Medical bedding and clothing management method and system based on RFID

Abstract

The invention discloses a medical bedding and clothing management method and system based on RFID, and the method comprises the steps: obtaining the real-time state data of bedding and clothing, comparing the real-time state data with historical data, and recognizing an abnormal fluctuation condition; performing deep mining on the abnormal fluctuation condition to obtain fluctuation influence distribution; obtaining a key variable from the fluctuation influence distribution, performing quantification processing on the washing effect according to the key variable to obtain a quantification result, and obtaining a washing effect classification result according to the quantification result; according to a washing effect classification result, constructing a correlation model to obtain a mapping relation between washing variable adjustment and effect improvement; according to the mapping relation between variable adjustment and effect improvement, the temperature variable and the time variable are adjusted, and an optimized configuration scheme is obtained; and executing a washing process according to the optimized configuration scheme to obtain an optimized washing effect, and carrying out secondary verification on the optimized washing effect to obtain a final configuration scheme. The safety of bedding and clothing management can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information management, and particularly relates to a medical bedding management method and system based on RFID. BACKGROUND

[0002] In the medical and health field, the cleaning and safety management of medical bedding is crucial, and is directly related to the health of patients and the sterility guarantee of the medical environment. As the core material in the daily operation of the hospital, the cleaning treatment effect of medical bedding not only affects infection control, but also plays a key role in the overall quality of medical services. However, the current management method often relies on manual inspection or sampling detection, and cannot code and search information for each piece of medical bedding, making it difficult to fully grasp the real state of each piece of bedding in the processing process. Especially in the face of large-scale washing demand, real-time tracking and accurate evaluation of the processing effect are lacking, so that potential risks are difficult to be discovered in time. SUMMARY

[0003] In order to solve the above technical problems, the present application provides a medical bedding management method and system based on RFID, which can improve the safety and efficiency of medical bedding management.

[0004] The present application provides a sitting forward bending measurement method based on machine vision, comprising: Obtain real-time state data of the bedding from the structured washing process data set, compare the real-time state data with historical data, and identify abnormal fluctuation conditions in the washing process; According to the identified abnormal fluctuation condition, the abnormal fluctuation condition is deeply mined to obtain the fluctuation influence distribution of the sterilization effect; From the fluctuation influence distribution, obtain the key variables, and according to the key variables, quantitatively process the washing effect of each piece of bedding to obtain the quantization result, and according to the quantization result, obtain the washing effect classification result of each piece of bedding; According to the washing effect classification result, an association model based on regression analysis is constructed, and a mapping relationship between washing variable adjustment and effect improvement is obtained according to the association model; According to the mapping relationship between the variable adjustment and the effect improvement, the temperature variable and the time variable are dynamically adjusted in real time to obtain an optimized configuration scheme; According to the optimized configuration scheme, the washing process is executed to obtain an optimized washing effect, and the optimized washing effect is verified again to obtain a final configuration scheme meeting the medical safety standard.

[0005] In some embodiments, before the real-time state data of the bedding is obtained from the structured washing process data set, a step of constructing a structured washing process data set is further included, which comprises: The temperature variable and the time variable in the washing process are continuously monitored, and washing variable data of each piece of clothing in each washing stage is obtained to obtain a washing variable change record; According to the washing variable change record, the washing data of each piece of clothing is archived to construct a structured washing process data set.

[0006] In some embodiments, according to the identified abnormal fluctuation condition, the abnormal fluctuation condition is deeply mined to obtain a fluctuation influence distribution for the sterilization effect, including: The temperature variable and the time variable corresponding to the abnormal fluctuation condition are compared with a medical safety standard threshold range, and if the temperature variable or the time variable exceeds the medical safety standard threshold range, the abnormal fluctuation data is classified and labeled to obtain an abnormal data set; The fluctuation correlation of the temperature variable and the time variable of the abnormal data set is disassembled item by item to determine a potential factor distribution affecting the sterilization effect; The potential factor distribution is quantitatively processed to obtain an influence weight of each factor on the sterilization effect, and factors with a weight exceeding a preset threshold are classified as key influencing factors to obtain a key factor list; According to the key factor list, the key influencing factors are associated with the abnormal fluctuation data to obtain a fluctuation influence distribution for the sterilization effect.

[0007] In some embodiments, the key variable is obtained from the fluctuation influence distribution, the washing effect of each piece of clothing is quantitatively processed according to the key variable to obtain a quantitative result, and the washing effect classification result of each piece of clothing is obtained according to the quantitative result, including: The key variable is obtained from the fluctuation influence distribution, and the washing effect data of the historical record and the current clothing are compared and analyzed to obtain comparison information corresponding to the key variable to obtain preliminary effect distribution data; According to the preliminary effect distribution data, abnormal information related to the fluctuation influence distribution is extracted, and the deviation of each piece of clothing in the washing effect is determined according to the abnormal information; If the deviation exceeds a preset threshold, the key variable is compared with the washing data in the historical record to obtain washing effect evaluation information of each piece of clothing; According to the effect evaluation information, the washing effect of the clothing is quantitatively processed to obtain a quantitative result; The quantitative result that meets the medical safety standard is determined as an expected effect, and otherwise, the quantitative result that does not meet the medical safety standard is determined as an unanticipated effect to obtain a washing effect classification result of each piece of clothing.

[0008] In some embodiments, the step of constructing a correlation model based on regression analysis according to the washing effect classification results to obtain a mapping relationship between washing variable adjustment and effect improvement includes: Based on the washing variable monitoring records, combined with the washing effect classification results and historical effect determination data, a correlation model based on regression analysis is constructed, and preliminary correlation data related to the washing effect is obtained from the correlation model; obtaining deviation information related to the washing effect according to the preliminary correlation data, and obtaining direction data of variable adjustment according to the deviation information; If the deviation information exceeds the preset threshold range, the variable adjustment direction data is correlated and compared with the historical effect improvement records to obtain the adjustment plan for each group of key variable combinations and obtain the adjusted configuration information; According to the adjusted configuration information, the mapping rules between the variable adjustment direction data and the washing effect are verified and processed to determine the final mapping relationship between the variable adjustment and the effect improvement.

