation device based on the Internet of Things in one embodiment of this application.

[0018] Figure 3 This is a schematic diagram of a device according to one embodiment of this application. Detailed Implementation

[0019] The present application will be further described in detail below with reference to the accompanying drawings.

[0020] In one embodiment, such as Figure 1 As shown, this application discloses a cross-institutional laboratory resource intelligent reservation method based on the Internet of Things, which specifically includes the following steps: S10: Obtain the laboratory access message triggered after the user completes registration and authentication, and obtain the laboratory full-process management parameters, including user identity data, training and assessment records, resource reservation information, permission status, and usage and billing data.

[0021] In this embodiment, the laboratory access message refers to the initiation message that triggers the process of entering the laboratory resource usage flow after a user completes registration and identity authentication on the cross-institutional laboratory resource sharing platform. The laboratory full-process management parameters refer to comprehensive management data used to determine whether a user is qualified to use the resources and whether they meet the reservation conditions.

[0022] Specifically, when a user completes registration and authentication on the platform and triggers a laboratory access message, the corresponding full-process management parameters of the laboratory are simultaneously obtained. These parameters include: user identity data (including the user's institution, identity type, research group information, and certification status); training and assessment records (including completed safety training, operational assessments, qualification validity periods, and assessment scores); resource reservation information (including the user's historical reservation records, current pending reservations, reservation time slots, and fulfillment status); permission status (including the user's access permissions, instrument operation permissions, site usage permissions, and whether permissions are frozen or enabled); and usage and billing data (including the user's account balance, settled fees, unsettled bills, and credit limit). By obtaining these multi-dimensional parameters, a complete data foundation is provided for subsequent intelligent analysis.

[0023] S20: After preprocessing user identity data, training and assessment records, resource reservation information, permission status, and usage billing data, a management dataset to be analyzed is obtained.

[0024] In this embodiment, preprocessing refers to the process of cleaning, normalizing, temporally aligning, and extracting features from multi-source heterogeneous data. The dataset to be analyzed refers to structured data that has undergone standardization and can be directly input into the model for computation and analysis.

[0025] Specifically, user identity data, training and assessment records, resource reservation information, permission status, and usage billing data are uniformly formatted, missing values ​​are filled, and outliers are removed. Then, the data is aligned chronologically according to the user's unique identifier and timeline. Data from different modules and sources are linked and integrated to form a standardized dataset that can be used for model calculations, ensuring the accuracy and reliability of subsequent analysis.

[0026] S30: Input the management dataset to be analyzed into the preset laboratory intelligent control model. The laboratory intelligent control model dynamically calculates the user permission and resource usage control results based on the correlation between the data in the management dataset to be analyzed.

[0027] In this embodiment, the laboratory intelligent management and control model refers to an intelligent computing model trained based on historical management data, used to analyze user behavior, permission status, and resource usage rules. The user permission and resource usage management and control results refer to the comprehensive results of permission judgment, resource adaptation, risk level, and usage restrictions output by the model after comprehensive calculation based on data correlation.

[0028] Specifically, the pre-processed dataset to be analyzed is input into a preset intelligent laboratory management and control model. Based on the correlation between the data, the model performs comprehensive analysis and dynamic calculation on user qualifications, training status, appointment behavior, permission validity and billing status, and finally outputs the user permission and resource usage management results, including whether the user has the right to use the resource, whether the resource can be booked, whether manual review is required, and whether there are any usage risks.

[0029] S40: Obtain user type and resource usage type, and generate corresponding suggestions for laboratory usage and permission maintenance based on user permissions and resource usage control results.

[0030] In this embodiment, user types include on-campus staff, students, personnel from external organizations, and corporate researchers. Resource usage types include instrument reservations, venue reservations, research service reservations, and animal facility usage. Laboratory usage and access control recommendations refer to the operation guidelines, qualification reminders, payment prompts, and access control restoration plans generated for users based on the control results.

[0031] Specifically, based on the current user's type and the type of resources requested, combined with the user's permissions and resource usage control results, corresponding laboratory usage suggestions and permission maintenance suggestions are generated for the user. These suggestions include successful reservation notifications, qualification expiration reminders, insufficient balance reminders, permission lockout explanations, and time-limited rectification guidelines. This allows users to clearly understand the current usage status and subsequent handling methods, achieving intelligent and standardized management of cross-institutional laboratory resources.

[0032] In this embodiment, by integrating multi-dimensional, end-to-end data such as user identity, training, appointments, permissions, and billing, the information barriers between traditional decentralized management systems are broken down, providing a data foundation for global intelligent decision-making. This method introduces a laboratory intelligent management and control model, deeply analyzes the correlations between various data points, and dynamically calculates comprehensive user permission and resource usage management results, realizing a shift from simple status judgment to multi-objective evaluation. Based on these results and specific scenarios, the system can generate personalized management suggestions, shifting the management model from post-processing to pre-emptive warning and proactive guidance. This improves the management refinement and resource utilization efficiency of large-scale laboratory resource sharing networks, reducing management inefficiencies caused by information fragmentation and delays in manual intervention.

[0033] In one embodiment, in step S20, after preprocessing user identity data, training and assessment records, resource reservation information, permission status, and usage billing data, a dataset to be analyzed and managed is obtained, specifically including: S21: Generate user entry and instrument use qualification levels based on user identity data and training and assessment records.

