A traditional Chinese medicine cupping device and method

Abstract

The application provides a traditional Chinese medicine cupping device and method, a multi-parameter association rule library is constructed through historical time sequence state data of multiple cupping units in the traditional Chinese medicine cupping device in a working process and cupping characteristics of the traditional Chinese medicine cupping device; a historical reference safety probability of each cupping unit is calculated through the multi-parameter association rule library and historical fault data of the traditional Chinese medicine cupping device; a safety state evaluation value of the corresponding cupping unit is determined according to time sequence state data of each cupping unit and the multi-parameter association rule library; based on a preset grading early warning standard of the traditional Chinese medicine cupping device, a risk early warning level of current work of the corresponding cupping unit is judged through the safety state evaluation value and the historical reference safety probability, and an early warning signal of the traditional Chinese medicine cupping device is generated from the risk early warning level. According to the application, the traditional Chinese medicine cupping device can be accurately graded and early warned and responded based on the association relationship between multiple parameters in a single cupping unit of the traditional Chinese medicine cupping device.

Description

Technical Field

[0001] This application relates to the field of traditional Chinese medicine cupping technology, and more specifically, to a traditional Chinese medicine cupping device and method. Background Technology

[0002] Cupping therapy is a classic external treatment method in Traditional Chinese Medicine. It combines the physical stimulation of cupping with the penetration of Chinese medicine. Through the negative pressure and heat effect inside the cup, local skin congestion is caused, meridians are unblocked, qi and blood circulation are promoted, and the body's self-regulation ability is stimulated. Meanwhile, the Chinese medicine ingredients penetrate directly to the lesion through the expanded skin pores, avoiding the metabolic burden on the stomach, intestines and liver caused by oral medications, and thus have stronger targeting.

[0003] As the implementing device for traditional Chinese medicine cupping therapy, cupping devices often employ a multi-unit collaborative operation mode. The stability and safety of their operation directly affect the therapeutic effect and the user's personal safety. Therefore, real-time monitoring and risk warning of the device's operating status are urgently needed. Currently, the status monitoring methods for existing cupping devices are relatively simple, mostly relying on a single sensor to collect real-time operating parameters of a single cupping unit and using simple numerical threshold comparisons to determine if anomalies exist. This approach fails to fully integrate historical operating data and the device's own cupping characteristics, making it impossible to establish an inherent correlation analysis mechanism between multiple parameters within a single cupping unit. It also makes it difficult to identify potential risks when a single parameter is within limits but multiple parameter combinations are abnormal. Therefore, how to accurately classify and issue early warnings for traditional Chinese medicine cupping devices based on the correlation between multiple parameters within a single cupping unit has become a challenge for the industry. Summary of the Invention

[0004] This application provides a traditional Chinese medicine cupping device and method, which can perform precise graded early warning response based on the correlation between multiple parameters within a single cupping unit of the traditional Chinese medicine cupping device.

[0005] Firstly, this application provides a state monitoring and early warning method based on multi-parameter association rules, applied to the state monitoring of a traditional Chinese medicine cupping device. The method includes the following steps: Acquire historical time-series status data of multiple cupping units in a traditional Chinese medicine cupping device during operation; Based on the historical time-series state data and the cupping characteristics of the traditional Chinese medicine cupping device, a multi-parameter association rule library is constructed to characterize the internal physical state correlation and safety risks of a single cupping unit. The historical baseline safety probability of each cupping unit is calculated using the multi-parameter association rule base and historical fault data of the traditional Chinese medicine cupping device. Real-time collection of time-series status data of each cupping unit; dynamic evaluation of the safety status of each cupping unit under current operation based on the time-series status data and the multi-parameter association rule base; obtaining the safety status evaluation value of the corresponding cupping unit. Based on the preset graded early warning standards of the traditional Chinese medicine cupping device, the risk warning level of the current operation of the corresponding cupping unit is determined by the safety status assessment value and the historical benchmark safety probability, and an early warning signal of the traditional Chinese medicine cupping device is generated from the risk warning level.

[0006] In some embodiments, the historical time-series status data includes the negative pressure value inside the cupping unit, the temperature inside the cupping unit, the working time, the start-stop status, the sealing status, and the contact status with the human body of each cupping unit during previous operations of the traditional Chinese medicine cupping device.

[0007] In some embodiments, constructing a multi-parameter association rule base based on the historical time-series state data and the cupping characteristics of the traditional Chinese medicine cupping device to characterize the internal physical state correlation and safety risks of a single cupping unit specifically includes: The historical time-series state data is preprocessed to obtain preprocessed historical time-series state data; The correlation between various monitoring parameters within a single cupping unit of the traditional Chinese medicine cupping device is determined based on the preprocessed historical time-series status data. To obtain the cupping characteristics of a traditional Chinese medicine cupping device; A multi-parameter association rule base is constructed based on the aforementioned relationships and cupping characteristics to characterize the internal physical state associations and safety risks of a single cupping unit.

[0008] In some embodiments, calculating the historical baseline safety probability of each cupping unit using the multi-parameter association rule base and historical fault data of the traditional Chinese medicine cupping device specifically includes: Obtain historical fault data of traditional Chinese medicine cupping devices; Type feature analysis is performed on the historical fault data to obtain historical fault type features; Obtain historical normal operation data of the traditional Chinese medicine cupping device; The frequency and percentage of failures of each cupping unit under conditions without real-time monitoring information are determined based on the historical fault data and the historical normal operation data. The historical baseline safety probability of each cupping unit is determined by the historical fault type characteristics, the fault frequency and proportion, and the multi-parameter association rule base.