[0009] In some embodiments, the temperature variable and the time variable are dynamically adjusted in real time according to the mapping relationship between the variable adjustment and the effect improvement to obtain an optimized configuration solution, including: According to the mapping relationship between the variable adjustment and the effect improvement, real-time data of the temperature and time variables are obtained, and the real-time data is matched with the historical parameter configuration to obtain preliminary deviation information; If the preliminary deviation information exceeds a preset threshold range, a dynamic control instruction is generated for the temperature variable and the time variable, and the adjustment direction of the washing equipment is calibrated in combination with the washing process monitoring data to determine the adjusted operating parameters; Transmitting the adjusted operating parameters to the washing equipment to obtain updated operating status information; According to the updated operating status information, the effect verification data is integrated with the configuration scheme to obtain an optimized configuration scheme suitable for the current scenario.

[0010] In some embodiments, performing a washing process according to the optimized configuration scheme to obtain an optimized washing effect, and performing a secondary verification on the optimized washing effect to obtain a final configuration scheme that meets medical safety standards, includes: Executing a washing process according to the optimized configuration scheme, obtaining a real-time data stream of an operating status during the washing process, and comparing the real-time data stream with a preset threshold range to obtain preliminary deviation information of the real-time data stream; If the preliminary deviation information exceeds the preset threshold range, the washing variables are dynamically calibrated, and the adjusted operating state parameters are determined in combination with the real-time feedback data during the monitoring process; transmit the adjusted operation state parameter to the washing equipment, and acquire an updated state record of the washing equipment; According to the updated state record, the washing effect data is compared with medical safety standard requirements to obtain a final configuration scheme conforming to the medical safety standard and applicable to the current scene.

[0011] In some embodiments, the present application provides an RFID-based medical linen management system, comprising: An abnormality monitoring module is configured to acquire real-time state data of the linen from a structured washing process data set, compare the real-time state data with historical data, and identify abnormal fluctuation conditions in the washing process; A fluctuation analysis module is configured to perform in-depth mining on the identified abnormal fluctuation conditions to obtain a fluctuation influence distribution for sterilization effect; A classification module is configured to acquire key variables from the fluctuation influence distribution, quantitatively process the washing effect of each piece of linen to obtain a quantitative result according to the key variables, and obtain a washing effect classification result of each piece of linen according to the quantitative result; A mapping module is configured to construct a correlation model based on regression analysis according to the washing effect classification result, and obtain a mapping relationship between washing variable adjustment and effect improvement according to the correlation model; A scheme configuration module is configured to perform real-time dynamic adjustment on temperature variables and time variables according to the mapping relationship between the variable adjustment and the effect improvement, and obtain an optimized configuration scheme; The scheme configuration module is further configured to perform a washing process according to the optimized configuration scheme, obtain an optimized washing effect, and perform secondary verification on the optimized washing effect to obtain a final configuration scheme conforming to the medical safety standard.

[0012] In some embodiments, the present application further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the RFID-based medical linen management method of any one of the above embodiments when executing the computer program.

[0013] In some embodiments, the present application further provides a computer-readable storage medium comprising a stored computer program, wherein the computer-readable storage medium controls the device where the computer-readable storage medium is located to execute the RFID-based medical linen management method of any one of the above embodiments when the computer program is running.

[0014] Compared with the prior art, the application has the following beneficial effects: the application discloses a medical clothing management method and system based on RFID, real-time state data of the clothing is obtained from a structured washing process data set, the real-time state data is compared with historical data to identify abnormal fluctuation conditions in the washing process, the identified abnormal fluctuation conditions are deeply mined to obtain fluctuation influence distribution for sterilization effect, key variables are obtained from the fluctuation influence distribution, washing effect of each piece of clothing is quantitatively processed to obtain a quantitative result according to the key variables, and washing effect classification results of the each piece of clothing are obtained according to the quantitative result, an association model based on regression analysis is constructed according to the washing effect classification results, a mapping relationship between washing variable adjustment and effect improvement is obtained according to the association model, temperature variables and time variables are dynamically adjusted in real time according to the mapping relationship between the variable adjustment and the effect improvement to obtain an optimized configuration scheme, a washing process is performed according to the optimized configuration scheme to obtain an optimized washing effect, and the optimized washing effect is verified again to obtain a final configuration scheme meeting medical safety standards. The above method extracts key factors affecting sterilization effect according to abnormal fluctuation conditions, quantitatively determines washing effect, obtains a mapping relationship between variable adjustment and effect improvement according to an association model, dynamically controls and optimizes washing parameters in an implementation process, and finally verifies and optimizes in cycles to ensure that washing treatment of medical clothing meets medical safety standards, realizes intelligent monitoring and continuous improvement of the washing process, and effectively guarantees medical and health safety. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 is a medical clothing management method flowchart provided by an embodiment of the application based on RFID; Figure 2 is a medical clothing management system structure diagram provided by another embodiment of the application based on RFID. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the application.

[0017] The core challenge of cleaning and safety management of medical textiles lies in how to ensure the overall controllability of the washing process and the reliability of the treatment effect. First, the washing process involves multiple variables such as temperature, time and cleaning agent dosage, and the dynamic changes of these factors directly affect the final sterilization effect, but the existing technology is difficult to record and analyze these variables in real time. Second, due to the lack of continuous tracking of individualized data of each piece of textile, it is difficult to establish an accurate correlation between treatment conditions and washing effect, so it is impossible to scientifically judge whether the textile meets the medical use standard. These two problems are intertwined, the former leads to the lack of data acquisition, and the latter further exacerbates the imperfection of the evaluation system, making the safety guarantee of medical textiles face severe challenges. Therefore, how to realize the dynamic monitoring of key variables during the washing process and establish a correlation model between treatment effect and sterilization effect based on individualized data has become a key problem to improve the management level of medical textiles.

[0018] To solve the above problems, with reference to Figure 1 The embodiments of the present application provide a medical textile management method based on RFID, comprising the following steps: Step 101, obtaining real-time state data of the textile from the structured washing process data set, comparing the real-time state data with historical data, and identifying abnormal fluctuation conditions in the washing process.

[0019] According to the pre-established data acquisition rules, the real-time data of temperature variables and time variables are extracted from the structured washing process data set, the real-time data are classified and processed to obtain a preliminary information record set. The temperature variables and time variables in the preliminary information record set are compared with the historical data to obtain a comparison result. If the comparison result shows that there is an abnormal condition, the related context data are extracted from the structured washing process data set, the state update content is adjusted to obtain an adjusted state information set. The real-time state data, abnormal fluctuation records and adjusted state information set are hierarchically archived by using a data storage tool, so that the changes of each group of data can be continuously tracked.