[0034] In this embodiment, user identity data includes attribute information obtained by the user during platform registration and synchronized from their affiliated institution's system, such as their affiliated unit, position / study status, research group, and validity period. Training and assessment records include historical records and results of all courses, safety exams, and operational assessments completed by the user on the platform or in certified third-party systems, including grades, certificates, and validity periods. The user's access and instrument usage qualification level is a standardized and quantified set of capability tags assigned to the user by the system after calculating the above information through a built-in rule engine. These tags characterize the permitted spatial range and the types and depth of operable equipment.

[0035] Specifically, in cross-institutional laboratory management scenarios, after a user completes registration and authentication, their identity data and training records are acquired by the system. For example, enterprise engineer user A's identity data is marked as a partner of the Collaborative Innovation Center and is within the validity period. Their training records show that they have passed the laboratory safety knowledge and advanced operation assessments for specific equipment. The system's built-in qualification mapping and calculation engine performs matching and reasoning based on a pre-set access rule knowledge base. This knowledge base defines the access thresholds for various laboratory areas and instruments. It determines that user A's identity meets the basic access requirements, and their specific training assessment records correspond to obtaining basic access qualifications and independent operator qualifications for specific instruments. Finally, a structured qualification level object is dynamically generated, such as {Basic Access: Effective, SEM Operation: Level 3}. This level is updated as records expire or information changes, serving as the core permission basis for all subsequent intelligent control decisions, thus achieving standardization and automation of permission judgment.

[0036] S22: After aligning the time nodes and process nodes according to the user's entry and instrument use qualification level, resource reservation information and permission status, the dataset to be analyzed is obtained.

[0037] In this embodiment, the user's access and instrument usage qualification levels are the capability tags generated in the previous step. Resource reservation information is the details of a user's reservation application for a specific laboratory resource, including the target resource, reservation time, and purpose. Permission status is the set of real-time control instructions implemented by the system or administrator on the user account. Time node and process node alignment involves correlating and correcting the above-mentioned data from different dimensions within a unified timeline and business process step coordinate system. The dataset to be analyzed is a snapshot of the user's overall status regarding a specific resource at a specific moment and process stage, obtained after alignment processing.

[0038] Specifically, when a user submits a resource reservation, their instantaneous state needs to be accurately characterized. For example, PhD student user B requests to use a high-speed centrifuge on Friday afternoon. First, time node alignment is performed: checking the validity period of user B's centrifuge operation qualification reveals that their certificate expires on Thursday evening, earlier than the reservation time, indicating that the qualification has expired at the time of reservation. Simultaneously, the target device's own status calendar is checked. Further, process node alignment is performed: checking user B's current permission status reveals that due to recent irregular behavior, they have been marked as requiring online confirmation from their supervisor for all device use, and the current reservation is in the submission-pending-review process node. This supervisor confirmation constraint is linked to the impending qualification expiration time constraint. By aligning this information along the time and business process axes, a highly contextualized dataset for analysis and management is constructed. This dataset is a coherent state description, recording the intersection and potential conflicts between user intent, their own capability time limits, and real-time rules. This allows the subsequent intelligent management model to perform in-depth analysis with spatiotemporal context and process awareness, thereby making accurate decisions and avoiding misjudgments due to information asynchrony.

[0039] In this embodiment, the model can autonomously learn business rules and behavioral patterns from historical data and identify key decision points, thereby achieving adaptive and dynamic optimization of management strategies. By constructing intelligent management trend curves, the model can learn the interaction patterns between user behavior, resource consumption, and management effectiveness, rather than memorizing isolated cases. Identifying management inflection points from the curves allows the model to automatically discover key thresholds for changes in management status, providing data support for proactive intervention. By setting dynamic calculation weights for inflection points and behavioral characteristics under different user and resource types and conducting iterative training, the model gains refined decision-making capabilities to differentiate between different management scenarios, making its management recommendations more targeted and improving the model's adaptability and decision-making effectiveness across different organizations and resource types.

[0040] In one embodiment, the laboratory intelligent control model is trained using the following method: S301: Obtain the correlation between training completion, appointment behavior, permission status and billing consumption of users under different user types and resource types during continuous use from historical management data, and construct intelligent management and control trend curves based on the correlation.

[0041] In this embodiment, historical management data refers to all user operation logs and business data accumulated over the long-term operation of the platform. User type and resource type are classification labels for users and laboratory resources. Training completion rate, appointment behavior, permission status, and billing consumption are four core dimensions characterizing user behavior. Correlation relationships are statistical regularities or causal patterns revealed through data analysis between these dimensions. The intelligent control trend curve is a continuous function graph or numerical relationship generated by fitting the above correlation relationships using a mathematical model, which can intuitively show how changes in a certain dimension affect the final management result.

[0042] Specifically, to train the intelligent management and control model for the laboratory, the system initiated large-scale historical data mining. The data warehouse stores the complete footprints of all past users. The model training engine performs complex correlation analysis to discover deep, cross-dimensional patterns related to user-resource types. For example, cluster analysis might reveal a positive correlation between the average training score and the frequency of erroneous operation codes in equipment repair records for undergraduate students using large precision instruments. For enterprise users paying for computing services, analysis might show that when their account balance remains below a certain threshold, the probability of specific avoidance patterns in subsequent appointments increases. Based on this, multiple intelligent management and control trend curves are constructed for different user-resource type combinations. For example, a curve is constructed for doctoral students and those using high-risk chemical equipment, with safety training scores on the horizontal axis and the estimated operational risk index on the vertical axis, identifying the inflection point score where risk accelerates. These curves extract scattered historical event data into mathematical models reflecting group behavior patterns and risk change trends, providing quantifiable and generalizable prior knowledge for intelligent decision-making, enabling the model to make reasonable inferences about critical states.

