A two-way interactive medical device intelligent repair system and a method of using the same

Abstract

The application discloses a bidirectional interactive medical equipment intelligent repair system and a use method thereof, relates to the technical field of intelligent medical equipment, and comprises a medical equipment sensor module, a data acquisition and processing module, an environment monitoring module, a CPU reprocessing module, a remote monitoring communication module and an interactive interface module; the medical equipment sensor module continuously monitors the real-time operation state of the medical equipment, acquires original monitoring data of the medical equipment, and sends the acquired original monitoring data of the operation state of the medical equipment to the data acquisition and processing module; the application sets the medical equipment sensor module and the environment monitoring module to monitor the operation state of the medical equipment and environmental parameters in real time, sets the CPU reprocessing module, the remote monitoring communication module and the interactive interface module to comprehensively analyze the preprocessed data, and utilizes a machine learning algorithm and a time sequence algorithm to accurately detect and predict faults.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent medical equipment, in particular to a bidirectional interactive medical equipment intelligent repair system and a use method thereof. BACKGROUND

[0002] The bidirectional interactive medical equipment intelligent repair system improves the efficiency of equipment management, reduces labor costs, and ensures the normal operation of medical equipment through automation and intelligent means, which is an essential way in modern hospital management.

[0003] For example, the application number CN201911393412.5 discloses a bidirectional interactive medical equipment intelligent repair system and a use method thereof, which periodically tests the medical equipment through the tester on the testing device, and autonomously determines whether the medical equipment has failed. When the medical equipment fails, the control center sends a maintenance instruction to the maintenance center, so that the maintenance center dispatches maintenance personnel to repair the medical equipment. Before repairing the medical equipment, the maintenance personnel transmit the fingerprint information of the maintenance personnel to the control center through the maintenance center, and at the same time, the fingerprint information of the maintenance personnel is input through the fingerprint collector on the thumb ring. When the maintenance personnel arrives at the location of the medical equipment, the information confirmation module on the control center compares the two fingerprint information to verify the identity of the maintenance personnel. The metal detector is moved up and down to scan the maintenance personnel, and after confirming that there is no error, the electric control door is automatically opened, and the maintenance personnel can repair the medical equipment. However, there are still defects such as environmental factors interference, network delay or unstable data transmission affecting the repair efficiency.

[0004] The existing technology has the following disadvantages: in actual application, the existing bidirectional interactive medical equipment intelligent repair system may cause inaccurate data collection by sensors or device monitoring data noise due to environmental factors such as electromagnetic interference and changes in temperature and humidity, leading to system misjudgment of device failure and unnecessary repair requests. In addition, the system relies too much on the Internet for data transmission and remote diagnosis, which may cause data transmission delay or interruption, delayed response, and incompatibility of data interfaces and communication protocols between different brands and models of medical equipment, leading to problems in data collection and analysis, and making the system unable to provide expected support at critical moments.

[0005] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] The application aims to provide a bidirectional interactive medical equipment intelligent repair system and a use method thereof.

[0007] To achieve the above-mentioned purpose, the application provides the following technical scheme: a bidirectional interactive medical equipment intelligent repair system, comprising a medical equipment sensor module, a data acquisition and processing module, an environment monitoring module, a CPU reprocessing module, a remote monitoring communication module and an interactive interface module.

[0008] The medical equipment sensor module: continuously monitors the real-time running state of the medical equipment, acquires the original monitoring data of the medical equipment, and sends the acquired original monitoring data of the running state of the medical equipment to the data acquisition and processing module, wherein the original monitoring data includes information of real-time acquisition of the temperature, vibration, current, voltage and running time of the medical equipment.

[0009] The data acquisition and processing module: using a preprocessing algorithm of data cleaning, noise filtering and statistical integration, the original monitoring data in the medical equipment sensor module is preprocessed after being received, preprocessed data is generated, and the processed data is sent to the CPU reprocessing module for noise filtering, abnormal value detection to obtain high-quality data.

[0010] The environment monitoring module: real-time monitoring of the state signal of the environment where the medical equipment is running, obtaining environmental influence parameter data, including environmental temperature, environmental humidity and electromagnetic interference intensity parameter information, and establishing a multivariate analysis model to compensate the environmental influence parameter data for evaluating and correcting the influence of the environmental parameters on the running of the medical equipment, transmitting the environmental influence parameter data to the data acquisition and processing module for preprocessing, and transmitting the algorithm logic of the multivariate analysis model to the CPU reprocessing module for compensation calculation.