[0020] In one possible implementation, in the process of medical clothing washing monitoring, real-time data collection and processing for temperature variables and time variables are particularly crucial. For example, during the washing process of a piece of clothing, the temperature of the main washing stage is collected as 65°C and the time node is 10:20 am through preset rules. The obtained temperature variable and time variable are compared with historical data. Assuming that the standard temperature range of the main washing stage in the historical data is 60 to 63°C, and the real-time collected 65°C is obviously too high, this data will be marked as abnormal. Further, after the abnormal condition is found, the context data is extracted from the process record for analysis. Assuming that the temperature of the piece of clothing in the pre-washing stage is 42°C, which meets the standard, but is too high in the main washing stage, the possible reasons are inferred in combination with the data of the previous and subsequent stages, such as abnormal heating of the equipment, and relevant records are generated. This context analysis helps to fully understand the background of the abnormal occurrence, and provides a basis for correction. According to the historical data and real-time records, the state update content is adjusted, and assuming that the inference that the temperature of the main washing stage is too high may affect the cleaning effect of the clothing, the state is updated to be checked, and it is suggested to reduce the temperature to 62°C. This adjustment process can timely respond to variable fluctuations and ensure washing quality. Finally, the real-time data, abnormal fluctuation records and adjusted state information are hierarchically archived. Assuming that the clothing with RFID B005 has temperature abnormality records in the main washing stage, it is archived as abnormal data layer, and normal data is archived in the standard layer. This hierarchical mode facilitates subsequent tracking and querying, and improves the efficiency of data management. In addition, when continuously tracking the data change, assuming that the temperature of a piece of clothing fluctuates from 35°C to 38°C in the rinsing stage, the time node and specific value of each fluctuation are recorded to ensure data integrity. This tracking mechanism can provide detailed basis for subsequent analysis and ensure the traceability of the process.

[0021] In step 102, according to the identified abnormal fluctuation condition, the abnormal fluctuation condition is deeply mined to obtain a fluctuation influence distribution for the sterilization effect.

[0022] In some embodiments, the temperature variable and time variable corresponding to the abnormal fluctuation condition are compared with the medical safety standard threshold range. If the temperature variable or time variable exceeds the medical safety standard threshold range, the abnormal data set is obtained by classifying and labeling the abnormal fluctuation data. The fluctuation correlation of the temperature variable and time variable of the abnormal data set is disassembled item by item to determine the potential factor distribution affecting the sterilization effect. The potential factor distribution is quantitatively processed to obtain the influence weight of each factor on the sterilization effect. The factors with weights exceeding a preset threshold are classified as key influencing factors to obtain a key factor list. According to the key factor list, the key influencing factors are associated with the abnormal fluctuation data to obtain a fluctuation influence distribution for the sterilization effect.

[0023] In this embodiment, the correlation between the temperature variable and the time variable of the abnormal data set is disassembled item by item. The time domain analysis method can be used to analyze the temperature fluctuation, the time deviation is compared by the stage duration ratio, and the cross influence of time and temperature is analyzed by the temperature-time correlation analysis (Pearson coefficient). The analytic hierarchy process (AHP) or entropy weight method can be used to quantitatively process the potential factor distribution, and the weight of each factor on the sterilization effect (taking the log10 of the biological indicator killing rate as the index) is calculated according to the historical data. The fluctuation influence distribution can be displayed in the form of a graph. Through the intuitive graph display, the user can quickly determine the intervention key point to ensure that the washing process meets the medical standard, which effectively improves the problem identification efficiency.

[0024] In a possible implementation, for example, the temperature data of a certain piece of clothing in the main washing stage is 66°C, the time duration is 25 minutes, and the medical standard threshold range is temperature 60-63°C and time 20-22 minutes. Therefore, the temperature and time both exceed the threshold range, and these abnormal data are marked as a high-risk category to form an abnormal data set. Feature extraction is performed on the abnormal data set. Assuming that the extraction result shows that there is a correlation between the temperature being too high and the time being extended, the fluctuation relationship between the two is disassembled item by item, and it is preliminarily judged that the temperature rise may lead to unstable sterilization effect. By analyzing the historical data, it is assumed that for every 1°C rise in temperature, the sterilization effect may decrease by 2%, and the time extension may exacerbate this effect. Such disassembly helps to determine the potential factor distribution, laying a foundation for subsequent quantitative processing. For example, in the quantitative processing link, the weight of the potential factor distribution is evaluated. Assuming that the weight of the temperature being too high is 0.6 and the weight of the time being extended is 0.3, and the preset weight threshold is 0.5, the temperature being too high is classified as a key influencing factor and is included in the key factor list. Based on the key factor list, the temperature being too high is associated with the parameter fluctuation data to form a fluctuation influence distribution. Assuming that the fluctuation influence distribution shows that the temperature being too high mainly occurs in the main washing stage, and the influence on the sterilization effect accounts for 60%, the temperature control problem needs to be prioritized.

[0025] Further, auxiliary monitoring means can be introduced to intervene in the key factors. Assuming that in the case of temperature being too high, the humidity sensor can be linked to analyze whether the temperature is out of control due to insufficient humidity. If the humidity data is 40%, which is lower than the standard threshold of 50%, it can be inferred that this is one of the potential reasons. This multi-dimensional analysis can support problem judgment from different aspects and improve the comprehensiveness of the solution.

[0026] Step 103, obtaining a key variable from the fluctuation influence distribution, quantitatively processing the washing effect of each piece of clothing according to the key variable to obtain a quantitative result, and obtaining a washing effect classification result of each piece of clothing according to the quantitative result.

[0027] In some embodiments, a key variable is obtained from the fluctuation influence distribution, historical records are compared and analyzed with current washing effect data of the clothes, comparison information corresponding to the key variable is obtained, and preliminary effect distribution data is obtained. According to the preliminary effect distribution data, abnormal information related to the fluctuation influence distribution is extracted, and the deviation of each piece of clothes in washing effect is determined according to the abnormal information. If the deviation exceeds a preset threshold, the key variable is compared with washing data in the historical records, and washing effect evaluation information of each piece of clothes is obtained. According to the effect evaluation information, the washing effect of the clothes is quantitatively processed, and a quantitative result is obtained. The quantitative result that meets the medical safety standard is determined as meeting the expected effect, otherwise, the quantitative result that does not meet the medical safety standard is determined as not meeting the expected effect, and a washing effect classification result of each piece of clothes is obtained.

[0028] In the present embodiment, the comparison information corresponding to the key variable refers to difference information obtained by comparing real-time washing data with standard reference values or historical qualified data. The abnormal information related to the fluctuation influence distribution refers to special data points deviating from the medical safety standard found by analyzing the monitoring data of the key variables (temperature, time, etc.) in the washing process.