[0043] S302: Obtain the control inflection point from the intelligent control trend curve, and set corresponding dynamic calculation weights for each control inflection point, training completion rate, and appointment behavior according to different user types and resource types.

[0044] In this embodiment, the control inflection point is a key point identified from the intelligent control trend curve. Near this point, the curve trend or the management result it represents will change significantly, often corresponding to the critical threshold for management decisions. The dynamically calculated weight is a numerical coefficient assigned to different evaluation dimensions and the interval near a specific inflection point. It determines the influence of the state of that dimension or interval in the final comprehensive decision and can adaptively adjust according to different user type-resource type scenarios.

[0045] Specifically, after obtaining the trend curves, the patterns need to be transformed into actionable parameters for real-time model decision-making. The algorithm automatically analyzes each curve; for example, it uses mathematical methods to identify the 85-point inflection point on the risk curve of a doctoral student using high-risk chemical equipment. After identifying the inflection point, the dynamic weight configuration stage begins. The weight configuration is determined through machine learning optimization. Basic weights are assigned to different features in different scenarios, and weight gain coefficients are set for intervals near the inflection point. For example, in the scenario of undergraduate students booking ordinary instruments, a higher basic weight is set for the booking behavior, and a medium basic weight is set for training completion. When the model detects that a student's safety exam score is near the inflection point of its corresponding curve, dynamic gain is triggered, temporarily increasing the weight of the training performance feature. In the scenario of enterprise users using paid services, the basic weights of billing consumption and account credit are significantly increased. The control inflection point may be set when the ratio of account balance to average monthly consumption equals 1; when it falls below this inflection point, the weight of the financial risk dimension is dynamically increased. Finally, a large-scale scenario-based weight strategy library is maintained. When processing a specific request, the model immediately obtains a set of dynamic weight parameters customized for the scenario based on the current user type and resource type, thereby achieving differentiated, refined, and adaptive optimization of the control strategy.

[0046] S303: Iteratively train the initial model by dynamically calculating weights under different scenarios to obtain a laboratory intelligent management and control model with adaptive judgment capabilities.

[0047] In this embodiment, the dynamically calculated weights for different scenarios refer to the set of parameters configured for various user type-resource type combinations. The initial model refers to a basic machine learning model framework before this training. Iterative training refers to the process of optimizing and adjusting the parameters of the initial model through multiple rounds using historical data with scenario labels and corresponding weights. The laboratory intelligent management and control model with adaptive judgment capabilities refers to the final model that, after training, can automatically identify the current decision-making scenario and invoke the corresponding evaluation logic for accurate judgment.

[0048] Specifically, after configuring the dynamically calculated weights, the final stage of model training is complete. The goal of this stage is to solidify the patterns and strategies discovered in the preceding steps into an executable software model. A training dataset is prepared, consisting of a large number of historical user behavior records. Each record is labeled with its user type and resource type scenario label, and associated with dynamically calculated weight parameters configured for that scenario. At the start of training, the corresponding initial model is loaded, such as a neural network or a gradient boosting decision tree model. In each iteration of training, the model reads a batch of training data. For each sample in the data, the model first loads the corresponding dynamically calculated weights based on its scenario label as the scoring criterion for this learning iteration. Then, the model attempts to calculate the sample features, predict a management result, and compares it with the actual historical management results recorded in the sample to calculate the prediction error. Based on this error, the model automatically adjusts its internal parameters through optimization algorithms such as backpropagation. During parameter adjustment, the model learns and internalizes the weight differences between different scenarios. For example, when processing samples of enterprise users using paid services, the model strengthens its learning of financial characteristics such as account balances; while when processing samples of undergraduate students using teaching equipment, the model enhances its learning of feature combinations of training performance and behavioral records. Through massive amounts of data and multiple iterations, the initial model can identify different scenarios and employ differentiated evaluation logic that aligns with the preset weighting strategy for each scenario. The final trained model possesses adaptive judgment capabilities and can be deployed and applied.

[0049] In this embodiment, the model can autonomously learn business rules and behavioral patterns from historical data and identify key decision points, thereby achieving adaptive and dynamic optimization of management strategies. By constructing intelligent management trend curves, the model can learn the interaction patterns between user behavior, resource consumption, and management effectiveness, rather than memorizing isolated cases. Obtaining management inflection points from the curves allows the model to automatically identify key thresholds for changes in management status, providing data support for proactive intervention. By setting dynamic calculation weights for inflection points and behavioral characteristics under different user and resource types and conducting iterative training, the model gains refined decision-making capabilities to differentiate between different management scenarios, making its management recommendations more targeted and improving the model's adaptability and decision-making effectiveness across different organizations and resource types.

[0050] In one embodiment, in step S30, the management dataset to be analyzed is input into a preset intelligent laboratory management and control model. The intelligent laboratory management and control model dynamically calculates the user permissions and resource usage control results based on the relationships between the data in the management dataset to be analyzed, specifically including: S31: Input the management dataset to be analyzed into the laboratory intelligent control model.

[0051] In this embodiment, the management dataset to be analyzed is a set of feature data that reflects the comprehensive status of a specific user for a specific resource at the current moment, generated after the aforementioned steps of cleaning, alignment, and structuring. The preset intelligent laboratory management model is a software decision engine that has been trained and deployed on a server, which encapsulates complex rules, patterns, and dynamic weight strategies learned from historical data.

