Platform and method for whole-cycle monitoring and compliance verification of digestive endoscopy disinfection process

Abstract

The invention discloses a digestive endoscope disinfection process full-cycle monitoring and compliance verification platform and method, and the platform comprises a data collection and preprocessing module which is used for collecting and preprocessing real-time state data and environment data, and generating a standardized data set; the path optimization and decision module is used for simulating a plurality of operation paths of a disinfection process by utilizing a Monte Carlo tree search algorithm and selecting an optimal disinfection path; the compliance reasoning and verification module is used for reasoning symbol rules in the disinfection process; the block chain evidence storage module is used for writing the data blocks into a block chain account book to form a disinfection data chain; the intelligent contract processing module is used for performing real-time judgment, automatically triggering an alarm and recording non-compliance operation; and the feedback and query module is used for querying, retrieving and auditing the whole-process information, alarm records and compliance events of the disinfection process. According to the invention, intelligent optimization of the disinfection process, real-time compliance verification and on-chain evidence storage are realized, and the safety supervision efficiency is comprehensively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of disinfection management and information security of medical devices, and particularly to a full-cycle monitoring and compliance verification platform and method for the disinfection process of digestive endoscopes. Background Art

[0002] In the current medical industry, the disinfection management of high-risk medical devices such as digestive endoscopes is an important link in infection prevention and control and medical safety. With the increasing use frequency of digestive endoscopes and the complexity of the disinfection process, hospitals and medical institutions generally adopt automated disinfection equipment and information systems for process management. Existing technologies usually rely on local data records of disinfection equipment or information management methods based on centralized databases to archive the operating status of equipment, disinfection parameters, and process results. Although such management solutions have improved the level of process automation, due to the lack of immutability of data storage methods, it is difficult to achieve trustworthy data storage throughout the process and transparent supervision by multiple departments, and the ability to judge compliance in real time is limited. There are risks such as data loss, fraud, or inability to hold accountable in a timely manner in the data of the disinfection process link.

[0003] In addition, traditional disinfection process monitoring systems mainly use preset static rules for compliance judgment, lacking the intelligent perception and dynamic optimization capabilities for dynamic changes in the disinfection environment, fluctuations in equipment parameters, and actual operation paths. This results in the system being difficult to achieve targeted risk assessment and operation optimization in the face of complex working conditions, operation differences, or multi-source data anomalies during the actual disinfection process, and it is also unable to perform intelligent, real-time, and multi-dimensional judgments on disinfection compliance. Especially in multi-point and multi-link collaborative scenarios, traditional systems are difficult to efficiently meet the requirements of process optimization, compliance traceability, and cross-institutional supervision, and it is difficult to balance management efficiency and data security.

[0004] Existing technologies also generally have problems of information silos and inconsistent standard interfaces. Data between different disinfection equipment and information systems lacks interoperability and sharing, and it is difficult to provide consistent and complete disinfection process data for multiple entities such as external supervision platforms and medical quality control departments. At the same time, existing monitoring systems have insufficient capabilities for real-time warning and automatic accountability of abnormal disinfection behaviors, usually relying on manual intervention or post-event auditing, and cannot effectively achieve risk closed-loop management throughout the process.

[0005] In summary, the existing technologies for monitoring the disinfection process of digestive endoscopes and verifying compliance are difficult to meet the comprehensive requirements of the modern medical industry for full-cycle monitoring, intelligent compliance verification, traceability throughout the process, and trustworthy collaboration among multiple institutions.

[0006] Therefore, how to provide a full-cycle monitoring and compliance verification platform for the disinfection process of digestive endoscopes is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0007] An object of the present invention is to provide a full-cycle monitoring and compliance verification platform for the disinfection process of digestive endoscopes. The present invention fully integrates the Monte Carlo tree search algorithm, neuro-symbolic reasoning technology, and blockchain evidence storage mechanism, and details the implementation methods for multi-path intelligent optimization of the disinfection process, real-time discrimination of compliance, and non-tamperable recording of the whole process data. Through the whole-process collection and intelligent analysis of the real-time status data, operation paths, operation parameters, and compliance verification results of the disinfection equipment, combined with smart contracts to achieve automated compliance warnings and traceability, the platform has the advantages of high intelligence, strong data security, accurate compliance discrimination, support for multi-subject trusted collaboration, and full-process traceability, effectively improving the informatization management and risk prevention and control levels of the medical disinfection process.

[0008] The full-cycle monitoring and compliance verification platform for the disinfection process of digestive endoscopes according to an embodiment of the present invention includes: A data collection and preprocessing module for collecting real-time status data and environmental data and performing preprocessing to generate a standardized data set; A path optimization and decision-making module for simulating multiple operation paths of the disinfection process using the Monte Carlo tree search algorithm based on the standardized data set and selecting the optimal disinfection path; A compliance reasoning and verification module for reasoning about the symbolic rules during the disinfection process based on the optimal disinfection path and outputting operation parameters and compliance verification results; A blockchain evidence storage module for writing the real-time status data, operation path, operation parameters, and compliance verification results of the disinfection equipment into the blockchain ledger in blocks to form an immutable disinfection data chain; A smart contract processing module for making real-time judgments on the disinfection data chain, automatically triggering alarms, and recording non-compliant operations; A feedback and query module for querying, retrieving, and auditing the whole-process information of the disinfection process, alarm records, and compliance events.

[0009] Optionally, the modules are implemented by the following methods: S1. Collect the real-time status data and environmental data of the disinfection equipment, and perform preprocessing to generate a standardized data set; S2. Based on the standardized data set, use the Monte Carlo tree search algorithm to simulate multiple operation paths of the disinfection process, and select the optimal disinfection path according to multiple variables during the disinfection process; S3. Based on the optimal disinfection path, use neuro-symbolic reasoning to reason about the symbolic rules during the disinfection process, and combine relevant regulations and standards to verify the compliance of the disinfection process, and dynamically adjust the operation parameters in the disinfection process; S4. Use blockchain technology to record the real-time status data of the disinfection equipment, the operation path during the disinfection process, the operation parameters in the disinfection process, and the compliance verification results, generating an immutable disinfection data chain; S5. Through a smart contract, conduct real-time verification on the disinfection data chain, automatically trigger an alarm and record non-compliant operations. When the disinfection time, equipment temperature, or other parameters do not meet the predetermined standards, the smart contract will automatically issue an alarm and record relevant information; S6. Based on the real-time verification results, generate a detailed disinfection report, and through a feedback mechanism, timely transmit the rectification suggestions for non-compliant operations to the operators.

[0010] Optionally, the real-time status data of the disinfection equipment specifically includes the operating status, temperature, humidity, pressure, disinfection time, operator information, and working status of the equipment, and the environmental data specifically includes the temperature, humidity, air quality, and lighting intensity in the disinfection environment.

[0011] Optionally, the preprocessing specifically includes cleaning, standardizing, filling missing values, detecting outliers, and converting data formats for the real-time status data of the disinfection equipment and the environmental data.