[0009] In some embodiments, dynamically evaluating the safety status of each cupping unit under its current operation based on various time-series state data and the multi-parameter association rule base to obtain the safety status evaluation value of the corresponding cupping unit specifically includes: The data of each time series state are matched and analyzed with the multi-parameter association rule base to obtain the basic state results of each cupping unit. Based on the multi-parameter association rule base, a comprehensive risk assessment is performed on the multi-parameter abnormal effects within each cupping unit to obtain the initial risk assessment value of the corresponding cupping unit. The safety status of the corresponding cupping unit under its current operation is assessed by evaluating the basic status results and the initial risk assessment value, thereby obtaining the safety status assessment value of the corresponding cupping unit.

[0010] In some embodiments, based on the preset graded early warning standards of the traditional Chinese medicine cupping device, determining the risk warning level of the current operation of the corresponding cupping unit through the safety status assessment value and the historical baseline safety probability specifically includes: Obtain the preset graded early warning standards for traditional Chinese medicine cupping devices; The safety status assessment value is compared with the preset graded early warning standard one by one to obtain the preliminary early warning level; The initial warning level is corrected by the historical baseline safety probability to obtain the risk warning level of the corresponding cupping unit's current operation.

[0011] In some embodiments, generating a warning signal for the traditional Chinese medicine cupping device based on the risk warning level specifically includes: Obtain the preset warning signal output rules of the traditional Chinese medicine cupping device; The risk warning level is matched with the preset warning signal output rules to generate a warning signal for the traditional Chinese medicine cupping device.

[0012] Secondly, this application provides a traditional Chinese medicine cupping device, which includes a status monitoring and early warning unit, the status monitoring and early warning unit comprising: The acquisition module is used to acquire historical time-series status data of multiple cupping units in the traditional Chinese medicine cupping device during the working process; The processing module is used to construct a multi-parameter association rule base for characterizing the internal physical state correlation and safety risks of a single cupping unit based on the historical time-series state data and the cupping characteristics of the traditional Chinese medicine cupping device. The processing module is also used to calculate the historical baseline safety probability of each cupping unit through the multi-parameter association rule base and the historical fault data of the traditional Chinese medicine cupping device; The processing module is also used to collect the time-series status data of each cupping unit in real time, and to dynamically evaluate the safety status of each cupping unit under its current operation based on the time-series status data and the multi-parameter association rule library, so as to obtain the safety status evaluation value of the corresponding cupping unit. The execution module is used to determine the risk warning level of the current operation of the corresponding cupping unit based on the preset graded warning standards of the traditional Chinese medicine cupping device, through the safety status assessment value and the historical benchmark safety probability, and generate a warning signal of the traditional Chinese medicine cupping device based on the risk warning level.

[0013] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described state monitoring and early warning method based on multi-parameter association rules.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned state monitoring and early warning method based on multi-parameter association rules.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The traditional Chinese medicine cupping device and method provided in this application first acquires historical time-series state data of multiple cupping units in the traditional Chinese medicine cupping device during operation; based on the historical time-series state data and the cupping characteristics of the traditional Chinese medicine cupping device, a multi-parameter association rule library is constructed to characterize the internal physical state correlation and safety risk of a single cupping unit; the historical baseline safety probability of each cupping unit is calculated using the multi-parameter association rule library and historical fault data of the traditional Chinese medicine cupping device; the time-series state data of each cupping unit is collected in real time, and the safety status of each cupping unit under current operation is dynamically evaluated based on the time-series state data and the multi-parameter association rule library to obtain the safety status evaluation value of the corresponding cupping unit; based on the preset graded early warning standard of the traditional Chinese medicine cupping device, the risk warning level of the current operation of the corresponding cupping unit is determined by the safety status evaluation value and the historical baseline safety probability, and an early warning signal of the traditional Chinese medicine cupping device is generated from the risk warning level.

[0016] Therefore, this application, in the control process of a traditional Chinese medicine cupping device, obtains historical time-series state data of multiple cupping units, providing time-series and comprehensive basic data support for subsequent safety assessments and the construction of a multi-parameter association rule base. Based on this historical time-series state data and cupping characteristics, a multi-parameter association rule base characterizing the physical state correlation and safety risks within a single cupping unit is constructed. This allows for the accurate establishment of safety correlation logic between multiple parameters within a single cupping unit, clarifying the impact of multi-parameter combinations on the safety of a single unit. Furthermore, by calculating the historical baseline safety probability of each cupping unit based on the multi-parameter association rule base and historical fault data, it can provide risk assessment support. The risk warning level determination provides a historical operational reliability reference; real-time collection of time-series status data of each cupping unit and dynamic evaluation of the current safety status of a single unit combined with a multi-parameter association rule base enable real-time, dynamic, and accurate determination of safety status, improving the timeliness and accuracy of safety assessment; finally, based on preset graded warning standards, combined with safety status assessment values ​​and historical benchmark safety probabilities, the risk warning level is determined and a warning signal is generated. This allows for precise graded warning response of the traditional Chinese medicine cupping device based on the correlation of multiple parameters within a single cupping unit, effectively solving the core problem of conducting precise graded warning response of the device based on the correlation of multiple parameters within a single unit. Using the solution proposed in this application, precise graded warning response of the traditional Chinese medicine cupping device can be achieved based on the correlation of multiple parameters within a single cupping unit. Attached Figure Description

[0017] Figure 1 This is an exemplary flowchart of a state monitoring and early warning method based on multi-parameter association rules, as shown in some embodiments of this application; Figure 2 This is an exemplary flowchart illustrating the determination of a multi-parameter association rule base according to some embodiments of this application; Figure 3 This is an exemplary flowchart illustrating the determination of a security status assessment value according to some embodiments of this application; Figure 4 This is a structural schematic diagram of a status monitoring and early warning unit according to some embodiments of this application; Figure 5 This is a schematic diagram of the structure of a computer device that implements a state monitoring and early warning method based on multi-parameter association rules, according to some embodiments of this application. Detailed Implementation

[0018] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] refer to Figure 1The figure is an exemplary flowchart of a state monitoring and early warning method based on multi-parameter association rules according to some embodiments of this application. The state monitoring and early warning method based on multi-parameter association rules mainly includes the following steps: In step 101, historical time-series status data of multiple cupping units in the traditional Chinese medicine cupping device during the working process are obtained.