[0052] Specifically, once the dataset to be analyzed and managed is prepared for a user request, the core intelligent decision-making process begins. This dataset is encapsulated into a standard-format data object, such as a feature vector containing hundreds of feature values, including multi-dimensional information such as user qualifications, appointment details, historical behavior statistics, real-time account status, and target resource status. Further, through an internally defined service call interface, this dataset object is used as input parameters to initiate an inference request to the laboratory's intelligent management and control model. This model is typically deployed as an independent microservice. Upon receiving the request, the model service loads the input data into its computation graph or inference engine, preparing for forward propagation computation.

[0053] S32: Based on the control trend curve and control inflection point, match the calculation weights corresponding to the current user type and resource type.

[0054] In this embodiment, the control trend curve and control inflection point are regularities learned by the model during the training phase for different scenarios. The current user type and resource type are the specific scenario identifiers corresponding to this decision request. The calculated weights are a dynamic set of parameters applicable to the current scenario, including basic weights and inflection point gain rules. Matching refers to the model retrieving and loading the weight configuration applicable to this decision from its internal storage or associated external policy library based on the scenario identifier.

[0055] Specifically, before the model begins substantive computational inference, it first needs to define the metrics to be used in this assessment, i.e., the assessment criteria. Based on the explicitly identified user type and resource type in the input dataset, the model combines these two to form a scenario key, and uses this key to retrieve its integrated scenario-based weighting strategy library. For example, for the scenario of visiting scholars using a biosafety level 2 laboratory, the strategy library pre-stores corresponding weight configurations, which may stipulate that biosafety training scores have a very high base weight. Simultaneously, the strategy library also links to the control trend curve and its inflection point information for this scenario. The model then checks the current user's specific value on this core dimension, such as their biosafety training score, and calculates the distance between this value and the identified inflection point. If the value falls within a preset sensitive interval near the inflection point, the model dynamically adjusts the effective weight of that feature dimension, for example, by multiplying its base weight by a gain coefficient. Through this scenario-based weight matching and dynamic gain mechanism for inflection point intervals, the model ensures that its assessment system has both historical experience-based stability and sufficient discriminatory power and prudence for high-risk or critical states.

[0056] S33: Based on the dataset to be analyzed and the matched calculation weights, perform comprehensive calculations to dynamically obtain user permissions and resource control results.

[0057] In this embodiment, the dataset to be analyzed is the set of input state features. The matched computational weights are dynamic parameters that evaluate the importance of each feature. Comprehensive calculation refers to the mathematical operation process in which the model combines feature values ​​with weights according to its internal algorithm, taking into account the nonlinear interactions between features. Dynamic acquisition means that the calculation results are generated in real time and change with the input data. The user permission and resource control results are the final structured decision conclusions output by the calculation process, which comprehensively reflect the model's evaluation of the current request across all consideration dimensions.

[0058] Specifically, after weight loading is complete, the model enters the core computation phase. This process is typically a complex, non-linear function computation. For example, in a neural network model, the input feature vector undergoes non-linear transformations through multiple hidden layers, which automatically learn and capture complex interactions between features. In a tree ensemble model, different decision paths are traversed through a series of conditional judgments. The computation is dynamic, primarily because the input for each computation is real-time and unique, and the applied weights are dynamically matched and adjusted according to the current scenario. Therefore, even if the same user applies for the same resource, the computation path and intermediate results will differ at different times or when different weight gain rules are triggered due to different states. Finally, the model outputs a structured user permission and resource management result object. This object typically contains information in several dimensions: core decision items, such as automatic approval or manual review; quantitative scoring, such as comprehensive credit score or risk assessment level; derived control parameters, such as recommended maximum usage time or required deposit; and related operation prompts.

[0059] In this embodiment, the trained model is transformed into an executable and interpretable real-time decision engine. By matching the calculated weights corresponding to the current scenario based on the control trend curve and inflection point, the real-time retrieval and application of decision rules in a scenario-based manner are achieved, ensuring a high degree of relevance of the decision-making basis. The comprehensive calculation based on the real-time input dataset to be analyzed and the matched weights demonstrates the model's dynamic reasoning capability; its output can be adjusted according to changes in the user's specific state, making control more refined and flexible. This matching and calculation process improves the system's adaptability to changing management scenarios. Furthermore, because the decision logic is based on explicit curves, inflection points, and weights, the interpretability of the model's decisions is increased to a certain extent, helping to enhance managers' trust in the intelligent decision-making process.

[0060] In one embodiment, step S40, namely obtaining the user type and resource usage type, and generating corresponding laboratory usage and permission maintenance suggestions for the user based on the user permissions and resource usage control results, specifically includes: S41: Obtain user permissions and resource control results for each user type corresponding to the resource type.

[0061] In this embodiment, the user type corresponding to the resource type refers to the specific scenario classification in which the current intelligent management and control decision occurs. The user permission and resource management result is a comprehensive and structured decision conclusion calculated and output by the intelligent management and control model in the previous step, specifically for the current request. Acquisition refers to the operation in which the system explicitly binds and associates the result with the specific user type-resource type scenario context that generated it after the model outputs the result.