[0012] Optionally, S2 specifically includes: S21. Based on the generated standardized dataset, divide the disinfection process into multiple independent stages, and each stage is defined as a hierarchical state space , which includes preprocessing, main disinfection, drying, detection, and storage stages; S22. Within each hierarchical state space , based on the operation nodes, state transitions, and operation parameters in each stage of the disinfection process, independently construct a Monte Carlo tree search subtree for each layer, and conduct path simulation and optimization; S23. During the node expansion process of each hierarchical subtree, according to the pre-set disinfection process compliance standards, including disinfection equipment operation specifications, disinfection time thresholds, temperature and pressure, and safety rules, conduct rule judgment on each expandable action, and only expand the actions that meet all the standards, forming a constraint-aware adaptive tree structure. The safety rules include equipment operation safety parameters and operator identity verification; S24. During the node expansion process of each node, through the monitoring of real-time disinfection status data, dynamically generate risk assessment factors for the disinfection process , and conduct path reward correction; S25. Introduce an adaptive reward mechanism based on real-time environmental feedback, dynamically adjust the path reward function by monitoring data in real time, and dynamically adjust the priority of path selection and adjust the reward function ; S26. During the simulation process, in combination with the real-time status data of the disinfection equipment, environmental data, and the risk assessment of the current disinfection path, the simulation path selection is dynamically guided by an adaptive policy network, which includes: An input layer that receives the real-time status data and environmental data of the disinfection equipment; A hidden layer that extracts features and processes information from the real-time status data and environmental data of the disinfection equipment through a multi-layer perceptron; An output layer that generates the selection probability of each operation path through the Softmax function and determines the priority of the path; The adaptive policy network is trained based on the historical operating status, disinfection time, disinfection effect, and monitoring data of the disinfection equipment, continuously adjusts the ratio of exploration and exploitation, and preferentially selects an operation sequence that meets the preset compliance standards, satisfies the risk control requirements, and is higher than the set threshold in terms of efficiency by setting the thresholds of compliance, risk, and efficiency, optimizing the path selection during the disinfection process. The adaptive policy network flexibly responds and adjusts the decision-making strategy according to the changes in the real-time disinfection environment; S27. During the path expansion and simulation process, according to the disinfection process compliance standard and the adaptive reward mechanism, prune the paths that do not meet the compliance standard, violate the timing or safety requirements, or the path reward does not reach the set threshold, and terminate the expansion and simulation of the path in advance; S28. Through parallel computing technology, perform multi-threaded or distributed processing on the simulation tasks of different hierarchical state spaces and different operation paths; S29. During each simulation and backtracking process, accumulate the return values of each hierarchical path and pass the optimal decision-making parameters of the current layer to the next-layer state space to achieve local optimal decision-making for each layer and global optimal path selection for the entire disinfection process; S210. Repeat steps S21 to S29 until the preset number of simulation times or the computing resource threshold is reached. Finally, combine the optimal paths of all layers and output the optimal disinfection path of the entire disinfection process as the basis for the optimization decision of the disinfection process.

[0013] Optionally, the specific content of S3 includes: S31. Based on the generated optimal disinfection path, extract the operation parameters, disinfection time, temperature, and humidity information during the disinfection process, and jointly construct a symbolic rule library in combination with relevant regulatory standards , where n is the total number of symbolic rules, and is the number of relevant regulatory standards; S32. Construct a neuro-symbolic inference model, which specifically includes: An input layer that receives the symbolic rule library , which includes relevant regulations and standards , real-time status data of the disinfection equipment and operation sequences ; Neural network layer, which performs feature extraction and high-dimensional representation learning on the data received by the input layer, and outputs high-dimensional feature representations; Symbolic rule encoding module, which encodes the symbolic rules and regulations and standards in the input layer into vectorized codes to obtain rule embeddings; Inference mechanism integration module, which inputs the high-dimensional feature representations output by the neural network layer and the rule embeddings output by the symbolic rule encoding module into the symbolic inference engine, performs joint inference through logical rules, and outputs local compliance determination values ; Output layer, which outputs a local compliance determination value vector , indicating the local compliance determination value, ; S33. Based on the obtained local compliance determination value vector , combined with the real-time status data of the disinfection equipment received by the input layer, the high-dimensional feature representations output by the neural network layer, the rule embeddings output by the symbolic rule encoding module, and the inference results of the inference mechanism integration module, compare each local compliance determination value with the relevant regulations and standards , and combine the time-sequence dependence relationship, risk assessment, and real-time environmental feedback data of the disinfection operation sequence to calculate the time-sequence risk-weighted global compliance score ; S34. For non-compliant or high-risk paths, based on the local compliance determination values output by the inference mechanism integration module, automatically generate a set of corrective operation suggestions, and adjust the operation parameters in the disinfection path. Each corrective operation suggestion corresponds to a specific corrective action; S35. Feedback the set of corrective operation suggestions, update the operation parameters of the disinfection path, and modify the operation parameters of the disinfection path by increasing or decreasing according to the corrective suggestions based on the current disinfection path parameters; S36. For paths determined to be compliant, continuously call the neural network layer and the inference mechanism integration module to optimize and adjust the disinfection parameters, and output the optimal parameter set through the policy function ; S37. During the path optimization process, use the symbolic rule encoding module and the inference mechanism integration module to automatically update the symbolic rule library according to the real-time status data of the disinfection equipment and environmental feedback, and generate an updated symbolic rule library ; S38. Train the neuro-symbolic inference model through the reinforcement learning mechanism to optimize the disinfection path selection and symbolic rule generation, through the compliance loss function , minimize compliance losses; S39. Input the updated symbolic rule library and operation parameters, re - simulate the path to ensure that the disinfection process is always compliant, efficient, and safe. Through a loop feedback mechanism, continuously monitor and optimize the disinfection path.

[0014] Optionally, the specific steps of S4 are as follows: S41. Collect the real - time status data of the disinfection equipment, the operation path during the disinfection process, the operation parameters of the dynamically adjusted disinfection process, the global compliance score and the updated symbolic rule library , and organize them into a data set ; S42. Chunk the data set according to the time sequence of the disinfection process and the unique device identifier . Each data chunk contains a timestamp, a device number, an operation path, operation parameters of the disinfection process, a global compliance score and the updated symbolic rule library ; S43. Perform a hash operation on each data chunk to obtain a block hash value. The hash input is the content of the current data chunk and the previous block hash value, and the hash algorithm used is consistent with the blockchain ledger; S44. Write the data chunk containing the hash value, timestamp, operation path, operation parameters of the disinfection process, global compliance score and the updated symbolic rule library into the blockchain ledger in the form of blocks in sequence to form a disinfection data chain ; S45. Authenticate each data chunk using a digital signature. The digital signature corresponds to the node identity one by one to ensure non - repudiation of data writing and operation traceability. The signature content includes the block hash value and the node identifier; S46. Based on the smart contract of the blockchain ledger, automatically detect the comparison relationship between the global compliance score in each data chunk and the relevant regulatory standards . If the score is lower than the set compliance threshold, it is automatically marked as a non - compliant event and recorded on the chain; S47. For all compliant and non - compliant events, record the disinfection process data and parameter adjustment information in detail in the blockchain ledger to achieve non - tamperable evidence storage and full - process traceable auditing for the whole process; S48. When the blockchain ledger receives a data query, call, or exception alarm request, retrieve the disinfection path parameters, device status, operation parameters, global compliance score , symbolic rule library and compliance events, supporting data transparency and traceability for full-process monitoring and compliance verification; S49. Regularly perform integrity verification on the blockchain ledger, and verify the consistency of blocks through the hash chain structure.

[0015] Optionally, the S5 specifically includes: S51. Compare the disinfection time, equipment temperature, and other key operation parameters with preset standards in real time, and make judgments according to the compliance rules set by the smart contract; S52. When the smart contract detects that the disinfection time, equipment temperature, or other key parameters do not meet the predetermined standards, immediately automatically determine it as a non-compliant operation; S53. For each non-compliant operation, the smart contract automatically triggers an early warning mechanism, generates alarm information, and sends it to relevant responsible personnel or management terminals in real time; S54. Automatically record and write the specific information of all non-compliant operations, including the operation time, equipment number, abnormal parameters, and specific values deviating from the standards, into the blockchain ledger; S55. Support querying, retrieving, and auditing the alarm information and non-compliant operations recorded in the blockchain ledger, facilitating the tracing of abnormal situations in the disinfection process and promoting rectification.

[0016] The beneficial effects of the present invention are: By deeply integrating the Monte Carlo tree search algorithm with neuro-symbolic reasoning, the present invention realizes multi-path intelligent simulation, optimization, and dynamic adjustment of the disinfection process, can automatically generate the optimal operation path and parameters for different disinfection working conditions and equipment states, and significantly improves the adaptability and intelligent decision-making level of the disinfection process. Using neuro-symbolic reasoning combined with regulatory standards to perform real-time compliance determination on each step of the operation, it realizes multi-dimensional and full-process intelligent compliance verification, effectively avoiding the problem of untimely recognition of abnormal and marginal situations under the traditional static rule system. At the same time, the present invention uses blockchain technology to write the real-time state data, operation path, operation parameters, and compliance verification results of the disinfection equipment into the blockchain ledger throughout the process, ensuring the immutability, full-life-cycle traceability, and multi-institutional trusted collaboration of the disinfection process data, and greatly improving the data security and liability traceability capabilities.