[0020] It should be noted that the historical time-series status data in this application refers to the operational information of each cupping unit continuously collected and recorded in chronological order during the previous operation of the traditional Chinese medicine cupping device. It represents the actual working status and parameter changes of the cupping unit over time, reflecting the operating rules, stability and potential abnormal trends of each cupping unit under different physiotherapy conditions and different working stages. Specifically, it includes continuous monitoring data of the negative pressure value inside the cup, the temperature inside the cup, the working time, the start-stop status, the sealing status and the contact status with the human body of each cupping unit during the previous operation of the traditional Chinese medicine cupping device.

[0021] In step 102, a multi-parameter association rule base is constructed based on the historical time-series state data and the cupping characteristics of the traditional Chinese medicine cupping device to characterize the internal physical state correlation and safety risks of a single cupping unit.

[0022] In some embodiments, reference Figure 2 The figure is an exemplary flowchart for determining a multi-parameter association rule base in some embodiments of this application. In this embodiment, the construction of a multi-parameter association rule base for characterizing the internal physical state association and safety risks of a single cupping unit based on the historical time-series state data and the cupping characteristics of the traditional Chinese medicine cupping device can be achieved by the following steps: In step 1021, the historical time-series state data is preprocessed to obtain preprocessed historical time-series state data; In step 1022, the correlation between various monitoring parameters within a single cupping unit of the traditional Chinese medicine cupping device is determined based on the preprocessed historical time-series state data. In step 1023, the cupping characteristics of the traditional Chinese medicine cupping device are obtained; In step 1024, a multi-parameter association rule base is constructed using the association relationship and the cupping characteristics to characterize the internal physical state association and safety risks of a single cupping unit.

[0023] In specific implementation, the historical time-series state data is preprocessed to obtain preprocessed historical time-series state data. This can be achieved in the following way: performing preprocessing operations in this field on the historical time-series state data, using the three-standard-deviation method to identify and remove abnormal deviations in the data, using linear interpolation to fill in missing time-series data, aligning the state data of multiple cupping units according to a unified sampling timestamp, and then using the minimum-maximum normalization method to map parameter data of different dimensions to a unified numerical range. At the same time, a moving average filtering algorithm is used to filter out random noise generated during data acquisition, resulting in regular, complete, and abnormal preprocessed historical time-series state data. Other methods can also be used in other embodiments, which are not limited here.

[0024] Furthermore, in specific implementation, determining the correlation between various monitoring parameters within a single cupping unit of the traditional Chinese medicine cupping device based on the preprocessed historical time-series state data can be achieved in the following way: using the Pearson correlation analysis algorithm, the correlation coefficients of various monitoring parameters in the preprocessed historical time-series state data, such as the negative pressure value inside the cup, the temperature inside the cup, the working time, the start-stop state, the sealing state, and the state of contact with the human body, are calculated one by one. This clarifies the strength of the linear correlation and the positive and negative correlation characteristics between each monitoring parameter. For each set of monitoring parameters to be analyzed in the preprocessed historical time-series state data... For each pair of parameters, a reasonable range of time lag orders is first set. This range is determined based on the sampling cycle and treatment workflow of the cupping device, typically from 0 to 10% of the number of sampling points within a single treatment cycle. Then, the cross-covariance values ​​are calculated for the time series of each pair of monitoring parameters at each set lag order. The lag order that maximizes the cross-covariance value is selected and defined as the lag time of the parameter pair. The corresponding maximum cross-covariance value is normalized and used as the lag coupling strength of the parameter pair in the time dimension. Simultaneously, the direction of lag influence between parameters is recorded, completing the process. The parameters are quantitatively determined based on time lag coupling. Then, according to the design safety specifications and operating standards of the traditional Chinese medicine cupping device, the safety threshold ranges and critical values ​​of each monitoring parameter are extracted. For parameter pairs with potential mutual constraints, the actual value distribution of the other parameter in the preprocessed data when one parameter is at a critical value is statistically analyzed. The probability of the latter exceeding its own safety threshold range is calculated. If this probability value is higher than the constraint determination threshold set in this field, the parameter pair is determined to have a safety constraint association, and this probability value is used as the quantitative strength of the safety constraint association. The constraint type, such as positive constraint or negative constraint, is also recorded. Finally, the time lag coupling relationship and quantitative strength of each parameter pair obtained from the above time-series cross-covariance analysis are summarized with the safety constraint association and quantitative strength obtained from the threshold constraint analysis. Combined with the linear association results obtained from Pearson correlation analysis, a complete association dataset covering three types—linear association, time lag coupling association, and safety constraint association—and their corresponding quantitative values ​​is formed. This dataset serves as the association relationship between all monitoring parameters within a single cupping unit. Other methods can be used in other embodiments, which are not limited here.

[0025] It should be noted that the cupping characteristics in this application refer to the inherent attributes, working rules and constraints of the traditional Chinese medicine cupping device in terms of structural design, operation control, traditional Chinese medicine physiotherapy and safety protection. They reflect the working mechanism of the device in adapting to physiotherapy scenarios, the operating rules of individual units, the safety boundaries of key parameters and the state risk constraint logic. Specifically, they include the inherent characteristics of the cupping unit's negative pressure safety range, temperature working range, start-stop control rules, individual unit working mode, sealing and skin contact requirements, physiotherapy working condition adaptation conditions, abnormal judgment criteria and safety protection constraints. They can be used to provide a constraint basis and judgment criteria for the safety constraint judgment of monitoring parameters, dynamic evaluation of device status and classification of risk warning levels.