[0029] In a possible implementation, the comparison of the historical records and the current washing data can be used to extract abnormal values. Assuming that the historical records show that the average temperature of a batch of clothes in the main washing stage is 62°C, and the current batch data is 65°C, which is obviously too high. By superimposing and comparing the two sets of data, the distribution difference of the temperature variable can be obtained preliminarily, laying a foundation for subsequent analysis. Further, the preliminary effect distribution data can be screened by extracting abnormal values. Assuming that the time of a piece of clothes in the main washing stage in the current batch is 28 minutes, and the average value of the historical records is 21 minutes, which exceeds the preset threshold range by 7 minutes. By comparison, it can be judged that the deviation of the clothes in the time variable is large, which may affect the sterilization effect. Such screening can accurately lock the problem data and avoid invalid analysis of normal data. If the temperature and time of a piece of clothes both exceed the standard, it is compared and analyzed with the historical data, and it is found that the proportion of similar deviations that have led to substandard sterilization in the past is as high as 70%. Such correlation comparison can generate specific effect evaluation information for each piece of clothes, helping to determine whether it meets the medical safety standard.

[0030] In a possible implementation, for the quantitative processing of the effect evaluation information, the quantitative calculation tool can convert the washing effect into a numerical index. Assuming that the temperature deviation and the time deviation of a piece of clothing correspond to impact values of 0.4 and 0.3 respectively, and the comprehensive evaluation value is 0.7, and the preset standard value is 0.5 or less, it is determined that the expected effect is not met. Finally, the washing effect classification result is obtained by combining the medical safety standard, and assuming that 10% of the data in a batch of clothing is classified as not meeting the expected effect, which is mainly concentrated on the problem of high temperature. Through the classification result, the relevant staff can clearly determine the link that needs to be adjusted and pay priority attention to temperature control. Auxiliary data of the equipment running state can also be introduced. Assuming that in the case of high temperature, the water pressure data of the equipment is found to be low, only 80% of the standard value, which may cause insufficient heat dissipation and thus push up the temperature. This multi-dimensional comparison can verify the root cause of the problem from different angles and improve the comprehensiveness of the judgment.

[0031] Further, after the abnormal value is extracted, a secondary detection link can be added for high-risk clothing. Assuming that a piece of clothing is marked as not meeting the expected effect, the washing effect test can be increased to ensure that it meets the standard. This further guarantees medical safety and provides more data support for subsequent optimization.

[0032] In step 104, an association model based on regression analysis is constructed according to the washing effect classification result, and a mapping relationship between washing variable adjustment and effect improvement is obtained according to the association model.

[0033] In some embodiments, according to the washing variable monitoring record, the washing effect classification result and the historical effect determination data are combined to construct an association model based on regression analysis, and preliminary association data related to the washing effect are obtained from the association model. These washing variables include but are not limited to temperature, washing time, disinfectant concentration, water flow intensity, pH value, etc. Key variable combinations are identified through mutual information method (MI) and random forest feature importance sorting. The association model can be a weighted superposition based on these key variable combinations, and the weight coefficients of each key variable can be dynamically adjusted according to the washing variable monitoring frequency. According to the preliminary association data, deviation information related to the washing effect is obtained, and direction data of variable adjustment is obtained according to the deviation information. If the deviation information exceeds a preset threshold range, the direction data of variable adjustment is associated and compared with the historical effect improvement record to obtain an adjustment scheme for each group of key variable combinations, and the adjusted configuration information is obtained. According to the adjusted configuration information, the mapping rule of the direction data of variable adjustment and the washing effect is verified and processed to determine the final mapping relationship between variable adjustment and effect improvement.

[0034] In this embodiment, the deviation information can be achieved through residual standardization, and the direction data of variable adjustment can be obtained by implementing the response surface method (RSM). The mapping rule between the direction data of variable adjustment and the washing effect can be verified by time series cross-validation or spatial verification method.

[0035] In one possible implementation, the differences between the variable parameters in the current washing process and the historical records are combed. Assuming that the historical records show that the average water temperature in the main washing stage is 60°C, and the current batch record is 63°C, this difference can be quickly identified, and it can be preliminarily judged that the temperature may be a key variable affecting the washing effect. This way helps to extract key information from massive data and lays a foundation for subsequent analysis. Further, according to the preliminary associated data, the deviation information related to the washing effect is extracted, assuming that the washing time of a piece of clothing in the current batch is 25 minutes, and the historical average value is 20 minutes, which exceeds the preset threshold by 5 minutes. Through parameter comparison processing, it can be determined that the time deviation may have an adverse effect on the washing effect, and then it is determined that the direction of variable adjustment should be to shorten the washing time. This screening method can accurately locate the problem and avoid resource waste. In the case where the deviation information exceeds the preset threshold, the analysis can be further deepened by comparing with the historical effect improvement records. Assuming that the temperature and time of a batch of clothes deviate, it is found that reducing the water temperature by 2°C and reducing the washing time by 3 minutes can effectively improve the sterilization pass rate in the past similar situation. According to the adjusted configuration information, the mapping rule between it and the sterilization effect is analyzed. Assuming that the adjusted water temperature is set to 61°C and the washing time is 22 minutes, it is found that the washing effect of the clothes after adjustment is closer to the standard value. This verification method can ensure the rationality of the adjustment scheme and provide a reliable basis for subsequent optimization. In addition, from the perspective of multi-dimensional support, auxiliary data of equipment running state can be introduced for verification. Assuming that in the case of large temperature deviation, the water flow speed of the equipment is found to be only 85% of the standard value, which may cause unstable temperature control. By combining the analysis of equipment data and washing variables, the root cause of the problem can be confirmed from different aspects, and the comprehensiveness of the adjustment scheme is improved. This multi-angle verification method helps to reduce misjudgment. Additional detection steps can also be added for high-risk clothes after adjustment. Assuming that a piece of clothing still has potential risks after adjustment, a second sterilization effect test can be arranged to ensure that it meets the medical safety standards. This way not only improves safety, but also accumulates more data support for subsequent variable optimization.

[0036] Step 105, according to the mapping relationship between the variable adjustment and the effect improvement, the temperature variable and the time variable are dynamically adjusted in real time, and the optimized configuration scheme is obtained.