[0017] The present invention also conducts real-time automated discrimination and alerts on compliance through a smart contract mechanism, capable of triggering warnings and detailed records at the first moment of non-compliant behavior in the disinfection process, significantly improving the efficiency and standardization level of abnormal risk response. The platform supports dynamic querying and auditing of the entire process data of disinfection, facilitating quality control, supervision, and multi-department collaboration, and realizing an integrated innovation solution from disinfection process optimization, intelligent compliance discrimination, full-process data security deposit to cross-institutional collaborative management. Compared with the prior art, the present invention significantly improves the intelligent, standardized, and information security levels of medical disinfection process management, providing more reliable technical support for nosocomial infection prevention and control and quality management in medical institutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings: Figure 1 is a flowchart of the full-cycle monitoring and compliance verification method for the disinfection process of digestive endoscopes proposed by the present invention; Figure 2 is a flowchart of the generation of the data chain of the blockchain and the automatic deposit of compliance events for the full-cycle monitoring and compliance verification method of the disinfection process of digestive endoscopes proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Now, the present invention will be further described in detail with reference to the drawings. These drawings are all simplified schematic diagrams, only illustrating the basic structure of the present invention in a schematic manner, so they only show the components related to the present invention.

[0020] Referring to Figure 1 and Figure 2 , the full-cycle monitoring and compliance verification platform for the disinfection process of digestive endoscopes includes: A data acquisition and preprocessing module for collecting real-time status data and environmental data and performing preprocessing to generate a standardized data set; A path optimization and decision-making module for simulating multiple operation paths of the disinfection process using the Monte Carlo tree search algorithm based on the standardized data set and selecting the optimal disinfection path; A compliance reasoning and verification module for reasoning about the symbol rules during the disinfection process based on the optimal disinfection path and outputting operation parameters and compliance verification results; A blockchain deposit module for writing the real-time status data of the disinfection equipment, operation paths, operation parameters, and compliance verification results into the blockchain ledger in blocks to form an immutable disinfection data chain; A smart contract processing module for making real-time judgments on the disinfection data chain, automatically triggering alarms, and recording non-compliant operations; The feedback and query module is used to query, retrieve and audit the entire disinfection process information, alarm records and compliance events.

[0021] In this implementation, the modules are implemented by the following method: S1. Collect real-time status data and environmental data of disinfection equipment, perform preprocessing, and generate standardized data sets; S2. Based on the standardized data set, the Monte Carlo tree search algorithm is used to simulate multiple operation paths of the disinfection process, and the optimal disinfection path is selected according to multiple variables in the disinfection process; S3. Based on the optimal disinfection path, neural symbolic reasoning is used to infer the symbolic rules in the disinfection process, and the compliance of the disinfection process is verified in combination with relevant regulations and standards, and the operating parameters in the disinfection process are dynamically adjusted; S4. Use blockchain technology to record the real-time status data of disinfection equipment, the operation path during the disinfection process, the operation parameters in the disinfection process, and the compliance verification results to generate an unalterable disinfection data chain; S5. Real-time verification of the disinfection data chain is carried out through smart contracts, which automatically triggers alarms and records non-compliant operations. When the disinfection time, equipment temperature or other parameters do not meet the predetermined standards, the smart contract will automatically issue an alarm and record relevant information; S6. Generate a detailed disinfection report based on real-time verification results, and promptly deliver rectification suggestions for non-compliant operations to operators through the feedback mechanism.

[0022] The present invention achieves high quality and consistency of input data of the disinfection process and improves the reliability of system decision-making by comprehensively collecting and standardizing the real-time status data and environmental data of the disinfection equipment. The Monte Carlo tree search algorithm is used to simulate and optimize the path of the multivariable disinfection process, which greatly enhances the intelligence and adaptability of the process optimization. Combining neural symbolic reasoning and regulatory standards, intelligent compliance reasoning and dynamic parameter adjustment are performed on the disinfection operation, so that the disinfection process can be flexibly adapted according to the actual situation, and the compliance judgment is more accurate and efficient. The blockchain technology is used to store the key data and compliance results throughout the process, ensuring that the disinfection data chain cannot be tampered with and can be traced throughout the process, and improving data security and transparency of responsibility attribution. Smart contracts realize automatic real-time verification of compliance and abnormal alarms, greatly improving the speed and standardization of risk response. Non-compliant operations can be identified in time and rectification suggestions can be formed, effectively supporting the closed-loop optimization process of operators. On the whole, the present invention significantly improves the informationization, intelligence and compliance management capabilities of the medical disinfection process, and enhances medical safety and regulatory efficiency.

[0023] In this embodiment, the real-time status data of the disinfection equipment specifically includes the operating status, temperature, humidity, pressure, disinfection time, operator information, and working status of the equipment, and the environmental data specifically includes the temperature, humidity, air quality, and lighting intensity in the disinfection environment.

[0024] In this embodiment, the preprocessing specifically includes cleaning, standardizing, filling missing values, detecting outliers, and converting data formats for the real-time status data and environmental data of the disinfection equipment. The cleaning, standardizing, filling missing values, detecting outliers, and converting data formats specifically refer to cleaning the collected real-time status data and environmental data of the disinfection equipment, removing duplicate, invalid, or logically contradictory data entries; then performing standardization processing to normalize and convert various data according to a unified dimension for subsequent model processing; for existing data missing situations, using mean filling, interpolation method, or model prediction method to complete missing value filling; in terms of outlier detection, identifying data that significantly deviates from the normal range through methods such as Z-score, box plot, or sliding window method and marking for processing; finally, uniformly converting the processed data into a structured format acceptable to the model, including operations such as time series recombination, field renaming, and encoding format standardization.

[0025] In this embodiment, S2 specifically includes: S21. Based on the generated standardized data set, divide the disinfection process into multiple independent stages, and each stage is defined as a hierarchical state space , which includes preprocessing, main disinfection, drying, detection, and storage stages; S22. In each hierarchical state space , based on the operation nodes, state transitions, and operation parameters in each stage of the disinfection process, independently construct a Monte Carlo tree search subtree for each layer to perform path simulation and optimization. The performing path simulation and optimization specifically refers to constructing an independent Monte Carlo tree search subtree for each stage of the disinfection process. In each layer of the subtree, simulate the state transition paths between different operation nodes, and gradually expand and evaluate the possible operation sequences according to the operation parameters of the current stage. By executing the simulation process in each subtree, predict the performance of each path in terms of efficiency, risk, resource occupancy, and compliance, and at the same time continuously adjust the search strategy according to the set reward mechanism to select the path with the optimal comprehensive benefit. Finally, output the optimal operation decision sequence for each stage. S23. During the node expansion process of each hierarchical subtree, according to the pre-set compliance standards for the disinfection process, including the operation specifications of disinfection equipment, disinfection time thresholds, temperature and pressure, and safety rules, rule judgments are made on each expandable action, and only the actions that meet all the standards are expanded to form a constraint-aware adaptive tree structure. The safety rules include the safe operating parameters of the equipment and the verification of the operator's identity. The specific rule judgment for each expandable action means that during the expansion process of Monte Carlo tree search, each operation action to be executed is checked item by item according to the compliance standards of the disinfection process, specifically including verifying whether the action complies with the equipment operation specifications, whether it is within the specified time, temperature, and pressure ranges, whether it meets the requirements of the equipment operating safety parameters, and whether it is initiated by an operator with legitimate permissions. Only when all the rules are met, the action is allowed to be expanded into the search tree; S24. During the expansion process of each node, by monitoring the real-time disinfection status data, risk assessment factors for the disinfection process are dynamically generated , and path reward correction is performed. The specific path reward correction means that during the expansion process of each node in Monte Carlo tree search, based on the real-time collected disinfection status data, the possible risk factors of the current operation path are evaluated, and the risk level is quantified as a risk assessment factor. Subsequently, this factor is introduced into the reward function of the path to adjust the original simulation return, reduce the reward value of high-risk paths, and increase the priority of low-risk paths, so as to guide the search algorithm to preferentially select disinfection paths with high safety and good stability, and optimize the overall process decision-making quality; S25. Introduce an adaptive reward mechanism based on real-time environmental feedback, dynamically adjust the path reward function through monitoring data, and dynamically adjust the priority of path selection. Adjust the reward function : ; Among them, is the simulation return, is the risk assessment reward generated based on real-time monitoring data, is the feedback reward based on the disinfection status, , , are weight factors; Reward function The practical significance of the formula lies in incorporating the dynamic environment and real-time risk feedback during the optimization process of the disinfection process into the path reward function to achieve intelligent adaptability in path selection. When the traditional Monte Carlo tree search algorithm optimizes the path, it mainly makes decisions based on preset rewards or historical data, and it is difficult to handle changes in the operating environment of disinfection equipment, sudden states, or external risk factors. In this invention, by introducing risk assessment rewards and disinfection status feedback rewards generated based on real-time monitoring data and assigning different weight factors, the reward function can reflect the equipment status, environmental changes, and risk levels in real time. This mechanism not only improves the flexibility of path simulation but also preferentially selects disinfection paths with low risks, high compliance, and excellent efficiency during the optimization process, thereby enhancing the safety and adaptability of the overall process. Through the dynamic adjustment of the reward function, the system can continuously integrate environmental changes and equipment feedback during the disinfection process simulation and decision-making process, form a closed-loop optimization decision, and finally output the optimal disinfection path that best meets the actual working conditions requirements. This innovative mechanism greatly enhances the intelligence and robustness of the disinfection process optimization and ensures the standardization of disinfection operations and medical safety.