[0026] In specific implementation, the construction of a multi-parameter association rule base to characterize the internal physical state correlation and safety risk of a single cupping unit, based on the aforementioned correlation relationships and cupping characteristics, can be achieved in the following way: using the correlation relationships between monitoring parameters as data basis, combined with the extracted cupping characteristics, a rule table modeling approach is adopted. The cupping unit, negative pressure, temperature, sealing state, fitting state, and safety state of a single unit are set as rule entries, and parameter correlation, state transmission, and safety constraints are set as rule conditions. The correlation probability and safety confidence level are calculated. The correlation probability is obtained by first normalizing the correlation coefficients obtained from Pearson correlation analysis to the 0-1 interval, then weighting and correcting it using the lag coupling strength determined by time-series cross-covariance analysis. Simultaneously, the actual frequency of synchronous changes and lag effects of each parameter in the preprocessed historical time-series state data is statistically analyzed, and combined with historical data... The probability of faults caused by abnormal parameter linkages in historical fault data is calibrated to form the final correlation probability. The safety confidence is calculated based on the predetermined safety thresholds and safety constraints of each monitoring parameter in the cupping characteristics. The effective proportion of each cupping unit's physical state being stable within the safe range in historical time-series state data is statistically analyzed. This is combined with the reliable frequency of no safety risks occurring in this state in historical fault data. At the same time, the quantitative strength of the correlation between safety constraints between parameters is integrated to perform a weighted summation calculation to obtain the safety confidence that represents the safety and reliability of the current state. The calculated correlation coefficient, correlation probability, and safety confidence value are used as attributes and labeled on the corresponding rule entries to complete the binding and construction of parameters, rules, and probability attributes one by one. Finally, a multi-parameter correlation rule library that can represent the correlation of physical state and safety risks within a single cupping unit is formed. Other methods can be used in other embodiments, which are not limited here.

[0027] It should be noted that the correlation in this application represents the quantitative intrinsic relationship between the linear correlation, time lag coupling, and safety constraints among the monitoring parameters and physical states of each cupping unit within a single cupping unit of the traditional Chinese medicine cupping device. It reflects the objective operating laws of mutual influence, state transmission, and safety constraints among the monitoring parameters and can be used to clarify the linkage logic between state variables. The multi-parameter correlation rule base represents the rule set of a single unit's physical state, the correlation between parameters, cupping characteristic constraints, and probability attributes. It reflects the logic of the transmission of a single unit's local physical state to the safety of the single unit, the risk probability distribution, and the degree of safety reliability. It can be used to calculate the historical baseline safety probability without real-time monitoring information, conduct dynamic safety assessments of the device's real-time operating status, and provide core reasoning basis for determining risk warning levels.

[0028] In step 103, the historical baseline safety probability of each cupping unit is calculated using the multi-parameter association rule base and the historical fault data of the traditional Chinese medicine cupping device.

[0029] In some embodiments, calculating the historical baseline safety probability of each cupping unit using the multi-parameter association rule base and historical fault data of the traditional Chinese medicine cupping device can be achieved through the following steps: Obtain historical fault data of traditional Chinese medicine cupping devices; Type feature analysis is performed on the historical fault data to obtain historical fault type features; Obtain historical normal operation data of the traditional Chinese medicine cupping device; The frequency and percentage of failures of each cupping unit under conditions without real-time monitoring information are determined based on the historical fault data and the historical normal operation data. The historical baseline safety probability of each cupping unit is determined by the historical fault type characteristics, the fault frequency and proportion, and the multi-parameter association rule base.

[0030] In specific implementation, the historical fault data of the traditional Chinese medicine cupping device can be obtained in the following way: extract and summarize the cupping unit number, occurrence time, manifestation, negative pressure / temperature / sealing status parameters at the time of triggering, and fault duration from the local storage log, upper computer monitoring record, fault alarm archive and after-sales maintenance record of the traditional Chinese medicine cupping device, and determine the above information as complete historical fault data. Other methods can also be used in other embodiments, which are not limited here.

[0031] In addition, in specific implementation, the historical fault data is analyzed for type characteristics to obtain historical fault type characteristics. This can be achieved in the following way: Historical fault data is categorized according to negative pressure exceeding limits, temperature abnormalities, sealing failure, poor skin adhesion, and unit start-up / shutdown abnormalities. For each type of fault, the corresponding parameter values ​​in all trigger cases of that type of fault are statistically analyzed, and the critical extreme values ​​of all trigger values ​​are taken as the trigger parameter critical values. For example, for negative pressure exceeding limits, the minimum / maximum exceeding limit value at the time of triggering is taken; for temperature abnormalities, the highest / lowest exceeding limit value at the time of triggering is taken. The number and quantity of cupping units within the unit affected by the fault when it occurs are statistically analyzed, and the associated units with the highest frequency are summarized as the cupping units affected by the associated fault. According to the timestamp order of the fault occurrence, the diffusion order of the fault from the initial occurrence unit to the associated units is sorted out to determine the fault propagation order. Finally, the statistically obtained trigger parameter critical values, associated cupping units, and fault propagation order are used as standardized historical fault type characteristics. Other methods can also be used in other embodiments, which are not limited here.

[0032] In addition, in specific implementation, the historical normal operation data of the cupping device can be obtained in the following way: based on the preset safety thresholds for negative pressure, temperature, and sealing status in the cupping characteristics, firstly, identify the time segments with "fault markers" and "alarm markers" in the historical time-series status data, and directly remove such time-series data; then, verify the negative pressure, temperature, and sealing status parameters of each cupping unit one by one, and remove the corresponding time segments whose parameter values ​​exceed the safety thresholds one by one; finally, select the continuous operation data in which the negative pressure, temperature, and sealing status are all stable within the safe range and there are no abnormal markers, and determine this part of the data as the historical normal operation data. Other methods can also be used in other embodiments, which are not limited here.