[0011] The CPU reprocessing module: receiving and comprehensively analyzing the preprocessed data of the medical equipment sensor module and the environment monitoring module collected by the data acquisition and processing module, using a high-level machine learning algorithm and establishing a time series analysis model for fault detection and prediction, generating fault detection and prediction results, and generating repair requests and alarm information according to the fault detection and prediction results to evaluate the equipment health status.

[0012] Remote monitoring communication module: according to the fault detection and prediction results in the CPU reprocessing module, obtain the analysis results and alarm information, and perform AES encryption processing on the analysis results and alarm information, to ensure the security and integrity of data transmission, real-time transmission and interaction to the interactive interface module of the remote monitoring terminal through the wireless network, to provide real-time data transmission and remote interaction function and support remote monitoring and diagnosis;

[0013] Interactive interface module: establish interface display and user interaction model, use data visualization tools, use remote monitoring communication module to display the medical equipment running state analysis results and alarm information obtained in the CPU reprocessing module, and provide interactive entrance and operation interface for users to realize user input and view medical equipment state, repair information, and can record and store all data and analysis results, provide historical data query and analysis function.

[0014] Optionally, the medical equipment sensor module obtains the original monitoring data as follows:

[0015] In the medical equipment, it is necessary to collect the information of temperature, vibration, current, voltage and running time of the medical equipment in real time, wherein the temperature information collection is through the device internal circuit topology, using thermocouple or thermistor as temperature sensor, directly measuring the analog voltage signal of the internal temperature of the medical equipment during operation, after amplification, filtering and analog-digital conversion ADC processing, the digital signal is obtained, that is, the actual temperature value that the data acquisition processing module can process is obtained, and is calibrated as Tp0;

[0016] The vibration information collection is to use an accelerometer or a piezoelectric sensor to directly measure the analog signal of the vibration amplitude and frequency of the medical equipment, after amplification, filtering and analog-digital conversion ADC processing, the digital signal is obtained, and then the fast Fourier transform FFT algorithm is used to extract the vibration amplitude and frequency characteristic signal that the data acquisition processing module can process, and is calibrated as Vb0;

[0017] The current information collection is to use a Hall effect sensor or a shunt resistor in the internal circuit topology of the medical equipment to directly measure the analog signal of the current passing through the medical equipment, after amplification, filtering and analog-digital conversion ADC processing, the digital signal is obtained, and then the calibration model of the Hall effect or shunt resistor is used to convert the digital signal into the actual current value, and is calibrated as Cr0;

[0018] The voltage information collection is to use a resistor divider as a sensor in the internal circuit topology of the medical equipment to directly measure the voltage analog signal of the medical equipment, after amplification, filtering and analog-digital conversion ADC processing, the digital signal is obtained, and then the calibration curve of the voltage sensor is used to convert the digital signal into the actual voltage value, and is calibrated as Vt0;

[0019] The running time information acquisition is to use a timing circuit in a circuit topology in the medical device, to directly acquire the running time of the medical device by using an accumulated timing algorithm, and to calibrate the running time as Rt0.

[0020] The original monitoring data is calibrated as ID0, and includes information of the temperature Tp0, the vibration Vb0, the current Cr0, the voltage Vt0 and the running time Rt0, i.e. ID0={Tp0, Vb0, Cr0, Vt0, Rt0}.

[0021] Optionally, the acquisition logic of the preprocessed data is as follows:

[0022] The original monitoring data ID0 is subjected to data cleaning and filtering denoising, for removing invalid data, error data and interference signals, wherein the calculation formula of the filtering denoising is In the formula, ID1 represents the output monitoring data after filtering, ID 0N-i represents each data in the input original monitoring data ID0, and N and i respectively represent the filtering window size and the i-th input data in the original monitoring data ID0.

[0023] The data after cleaning and denoising is filled with missing data by using a linear interpolation method, and is smoothed by using a moving average method, for ensuring the continuity of the data and reducing random fluctuations, wherein the calculation formula of the linear interpolation is In the formula, ID 2t represents the interpolation at time t, represents the known filtered output monitoring data ID1 at time t2, represents the known filtered output monitoring data ID1 at time t1, and t2 and t1 respectively represent the times of adjacent known data points; the calculation formula of the moving average is In the formula, ID3 represents the moving average value at time t, represents the data point after interpolation and filling of missing data at time t, and N and i respectively represent the filtering window size and the i-th input data in the original monitoring data ID0.