[0026] S26. During the simulation process, in combination with the real-time status data of the disinfection equipment, environmental data, and the risk assessment of the current disinfection path, the simulation path selection is dynamically guided by an adaptive policy network, and the adaptive policy network includes: An input layer that receives the real-time status data and environmental data of the disinfection equipment; A hidden layer that extracts features and processes information from the real-time status data and environmental data of the disinfection equipment through a multi-layer perceptron. The specific process of extracting features and processing information refers to performing non-linear mapping and dimensionality reduction processing on the input real-time status data and environmental data of the disinfection equipment through a multi-layer perceptron structure, and automatically mining the potential high-order correlation features therein. This process includes weighted calculation of the original input, activation function conversion, and multi-layer information fusion to extract key feature representations that can reflect disinfection effects, safety risks, or operation anomalies. An output layer that generates the selection probability of each operation path through the Softmax function and determines the priority of the path; The adaptive policy network is trained based on the historical operating status, disinfection time, disinfection effect, and monitoring data of the disinfection equipment, continuously adjusts the ratio of exploration and exploitation, and preferentially selects operation sequences that meet the preset compliance standards, meet the risk control requirements, and are higher than the set threshold in terms of efficiency by setting thresholds for compliance, risk, and efficiency, so as to optimize the path selection during the disinfection process. The adaptive policy network flexibly responds and adjusts the decision-making strategy according to the real-time changes in the disinfection environment; S27. During path expansion and simulation, according to the compliance standards of the disinfection process and the adaptive reward mechanism, prune the paths that do not meet the compliance standards, violate the timing or safety requirements, or whose path rewards do not reach the set threshold, and terminate the expansion and simulation of the path in advance; S28. Through parallel computing technology, perform multi-threaded or distributed processing on the simulation tasks of different hierarchical state spaces and different operation paths. The specific implementation of multi-threaded or distributed processing means that when executing the disinfection process path simulation task, use the parallel computing framework to parallelly allocate the simulation subtasks corresponding to each hierarchical state space and different operation paths under the same state space to multiple computing threads or computing nodes for running, significantly improving the overall simulation efficiency. Specifically, multi-threaded processing enables multiple processing threads to synchronously run multiple path simulation tasks within a single computing node; while distributed processing divides the tasks and distributes them to multiple physical nodes or virtual computing resources, and uses a task scheduling mechanism to coordinate concurrent execution, ensuring that under the premise of ensuring the integrity and consistency of the simulation, the path search and optimization time are shortened to meet the real-time requirements of large-scale disinfection path calculation; S29. During each simulation and backtracking process, accumulate the return values of each hierarchical path, and pass the optimal decision parameters of the current layer to the next layer of the state space to achieve local optimal decision-making for each layer and global optimal path selection for the entire disinfection process; S210. Repeat steps S21 to S29 until the preset number of simulation times or the computing resource threshold is reached. Finally, combine the optimal paths of all layers and output the optimal disinfection path of the entire disinfection process as the basis for the optimization decision of the disinfection process.

[0027] The present invention divides the disinfection process into multiple independent stages, and adopts a hierarchical state space and a hierarchical Monte Carlo tree search strategy to achieve fine modeling of the entire disinfection process and intelligent path optimization. Subtrees of the Monte Carlo tree are independently constructed for each stage, combined with operation nodes, parameters, and state transition mechanisms, making the path simulation and optimization process more flexible and controllable. By introducing compliance standards, operation safety, and personnel identity verification in node expansion, it effectively ensures the compliance and safety of each operation. Real-time monitoring data and environmental feedback dynamically participate in path rewards and risk assessments, forming an adaptive reward mechanism, which not only improves the rationality of path selection but also can respond quickly to changes in the environment and working conditions. An adaptive policy network is adopted to continuously optimize the simulation strategy according to the real-time device status and historical operation data, automatically adjusting the exploration and exploitation ratio to ensure that the operation path that meets compliance, risk control, and high efficiency is preferentially selected. Pruning and parallel simulation technologies are introduced to effectively screen out non-compliant or low-priority paths and improve the calculation efficiency, promoting the efficient output of the globally optimal disinfection path. Overall, the present invention significantly improves the intelligence, real-time performance, and global nature of disinfection process optimization, and enhances the safety guarantee and quality control capabilities of the disinfection process.