[0033] In addition, in specific implementation, the frequency and proportion of failures of each cupping unit under the condition of no real-time monitoring information can be determined based on the historical failure data and the historical normal operation data. This can be achieved by the following method: first, count the total number of effective running segments, the total number of failures, and the total number of normal operations for a single cupping unit; then, calculate the frequency and proportion of failures of each cupping unit under the condition of no real-time monitoring information using the formulas: failure frequency = total number of failures ÷ total number of effective running segments, failure proportion = failure frequency ÷ (failure frequency + normal operation frequency), and normal operation proportion = normal operation frequency ÷ (failure frequency + normal operation frequency). In other embodiments, other methods can also be used to achieve this, which are not limited here.

[0034] In addition, in specific implementation, the historical baseline safety probability of each cupping unit can be determined by the historical fault type characteristics, the fault frequency and proportion, and the multi-parameter association rule base in the following way: The historical fault type characteristics are used to divide the system into three states: safe, slightly abnormal, and fault risk. A multi-index weighted fusion method is used to specifically integrate the basic proportion with the association probability and safety confidence in the multi-parameter association rule base: Fixed empirical weights are preset, with the basic proportion weight set at 0.4, the association probability weight at 0.3, and the safety confidence weight at 0.3. The fixed empirical weights are preset based on the safety design priority of the traditional Chinese medicine cupping device, the statistical verification results of historical operating data, and the conventional engineering experience in assessing the status of physiotherapy equipment in this field. The basic proportion is directly statistically derived raw data. The contribution to the prior probability is the highest, so it is set to 0.4. The association probability and safety confidence are auxiliary correction indicators of the multi-parameter association rule base. Their contributions are similar and lower than the basic proportion, so they are set to 0.3 respectively. For each state, the fusion value is calculated as: basic proportion of the state × 0.4 + association probability of the state × 0.3 + safety confidence of the state × 0.3. The fusion values ​​of the three states are then mapped to the 0-1 interval to complete the normalization process. The fusion values ​​of the three states after correction and normalization are used as the prior safety probability of each cupping unit under the condition of no real-time monitoring information. Based on the distribution of each cupping unit, the historical benchmark safety probability of each cupping unit is formed. Other methods can be used in other embodiments, which are not limited here.

[0035] It should be noted that the historical fault data in this application refers to various fault-related information recorded during the previous operation of the traditional Chinese medicine cupping device, reflecting the fault occurrence and related parameter performance of each cupping unit of the device; the historical fault type characteristics refer to the fault classification and corresponding triggering threshold, related units, and transmission rules characteristics obtained after classifying and sorting the historical fault data, reflecting the occurrence mechanism and impact logic of different faults; the historical normal operation data refers to the historical time-series state data of the traditional Chinese medicine cupping device with no faults and all parameters within the safe range, reflecting the stable operation pattern of the cupping unit under normal working conditions; the fault frequency refers to the total number of faults occurring in each cupping unit within the historical operating cycle, reflecting the frequency of fault occurrence in the corresponding unit; the proportion refers to the proportion of fault state and normal state in the total operating period, reflecting the basic distribution of each state of the device; the historical baseline safety probability refers to the probability set of each cupping unit being in a safe, abnormal, or fault state when there is no real-time monitoring information, reflecting the inherent safety probability distribution pattern of the cupping unit, which can be used for real-time dynamic assessment of the device's safety status and determination of risk warning levels.

[0036] In step 104, the time-series status data of each cupping unit is collected in real time. Based on the time-series status data and the multi-parameter association rule base, the safety status of each cupping unit under its current operation is dynamically evaluated to obtain the safety status evaluation value of the corresponding cupping unit.

[0037] In practice, during the operation of the traditional Chinese medicine cupping device, the negative pressure sensor, temperature sensor, sealing status sensor, and skin adhesion sensor integrated on each cupping unit synchronously collect corresponding physical quantity signals according to the device's preset fixed sampling period. After amplification, filtering, and other signal conditioning of the collected analog signals, they are converted into digital signals by the analog-to-digital converter module. Each set of digital signals is then marked with a corresponding sampling timestamp and cupping unit number to complete the timing and source marking. Subsequently, the marked data is temporarily cached locally to ensure data continuity and no loss. Finally, the real-time timing status data of each cupping unit is organized in chronological order.

[0038] In some embodiments, reference Figure 3 The diagram is an exemplary flowchart for determining the safety status assessment value in some embodiments of this application. In this embodiment, the safety status of each cupping unit under its current operation is dynamically assessed based on various time-series state data and the multi-parameter association rule base. The safety status assessment value of the corresponding cupping unit can be obtained by the following steps: In step 1041, the time-series state data and the multi-parameter association rule base are matched and analyzed to obtain the basic state results of each cupping unit; In step 1042, a comprehensive risk assessment of the multi-parameter abnormal effects within each cupping unit is performed based on the multi-parameter association rule base to obtain the initial risk assessment value of the corresponding cupping unit. In step 1043, the safety status of the corresponding cupping unit under its current operation is evaluated by the basic status results and the initial risk assessment value, and the safety status assessment value of the corresponding cupping unit is obtained.