[0024] The data after filling and smoothing is subjected to Z-score method detection of abnormal values and standardization processing, to obtain high-quality preprocessed data of uniform scale data, calibrated as ID0', for preventing the influence of abnormal data on subsequent analysis, wherein the calculation formula of the Z-score method is In the formula, ID0' represents the preprocessed data obtained by processing the original monitoring data ID0, represents the mean value of the original monitoring data ID0, represents the standard deviation of the original monitoring data ID0.

[0025] Optionally, the environment monitoring module acquires the environment influence parameter data as follows:

[0026] During the operation of the medical device, it is necessary to monitor the parameter signals of the environmental temperature, the environmental humidity and the electromagnetic interference intensity in the environment where the medical device is running, wherein the environmental temperature is an analog signal directly measured by a temperature sensor, which is converted into a digital signal after signal amplification by an operational amplifier and noise filtering by a low-pass filter of the sensor, and the sensor is calibrated for accuracy to obtain an actual environmental temperature signal Tp'0 for transmission;

[0027] The environmental humidity is an analog signal directly measured by a humidity sensor, which is converted into a digital signal after signal amplification by an operational amplifier and noise filtering by a low-pass filter of the sensor, and the sensor is calibrated for accuracy to obtain an actual environmental humidity signal Hm'0 for transmission;

[0028] The electromagnetic interference intensity is an analog signal directly detected by a Hall effect sensor, which is converted into a digital signal after signal amplification by an operational amplifier and noise filtering by a low-pass filter of the sensor, and the sensor is calibrated for accuracy to obtain an actual electromagnetic interference intensity signal Emi'0 for transmission;

[0029] The environment influence parameter data is calibrated as EPD0, and includes the parameter signals of the environmental temperature Tp'0, the environmental humidity Hm'0 and the electromagnetic interference intensity Emi'0, i.e. EPD0={Tp'0, Hm'0, Emi'0}.

[0030] Optionally, the influence evaluation of the environment influence parameter data by the multivariate analysis model is as follows:

[0031] The historical data of the environment influence parameter data EPD0 is collected, and at the same time, the preprocessed data ID0' of the running state of the medical device is collected as a response variable;

[0032] The correlation analysis is used to evaluate the correlation between each environmental parameter and the device running state, and the multivariate analysis model is fitted by using a multiple linear regression algorithm, wherein the calculation formula of the multiple linear regression algorithm is ID0'=β0+β i ×EPD0, and β i ×EPD0=β1×Tp'0+β2×Hm'0+β3×Emi'0, i∈[1,3], wherein β0 represents an intercept, β i represents a regression coefficient corresponding to the environment influence parameter data EPD0, and β1, β2 and β3 represent the regression coefficients of the environmental temperature Tp'0, the environmental humidity Hm'0 and the electromagnetic interference intensity Emi'0, respectively.

[0033] Specifically, the environmental impact parameter data EPD0 is input into the multivariate analysis model, a predicted medical device running state change is output through the model, the influence degree of the environmental parameters on the device running is evaluated, and the compensation amount of the environmental parameters on the device running state is calculated. The running state data of the medical device is corrected through environmental compensation calculation. The calculation formula of the compensation amount is ΔID0' = β1x ΔTp'0 + β2x ΔHm'0 + β3x ΔEmi0', and ID 0′ = ID0' - ΔID0', wherein ΔID0' represents the compensation amount of the environmental impact parameter data EPD0 on the running state ID0' of the medical device, ΔTp'0, ΔHm'0, and ΔEmi0' represent the influence degree of the environmental temperature Tp'0, the environmental humidity Hm'0, and the electromagnetic interference intensity Emi0' in the environmental impact parameter data EPD0 on the running state ID0' of the medical device in the multivariate analysis model, ID0' represents the correction value of applying the compensation amount to the running state ID0' data of the medical device;

[0034] The goodness of fit R 2 and the mean square error MSE value of the multivariate analysis model are re-evaluated to ensure the reliability of the multivariate analysis model. The multivariate analysis model is tested using a verification data set to evaluate the prediction accuracy of the multivariate analysis model, and the parameters of the multivariate analysis model are adjusted according to the verification result to improve the performance of the multivariate analysis model.