[0062] Specifically, after the laboratory intelligent management and control model completes its calculations and outputs the management and control results, this result object must be closely integrated with the original request context that triggered the calculation in order to be correctly interpreted by subsequent steps. The result processing module receives the result and simultaneously holds the metadata of this request, which crucially includes the user type and the target resource type. The system performs a result-scenario association operation. For example, the model output may include a comprehensive risk assessment score of 65. The processing module will explicitly mark this score as being obtained in a specific scenario where the user type is a master's student and the resource type is the use of a high-temperature and high-pressure reactor. This means that the risk semantics implied by this score of 65, and the corresponding management measures, are completely different from the score obtained in a scenario where the user type is a researcher and the resource type is the reservation of a regular oven. The system will traverse all key fields in the management and control results, labeling each item with the specific scenario tag upon which it was generated. This constructs a scenario-based result object, ensuring that in subsequent steps, user prompts or management and control actions can be generated based on accurate scenario understanding, thereby guaranteeing the accuracy and appropriateness of management responses.

[0063] S42: If the control result is lower than the preset usage permission threshold, then generate laboratory usage and maintenance suggestions based on user identity data, remaining resource types and current training status.

[0064] In this embodiment, the preset access permission threshold is a management red line value pre-set by the system for different user type-resource type scenarios, used to determine whether the control result is acceptable. Below this threshold, it means that the risk or non-compliance level of the current request exceeds the scope of automatic permission. User identity data is the user's detailed background information. Remaining resource types refer to a list of other resource options available on the platform that are functionally similar or alternatives when the user's preferred resource is unavailable or restricted. Current training status is the specific situation regarding the user's completion, validity, expiration, or deficiency of the qualifications required for the target resource. Laboratory usage and maintenance recommendations are personalized action guidelines generated based on the specific reasons for falling below the threshold, combined with the user's background and available alternatives, aimed at guiding the user to restore compliance or adjust their plans.

[0065] Specifically, an internal dynamic permission threshold matrix is ​​maintained, defining trigger points for management actions in various management scenarios. The control results obtained in the previous step, tagged with scenario labels, are compared with the corresponding thresholds in the threshold matrix. When the comparison reveals a control result below a preset threshold, a deep suggestion generation logic is initiated. At this point, the intelligent suggestion generation engine is activated. This engine uses the specific reasons why the result is below the threshold as the core of problem diagnosis, and then queries three aspects of remedial and guidance information: precise user identity data, the types of remaining resources available within the platform, and the user's current lacking or expired training status. Based on this information, the engine selects the most matching template from a predefined template library, fills in the specific variable content, and generates a precise and actionable suggestion. For example, for a doctoral student whose appointment is blocked due to expired specialized security certification and insufficient account balance, the generated suggestion will clearly list these two reasons and guide them to immediately complete the specified online retraining assessment and recharge their account with a specific amount. It may also provide an immediately usable alternative device option with low permission requirements. This recommendation reflects the rigid principles of system management and provides a clear compliance path, aiming to guide users to proactively solve problems, thereby improving management efficiency and user satisfaction.

[0066] In this embodiment, the model's output evaluation results are transformed into specific, actionable management actions, achieving hierarchical and precise management reach. By introducing preset access permission thresholds, a clear trigger boundary is established between continuous evaluation results and discrete management intervention actions, allowing management resources to focus on the objects requiring intervention and improving management efficiency. When generating suggestions, the system comprehensively considers user identity, remaining available resource types, and current training status, making the suggestions differentiated and precise. For example, different permission restoration paths are provided for users with different identities. This precise guidance increases users' willingness and efficiency in implementing suggestions, helping users proactively maintain compliance and reducing situations where management measures are not effectively implemented due to suggestion generalization.

[0067] In one embodiment, in step S42, if the control result is lower than a preset usage permission threshold, then a laboratory usage and maintenance suggestion is generated based on user identity data, remaining resource type, and current training status, specifically including: S421: Determine whether user training is complete, whether the assessment is satisfactory, whether the usage rights are valid, and whether the account balance meets the billing conditions.

[0068] In this embodiment, whether user training is complete refers to determining whether the user has completed all required training courses or learning modules required by the target resource. Whether the assessment is satisfactory refers to determining whether the user has passed the corresponding qualification exam or practical assessment after completing the training. Whether the usage permission is valid is a comprehensive judgment, including checking whether the user's account is in a normal state, whether their operational qualifications for the target resource are valid, and whether any temporary usage restrictions have been imposed by a superior administrator or system rules. Whether the account balance meets the billing conditions refers to determining whether the available funds in the user's pre-deposited account are sufficient to cover the estimated cost of this operation or the minimum pre-deduction required by the system, according to the billing rules associated with this reservation or use.

[0069] Specifically, when the intelligent management and control model outputs a result indicating the need for maintenance recommendations, and the reason is a comprehensive permission issue, the system will initiate this standardized verification process to clearly inform the user which specific condition(s) are not met. This verification is executed concurrently or rapidly sequentially. First, training and assessment verification is performed: the system queries the user's training record database, checks the required training list associated with the target resource, verifies whether the user has completed all courses in the list, and checks whether the final assessment results for completed courses meet the standards. Second, the validity of usage permissions is verified: the system checks the user's account status field, checks the validity period of the qualification tags obtained and associated with the target resource, and queries the permission policy table to check for any unmet temporary restrictions. Finally, the account balance is verified: the system calculates the estimated cost based on the resource's billing standard and the current reservation duration, queries the user's real-time account balance, and compares the values.

[0070] S422: If any condition is not met, lock the access rights to the corresponding resource and generate maintenance suggestions such as time-limited training, supplementary payment, or recertification.

[0071] In this embodiment, locking access to a corresponding resource refers to an automatic control action performed by the system, which temporarily prohibits users from making reservations, access authorizations, device logins, and other operations on specific target resources until all access conditions are met. Maintenance suggestions such as time-limited training, supplementary payment, or re-authentication are generated based on the specific diagnostic results of S421, providing clear operational instructions on how to unlock and restore permissions. These instructions typically include specific task content, completion deadlines, and operation entry points.