[0039] In specific implementation, the basic state results of each cupping unit are obtained by matching and analyzing the time-series state data with the multi-parameter association rule base. This can be achieved in the following way: the real-time collected time-series state data of each cupping unit is matched with the cupping unit entity, negative pressure parameter node, temperature parameter node, sealing state node, and fitting state node with unique identifiers in the multi-parameter association rule base using a dual matching of unit number and parameter type. The preset safety threshold, association probability, and safety confidence level attribute information of each node in the graph are retrieved. Then, the real-time parameters in the time-series state data of each cupping unit are numerically compared and verified. If the parameter value is within the safety threshold range marked in the graph, it is determined that the parameter is compliant; if it exceeds the range, it is determined that the parameter is abnormal. When the parameter is compliant, it is classified as a safety level; when the parameter deviates from the safety threshold by ≤10%, it is classified as a slight abnormality level; and when the parameter deviates from the safety threshold by >10%, it is classified as a fault risk level. In this way, the basic state results of each cupping unit containing unit number, parameter type, and state level are obtained. Other methods can also be used in other embodiments, which are not limited here.

[0040] In addition, in specific implementation, the initial risk assessment value of the corresponding cupping unit can be obtained by comprehensively assessing the impact of multi-parameter anomalies within each cupping unit based on the multi-parameter association rule library. This can be achieved in the following way: First, each abnormal parameter is assigned a value according to its state level, with a base score of 20 points for minor anomalies and a base score of 50 points for fault risk. Then, the risk coefficient is calculated based on the association probability between the abnormal parameter and other parameters in the multi-parameter association rule library. The risk coefficient = association probability × number of influencing parameters. The number of influencing parameters is determined by locating the fault propagation path and parameter association relationship corresponding to the currently abnormal parameter in the multi-parameter association rule library, and directly counting the total number of parameters that have linkage constraints, parameter associations, or fault propagation associations with the abnormal parameter. This total number is the influencing parameter corresponding to the abnormal parameter. The determination of the quantity and fault propagation path is as follows: Based on the timestamps of historical fault occurrences, the sequence of various faults from the first abnormal parameter to the subsequent abnormal parameters is statistically analyzed. Then, combined with the parameter association relationships, safety constraint associations, and fault type characteristics already marked in the multi-parameter association rule base, the transmission link of the fault from the source parameter to the associated parameters is sorted out. This ordered transmission link sorted out according to the order of fault occurrence and association relationship is the fault propagation path. The risk score of a single abnormal parameter is calculated by the base score × risk coefficient. Then, the risk scores of all abnormal parameters are summed item by item, that is, the initial risk assessment value = Σ risk score of a single abnormal parameter, to obtain the initial risk assessment value of the corresponding cupping unit. Other methods can also be used in other embodiments, which are not limited here.

[0041] In addition, in specific implementation, the safety status of the corresponding cupping unit under its current operation is assessed by evaluating the basic status results and the initial risk assessment value. The safety status assessment value of the corresponding cupping unit can be obtained in the following way: First, the basic status results are quantified and assigned values: Safety = 100 points, Minor Abnormality = 60 points, Fault Risk = 20 points. Then, the arithmetic mean of the quantified scores of all parameters of the cupping unit is calculated as the comprehensive basic status score. A weight of 0.6 is assigned to the comprehensive basic status score, and a weight of 0.4 is assigned to the initial risk assessment value. The weighted fusion calculation method is: Comprehensive Safety Status Score = Comprehensive Basic Status Score × 0.6 + Initial Risk Assessment Value × 0.4. The comprehensive basic status score directly reflects the safety status of the cupping unit. The compliance status of the unit's real-time parameters is the core direct basis for judging the safety of a single unit, and therefore it is assigned a higher weight of 0.6. The initial risk assessment value is an indirect risk quantification based on the internal correlation and transmission of a single unit, and is only used as an auxiliary correction indicator to make up for the one-sidedness of the single parameter assessment, so it is assigned a weight of 0.4. Then, the minimum-maximum normalization method is used to map the comprehensive safety status score to the interval of 0 to 1. The normalization formula is: assessment value = (current comprehensive score - minimum score) / (maximum score - minimum score), where the minimum score is 0 and the maximum score is 100. Finally, a safety status assessment value that can quantify the current working safety level of the cupping unit is obtained. Other methods can be used in other embodiments, which are not limited here.

[0042] It should be noted that the basic status results in this application represent the judgment results of the safety, minor abnormalities, and failure risks of each cupping unit, reflecting the real-time compliance and operating status of the parameters of a single cupping unit, and can be used to determine whether a single unit is working normally; the initial risk assessment value reflects the degree of transmission and diffusion of abnormal states within a single cupping unit and the overall potential risk level, and can be used to quantify associated failure risks and make up for the one-sidedness of single unit status assessment; the safety status assessment value reflects the comprehensive safety level of the current overall operation of the cupping unit, and can be used to directly determine the safety level of the device, providing core quantitative basis for risk warning and safety control.

[0043] In step 105, based on the preset graded early warning standard of the traditional Chinese medicine cupping device, the risk warning level of the current operation of the corresponding cupping unit is determined by the safety status assessment value and the historical benchmark safety probability, and an early warning signal of the traditional Chinese medicine cupping device is generated from the risk warning level.

[0044] In some embodiments, the risk warning level of the corresponding cupping unit's current operation can be determined by the following steps based on the preset graded early warning standards of the traditional Chinese medicine cupping device, using the safety status assessment value and the historical baseline safety probability: Obtain the preset graded early warning standards for traditional Chinese medicine cupping devices; The safety status assessment value is compared with the preset graded early warning standard one by one to obtain the preliminary early warning level; The initial warning level is corrected by the historical baseline safety probability to obtain the risk warning level of the corresponding cupping unit's current operation.