[0035] Optionally, the fault detection logic of the machine learning algorithm for the medical device running state is as follows:

[0036] The preprocessed data ID0' is divided into a 70% training set and a 30% test set, and a support vector machine model in the machine learning algorithm is used to input the training set for training. The training calculation formula of the support vector machine model is f(ID0') = w T x ID0' + B0, wherein f(ID0') represents the training result of the preprocessed data ID0', w represents the weight vector of the preprocessed data ID0, T represents the transpose, and B0 represents the bias of the support vector machine;

[0037] The test set is used to evaluate the accuracy performance of the support vector machine model, and the trained support vector machine model is applied to the fault detection of the medical device running state. The fault detection result is output and fault judgment is performed. The calculation formula of the accuracy performance is wherein represents the accuracy rate of the preprocessed data ID0' when performing fault detection, respectively represent the true positive, true negative, false positive, and false negative of the preprocessed data ID0' when performing fault detection.

[0038] When the output of the fault detection result indicates that the current medical equipment has a fault, a repair request and an alarm information are generated, the alarm information is determined using an alarm threshold, and the repair request is generated using the degree diagnosis result of the alarm signal.

[0039] Optionally, the prediction of the running state of the medical equipment by the time series analysis model is as follows:

[0040] The time series data of the preprocessed data ID0' is arranged and preprocessed, time series decomposition and standardization processing are performed, and the calculation formula of the time series standardization processing is In the formula, denotes the time series standardized value of the preprocessed data ID0', denotes the original value of the preprocessed data ID0' at time t, denotes the time series mean value of the preprocessed data ID0', denotes the time series standard deviation of the preprocessed data ID0';

[0041] The time series standardized value of the running state ID0' of the medical equipment is predicted using an autoregressive integrated moving average ARIMA model to generate a prediction result, and the calculation formula of the ARIMA model is In the formula, denotes the prediction value of the time series standardized value at time t, C0denotes the constant of the ARIMA model, λ1, …, λ k respectively denote the autoregressive coefficients of the ARIMA model, respectively denote the moving average coefficients of the ARIMA model, denotes the error term of the time series standardized value at time t, k and m respectively denote the kth and mth moments at time t;

[0042] The model parameters are adjusted using a mean square error loss function to obtain a trained time series analysis model, and the trained time series analysis model is applied to the current medical equipment to predict the running state, and the calculation formula of the mean square error loss function is In the formula, denotes the loss value of the mean square error, denotes the time series standardized true value of the preprocessed data ID0', denotes the prediction value of the time series standardized value, M and j respectively denote the sample quantity of the preprocessed data ID0' and the jth data in the sample;

[0043] By analyzing the prediction output result of the time series prediction model, it is determined whether the medical equipment will fail during operation in the next time period. When the prediction output result indicates that a failure will occur at the next time point, an early warning information is generated.

[0044] Optionally, the analysis result and the alarm information are obtained as follows:

[0045] The fault detection and prediction results are obtained from the CPU reprocessing module, and the timestamp, equipment ID, fault type, and fault severity warranty decision information are extracted from the fault detection and prediction results.

[0046] According to the fault type and severity, the prediction results are classified and labeled, and the time series data that may fail, the predicted future time point, the predicted fault type, the possibility and the severity of the prediction information are extracted.

[0047] The prediction data is analyzed to identify high-risk time points and corresponding fault types, and the alarm information is generated according to the fault detection and prediction results.

[0048] The obtained analysis results and alarm information are arranged into XML data format to be encrypted, an AES key is obtained to encrypt the XML data format, and the encrypted data is transmitted in real time to the interactive interface module of the remote monitoring terminal through the wireless network HTTP protocol.

[0049] The data is decrypted and displayed in the interactive interface module, and the corresponding operation options of confirming the alarm and requesting maintenance are provided.

[0050] Optionally, the processing steps of the interactive interface and the operation interface are as follows:

[0051] A unified data format and communication protocol, i.e. XML data format and wireless communication HTTP protocol, are defined for all medical equipment to ensure compatibility.

[0052] A unified management API gateway and middleware deployed behind the API gateway are set in the two-way interactive medical equipment intelligent repair system to uniformly process interface requests of different medical equipment and convert and process data formats of different equipment to ensure data uniformity.

[0053] An OpenAPI tool is used to define a standardized interface for medical equipment to ensure that all equipment comply with the same interface specification.

[0054] A visual user interface is designed and an intuitive operation portal is provided to display the running status of all medical equipment and the corresponding alarm information.