[0028] In this embodiment, S3 specifically includes: S31. Based on the generated optimal disinfection path, extract the operation parameters, disinfection time, temperature, and humidity information during the disinfection process, and jointly construct a symbolic rule library in combination with relevant regulatory standards , where n is the total number of symbolic rules, is the number of relevant regulatory standards; S32. Construct a neuro-symbolic reasoning model, specifically including: Input layer, which receives the symbolic rule library , which contains relevant regulatory standards , real-time status data of disinfection equipment, and operation sequences ; Neural network layer, which performs feature extraction and high-dimensional representation learning on the data received by the input layer, and outputs a high-dimensional feature representation. The so-called performing feature extraction and high-dimensional representation learning means that the neural network layer performs non-linear mapping and pattern recognition on the real-time status data of disinfection equipment, operation sequences, symbolic rules, etc. received by the input layer through a multi-layer neuron structure, extracts the representative key features therein, and converts them into vector representations in a high-dimensional space. This process includes convolution operations, activation function transformations, normalization processing, and inter-layer weight connections, etc. Through multi-layer perception and training optimization, the original input data has stronger separability and expression ability in the high-dimensional space; Symbolic rule encoding module, for the symbolic rules and regulatory standards in the input layer Perform vectorized encoding to obtain rule embeddings. The vectorized encoding specifically means that the symbolic rule encoding module converts the symbolic rules in the input layer and the structured or semi-structured text information in the regulations and standards into numerical vector forms through a preset symbolic embedding method. This process includes operations such as symbolic word segmentation, semantic feature extraction, keyword marking, and rule structure analysis. Combining encoding techniques such as One-Hot encoding, word vectors, and structure embeddings, the symbolic semantics are mapped into vector representations of a fixed dimension, thereby realizing the numerical expression of the semantic relationships and logical structures between rules and forming "rule embeddings" that can be fused and inferred with the output of the neural network. The inference mechanism integration module inputs the high-dimensional feature representation output by the neural network layer and the rule embeddings output by the symbolic rule encoding module into the symbolic inference engine, and performs joint inference through logical rules to output local compliance determination values. The joint inference through logical rules specifically means that the inference mechanism integration module takes the high-dimensional feature representation output by the neural network layer and the rule embedding vector generated by the symbolic rule encoding module as joint inputs and passes them into the symbolic inference engine. According to the preset formal logical rules, semantic matching and constraint verification are performed, so as to judge the compliance of each operation step or state node. This inference process not only depends on the data features learned by the deep model, but also relies on the symbolic rules explicitly expressed in the regulations and standards, realizing the integration of "data-driven" and "knowledge-driven". The inference engine will compare the identified states with the rule conditions, and combine the operation sequence, parameter range, and state transition to evaluate whether each operation meets the compliance requirements item by item, and finally output local compliance determination values. The output layer outputs a vector of local compliance determination values. , represents the local compliance determination value. ; S33. Based on the obtained vector of local compliance determination values , combined with the real-time status data of the disinfection equipment received by the input layer, the high-dimensional feature representation output by the neural network layer, the rule embeddings output by the symbolic rule encoding module, and the inference results of the inference mechanism integration module, compare each local compliance determination value with the relevant regulations and standards and combine the temporal dependence relationship, risk assessment, and real-time environment feedback data of the disinfection operation sequence to calculate the globally weighted compliance score of temporal risk : ; Among them, is the weight of the local determination item, is the risk coefficient of the rd step, is the environmental feedback weighting coefficient, is the environmental feedback correction value, is the real-time feedback data, is the time-sequence dependence weighting coefficient, is the time-sequence dependence determination result of the operation sequence, and H is the total number of local compliance determination items, is the matching indication function of the rules and regulations standards. If does not meet the relevant regulatory standards the corresponding compliance threshold , it is determined as non-compliant, otherwise it is compliant, and a correction mechanism is triggered; Global compliance score The practical significance of the formula is to realize the comprehensive compliance evaluation of each operation step of the disinfection process in different risk environments through the global compliance scoring mechanism with time-sequence risk weighting. This formula not only considers the compliance determination results of each local operation, but also introduces multi-dimensional dynamic factors such as risk coefficients, environmental feedback, and time-sequence dependence, incorporating the real-time state, external environment, and regulatory standards during the disinfection operation process into a unified evaluation system. By assigning weights to each operation node and combining with the actual risks, the system can accurately reflect the importance of certain high-risk or key links in the overall process. At the same time, through the environmental feedback correction value and time-sequence dependence weighting, it can effectively adapt to the working condition changes and process complexity during the disinfection process. The introduction of the matching indication function ensures that only the operations that truly meet the relevant regulatory standards are recognized and included in the total compliance score. Finally, the global compliance scoring result can not only be used as the basis for determining whether the process is compliant, but also provide quantitative support for the subsequent generation of correction suggestions and path optimization. This mechanism significantly improves the scientificity and sensitivity of compliance discrimination, providing a solid decision-making basis for the intelligent supervision, risk warning, and continuous optimization of the medical disinfection process.

[0029] S34. For non-compliant or high-risk paths, based on the local compliance determination values output by the inference mechanism integration module, automatically generate a set of corrective operation suggestions, and adjust the operation parameters in the disinfection path. Each corrective operation suggestion corresponds to a specific corrective action; S35. Feed back the set of corrective operation suggestions, update the operation parameters of the disinfection path, and on the basis of the current disinfection path parameters, increase or decrease and modify the operation parameters of the disinfection path according to the corrective suggestions; S36. For the paths determined to be compliant, continuously call the neural network layer and the inference mechanism integration module to optimize and adjust the disinfection parameters, and output the optimal parameter set through the policy function : ; Among them, is the disinfection cost of path , is the set of candidate disinfection path operation parameters,​ represents the parameters corresponding to the j-th operation step in the disinfection path indicates whether the parameters of the j-th operation step meet the compliance requirements. If they meet the requirements, the value is 1; if not, the value is 0 represents the parameter set P that minimizes the total cost. X represents the number of disinfection operation steps Optimal parameter set The practical significance of the formula is to provide a scientific quantitative decision-making basis for the parameter setting and path optimization of the disinfection process, ensuring the optimal utilization of resources in the disinfection process on the premise of meeting compliance. The formula takes all possible combinations of operation parameters as the candidate set, combines the compliance judgment results of each operation parameter, filters out all compliant parameter configurations, and accumulates the weighted disinfection costs of these compliant paths. Through the goal of "minimizing the total cost", the system can automatically select the optimal parameter combination that not only meets the regulatory standards but also reduces the disinfection time, energy consumption or resource consumption. The compliance indicator function ensures that no non-compliant solutions will appear during the optimization process, improving the standardization and reliability of decision-making. This mechanism not only adapts to the dynamic requirements of different disinfection equipment and environments but also can be flexibly adjusted according to the actual operating costs, thus realizing the organic combination of process optimization and compliance supervision. Overall, the formula effectively improves the economy, science and intelligence level of the disinfection process, promoting the medical institutions to achieve efficient operation and quality improvement on the basis of safety and compliance

[0030] S37. During the path optimization process, use the symbolic rule encoding module and the reasoning mechanism integration module to automatically update the symbolic rule library according to the real-time status data of the disinfection equipment and the environmental feedback, and generate an updated symbolic rule library ; S38. Train the neuro-symbolic reasoning model through the reinforcement learning mechanism to optimize the disinfection path selection and symbolic rule generation, and through the compliance loss function , minimize the compliance loss: ; where is the compliance penalty is the total number of training samples represents the global compliance score corresponding to the -th training sample is the preset compliance threshold is the indicator function. When the compliance score of the -th sample is lower than the compliance threshold , the value is 1, indicating that the sample is non-compliant; otherwise, the value is 0 Compliance loss function The practical significance of the formula lies in introducing a compliance-oriented automatic learning mechanism into the training of the neuro-symbolic reasoning model and the optimization process of the disinfection path, enabling the model to enhance its ability to identify and avoid compliance risks during continuous training iterations. By comparing the global compliance scores of all training samples with a preset threshold, this loss function automatically identifies non-compliant samples and imposes penalties on their degree of violation, thereby guiding the model to continuously reduce the probability of non-compliant paths during the learning process. The introduction of the penalty mechanism prompts the model to pay more attention to those disinfection paths that are prone to risks or violations of regulations, enhancing the model's sensitivity and correction ability to compliance issues under complex working conditions. This mechanism not only enhances the generalization ability and adaptability of the model but also achieves a deep integration of optimized path selection and strengthened compliance management. By minimizing the compliance loss, the system can continuously output disinfection path plans that meet the actual regulatory requirements and safety standards under dynamic environments and changing rules, providing solid data and model support for the intelligent management and risk prevention and control of medical disinfection processes.

[0031] S39. Input the updated symbolic rule base and operation parameters, re-simulate the path to ensure that the disinfection process is always compliant, efficient, and safe, and continuously monitor and optimize the disinfection path through a loop feedback mechanism.

[0032] In this invention, by constructing a symbolic rule base based on regulatory standards and operation parameters and combining it with a neuro-symbolic reasoning model, intelligent compliance determination and dynamic optimization of each operation step in the disinfection process are achieved. Through the real-time status data, operation sequences, and regulatory rules collected by the input layer, the model can perform in-depth feature extraction and encoding on multi-dimensional information and jointly output the compliance determination results of the operation steps through logical reasoning. Under the time-series risk weighting mechanism, the system comprehensively considers time-series dependencies, risk factors, and environmental feedback to achieve global compliance scoring and risk quantification for the entire disinfection process, and can accurately identify non-compliant or high-risk operations. Corrective suggestions are automatically generated and fed back for non-compliant paths, prompting dynamic adjustment of process parameters to achieve real-time closed-loop operation and proactive risk intervention. For compliant paths, the system continuously optimizes the disinfection parameters to further improve resource utilization efficiency through a cost minimization strategy. The reinforcement learning mechanism endows the model with the ability of adaptive evolution, continuously improving the generalization level of path optimization and compliance discrimination. The symbolic rule base can be dynamically updated according to the environment and equipment status to ensure that the decision-making system always highly matches the actual scenario. Overall, this invention significantly improves the intelligent compliance discrimination ability, process optimization efficiency, and risk prevention and control level of the disinfection process, providing precise, efficient, and sustainable technical support for medical disinfection management.