[0045] In practice, the system first reads a preset tiered warning standard from the traditional Chinese medicine cupping device. This standard is based on equipment safety design specifications, clinical usage requirements, and historical fault data, classifying risk levels into four levels: safe, Level 1 warning, Level 2 warning, and Level 3 warning. It also specifies the corresponding threshold values ​​for safety status assessments: safe 0.8–1.0, Level 1 warning 0.6–0.8, Level 2 warning 0.4–0.6, and Level 3 warning 0–0.4. Subsequently, the safety status assessment value is compared against each of the four threshold ranges in the tiered warning standard to determine the precise range to which the assessment value belongs, thus directly determining the corresponding preliminary warning level. Then, the fault risk probability value corresponding to the fault risk state in the historical baseline safety probability is extracted, and the correction is performed according to the preset fixed correction rule: if the initial warning level is Level 1 warning but the historical baseline safety probability is >0.9, the initial warning level is downgraded to safe; if the initial warning level is Level 2 warning but the historical baseline safety probability is >0.8, it is downgraded to Level 1 warning; if the historical baseline safety probability is <0.1, the initial warning level is upgraded by one level; in other cases, the initial warning level is directly used. After correction by this rule, the risk warning level corresponding to the current operation of the cupping unit is finally obtained. Other methods can also be used in other embodiments, which are not limited here.

[0046] It should be noted that the graded early warning standard in this application refers to the pre-set quantitative judgment rules of the traditional Chinese medicine cupping device, which include the range of safety status assessment values ​​and the corresponding risk levels. It reflects the graded judgment standard of equipment safety and risk and can be used as the judgment benchmark for the preliminary early warning level and the final risk early warning level. The preliminary early warning level represents the basic risk judgment of the current real-time operating status of the equipment, reflecting the basic safety risk level corresponding to the current real-time parameters of the equipment, and can be used to quickly give the initial risk judgment. The risk early warning level reflects the current overall true safety risk level of the cupping unit and can be used to directly trigger the corresponding early warning prompt, providing the core basis for equipment safety control and protection actions.

[0047] In some embodiments, generating a warning signal for a traditional Chinese medicine cupping device based on the risk warning level can be achieved through the following steps: Obtain the preset warning signal output rules of the traditional Chinese medicine cupping device; The risk warning level is matched with the preset warning signal output rules to generate a warning signal for the traditional Chinese medicine cupping device.

[0048] In practice, the system first reads the pre-stored warning signal output rules from the main control unit of the cupping device. These rules are set according to the equipment's safety control requirements and specify the frequency of the audible and visual alarms, the content displayed on the screen, the color of the status indicator lights, and the specific output format for whether to trigger protective actions for different risk warning levels. Then, the risk warning level is compared and matched with the warning signal output rules one by one. Based on the matching results, the system locates the signal output format and control command corresponding to the current risk level. The main control unit of the cupping device then drives the audible and visual alarm module, the display module, and the safety control module to perform corresponding actions according to the matched commands, ultimately generating and outputting a warning signal that completely corresponds to the current risk warning level.

[0049] It should be noted that the preset warning signal output rules in this application are the warning output forms and control execution logic pre-set by the traditional Chinese medicine cupping device, corresponding one-to-one with each risk warning level. They reflect the standardized response requirements of the device for different safety risk levels and can be used as the matching basis between risk warning levels and warning signals to standardize the device's warning output method. The warning signals are audible and visual prompts, screen reminders, and safety control instructions generated based on the risk warning level and warning signal output rules. They reflect the current actual safety risk level and abnormal operating status of the device and can be used to intuitively inform users of the risk level while triggering corresponding safety protection actions to ensure the safe use of the traditional Chinese medicine cupping device.

[0050] In another aspect, in some embodiments, this application provides a traditional Chinese medicine cupping device, which includes a status monitoring and early warning unit, as referenced. Figure 4 The figure is a schematic diagram of the structure of a status monitoring and early warning unit 400 according to some embodiments of this application. The status monitoring and early warning unit 400 includes: an acquisition module 401, a processing module 402, and an execution module 403, which are described below: The acquisition module 401 in this application is mainly used to acquire historical time-series status data of multiple cupping units in the traditional Chinese medicine cupping device during the working process. Processing module 402, in this application, is used to construct a multi-parameter association rule library based on the historical time-series state data and the cupping characteristics of the traditional Chinese medicine cupping device to characterize the internal physical state association and safety risks of a single cupping unit; It should be noted that the processing module 402 in this application is also used to calculate the historical baseline safety probability of each cupping unit through the multi-parameter association rule base and the historical fault data of the traditional Chinese medicine cupping device; In addition, it should be noted that the processing module 402 in this application is also used to collect the time-series status data of each cupping unit in real time, and to dynamically evaluate the safety status of each cupping unit under the current operation based on the time-series status data and the multi-parameter association rule library, so as to obtain the safety status evaluation value of the corresponding cupping unit. The execution module 403 in this application is mainly used to determine the risk warning level of the current operation of the corresponding cupping unit based on the preset graded warning standard of the traditional Chinese medicine cupping device, through the safety status assessment value and the historical benchmark safety probability, and generate a warning signal of the traditional Chinese medicine cupping device based on the risk warning level.

[0051] In addition, this application also provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described state monitoring and early warning method based on multi-parameter association rules.

[0052] In some embodiments, reference Figure 5 The figure is a schematic diagram of the structure of a computer device implementing a state monitoring and early warning method based on multi-parameter association rules, according to some embodiments of this application. The state monitoring and early warning method based on multi-parameter association rules in the above embodiments can... Figure 5 The computer device shown is used to implement this, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0053] Processor 501 can be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0054] The communication bus 502 can be used to transmit information between the aforementioned components.

[0055] Memory 503 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CDROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 503 may exist independently and be connected to processor 501 via communication bus 502. Memory 503 may also be integrated with processor 501.

[0056] The memory 503 stores program code for executing the scheme of this application, and its execution is controlled by the processor 501. The processor 501 executes the program code stored in the memory 503. The program code may include one or more software modules. The method used in the above embodiments can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0057] Communication interface 504 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0058] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0059] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0060] In addition, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described state monitoring and early warning method based on multi-parameter association rules.