[0055] Optionally, a method for using a two-way interactive medical equipment intelligent repair system, comprising the following steps:

[0056] S1, real-time monitoring the running state data of the medical equipment through the sensor module of the medical equipment, and monitoring the change parameters of the medical equipment affected by the environment during operation through the environment monitoring module, and transmitting the collected original monitoring data and environmental influence parameter data to the data acquisition and processing module for preprocessing;

[0057] S2, receiving the collected data from the sensor module and the environment monitoring module of the medical equipment, and after the preliminary processing of data cleaning, filtering and denoising, and standardization of the original monitoring data and environmental influence parameter data, obtaining preprocessed data, and transmitting to the CPU reprocessing module for further analysis;

[0058] S3, the CPU reprocessing module is used for comprehensive analysis of the data to detect faults and predict the state of the medical equipment during operation, and generate fault detection and prediction results, and further generate repair request and alarm information;

[0059] S4, obtaining the analysis results and alarm information in the CPU reprocessing module, converting them into XML data format and performing AES encryption processing, and then transmitting them to the interactive interface module of the remote monitoring terminal through the wireless network HTTP protocol to display the data;

[0060] S5, the user interacts on the interactive interface module of the remote monitoring terminal according to the provided user interaction entrance and operation interface, combines the displayed running state of the medical equipment, fault detection results and alarm information, including viewing the device state and alarm information, and submits a maintenance request, at the same time, the maintenance personnel receives the repair request, handles the fault, and feeds back the processing result.

[0061] In the above technical solution, the technical effects and advantages provided by the present application are as follows:

[0062] The present application provides a medical equipment sensor module and an environment monitoring module, which can real-time monitor the running state and environmental parameters of the medical equipment, and a CPU reprocessing module, a remote monitoring communication module and an interactive interface module are provided to comprehensively analyze the preprocessed data, and machine learning algorithm and time series algorithm are used for accurate fault detection and prediction, ensuring the safety and integrity of data transmission, and the intelligent repair of medical equipment is more accurate, not only shortening the fault handling time and improving the maintenance efficiency, but also reducing the equipment downtime, further realizing the functions of real-time monitoring, data processing, remote monitoring, user interaction and fault warning of medical equipment, and improving the safety, maintenance efficiency and user experience of medical equipment. BRIEF DESCRIPTION OF DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only represent some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained based on these drawings.

[0064] Figure 1 A module schematic diagram of the bidirectional interactive medical equipment intelligent repair system of the present application.

[0065] Figure 2 A use method flow chart of the bidirectional interactive medical equipment intelligent repair system of the present application. DETAILED DESCRIPTION

[0066] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these example implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example implementations to those skilled in the art.

[0067] Example 1

[0068] The present application provides a bidirectional interactive medical equipment intelligent repair system as shown in Figure 1 The bidirectional interactive medical equipment intelligent repair system comprises a medical equipment sensor module, a data acquisition and processing module, an environment monitoring module, a CPU reprocessing module, a remote monitoring communication module and an interactive interface module.

[0069] The medical equipment sensor module continuously monitors the real-time running state of the medical equipment, acquires the original monitoring data of the medical equipment, and sends the acquired original monitoring data of the running state of the medical equipment to the data acquisition and processing module. The original monitoring data includes information of real-time acquisition of temperature, vibration, current, voltage and running time of the medical equipment.

[0070] Specifically, the steps of acquiring the original monitoring data by the medical equipment sensor module are as follows:

[0071] In the medical equipment, the information of temperature, vibration, current, voltage and running time of the medical equipment needs to be acquired in real time. Among them, the temperature information acquisition is through the device internal circuit topology, using a thermocouple or a thermistor as a temperature sensor to directly measure the analog voltage signal of the internal temperature of the medical equipment during operation, and after amplification, filtering and analog-to-digital conversion ADC processing, a digital signal is obtained, that is, the actual temperature value that can be processed by the data acquisition and processing module is obtained, and is calibrated as Tp0.

[0072] The vibration information collection is to directly measure the vibration amplitude and frequency of the medical device using an accelerometer or a piezoelectric sensor to obtain an analog signal, and after amplification, filtering and analog-to-digital conversion ADC processing, a digital signal is obtained, and then using a fast Fourier transform FFT algorithm, the vibration amplitude and frequency characteristic signals that the data acquisition and processing module can process are extracted, and are calibrated as Vb0;

[0073] The current information collection is to directly measure the current through the medical device using a Hall effect sensor or a shunt resistor in the circuit topology structure of the medical device to obtain an analog signal, and after amplification, filtering and analog-to-digital conversion ADC processing, a digital signal is obtained, and then using the calibration model of the Hall effect or the shunt resistor, the digital signal is converted into an actual current value, and is calibrated as Cr0;

[0074] The voltage information collection is to directly measure the voltage of the medical device using a resistor divider as a sensor in the circuit topology structure of the medical device to obtain an analog signal, and after amplification, filtering and analog-to-digital conversion ADC processing, a digital signal is obtained, and then using the calibration curve of the voltage sensor, the digital signal is converted into an actual voltage value, and is calibrated as Vt0;

[0075] The running time information collection is to directly obtain the running time of the medical device using a timing circuit in the circuit topology structure of the medical device, and using an accumulated timing algorithm, and is calibrated as Rt0.