[0037] According to the mapping relationship between the variable adjustment and the effect improvement, real-time data of variable temperature and time variable are obtained from the running state, the real-time data is matched with historical parameter configuration to obtain preliminary deviation information. If the preliminary deviation information exceeds a preset threshold range, a dynamic control instruction is generated for the temperature variable and the time variable, the adjustment direction of the washing equipment is calibrated in combination with the washing process monitoring data, and the adjusted running parameter is determined. The adjusted running parameter is transmitted to the washing equipment to obtain updated running state information. According to the updated running state information, effect verification data and configuration scheme are fused to obtain an optimized configuration scheme suitable for the current scene. The effect verification data refers to quantitative data obtained by actual detection, which can prove whether the washing effect after parameter adjustment meets the standard, including but not limited to sterilization rate, residual pollutant detection data, actual execution record of the adjusted running parameter, etc.

[0038] In one possible implementation, core variable data such as washing temperature and washing time can be extracted from the running state of the washing equipment. Assuming that the temperature of the main washing stage of the current batch of served clothes is 62°C, and the ideal range of the historical parameter configuration is 58 to 60°C, it can be quickly judged that the temperature exceeds the threshold range, and preliminary deviation information is generated. This way can find potential problems in time and provide basis for subsequent adjustment. Further, dynamic control instructions can be generated according to the deviation of the washing temperature and time. Assuming that the washing time record is 28 minutes, and the historical standard value is 20 to 25 minutes, after combining the process monitoring data analysis, it is recommended to shorten the time to 23 minutes, and at the same time, the temperature is lowered to 59°C. This calibration method can ensure that the adjustment direction fits the actual needs and avoid resource waste caused by excessive adjustment. After transmitting the adjusted running parameters to the washing equipment, the updated running state information is obtained. Assuming that the temperature is stabilized at 59°C and the time is controlled at 23 minutes after adjustment, the feedback information shows that the equipment running state has approached the expected standard. This real-time feedback mechanism helps to confirm whether the adjustment is effective, and at the same time, accumulates data support for subsequent optimization. Further, the effect data after adjustment can be compared with the historical configuration scheme. Assuming that the sterilization index of a batch of served clothes is significantly improved after adjustment, through analysis, it is found that the combination of temperature 59°C and time 23 minutes is more suitable for the current scene, and then an improved parameter configuration content is generated. This way can continuously optimize the washing process and ensure that the parameter configuration adapts to the needs of different batches. In addition, assuming that the water flow speed of the equipment is found to be low after temperature adjustment, which is only 90% of the standard value, which may affect the uniformity of temperature distribution, through comprehensive analysis, the root cause of the problem can be confirmed and the equipment maintenance strategy can be optimized. This multi-dimensional verification method can reduce deviation misjudgment and improve overall reliability. It should be noted that in high-risk scenarios, additional monitoring links can be added for the served clothes after adjustment. Assuming that a piece of served clothes belongs to a special material and may be more sensitive to temperature changes, additional running state checks can be arranged to ensure that its washing effect meets the medical safety standards. This supplementary measure not only improves safety, but also provides more reference data for subsequent parameter optimization.

[0039] In step 106, a washing process is performed according to the optimized configuration scheme, an optimized washing effect is obtained, and the optimized washing effect is verified again to obtain a final configuration scheme that meets the medical safety standards.

[0040] In some embodiments, the washing process is performed according to the optimized configuration scheme, real-time data flow of the running state in the washing process is obtained according to a pre-established monitoring rule of a washing variable, the real-time data flow is compared with a preset threshold range to obtain preliminary deviation information of the real-time data flow. If the preliminary deviation information exceeds the preset threshold range, the washing variable is dynamically calibrated, and adjusted running state parameters are determined in combination with real-time feedback data in the monitoring process. The adjusted running state parameters are transmitted to the washing equipment, and updated state records of the washing equipment are obtained. According to the updated state records, the washing effect data are compared with medical safety standard requirements to obtain a final configuration scheme that meets the medical safety standards and is suitable for the current scene.

[0041] In one possible implementation, real-time data streams are extracted from the operating state of the washing equipment according to pre-established washing variable monitoring rules, such as temperature, rotation speed and other key variables during the washing process. By comparing with the pre-set threshold range, it can be quickly judged whether there is deviation. Assuming that the rule sets that the water temperature should be maintained between 55 and 60°C, if the real-time data stream shows that the current water temperature is 63°C, which obviously exceeds the pre-set threshold range, a preliminary deviation information will be generated, prompting the need for adjustment. Further dynamic calibration is carried out according to the real-time data stream. Combined with the feedback data in the monitoring cycle, it is analyzed that the water temperature is too high, which may be related to the continuous operation of the heating device, and then it is suggested to reduce the heating power and adjust the water temperature to 58°C. This calibration method can quickly respond to deviations and ensure that the washing process meets the requirements, while avoiding energy waste caused by excessive adjustment. The adjusted 58°C water temperature parameter is transmitted to the washing equipment. After the equipment receives the instruction, the operating state will be updated. The updated state record is obtained through the data feedback tool, and it is assumed that the water temperature is stable at 58°C, and other indicators such as washing time are also within the normal range, indicating that the initial adjustment meets the medical safety standards. This real-time feedback mechanism can timely confirm the effectiveness of the adjustment and provide data support for subsequent optimization. Finally, the washing effect data is matched with the medical safety standards, and it is assumed that the standard requires that the washing process must ensure a certain disinfection effect, and the adjusted state record shows that the relevant indicators have met the standard, then a verification report will be generated to confirm that the current parameters are suitable for the washing scene of the batch of clothes. This verification method helps to ensure that the washing effect meets the strict medical requirements. If the verification report shows that the adjusted parameter combination has been stable in multiple batches, such as water temperature of 58°C combined with a specific washing time that can continuously meet the disinfection demand, then this combination will be solidified as the final configuration scheme suitable for the current scene. This method can provide reliable reference for subsequent washing tasks and reduce the cost of repeated adjustment. In addition, if some auxiliary indicators are found to be abnormal during the monitoring process, such as low water pressure that may affect the uniformity of washing, further analysis of the root cause of the problem can be carried out combined with the real-time data stream, and optimization of equipment maintenance strategy is suggested. This multi-dimensional analysis method can improve the comprehensiveness of the scheme and ensure the stability of the washing process. For additional protection of medical safety standards, if special materials are involved, additional inspection steps can be recommended in the verification report, such as checking whether the residual materials after washing meet the standards. This supplementary measure can further improve safety and ensure that the washing effect meets the expectations.