[0072] Specifically, if any condition in the S421 verification process is not met, an automated control execution pipeline will be triggered. First, an automatic access control operation is executed: the system sends synchronous instructions to the appointment management module, access control module, and device login verification module, setting the associated operation status between the user and the target resource to locked. For example, it immediately cancels any currently invalid appointments for that device, temporarily prohibits the user from submitting new appointment requests for that device in the appointment system, temporarily removes the user's access to the laboratory where the device is located in the access control system, and refuses the user's account login on the device login interface. This action is immediate and mandatory, technically eliminating the possibility of continuing to use the equipment without meeting safety, compliance, or financial conditions, thus ensuring the bottom line of laboratory management. Simultaneously, the system generates highly targeted and precise maintenance suggestions based on the specific conditions not met. These suggestions clearly list all non-compliant items and provide specific solutions for each. For example, if a user fails an assessment, a specific course link is provided; if the balance is insufficient, the required recharge amount and payment channel are specified; if the qualification has expired, the recertification application process is explained. This combination of locking permissions and generating instructions achieves closed-loop management by blocking illegal channels and clearing compliant paths. It not only effectively prevents risks but also guides users to proactively return to compliant usage in a clear and operable manner.

[0073] In this embodiment, a multi-layered, strongly constrained access verification mechanism was constructed, enabling the automatic and immediate execution of management actions. By clearly defining four core conditions—training completion, passing the assessment, valid permissions, and sufficient balance—management requirements are transformed into hard rules that the system can automatically verify. When any condition is not met, the corresponding permissions are automatically locked. This action achieves zero-delay automatic execution of management strategies, technically ensuring laboratory safety and compliance, and avoiding delays and oversights inherent in manual management. Simultaneously with locking permissions, the system generates maintenance suggestions containing specific solutions, such as requiring training within a specified time or supplementary payment. This combines blocking non-compliant paths with facilitating compliant paths, transforming management conflicts into a clear problem-solving process, and improving the guiding effect and user acceptance of management measures.

[0074] In one embodiment, the IoT-based cross-institutional laboratory resource intelligent reservation method further includes reservation and automatic billing management steps: S50: Obtain the user's request to reserve instruments, venues or scientific research services, and read the user's current permission status, credit score and account balance information.

[0075] In this embodiment, a user-initiated reservation request refers to an application formally submitted by the user after selecting a specific laboratory resource and setting the usage time on the platform interface. The user's current permission status refers to the real-time control status of the user account and its relation to the reserved resource at the moment the reservation is being processed. The credit score is a rating dynamically calculated by the system based on the user's historical behavior, used to measure their creditworthiness. Account balance information refers to the funds pre-deposited by the user on the platform that can be used to pay for resource usage fees.

[0076] Specifically, when a user submits a reservation request on the platform, a parallel real-time status verification process is triggered before the system officially processes the request and writes it into the resource schedule. The system needs to obtain the user's comprehensive status at the current moment, especially information related to performance capability and credit. First, the system queries the user's current permission status, checking whether their account is normal and whether there are any restrictions automatically marked by the system due to failure to complete prerequisite tasks. Next, it reads the user's current credit score from the credit management module, which is usually dynamically calculated from a base score, performance bonus points, and violation deduction points. Finally, it reads the user's account balance information in real time from the financial settlement module. This process is completed synchronously in real time, ensuring that the system uses the latest and most accurate snapshot of the user's credit and financial status for subsequent decisions, providing accurate input data for judging the financial feasibility and credit reliability of the reservation request.

[0077] S60: Calculate the estimated cost based on the pre-design fee rules and appointment duration, and compare the account balance with the estimated cost.

[0078] In this embodiment, the pre-design fee rule is the charging standard set by the platform for different resources, which may include hourly billing, per-use billing, billing based on the number of samples, and time-based rates. The reservation duration is the length of time the user requests to use the resource. The estimated cost is the amount of money expected to be incurred for this use, calculated based on the billing rules and the reservation duration. Comparing the account balance with the estimated cost is a simple numerical comparison operation, aimed at determining whether the user's current financial capacity is sufficient to cover the expected cost of this reservation.

[0079] Specifically, after obtaining the user's reservation request details and account balance, the system needs to quickly assess the feasibility of the reservation from a financial perspective. The system retrieves the pre-designed fee rules for the target resource. Based on these rules and the reservation duration submitted by the user, the system automatically calculates the estimated cost of the reservation. For example, for a device that charges by the hour, the cost is the rate multiplied by the number of hours. After the calculation, the system automatically performs a comparison operation: comparing the user's real-time account balance with the calculated estimated cost. This step transforms the abstract, clause-based billing policy into a concrete economic cost directly related to the reservation and immediately measures it against the user's actual funds. This makes the reservation request no longer a simple request for time occupancy, but a substantive service contract request with attached payment guarantee, thereby ensuring the validity and seriousness of the reservation from a financial perspective and providing a basis for possible subsequent automatic deduction or guarantee mechanisms.

[0080] S70: When the comparison result shows sufficient balance, the payment is automatically deducted and a reservation success instruction is generated; when the comparison result shows insufficient balance, the reservation is terminated and a balance reminder message is triggered.