[0076] The original monitoring data is calibrated as ID0, and includes the information of temperature Tp0, vibration Vb0, current Cr0, voltage Cr0 and running time Rt0, i.e. ID0={Tp0, Vb0, Cr0, Vt0, Rt0}.

[0077] The data acquisition and processing module: using the preprocessing algorithm of data cleaning, noise filtering and statistical integration, the original monitoring data in the medical device sensor module received is preprocessed to generate preprocessed data, and the processed data is sent to the CPU reprocessing module for noise filtering and abnormal value detection to obtain high-quality data.

[0078] Specifically, the acquisition logic of the preprocessed data is as follows:

[0079] The original monitoring data ID0 is cleaned and filtered to remove invalid data, error data and interference signals, wherein the calculation formula of the filtering and denoising is In the formula, ID1 represents the output monitoring data after filtering, ID 0N-i represents each data in the input original monitoring data ID0, and N and i respectively represent the filter window size and the i-th input data in the original monitoring data ID0.

[0080] The cleaned and denoised data is filled with missing data using linear interpolation method and smoothed using moving average method to ensure data continuity and reduce random fluctuations, wherein the calculation formula of linear interpolation is ID3= (ID1+ ID2) / 2 2t ID2= ID0 (t2) is the known filtered output monitoring data at time t2, ID2= ID0 (t2) is the known filtered output monitoring data at time t2, ID2= ID0 (t2) is the known filtered output monitoring data at time t2, ID3= (ID1+ ID2) / 2 ID2= ID0 (t2) is the known filtered output monitoring data at time t2,

[0081] The filled and smoothed data is further detected for abnormal values and standardized using Z-score method to obtain high-quality preprocessed data of uniform scale, labeled as ID0', to prevent the influence of abnormal data on subsequent analysis, wherein the calculation formula of Z-score method is ID0'= (ID0- μ) / σ μ= (ID0+ ID0+ ID0+ ID0+ ID0) / 5 σ= (ID0- ID0- ID0- ID0- ID0) / 5

[0082] The environmental monitoring module monitors the state signals of the environment in which the medical device is running in real time, obtains environmental influence parameter data including parameter information of environmental temperature, environmental humidity and electromagnetic interference intensity, establishes a multivariate analysis model, performs compensation calculation on the environmental influence parameter data to evaluate and correct the influence of the environmental parameters on the operation of the medical device, transmits the environmental influence parameter data to the data acquisition and processing module for preprocessing, and transmits the algorithm logic of the multivariate analysis model to the CPU reprocessing module for compensation calculation.

[0083] Specifically, the steps of obtaining environmental influence parameter data by the environmental monitoring module are as follows:

[0084] During the operation of the medical device, the parameter signals of environmental temperature, environmental humidity and electromagnetic interference intensity in the environment in which the medical device is running need to be monitored in real time, wherein the environmental temperature is an analog signal directly measured by a temperature sensor, which is converted into a digital signal after signal amplification by an operational amplifier and noise filtering by a low-pass filter built-in the sensor, and the sensor is calibrated for precision to obtain the actual environmental temperature signal for transmission, labeled as Tp'0;

[0085] The environmental humidity is an analog signal of the environmental humidity directly measured by a humidity sensor, which is converted into a digital signal after signal amplification by an operational amplifier and noise filtering by a low-pass filter of the sensor, and the sensor is calibrated for precision to obtain an actual environmental humidity signal for transmission, which is calibrated as Hm'0.

[0086] The electromagnetic interference intensity is an analog signal of the electromagnetic interference intensity of the medical device in the environment directly detected by a Hall effect sensor, which is converted into a digital signal after signal amplification by an operational amplifier and noise filtering by a low-pass filter of the sensor, and the sensor is calibrated for precision to obtain an actual electromagnetic interference intensity signal for transmission, which is calibrated as Emi'0.