[0042] The RFID-based medical clothing management method of the above embodiment obtains real-time state data of the clothing from a structured washing process data set, compares the real-time state data with historical data, identifies abnormal fluctuation conditions in the washing process, according to the identified abnormal fluctuation conditions, deeply mines the abnormal fluctuation conditions to obtain a fluctuation influence distribution for the sterilization effect, obtains key variables from the fluctuation influence distribution, quantitatively processes the washing effect of each piece of clothing according to the key variables to obtain a quantitative result, and obtains a washing effect classification result of each piece of clothing according to the quantitative result, constructs a correlation model based on regression analysis according to the washing effect classification result, obtains a mapping relationship between washing variable adjustment and effect improvement, adjusts the temperature variable and the time variable in real time according to the mapping relationship between the variable adjustment and the effect improvement, obtains an optimized configuration scheme, executes the washing process according to the optimized configuration scheme, obtains an optimized washing effect, and performs secondary verification on the optimized washing effect to obtain a final configuration scheme that meets the medical safety standard. The above method extracts key factors affecting the sterilization effect according to the abnormal fluctuation conditions, quantitatively determines the washing effect, obtains the mapping relationship between variable adjustment and effect improvement according to the correlation model, dynamically controls and optimizes the washing parameters, and finally verifies and optimizes the washing process in a loop to ensure that the washing treatment of the medical clothing meets the medical safety standard, realizes intelligent monitoring and continuous improvement of the washing process, and effectively guarantees the medical and health safety.

[0043] In some embodiments, before step 101, a step of constructing a structured washing process data set is further included, which comprises: Step 201, continuously monitoring the temperature variable and the time variable in the washing process, obtaining washing variable data of each piece of clothing in each washing stage, and obtaining washing variable change records.

[0044] The basic information of each piece of medical clothing to be washed is obtained by a washing device or a scanning device, including clothing type, brand, color, material and other data, the unique identification information of the clothing is obtained by using a sensor device to read the bar code or two-dimensional code on the clothing label. In addition, the personal information of the user can also be obtained from the user database, including the user's name, contact information, account information, etc. The information of each piece of medical clothing to be washed is mapped to a digital identity, i.e. each piece of medical clothing to be washed is matched with the user's identity information, a set of unique RFID identification codes (Radio Frequency Identification Identification Code) are generated, which are generated by an RFID tag generator according to the clothing characteristics and user information. Each RFID identification code is bound to each piece of medical clothing to be washed, which facilitates the tracking and management of each piece of medical clothing.

[0045] The washing process of each medical clothing is continuously monitored by deploying sensor devices, and the temperature and time variables of each clothing at each washing stage of pre-washing, main washing, rinsing and drying are obtained to form an initial washing variable dataset, and the washing variable dataset is stored in a pre-established database to obtain a stage monitoring record. According to the initial washing variable dataset, the variable changes of each clothing at different washing stages are classified and arranged, and the temperature and time variables are compared stage by stage. If the temperature variable exceeds the preset threshold range, it is marked as an abnormal variable. The time variable and washing stage information corresponding to the abnormal variable are obtained, and if the duration of the abnormal variable exceeds the preset threshold, an adjustment instruction for the abnormal variable is generated to obtain an adjustment scheme record. According to the adjustment instruction, the washing variables of each clothing are dynamically updated, and the adjusted temperature and time variables are entered into the database to form a complete variable change record.

[0046] In a possible implementation, in the process of medical clothing washing monitoring, each piece of clothing is continuously monitored at each washing stage of pre-washing, main washing, rinsing and drying by a sensor device, and temperature and time variables are obtained to form an initial dataset. Assuming that the temperature of a piece of clothing should be maintained at 60-65 degrees Celsius during main washing, but the sensor device shows that the temperature reaches 70 degrees Celsius, and the duration is 10 minutes, which exceeds the preset threshold range of 5 degrees Celsius, it is marked as an abnormal variable. Such a monitoring method can accurately locate the problem stage and ensure that the washing process meets the hygiene standards. Further, for the abnormal variable, the corresponding time variable and washing stage information can be extracted from the database. Assuming that the abnormal variable occurs during main washing and lasts for 10 minutes, which exceeds the preset threshold of 5 minutes, the persistence is analyzed by a logical judgment tool to generate an adjustment instruction, such as reducing the heating power or shortening the heating time. This method helps to correct deviations in a timely manner and ensures washing effect and clothing safety. When dynamically updating the washing variables, the adjusted temperature variable such as 62 degrees Celsius and the time variable such as 8 minutes are entered into the database to form a complete record. When judging the completeness of the record, if some stage data is missing, the system will prompt to supplement to ensure that the data is traceable. This updating mechanism can improve the reliability of the data and provide a basis for subsequent analysis.

[0047] In a possible implementation, when classifying and arranging variable changes, temperature data and time data can be divided by stage and compared one by one. For example, the temperature threshold for the rinsing stage is 30-35 degrees Celsius, and if a piece of clothing records 38 degrees Celsius, it is marked as an abnormal variable. This detailed classification helps to quickly locate the root cause of the problem and reduce the cost of manual investigation. In addition, when generating an adjustment scheme, if the temperature during main washing is consistently high, it can be recommended to increase the water volume or adjust the detergent ratio. This not only solves the current problem, but also optimizes the subsequent washing process, reduces equipment wear and energy consumption.

[0048] In a possible implementation, when the database stores the phase monitoring records, the records can be stored according to the RFID of the clothing and the washing batch. For example, the clothing numbered A001 has a temperature of 63°C and a time of 15 minutes in the main washing phase of a batch, and such a record facilitates historical data query and trend analysis, improves data management efficiency, and provides support for quality control. When the logical judgment tool is used to analyze the persistence of variables, if the temperature in the drying phase continuously exceeds 80°C for 20 minutes, which exceeds the threshold value by 10 minutes, an emergency stop command will be generated to avoid damage to the clothing. This analysis method can effectively prevent potential risks and ensure washing safety and equipment life.

[0049] In step 202, according to the washing variable change records, the washing data of each piece of clothing is archived to construct a structured washing process data set.

[0050] According to the pre-established database storage structure, the washing variable data (such as temperature variables and time variables) and individual data (RFID) of each piece of clothing are classified and arranged, time nodes (such as the start and end times of pre-washing) and their corresponding state information (such as high-temperature abnormalities) are obtained from the washing process, the washing variable data is associated and matched with the time nodes, and a structured process record set of each piece of clothing is generated. The individual data of each piece of clothing is stored in layers with the structured process record set to obtain a structured washing process data set of each piece of clothing. In this embodiment, in the structured washing process data set of each piece of clothing, the individual data RFID of the clothing corresponds to the washing variable data, the time nodes of the washing process, and their corresponding state information one by one, forming a complete archiving result. If there is missing state information or abnormal washing variable in the archiving result, the individual data of the clothing is extracted, the missing part is updated, the supplemented information integration record is obtained, and a complete data record is obtained, which records the detailed state information of each time node in the washing process of each piece of clothing.