[0061] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0062] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A state monitoring and early warning method based on multi-parameter association rules, applied to the state monitoring of a traditional Chinese medicine cupping device, characterized in that, The method includes the following steps: Acquire historical time-series status data of multiple cupping units in a traditional Chinese medicine cupping device during operation; Based on the historical time-series state data and the cupping characteristics of the traditional Chinese medicine cupping device, a multi-parameter association rule library is constructed to characterize the internal physical state correlation and safety risks of a single cupping unit. The historical baseline safety probability of each cupping unit is calculated using the multi-parameter association rule base and historical fault data of the traditional Chinese medicine cupping device. Real-time collection of time-series status data of each cupping unit; dynamic evaluation of the safety status of each cupping unit under current operation based on the time-series status data and the multi-parameter association rule base; obtaining the safety status evaluation value of the corresponding cupping unit. Based on the preset graded early warning standards of the traditional Chinese medicine cupping device, the risk warning level of the current operation of the corresponding cupping unit is determined by the safety status assessment value and the historical benchmark safety probability, and an early warning signal of the traditional Chinese medicine cupping device is generated from the risk warning level.

2. The method as described in claim 1, characterized in that, The historical time-series status data includes the negative pressure value inside the cup, the temperature inside the cup, the working time, the start-stop status, the sealing status, and the contact status with the human body of each cupping unit during previous operations of the traditional Chinese medicine cupping device.

3. The method as described in claim 1, characterized in that, Based on the historical time-series state data and the cupping characteristics of the traditional Chinese medicine cupping device, a multi-parameter association rule base is constructed to characterize the internal physical state correlation and safety risks of a single cupping unit. Specifically, it includes: The historical time-series state data is preprocessed to obtain preprocessed historical time-series state data; The correlation between various monitoring parameters within a single cupping unit of the traditional Chinese medicine cupping device is determined based on the preprocessed historical time-series status data. To obtain the cupping characteristics of a traditional Chinese medicine cupping device; A multi-parameter association rule base is constructed based on the aforementioned relationships and cupping characteristics to characterize the internal physical state associations and safety risks of a single cupping unit.

4. The method as described in claim 1, characterized in that, The calculation of the historical baseline safety probability of each cupping unit based on the multi-parameter association rule base and historical fault data of the traditional Chinese medicine cupping device specifically includes: Obtain historical fault data of traditional Chinese medicine cupping devices; Type feature analysis is performed on the historical fault data to obtain historical fault type features; Obtain historical normal operation data of the traditional Chinese medicine cupping device; The frequency and percentage of failures of each cupping unit under conditions without real-time monitoring information are determined based on the historical fault data and the historical normal operation data. The historical baseline safety probability of each cupping unit is determined by the historical fault type characteristics, the fault frequency and proportion, and the multi-parameter association rule base.

5. The method as described in claim 1, characterized in that, Based on the various time-series state data and the multi-parameter association rule base, the safety status of each cupping unit under its current operation is dynamically evaluated, and the safety status evaluation value of the corresponding cupping unit is obtained, specifically including: The data of each time series state are matched and analyzed with the multi-parameter association rule base to obtain the basic state results of each cupping unit. Based on the multi-parameter association rule base, a comprehensive risk assessment is performed on the multi-parameter abnormal effects within each cupping unit to obtain the initial risk assessment value of the corresponding cupping unit. The safety status of the corresponding cupping unit under its current operation is assessed by evaluating the basic status results and the initial risk assessment value, thereby obtaining the safety status assessment value of the corresponding cupping unit.

6. The method as described in claim 1, characterized in that, Based on the preset graded early warning standards of the traditional Chinese medicine cupping device, the risk warning level of the corresponding cupping unit is determined by the safety status assessment value and the historical benchmark safety probability. Specifically, this includes: Obtain the preset graded early warning standards for traditional Chinese medicine cupping devices; The safety status assessment value is compared with the preset graded early warning standard one by one to obtain the preliminary early warning level; The initial warning level is corrected by the historical baseline safety probability to obtain the risk warning level of the corresponding cupping unit's current operation.

7. The method as described in claim 1, characterized in that, The specific methods for generating warning signals for traditional Chinese medicine cupping devices based on the aforementioned risk warning level include: Obtain the preset warning signal output rules of the traditional Chinese medicine cupping device; The risk warning level is matched with the preset warning signal output rules to generate a warning signal for the traditional Chinese medicine cupping device.

8. A traditional Chinese medicine cupping device, comprising a status monitoring and early warning unit, characterized in that, The status monitoring and early warning unit includes: The acquisition module is used to acquire historical time-series status data of multiple cupping units in the traditional Chinese medicine cupping device during the working process; The processing module is used to construct a multi-parameter association rule base for characterizing the internal physical state correlation and safety risks of a single cupping unit based on the historical time-series state data and the cupping characteristics of the traditional Chinese medicine cupping device. The processing module is also used to calculate the historical baseline safety probability of each cupping unit through the multi-parameter association rule base and the historical fault data of the traditional Chinese medicine cupping device; The processing module is also used to collect the time-series status data of each cupping unit in real time, and to dynamically evaluate the safety status of each cupping unit under its current operation based on the time-series status data and the multi-parameter association rule library, so as to obtain the safety status evaluation value of the corresponding cupping unit. The execution module is used to determine the risk warning level of the current operation of the corresponding cupping unit based on the preset graded warning standards of the traditional Chinese medicine cupping device, through the safety status assessment value and the historical benchmark safety probability, and generate a warning signal of the traditional Chinese medicine cupping device based on the risk warning level.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the state monitoring and early warning method based on multi-parameter association rules as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the state monitoring and early warning method based on multi-parameter association rules as described in any one of claims 1 to 7.

Images