[0033] In this embodiment, the specific content of S4 includes: S41. Collect the real-time status data of the disinfection equipment, the operation path during disinfection, the operation parameters of the dynamically adjusted disinfection process, the global compliance score and the updated symbolic rule library , and organize them into a data set ; S42. Chunk the data set according to the time sequence of the disinfection process and the unique device identifier . Each data chunk contains a timestamp, a device number, an operation path, the operation parameters of the disinfection process, the global compliance score and the updated symbolic rule library ; S43. Perform a hash operation on each data chunk to obtain a block hash value, where the hash input is the content of the current data chunk and the hash value of the previous block, and the hash algorithm used is consistent with the blockchain ledger; S44. Write the data chunk containing the hash value, timestamp, operation path, the operation parameters of the disinfection process, the global compliance score and the updated symbolic rule library into the blockchain ledger in the form of blocks in sequence to form a disinfection data chain ; S45. Authenticate each data chunk using a digital signature. The digital signature corresponds one-to-one with the node identity to ensure non-repudiation of data writing and operation traceability. The signature content includes the block hash value and the node identifier; S46. Automatically detect the comparison relationship between the global compliance score in each data chunk and the relevant regulatory standards based on the smart contract of the blockchain ledger. If the score is lower than the set compliance threshold, it will be automatically marked as a non-compliance event and recorded on the chain; S47. For all compliance and non-compliance events, record the disinfection process data and parameter adjustment information in detail in the blockchain ledger to achieve non-tamperable evidence storage and full-process traceable audit for the entire process; S48. When the blockchain ledger receives a data query, call, or exception alert request, retrieve the disinfection path parameters, device status, operation parameters, global compliance score , the symbolic rule library and compliance events based on the ledger content to support the data transparency and traceability of the full-process monitoring and compliance verification; S49. Regularly perform integrity verification on the blockchain ledger to verify the consistency of the blocks through the hash chain structure.

[0034] The present invention uniformly collects and structures the real-time status data of the disinfection equipment, the operation path of the disinfection process, the dynamically adjusted operation parameters, the global compliance score and the updated symbolic rule library to form a high-quality data set, providing a basic guarantee for the subsequent whole process information storage. Through block storage and hash operation, each data block has a unique identification and tamper-proof characteristics to ensure the integrity and security of the data chain. The blockchain account book adopts sequential writing and digital signature authentication to achieve the non-repudiation and responsibility traceability of key data in the disinfection process. The automatic detection mechanism based on smart contracts can compare the global compliance score with regulatory standards in real time. When non-compliant events are found, they are immediately marked and recorded on the chain, which improves the risk warning and automatic supervision capabilities. The whole process data is recorded in detail regardless of compliance, which greatly enhances the transparency, compliance and traceability of the disinfection operation. The account book supports dynamic query and abnormal alarm response, providing convenient and efficient technical support for regulatory departments, quality control management and accountability analysis. Regular integrity verification further ensures the continuous reliability of the blockchain account book, and overall improves the trusted storage, risk management and intelligent supervision level of medical disinfection data.

[0035] In this implementation manner, S5 specifically includes: S51. Compare the disinfection time, equipment temperature and other key operating parameters with the preset standards in real time, and make judgments based on the compliance rules set by the smart contract. The real-time comparison with the preset standards specifically means that the system continuously collects real-time data on disinfection time, equipment temperature and other key operating parameters during the disinfection operation, and compares them item by item with the compliance standards pre-stored in the smart contract. The comparison includes but is not limited to: whether the current disinfection time meets the minimum duration requirement, whether the current equipment temperature is within the set temperature range, and whether parameters such as humidity or pressure remain within a safe range. The system uses threshold judgment, range verification or logical rule matching to achieve rapid comparison, ensuring that abnormal conditions are identified as soon as the parameters deviate from the standard, providing a basis for subsequent compliance judgments and early warnings; S52. When the smart contract detects that the disinfection time, equipment temperature or other key parameters do not meet the predetermined standards, it will be automatically determined as a non-compliant operation; S53. For each non - compliant operation, the smart contract automatically triggers an early - warning mechanism to generate an alarm message and send it in real - time to the relevant responsible personnel or management terminal. The alarm message specifically refers to a set of structured data automatically generated by the smart contract after detecting a non - compliant operation, including the timestamp of the anomaly occurrence, the corresponding disinfection equipment number, the operator's identity identifier, the specific parameter items of non - compliance and the value range of their deviation from the standard, the non - compliance level assessment result, and the recommended preliminary disposal measures. This information is pushed in real - time through the system interface to the mobile terminals of the responsible personnel, the management background, or the alarm control platform for quickly responding to and handling abnormal events. S54. Automatically record and write the specific information of all non - compliant operations, including the operation time, equipment number, abnormal parameters, and the specific values of deviation from the standard, into the blockchain ledger. S55. Support querying, retrieving, and auditing the alarm information and non - compliant operations recorded in the blockchain ledger, which is convenient for tracing abnormal situations in the disinfection process and promoting rectification. The query, retrieval, and auditing specifically mean that through the interface tool, users can quickly screen and locate the data in the blockchain ledger according to dimensions such as time range, equipment number, and abnormal type, and call historical alarm records and non - compliant operation details. The system supports generating operation logs and event chains to assist management personnel in restoring the abnormal process, checking the source of parameter deviation, and providing a visual audit report to comprehensively support the tracing, responsibility division, and rectification analysis of abnormal situations in the disinfection process.

[0036] Through the smart contract in the present invention, real - time comparison is made between key operation parameters such as disinfection time and equipment temperature and the preset standards, enabling timely detection of any non - compliant operations during the operation of the disinfection process. The smart contract has the ability of automatic discrimination and response. Once parameter anomalies are detected, it is immediately automatically determined as non - compliant and the early - warning mechanism is triggered in real - time, quickly sending the alarm message to the relevant responsible persons or management terminals, significantly improving the timeliness of risk response and operation safety. The detailed information of each non - compliant operation, including the operation time, equipment number, and specific abnormal parameters, is automatically written into the blockchain ledger, realizing non - tamperable evidence storage and transparent traceability throughout the process. The system also supports querying, retrieving, and auditing all alarms and non - compliant events, which is convenient for management personnel to efficiently trace the causes of anomalies, promptly promote process rectification and risk closed - loop. Overall, the present invention greatly improves the automation, intelligence, and compliance level of disinfection process monitoring, providing strong data support and risk prevention and control capabilities for nosocomial infection control and quality management in medical institutions.

[0037] In this embodiment, the specific content of S6 includes: Based on the device status data, operation paths, parameter anomaly records, and compliance scoring results collected during the real-time verification process, a structured and detailed disinfection report is automatically generated. This report includes the operation parameter values at each stage, the compliance analysis results compared with the standards, the judgment basis, the anomaly event log, and the historical data comparison results, etc., ensuring that the content is traceable, quantifiable, and verifiable. At the same time, through the built-in feedback mechanism, the system combines the corrective suggestions given by the neuro-symbolic reasoning module to automatically form a list of rectification suggestions for non-compliant operations, and conveys them to the operators in a timely manner through digital terminals or prompt interfaces, helping them quickly locate the problem areas, guiding parameter adjustment and process correction, and realizing the closed-loop management and continuous optimization of the disinfection process.

[0038] Example 1: To verify the feasibility of the present invention in implementation, the present invention is applied to the digestive endoscopy center of a certain tertiary hospital, where about 24,000 endoscopic examinations and treatments are completed annually. Previously, the center adopted the traditional method of manual inspection + decentralized information system recording. The compliance rate of the disinfection process was affected by factors such as equipment fluctuations, environmental interference, and human omissions. Data tracing was difficult, and abnormal disinfection operations were difficult to detect and manage in a closed loop. In May 2024, the hospital deployed the "Full-cycle Monitoring and Compliance Verification Platform for Digestive Endoscopy Disinfection Process" proposed by the present invention on all 4 endoscopic disinfection devices and supporting drying cabinets and detection areas.