[0087] The environmental impact parameter data is calibrated as EPD0, and the parameter signals of the environmental temperature Tp'0, the environmental humidity Hm'0, and the electromagnetic interference intensity Emi'0 are included, i.e., EPD0={Tp'0, Hm'0, Emi'0}.

[0088] Specifically, the influence evaluation step of the multivariate analysis model on the environmental impact parameter data is as follows:

[0089] The historical data of the environmental impact parameter data EPD0 is collected, and at the same time, the preprocessed data ID0' of the running state of the medical device is collected as a response variable;

[0090] The correlation analysis is used to evaluate the correlation between each environmental parameter and the running state of the device, and the multivariate analysis model is fitted by using a multiple linear regression algorithm, wherein the calculation formula of the multiple linear regression algorithm is ID0'=β0+β i ×EPD0, and β i ×EPD0=β1×Tp'0+β2×Hm'0+β3×Emi'0, i∈[1,3], wherein β0 represents an intercept, β i represents a regression coefficient corresponding to the environmental impact parameter data EPD0, β1, β2, and β3 represent regression coefficients of the environmental temperature Tp'0, the environmental humidity Hm'0, and the electromagnetic interference intensity Emi'0, respectively;

[0091] Specifically, the environmental impact parameter data EPD0 is input into the multivariate analysis model, the predicted change of the running state of the medical device is output by the model, the influence degree of the environmental parameter on the running of the device is evaluated, the compensation amount of the environmental parameter on the running state of the device is calculated, the running state data of the medical device is corrected by the environmental compensation calculation, and the calculation formula of the compensation amount is ΔID0'=β1×ΔTp'0+β2×ΔHm'0+β3×ΔEmi'0, and ID0'= ID0'- ΔID0', wherein ΔID0' represents a compensation amount of the environmental impact parameter data EPD0 to the operation state ID0' of the medical device, ΔTp'0, ΔHm'0, and ΔEmi0' represent degrees of influence of the environmental temperature Tp'0, the environmental humidity Hm'0, and the electromagnetic interference intensity Emi0' in the environmental impact parameter data EPD0 to the operation state ID0' of the medical device in the multivariate analysis model, ID0' represents a correction value of applying the compensation amount to the operation state ID0' data of the medical device;

[0092] re-evaluating the goodness of fit R of the multivariate analysis model 2 and the mean square error MSE value, for ensuring the reliability of the multivariate analysis model, and testing the multivariate analysis model using the verification data set, evaluating the prediction accuracy of the multivariate analysis model, and adjusting the parameters of the multivariate analysis model according to the verification result to improve the performance of the multivariate analysis model.

[0093] The CPU reprocessing module receives and comprehensively analyzes the preprocessed data and the environmental impact parameter data collected by the data acquisition and processing module from the sensor module of the medical device and the environmental monitoring module, uses a high-level machine learning algorithm and establishes a time series analysis model for fault detection and prediction, generates fault detection and prediction results, and generates repair requests and alarm information according to the fault detection and prediction results to evaluate the health status of the device.

[0094] Specifically, the fault detection logic of the machine learning algorithm for the operation state of the medical device is as follows:

[0095] The preprocessed data ID0' is divided into a 70% training set and a 30% test set, and a support vector machine model in the machine learning algorithm is used to input the training set for training, wherein the training calculation formula of the support vector machine model is f(ID0') = w T × ID0' + B0, wherein f(ID0') represents the training result of the preprocessed data ID0', w represents the weight vector of the preprocessed data ID0', T represents the transpose, and B0 represents the bias of the support vector machine;

[0096] The test set is used to evaluate the accuracy performance of the support vector machine model, and the trained support vector machine model is applied to the fault detection of the operation state of the medical device, and the fault detection result is output and fault judgment is performed, and the calculation formula of the accuracy performance is wherein represents the accuracy of the preprocessed data ID0' when performing fault detection, respectively represent the true positive, true negative, false positive, and false negative of the preprocessed data ID0' when performing fault detection;

[0097] When the output of the fault detection result indicates that the current medical equipment has a fault, a repair request and an alarm information are generated, the alarm information is determined using an alarm threshold, and the repair request is generated using the degree diagnosis result of the alarm signal.