[0081] In this embodiment, automatic deduction means that when the balance is sufficient, the system automatically deducts funds equal to the estimated cost from the user's account balance as a deposit or pre-deduction for the reservation without requiring the user to confirm payment again. The reservation success instruction is a command sent by the system to the reservation management module after successful deduction, confirming that the time slot has been officially occupied, and simultaneously returning final confirmation of reservation success to the user. Reservation termination means that when the balance is insufficient, the system immediately stops processing the reservation request and will not write it to the resource schedule. The balance reminder message is a notification sent by the system to the user, informing them that the reservation failed due to insufficient balance and prompting them to recharge.

[0082] Specifically, this is the final execution step of reservation and billing control. The system generates a branching process based on the balance comparison result. If the balance is sufficient, the system determines that the user's payment ability is reliable and immediately performs an automatic deduction operation, deducting the corresponding amount from the user's account in real time. This fund is usually frozen as a performance guarantee. After the deduction operation is successful, the system immediately generates a reservation success instruction. This instruction, on the one hand, officially marks the resource's status during the reservation period as occupied, locking the resource; on the other hand, it sends a success notification containing reservation details and deduction voucher to the user's interface or message center. This achieves atomic operation of reservation and payment guarantee, greatly simplifies the user process, and generates a valid reservation with economic binding force. If the balance is insufficient, the system determines that the payment ability cannot guarantee this reservation and immediately terminates the processing of the reservation request, ensuring that the time period can still be reserved by other users to ensure resource utilization efficiency. At the same time, the system triggers a balance reminder message, notifying the user that their reservation has been canceled due to insufficient balance, and clearly indicating the amount that needs to be recharged. This instant termination and reminder mechanism prevents invalid reservations from occupying scarce resource time slots for extended periods and directly guides users to recharge and re-initiate valid reservations, forming a positive management guidance cycle. The entire process enables proactive and real-time control of financial risks in the reservation business.

[0083] In this embodiment, resource reservation and payment settlement are deeply integrated, and pre-verification based on users' real-time credit and payment ability is performed, achieving automated closed-loop business processes and proactive financial risk prevention. Permissions, credit, and account balance are simultaneously verified upon reservation initiation, conducting a comprehensive pre-screening of eligibility and payment ability, thus advancing financial risk assessment. Estimated costs are calculated based on billing rules and reservation duration, and the balance is compared, transforming abstract rules into real-time cost estimates and linking them to payment ability, improving transaction transparency. When the balance is sufficient, payment is automatically deducted and the reservation is confirmed, achieving atomic operations between reservation and payment, simplifying the user process, and generating reservation instructions with payment security. When the balance is insufficient, the reservation is terminated and a reminder is sent, preventing invalid reservations from consuming resources and guiding users to recharge in time to re-initiate valid reservations, thereby improving the effectiveness of resource scheduling and the operational efficiency of the institution.

[0084] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0085] In one embodiment, an IoT-based intelligent reservation device for cross-institutional laboratory resources is provided, which corresponds one-to-one with the IoT-based intelligent reservation method for cross-institutional laboratory resources described in the above embodiments. For example... Figure 2As shown, this IoT-based intelligent reservation device for cross-institutional laboratory resources includes a parameter acquisition module, a dataset acquisition module, a resource management module, and a suggestion generation module. Detailed descriptions of each functional module are as follows: The parameter acquisition module is used to acquire the laboratory access message triggered after the user completes registration and authentication, and to acquire the laboratory's full-process management parameters. These parameters include user identity data, training and assessment records, resource reservation information, permission status, and usage and billing data. The dataset acquisition module is used to preprocess user identity data, training and assessment records, resource reservation information, permission status, and usage billing data to obtain the dataset to be analyzed and managed. The resource management module is used to input the dataset to be analyzed into the preset intelligent laboratory management model. The intelligent laboratory management model dynamically calculates the user permissions and resource usage management results based on the relationship between the data in the dataset to be analyzed. The suggestion generation module is used to obtain user type and resource usage type, and generate corresponding suggestions for laboratory usage and permission maintenance for users based on user permissions and resource usage control results.

[0086] Specific limitations regarding the IoT-based intelligent reservation device for cross-institutional laboratory resources can be found in the limitations of the IoT-based intelligent reservation method for cross-institutional laboratory resources described above, and will not be repeated here. Each module in the aforementioned IoT-based intelligent reservation device for cross-institutional laboratory resources can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0087] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements an IoT-based intelligent reservation method for cross-institutional laboratory resources.

[0088] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: Get the laboratory access message triggered after the user completes registration and authentication, and get the laboratory full-process management parameters, including user identity data, training and assessment records, resource reservation information, permission status and usage billing data; After preprocessing user identity data, training and assessment records, resource reservation information, permission status, and usage billing data, a dataset to be analyzed and managed is obtained. Input the dataset to be analyzed into the preset intelligent laboratory management and control model. The intelligent laboratory management and control model dynamically calculates the user permissions and resource usage control results based on the correlation between the data in the dataset to be analyzed. Obtain user type and resource usage type, and generate corresponding suggestions for laboratory usage and permission maintenance based on user permissions and resource usage control results.

[0089] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Get the laboratory access message triggered after the user completes registration and authentication, and get the laboratory full-process management parameters, including user identity data, training and assessment records, resource reservation information, permission status and usage billing data; After preprocessing user identity data, training and assessment records, resource reservation information, permission status, and usage billing data, a dataset to be analyzed and managed is obtained. Input the dataset to be analyzed into the preset intelligent laboratory management and control model. The intelligent laboratory management and control model dynamically calculates the user permissions and resource usage control results based on the correlation between the data in the dataset to be analyzed. Obtain user type and resource usage type, and generate corresponding suggestions for laboratory usage and permission maintenance based on user permissions and resource usage control results.