[0039] First, the platform uses automatic collection devices and environmental sensors to obtain key data of the entire process in real time, such as the device operation status, operation parameters (such as temperature, humidity, disinfectant concentration, disinfection duration), environmental humidity, and operator identity. These data are preprocessed to generate a standardized data set, which is used as the input for the intelligent optimization and compliance discrimination of the platform. The core algorithm of the platform uses Monte Carlo tree search to simulate the entire process path of multiple operation stages such as cleaning, main disinfection, drying, and detection, and intelligently selects the optimal path according to the real-time working conditions of each disinfection task. Then, the neuro-symbolic reasoning module will conduct intelligent compliance determination on each operation step according to national standards, hospital disinfection SOPs, and the real-time collected process parameters, and automatically generate rectification suggestions for non-compliant or risky paths to support the dynamic adjustment of disinfection parameters.

[0040] After all key data and compliance scores in the disinfection process are automatically verified by the smart contract, they are written into the blockchain ledger in real-time and in chunks. Each record contains the device number, operator ID, timestamp, and digital signature, ensuring that the entire process is tamper-proof and traceable. Once the system detects insufficient disinfection duration, temperature below the standard, or abnormal operation parameters, it can automatically alarm within 15 seconds and notify the responsible nurses and hospital infection management personnel through multiple terminals such as mobile phones and computers. All abnormal data, rectification processes, and feedback results are synchronously solidified in the blockchain ledger, facilitating subsequent accountability, quality control, and audits by regulatory departments. The platform automatically generates disinfection reports for each batch, providing reliable data for hospital infection management, internal self-inspection, and external supervision.

[0041] From May to July 2024, a certain tertiary hospital compared the disinfection process monitoring data and compliance management effects for three months before and after the implementation of the system of the present invention, and significant improvements were achieved. After the platform was launched, the compliance rate of the disinfection process increased, the abnormal response time was significantly shortened, the manual intervention and false alarm rate decreased significantly, the hospital infection risk was effectively controlled, and no cross-infection events caused by non-compliant disinfection occurred. The following is a comparison of the main data in this center from February to April 2024 (before the system was launched) and from May to July 2024 (after the system was launched).

[0042] Table 1 Comparison of the effects of the intelligent supervision platform for the disinfection process in the digestive endoscopy center before and after application

[0043] It can be clearly seen from Table 1 above that the implementation of the present invention effectively improves the compliance and safety of the disinfection process. First, the average compliance rate of the disinfection process increased from 95.6% before the system was launched to 99.7%, indicating that the platform realizes the full-process intelligent control of disinfection operations, greatly reducing the risks brought by manual omissions and non-standard operations. The average time limit for abnormal disinfection alarms was shortened from 2.2 hours to 18 seconds, and the time for correcting abnormal device parameters decreased from 61 minutes to 8 minutes, reflecting the extremely high automation and real-time performance of the system in abnormal detection, response, and problem handling, and greatly improving the risk warning and handling efficiency. The number of non-compliant disinfection batches decreased significantly, from 43 batches to 5 batches, greatly reducing the hospital infection risk and management pressure.

[0044] In addition, the accuracy rate of data traceability has increased from 91.8% to 100%, indicating that blockchain evidence storage and full-process digital management enable all disinfection data to be accurately and completely traced, completely eliminating data loss and tampering. After the platform was launched, a total of 317 batches of disinfection reports were automatically generated, providing efficient and standardized data support for managers and regulatory authorities. More prominently, the number of nosocomial infection events related to disinfection has decreased from 1 to 0, and potential safety hazards have been basically eliminated. The proportion of manual records and interventions has also dropped from 100% to 14.2%, greatly reducing the burden on medical staff and improving work efficiency. Overall, the application of the platform not only realizes the intelligentization, standardization, and digitalization of the entire disinfection process, but also brings a qualitative leap to the medical safety and management level of the hospital.

[0045] As described above, the above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes, should be covered by the protection scope of the present invention.

Claims

1. A full-cycle monitoring and compliance verification platform for the disinfection process of digestive endoscopes, characterized in that, It includes: A data acquisition and preprocessing module, which is used to collect real-time status data and environmental data and perform preprocessing to generate a standardized data set; A path optimization and decision-making module, which is used to simulate multiple operation paths of the disinfection process using the Monte Carlo tree search algorithm based on the standardized data set and select the optimal disinfection path; A compliance reasoning and verification module, which is used to reason about the symbolic rules in the disinfection process based on the optimal disinfection path and output operation parameters and compliance verification results; A blockchain evidence storage module, which is used to write the real-time status data, operation path, operation parameters and compliance verification results of the disinfection equipment into the blockchain ledger in blocks to form an immutable disinfection data chain; A smart contract processing module, which is used to make real-time judgments on the disinfection data chain, automatically trigger alarms and record non-compliant operations; A feedback and query module, which is used to query, retrieve and audit the whole-process information of the disinfection process, alarm records and compliance events.

2. The full-cycle monitoring and compliance verification method for the disinfection process of digestive endoscopes is applied to the full-cycle monitoring and compliance verification platform for the disinfection process of digestive endoscopes described in claim 1, and is characterized in that, It includes the following steps: S1. Collect the real-time status data and environmental data of the disinfection equipment, and perform preprocessing to generate a standardized data set; S2. Based on the standardized data set, use the Monte Carlo tree search algorithm to simulate multiple operation paths of the disinfection process, and select the optimal disinfection path according to multiple variables in the disinfection process; S3. Based on the optimal disinfection path, use neuro-symbolic reasoning to reason about the symbolic rules in the disinfection process, and conduct compliance verification on the disinfection process in combination with relevant regulations and standards, and dynamically adjust the operation parameters in the disinfection process; S4. Use blockchain technology to record the real-time status data of the disinfection equipment, the operation path in the disinfection process, the operation parameters in the disinfection process and the compliance verification results to generate an immutable disinfection data chain; S5. Through the smart contract, conduct real-time verification on the disinfection data chain, automatically trigger alarms and record non-compliant operations. When the disinfection time, equipment temperature or other parameters do not meet the predetermined standards, the smart contract will automatically issue an alarm and record the relevant information; S6. Based on the real-time verification results, generate a detailed disinfection report, and timely transmit the rectification suggestions for non-compliant operations to the operators through the feedback mechanism.

3. The full-cycle monitoring and compliance verification method for the disinfection process of digestive endoscopes according to claim 2, characterized in that, The real-time status data of the disinfection equipment specifically includes the running status, temperature, humidity, pressure, disinfection time, operator information and working status of the equipment, and the environmental data specifically includes the temperature, humidity, air quality and lighting intensity in the disinfection environment.

4. The full-cycle monitoring and compliance verification method for the disinfection process of digestive endoscopes according to claim 2, characterized in that, The preprocessing specifically includes cleaning, standardizing, filling missing values, detecting outliers and converting data formats for the real-time status data and environmental data of the disinfection equipment.