[0051] In a possible implementation, in the process of medical linen washing monitoring, it is particularly important to sort and organize the washing variable data and individual data RFID for each piece of linen. The temperature data and time data of each piece of linen need to be recorded in the pre-washing, main washing, rinsing and drying stages during the washing process. By associating and matching these data with specific time nodes through a data organization tool, a clear structured record set can be formed. For example, the temperature record of a piece of linen in the main washing stage is 62℃, and the time node is 10:15 am. Such matching can intuitively reflect the change of the washing state. Further, when the structured process record set is entered into the database for archiving, the individual data RFID and the structured process record set can be stored in layers according to the linen number. Assuming that the linen numbered B002 in a certain washing, the state information in the pre-washing stage shows normal, while the temperature in the main washing stage is too high. By matching the state information with the washing variables, a complete archiving result can be quickly generated. This layered storage facilitates subsequent query and traceability. If the archiving result shows that the state information is missing or the washing variable is abnormal, the individual data can be extracted from the database for supplementary update. Assuming that a piece of linen lacks temperature record in the rinsing stage, the historical data will be extracted, and the possible value is 32℃, which is updated to the storage record. When stored in the database, the data can be classified according to the washing batch and the individual data RFID of the linen to ensure the efficiency of data archiving. For example, the linen numbered C003 in a batch has complete data in all stages, which will be preferentially archived as a standard record, while the linen with incomplete data will be marked as to be supplemented. This classification method can improve the orderliness of data management and facilitate subsequent quality inspection.

[0052] Further, when continuously comparing the state information of the linen at each time node, the washing variable can be dynamically adjusted. Assuming that the temperature of a piece of linen in the drying stage continuously exceeds 82℃, it will be adjusted to 78℃ according to the historical record and the current state, forming the final individualized washing data archiving result. This dynamic adjustment mechanism can timely respond to variable fluctuations. In addition, when analyzing the changes of washing variables in different stages, the rationality of the data can be verified from multiple aspects. Assuming that the time node of a piece of linen in the main washing stage shows 10:10 am, the temperature is 61℃, and the state information is normal, it is confirmed to be normal by comparison with the preset standard; if the temperature in the rinsing stage is 36℃, which is slightly higher than the standard range, it is recorded as an observation state. This multi-angle comparison helps to fully grasp the details of the washing process.

[0053] Reference Figure 2 The application also provides a medical linen management system based on RFID, comprising: The anomaly monitoring module 301 is configured to acquire real-time state data of the laundry from a structured washing process data set, compare the real-time state data with historical data, and identify an abnormal fluctuation condition in the washing process. The fluctuation analysis module 302 is configured to perform in-depth mining on the abnormal fluctuation condition according to the identified abnormal fluctuation condition, and obtain a fluctuation influence distribution for a sterilization effect. The classification module 303 is configured to acquire a key variable from the fluctuation influence distribution, perform quantitative processing on a washing effect of each piece of laundry according to the key variable to obtain a quantitative result, and obtain a washing effect classification result of the each piece of laundry according to the quantitative result. The mapping module 304 is configured to construct a correlation model based on regression analysis according to the washing effect classification result, and obtain a mapping relationship between washing variable adjustment and effect improvement according to the correlation model. The scheme configuration module 305 is configured to perform real-time dynamic adjustment on a temperature variable and a time variable according to the mapping relationship between the variable adjustment and the effect improvement, and obtain an optimized configuration scheme. The scheme configuration module 305 is further configured to perform a washing process according to the optimized configuration scheme, obtain an optimized washing effect, perform secondary verification on the optimized washing effect, and obtain a final configuration scheme that meets a medical safety standard.

[0054] It should be noted that the RFID-based medical laundry management system provided in the embodiments of the present application is used to perform all process steps of the RFID-based medical laundry management method provided in the above embodiments, and the working principles and beneficial effects of the two are one-to-one corresponding, and thus will not be repeated.

[0055] The embodiments of the present application further provide an electronic device. The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, for example, a data acquisition program. The processor implements the steps in the above RFID-based medical laundry management method embodiments when executing the computer program, for example Figure 1 The processor implements the functions of the modules / units in the above system embodiments when executing the computer program, for example, a data acquisition module.

[0056] For example, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the electronic device.

[0057] The electronic device can be a computing device such as a desktop computer, a notebook computer, a palm computer, a smart tablet, etc. The electronic device can include, but is not limited to, a processor, a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device, and the electronic device can include more or fewer components than the above, or combine certain components, or different components, for example, the electronic device can also include an input / output device, a network access device, a bus, etc.

[0058] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The processor is the control center of the electronic device, and connects various parts of the electronic device through various interfaces and lines.

[0059] The memory can be used to store the computer program and / or modules, and the processor realizes various functions of the electronic device by running or executing the computer program and / or modules stored in the memory, and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function (such as a sound playing function, an image playing function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory device.

[0060] The modules / units integrated in the electronic device, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can implement the steps of each method embodiment when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can include any entity or device, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. that can carry the computer program code. It should be noted that the contents included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0061] It should be noted that the above-described device embodiments are only schematic, and the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. In addition, the connection relationship between the modules in the device embodiment provided by the present application indicates that there is a communication connection between them, which can be realized as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor.

[0062] The above-described specific embodiments further illustrate the purpose, technical solutions, and beneficial effects of the present application. It should be understood that the above-described specific embodiments are only for the specific embodiments of the present application and do not limit the protection scope of the present application. It is particularly pointed out that any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A medical clothing management method based on RFID, characterized in that: include: Acquire real-time status data of linens from a structured washing process dataset, compare the real-time status data with historical data, and identify abnormal fluctuations in the washing process; Based on the identified abnormal fluctuation conditions, the abnormal fluctuation conditions are deeply mined to obtain the fluctuation impact distribution on the sterilization effect; Obtaining key variables from the fluctuation influence distribution, quantifying the washing effect of each piece of clothing according to the key variables to obtain a quantified result, and obtaining a classification result of the washing effect of each piece of clothing according to the quantified result; According to the washing effect classification results, a correlation model based on regression analysis is constructed, and a mapping relationship between washing variable adjustment and effect improvement is obtained according to the correlation model; According to the mapping relationship between the variable adjustment and the effect improvement, the temperature variable and the time variable are adjusted dynamically in real time to obtain an optimized configuration solution; The washing process is performed according to the optimized configuration scheme to obtain an optimized washing effect, and the optimized washing effect is verified twice to obtain a final configuration scheme that meets medical safety standards.