[0090] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0091] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0092] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. An Internet of Things-based intelligent reservation method for cross-institutional laboratory resources, characterized in that, The IoT-based intelligent reservation method for cross-institutional laboratory resources includes: Obtain the laboratory access message triggered after the user completes registration and authentication, and obtain the laboratory full-process management parameters, wherein the laboratory full-process management parameters include user identity data, training and assessment records, resource reservation information, permission status and usage billing data; After preprocessing the user identity data, the training and assessment records, the resource reservation information, the permission status, and the usage and billing data, a dataset to be analyzed and managed is obtained. The dataset to be analyzed is input into a preset intelligent laboratory management and control model. The intelligent laboratory management and control model dynamically calculates the user permissions and resource usage management results based on the correlation between the data in the dataset to be analyzed. Obtain user type and resource usage type, and generate corresponding laboratory usage and permission maintenance suggestions for users based on the user permissions and resource usage control results. 2.The IoT-based cross-institutional laboratory resource intelligent reservation method of claim 1, wherein, After preprocessing the user identity data, training and assessment records, resource reservation information, permission status, and usage billing data, a management dataset to be analyzed is obtained, specifically including: Based on the user identity data and the training and assessment records, generate the user's qualification level for entering the room and using the equipment; After aligning the time nodes and process nodes according to the user's entry and instrument usage qualification level, the resource reservation information and the permission status, the dataset to be analyzed and managed is obtained.

3. The IoT-based cross-institutional laboratory resource intelligent reservation method according to claim 1, wherein, The intelligent laboratory management and control model was trained using the following method: From historical management data, obtain the correlation between training completion, appointment behavior, permission status and billing consumption under different user types and resource types during continuous use, and construct an intelligent management and control trend curve based on the correlation. The control inflection point is obtained from the intelligent control trend curve, and a corresponding dynamic calculation weight is set for each control inflection point, the training completion rate, and the appointment behavior according to different user types and resource types. The initial model is iteratively trained using the dynamically calculated weights under different scenarios to obtain the intelligent laboratory management model with adaptive judgment capabilities.

4. The method for intelligent reservation of cross-institutional laboratory resources based on the Internet of Things according to claim 3, characterized in that, The step involves inputting the dataset to be analyzed into a preset intelligent laboratory management model. The intelligent laboratory management model dynamically calculates user permissions and resource usage control results based on the relationships between the data in the dataset, specifically including: Input the management dataset to be analyzed into the laboratory intelligent control model; Based on the control trend curve and the control inflection point, match the calculation weights corresponding to the current user type and resource type; The user permissions and resource control results are dynamically obtained by comprehensively calculating the dataset to be analyzed and the matched calculation weights.

5. The method for intelligent reservation of cross-institutional laboratory resources based on the Internet of Things according to claim 1, characterized in that, The process of obtaining user type and resource usage type, and generating corresponding laboratory usage and permission maintenance suggestions for users based on the user permission and resource usage control results, specifically includes: Retrieve the user permissions and resource management results for each user type corresponding to the resource type; If the control result is lower than the preset usage permission threshold, then the laboratory usage and maintenance suggestions are generated based on the user identity data, remaining resource types, and current training status.

6. The method for intelligent reservation of cross-institutional laboratory resources based on the Internet of Things according to claim 5, characterized in that, If the control result is lower than the preset usage permission threshold, then the laboratory usage and maintenance suggestions are generated based on the user identity data, remaining resource type, and current training status, specifically including: Determine whether user training is complete, whether the assessment is satisfactory, whether the usage rights are valid, and whether the account balance meets the billing conditions; If any condition is not met, the access rights to the corresponding resources will be locked, and maintenance suggestions such as time-limited training, supplementary payment, or recertification will be generated.

7. The method for intelligent reservation of cross-institutional laboratory resources based on the Internet of Things according to claim 1, characterized in that, It also includes reservation and automatic billing control steps: Get user-initiated requests for instrument, venue, or research service reservations, and read the user's current permission status, credit score, and account balance information; The estimated cost is calculated based on the pre-design fee rules and the reservation duration, and the account balance is compared with the estimated cost. When the comparison result shows sufficient balance, the payment will be automatically deducted and a reservation success instruction will be generated; when the comparison result shows insufficient balance, the reservation will be terminated and a balance reminder message will be triggered.

8. A smart reservation device for cross-institutional laboratory resources based on the Internet of Things, characterized in that, The IoT-based cross-institutional laboratory resource intelligent reservation device includes: The parameter acquisition module is used to acquire the laboratory access message triggered after the user completes registration and authentication, and to acquire the laboratory full-process management parameters, wherein the laboratory full-process management parameters include user identity data, training and assessment records, resource reservation information, permission status and usage billing data; The dataset acquisition module is used to preprocess the user identity data, the training and assessment records, the resource reservation information, the permission status, and the usage and billing data to obtain the dataset to be analyzed and managed. The resource management module is used to input the dataset to be analyzed into a preset intelligent laboratory management model. The intelligent laboratory management model dynamically calculates the user permissions and resource usage management results based on the correlation between the data in the dataset to be analyzed. The suggestion generation module is used to obtain user type and resource usage type, and generate corresponding laboratory usage and permission maintenance suggestions for users based on the user permissions and resource usage control results.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the IoT-based cross-institutional laboratory resource intelligent reservation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the IoT-based cross-institutional laboratory resource intelligent reservation method as described in any one of claims 1 to 7.

Images