5. The full-cycle monitoring and compliance verification method for the disinfection process of digestive endoscopes according to claim 2, characterized in that, The S2 specifically includes: S21. Based on the generated standardized data set, divide the disinfection process into multiple independent stages, each stage being defined as a hierarchical state space , including pre-treatment, main disinfection, drying, detection, and storage stages; S22. In each hierarchical state space Based on the operation nodes, state transitions, and operation parameters at each stage of the disinfection process, independently construct a Monte Carlo tree search subtree for each layer to perform path simulation and optimization; S23. During the node expansion process of each hierarchical subtree, according to the pre-set disinfection process compliance standards, including disinfection equipment operation specifications, disinfection time thresholds, temperature and pressure, and safety rules, conduct rule judgments on each expandable action, and only expand the actions that meet all the standards to form a constraint-aware adaptive tree structure. The safety rules include equipment operation safety parameters and operator identity verification; S24. During the expansion process of each node, risk assessment factors for the disinfection process are dynamically generated by monitoring the real-time disinfection status data , and path reward correction is performed; S25. Introduce an adaptive reward mechanism based on real-time environmental feedback, dynamically adjust the path reward function by monitoring data in real time, dynamically adjust the priority of path selection, and adjust the reward function ; S26. During the simulation process, in combination with the real-time status data of the disinfection equipment, environmental data, and the risk assessment of the current disinfection path, the simulation path selection is dynamically guided by an adaptive policy network, which includes: An input layer that receives the real-time status data of the disinfection equipment and environmental data; A hidden layer that extracts features and processes information from the real-time status data of the disinfection equipment and environmental data through a multi-layer perceptron; An output layer that generates the selection probability of each operation path through the Softmax function and determines the priority of the path; The adaptive policy network is trained based on the historical operating status, disinfection time, disinfection effect, and monitoring data of the disinfection equipment, continuously adjusts the exploration and exploitation ratio, and preferentially selects an operation sequence that meets the preset compliance standards, satisfies the risk control requirements, and is higher than the set threshold in terms of efficiency by setting the thresholds of compliance, risk, and efficiency, optimizing the path selection during the disinfection process. The adaptive policy network flexibly responds and adjusts the decision-making strategy according to the changes in the real-time disinfection environment; S27. During the path expansion and simulation process, according to the compliance standards of the disinfection process and the adaptive reward mechanism, paths that do not meet the compliance standards, violate the timing or safety requirements, or whose path rewards do not reach the set threshold are pruned, and the expansion and simulation of the path are terminated in advance; S28. Through parallel computing technology, perform multi-threaded or distributed processing on simulation tasks with different hierarchical state spaces and different operation paths; S29. During each simulation and backtracking process, the return value of each hierarchical path is accumulated, and the optimal decision-making parameters of the current layer are passed to the next-layer state space to achieve the local optimal decision-making of each layer and the global optimal path selection of the entire disinfection process; S210. Repeat steps S21 to S29 until the preset number of simulation times or the computing resource threshold is reached. Finally, combine the optimal paths of all layers and output the optimal disinfection path of the entire disinfection process as the basis for the optimization decision of the disinfection process.

6. The full-cycle monitoring and compliance verification method for the disinfection process of digestive endoscopes according to claim 5, wherein The specific content of S3 is as follows: S31. Based on the generated optimal disinfection path, extract the operation parameters, disinfection time, temperature, and humidity information during the disinfection process, and combine them with relevant regulatory standards , and jointly construct a symbolic rule library , where n is the total number of symbolic rules, is the number of relevant regulatory standards; S32. Construct a neuro-symbolic reasoning model, which specifically includes: The input layer receives the symbolized rule library , which contains relevant regulatory standards , real-time status data of the disinfection equipment, and operation sequences ; A neural network layer that extracts features and performs high-dimensional representation learning on the data received by the input layer, and outputs a high-dimensional feature representation; Symbol rule encoding module, for the symbol rules and regulatory standards in the input layer Perform vectorized encoding to obtain rule embeddings; The inference mechanism integration module inputs the high-dimensional feature representation output by the neural network layer and the rule embedding output by the symbolic rule encoding module into the symbolic inference engine, performs joint inference through logical rules, and outputs the local compliance determination value ; Output layer, outputting a local compliance determination value vector , indicating the local compliance determination value, ; S33. Based on the obtained local compliance determination value vector , combining the real-time status data of the disinfection equipment received by the input layer, the high-dimensional feature representation output by the neural network layer, the rule embedding output by the symbolic rule encoding module, and the inference result of the inference mechanism integration module, compare each local compliance determination value with the relevant regulatory standards , and combining the time-sequence dependence relationship, risk assessment, and real-time environment feedback data of the disinfection operation sequence , calculate the time-sequence risk-weighted global compliance score ; S34. For non-compliant or high-risk paths, based on the local compliance determination value output by the reasoning mechanism integration module, an automatic correction operation suggestion set is generated, and the operation parameters in the disinfection path are adjusted. Each correction operation suggestion corresponds to a specific correction action; S35. Feedback the correction operation suggestion set, update the operation parameters of the disinfection path, and modify the operation parameters of the disinfection path by increasing or decreasing according to the correction suggestions based on the current disinfection path parameters; S36. For the path determined to be compliant, continuously call the neural network layer and the inference mechanism integration module to optimize and adjust the disinfection parameters, and output the optimal parameter set through the policy function Output the optimal parameter set ; S37. During the path optimization process, the symbolic rule encoding module and the inference mechanism integration module are used to automatically update the symbolic rule library according to the real-time status data of the disinfection equipment and the environmental feedback, and generate an updated symbolic rule library ; S38. Train a neuro-symbolic reasoning model through a reinforcement learning mechanism to optimize the selection of disinfection paths and the generation of symbolic rules, and minimize the compliance loss through a compliance loss function , minimizing the compliance loss; S39. Input the updated symbolic rule library and operation parameters, re-simulate the path to ensure that the disinfection process is always compliant, efficient, and safe, and continuously monitor and optimize the disinfection path through a loop feedback mechanism.

7. The full-cycle monitoring and compliance verification method for the disinfection process of digestive endoscopes according to claim 6, wherein, The specific content of S4 is as follows: S41. Collect the real-time status data of the disinfection equipment, the operation path during the disinfection process, the operation parameters of the dynamically adjusted disinfection process, the global compliance score and the updated symbolic rule library , and organize them into a data set ; S42. Chunk the dataset according to the chronological order of the disinfection process and the unique device identifier such that each data chunk contains a timestamp, a device number, an operation path, disinfection process operation parameters, a global compliance score and an updated symbolic rule base ; S43. Perform a hash operation on each data block to obtain a block hash value, where the hash input is the content of the current data block and the previous block hash value, and the used hash algorithm is consistent with the blockchain ledger; S44. Write the data block containing the hash value, timestamp, operation path, disinfection process operation parameters, global compliance score and the updated symbolized rules library into the blockchain ledger in the form of blocks in sequence to form a disinfection data chain ; S45. Authenticate each data block using digital signatures, where the digital signatures correspond one-to-one with node identities to ensure non-repudiation of data writing and traceability of operations. The signature content includes the block hash value and the node identifier; S46. The smart contract based on the blockchain ledger automatically detects the global compliance score in each data block and the comparison relationship with relevant regulatory standards . If the score is lower than the set compliance threshold, it is automatically marked as a non-compliant event and recorded on the chain; S47. For all compliant and non-compliant events, detailedly record the disinfection process data and parameter adjustment information into the blockchain ledger to achieve non-tamperable evidence storage and full-process traceable auditing; S48. When the blockchain ledger receives a data query, call, or exception alert request, retrieve the disinfection path parameters, device status, operation parameters, global compliance score, , symbolic rule library and compliance events to support data transparency and traceability for full-process monitoring and compliance verification; S49. Regularly perform integrity verification on the blockchain ledger, and verify the consistency of blocks through the hash chain structure.

8. The full-cycle monitoring and compliance verification method for the disinfection process of digestive endoscopes according to claim 7, wherein, The specific content of S5 is as follows: S51. Compare the disinfection time, equipment temperature, and other key operation parameters with the preset standards in real time, and make judgments according to the compliance rules set by the smart contract; S52. When the smart contract detects that the disinfection time, equipment temperature, or other key parameters do not meet the predetermined standards, immediately automatically determine it as a non-compliant operation; S53. For each non-compliant operation, the smart contract automatically triggers an early warning mechanism, generates alarm information, and sends it to the relevant responsible personnel or management terminal in real time; S54. Automatically record and write the specific information of all non-compliant operations, including the operation time, equipment number, abnormal parameters, and specific values deviating from the standards, into the blockchain ledger; S55. Support querying, retrieving, and auditing the alarm information and non-compliant operations recorded in the blockchain ledger to facilitate tracing abnormal situations in the disinfection process and promoting rectification.

Images