2. The method according to claim 1, characterized in that Before acquiring the real-time status data of the bedding from the structured washing process data set, the method further includes the step of constructing a structured washing process data set, which includes: Continuously monitor the temperature and time variables during the washing process, obtain the washing variable data of each piece of clothing at each washing stage, and obtain the washing variable change record; According to the change records of washing variables, the washing data of each piece of clothing is archived and a structured washing process dataset is constructed.

3. The method according to claim 1, characterized in that According to the identified abnormal fluctuation condition, the abnormal fluctuation condition is deeply mined to obtain the fluctuation impact distribution on the sterilization effect, including: Comparing the temperature variable and time variable corresponding to the abnormal fluctuation condition with the threshold range of the medical safety standard, if the temperature variable or the time variable exceeds the threshold range of the medical safety standard, classifying and labeling the abnormal fluctuation data to obtain an abnormal data set; Deconstructing the fluctuation correlation between the temperature variable and the time variable of the abnormal data set item by item to determine the distribution of potential factors affecting the sterilization effect; Quantifying the distribution of potential factors to obtain the influence weight of each factor on the sterilization effect, classifying factors whose weights exceed a preset threshold as key influencing factors, and obtaining a list of key factors; According to the key factor list, the key influencing factors are associated with the abnormal fluctuation data to obtain the fluctuation influence distribution for the sterilization effect.

4. The method according to claim 1, wherein The step of obtaining key variables from the fluctuation influence distribution, quantifying the washing effect of each piece of clothing according to the key variables to obtain a quantified result, and obtaining a classification result of the washing effect of each piece of clothing according to the quantified result includes: Obtaining key variables from the fluctuation impact distribution, comparing and analyzing historical records with current laundry effect data, obtaining comparative information corresponding to the key variables, and obtaining preliminary effect distribution data; extracting abnormal information related to the fluctuation influence distribution based on the preliminary effect distribution data, and determining the deviation of the washing effect of each piece of clothing based on the abnormal information; If the deviation exceeds a preset threshold, the key variable is compared with the washing data in the historical records to obtain washing effect evaluation information for each piece of clothing; quantifying the washing effect of the bedding according to the effect evaluation information to obtain a quantitative result; The quantitative results that meet the medical safety standards are determined as expected effects. Conversely, those that do not meet the medical safety standards are determined as unsatisfactory effects, and the classification results of the washing effects of each piece of clothing are obtained.

5. The method according to claim 1, wherein According to the washing effect classification results, a correlation model based on regression analysis is constructed to obtain a mapping relationship between washing variable adjustment and effect improvement, including: Based on the washing variable monitoring records, combined with the washing effect classification results and historical effect determination data, a correlation model based on regression analysis is constructed, and preliminary correlation data related to the washing effect is obtained from the correlation model; obtaining deviation information related to the washing effect according to the preliminary correlation data, and obtaining direction data of variable adjustment according to the deviation information; If the deviation information exceeds the preset threshold range, the variable adjustment direction data is correlated and compared with the historical effect improvement records to obtain the adjustment plan for each group of key variable combinations and obtain the adjusted configuration information; According to the adjusted configuration information, the mapping rules between the variable adjustment direction data and the washing effect are verified and processed to determine the final mapping relationship between the variable adjustment and the effect improvement.

6. The method according to claim 1, characterized in that According to the mapping relationship between the variable adjustment and the effect improvement, the temperature variable and the time variable are adjusted dynamically in real time to obtain an optimized configuration solution, including: According to the mapping relationship between the variable adjustment and the effect improvement, real-time data of the temperature and time variables are obtained, and the real-time data is matched with the historical parameter configuration to obtain preliminary deviation information; If the preliminary deviation information exceeds a preset threshold range, dynamic control instructions are generated for the temperature variable and the time variable, and the adjustment direction of the washing equipment is calibrated in combination with the washing process monitoring data to determine the adjusted operating parameters; Transmitting the adjusted operating parameters to the washing equipment to obtain updated operating status information; According to the updated operating status information, the effect verification data is integrated with the configuration scheme to obtain an optimized configuration scheme suitable for the current scenario.

7. The method according to claim 1, characterized in that The washing process is performed according to the optimized configuration scheme to obtain an optimized washing effect, and the optimized washing effect is verified twice to obtain a final configuration scheme that meets medical safety standards, including: Executing a washing process according to the optimized configuration scheme, obtaining a real-time data stream of an operating status during the washing process, and comparing the real-time data stream with a preset threshold range to obtain preliminary deviation information of the real-time data stream; If the preliminary deviation information exceeds the preset threshold range, the washing variables are dynamically calibrated, and the adjusted operating state parameters are determined in combination with the real-time feedback data during the monitoring process; transmitting the adjusted operating status parameters to the washing equipment, and obtaining an updated status record of the washing equipment; According to the updated status record, the washing effect data is compared with the requirements of the medical safety standards to obtain a final configuration solution that is applicable to the current scenario and meets the medical safety standards.

8. A medical bedding management system based on RFID, characterized in that: include: An abnormality monitoring module is used to obtain real-time status data of bedding from the structured washing process data set, compare the real-time status data with historical data, and identify abnormal fluctuations in the washing process; The fluctuation analysis module is used to conduct in-depth mining of the abnormal fluctuation conditions based on the identified abnormal fluctuation conditions to obtain the fluctuation impact distribution on the sterilization effect; a classification module, configured to obtain key variables from the fluctuation influence distribution, quantify the washing effect of each piece of clothing according to the key variables to obtain a quantified result, and obtain a classification result of the washing effect of each piece of clothing according to the quantified result; A mapping module, configured to construct a correlation model based on regression analysis according to the washing effect classification results, and obtain a mapping relationship between washing variable adjustment and effect improvement according to the correlation model; A solution configuration module dynamically adjusts the temperature and time variables in real time according to the mapping relationship between the variable adjustment and the effect improvement to obtain an optimized configuration solution; The scheme configuration module is also used to execute the washing process according to the optimized configuration scheme to obtain the optimized washing effect, and perform secondary verification on the optimized washing effect to obtain a final configuration scheme that meets medical safety standards.

9. An electronic device, characterized in that: The medical device comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the medical device implements the RFID-based medical bedding management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the RFID-based medical bedding management method according to any one of claims 1 to 7.

Images