[0098] Specifically, the prediction step of the time series analysis model for the running state of the medical equipment is as follows:

[0099] The time series data of the preprocessed data ID0' is arranged and preprocessed, time series decomposition and standardization processing are performed, and the calculation formula of the time series standardization processing is In the formula, denotes the time series standardized value of the preprocessed data ID0', denotes the original value of the preprocessed data ID0' at time t, denotes the time series mean value of the preprocessed data ID0', denotes the time series standard deviation of the preprocessed data ID0';

[0100] The time series standardized value of the running state of the medical equipment ID0' is predicted using an autoregressive integrated moving average ARIMA model , and a prediction result is generated, and the calculation formula of the ARIMA model is In the formula, denotes the prediction value of the time series standardized value at time t, C0denotes the constant of the ARIMA model, λ1,..., λ k denote the autoregressive coefficients of the ARIMA model, denote the moving average coefficients of the ARIMA model, denotes the error term of the time series standardized value at time t, k, m denote the kth and mth moments at time t;

[0101] The model parameters are adjusted using the mean square error loss function to obtain a trained time series analysis model, and the trained time series analysis model is applied to the current medical equipment to predict the running state, and the calculation formula of the mean square error loss function is In the formula, denotes the loss value of the mean square error, denotes the time series standardized true value of the preprocessed data ID0', denotes the prediction value of the time series standardized value, M, j denote the sample size and the jth data in the sample of the preprocessed data ID0', respectively;

[0102] By analyzing the prediction output result of the time series prediction model, it is judged whether the medical equipment will fail in the running process in the next time period. When the prediction output result shows that a failure will occur at the next time point, an early warning information is generated.

[0103] The remote monitoring communication module: according to the fault detection and prediction results in the CPU reprocessing module, the analysis results and alarm information are obtained and AES encryption processing is performed on the analysis results and alarm information, which is used to ensure the security and integrity of data transmission. Real-time transmission and interaction to the interactive interface module of the remote monitoring terminal through wireless network is used to provide real-time data transmission and remote interaction function and support remote monitoring and diagnosis.

[0104] Specifically, the analysis results and alarm information are obtained as follows:

[0105] The fault detection and prediction results are obtained from the CPU reprocessing module, and the timestamp, device ID, fault type, and fault severity warranty decision information are extracted from the fault detection and prediction results;

[0106] According to the fault type and severity, classification and labeling are performed, the prediction results are analyzed, and the time series data that may fail, the predicted future time point, the predicted fault type, the possibility and the severity of the prediction information are extracted;

[0107] The prediction data is analyzed, the high-risk time point and the corresponding fault type are identified, and the alarm information is generated according to the fault detection and prediction results;

[0108] The obtained analysis results and alarm information are arranged into XML data format to be encrypted, an AES key is obtained, the XML data format is encrypted, and then transmitted to the interactive interface module of the remote monitoring terminal through wireless network HTTP protocol in real time;

[0109] The data is decrypted and displayed and interacted in the interactive interface module, and the corresponding operation options of confirming the alarm and requesting the repair are provided.

[0110] The interactive interface module: an interface display and user interaction model is established, a data visualization tool is used, the medical equipment running state analysis results and alarm information obtained from the CPU reprocessing module are displayed, and an interactive entrance and operation interface are provided for the user to input and view the medical equipment state and repair information, and all data and analysis results can be recorded and stored to provide historical data query and analysis function.

[0111] Specifically, the processing steps of the interactive entrance and operation interface are as follows:

[0112] A uniform data format and communication protocol, namely XML data format and wireless communication HTTP protocol, are defined for all medical devices to ensure compatibility;

[0113] A uniform management API gateway and middleware deployed behind the API gateway are set in the bidirectional interactive medical device intelligent repair system to uniformly process interface requests of different medical devices and convert and process data formats of different devices to ensure data uniformity.

[0114] An OpenAPI tool is used to define a standardized interface for medical devices to ensure that all devices follow the same interface specification.

[0115] A visual user interface is designed and intuitive operation entry is provided to display the running status of all medical devices and corresponding alarm information.

[0116] Embodiment 2

[0117] The present application provides a use method of a bidirectional interactive medical device intelligent repair system as shown in Figure 2 The use method comprises the following steps:

[0118] S1, real-time monitoring the running state data of the medical device through the sensor module of the medical device, and monitoring the change parameters of the medical device affected by the environment during operation through the environment monitoring module, and transmitting the collected original monitoring data and environmental influence parameter data to the data acquisition and processing module for preprocessing;

[0119] S2, receiving the collected data from the sensor module and the environment monitoring module of the medical device, performing data cleaning, filtering and denoising, and standardization preliminary processing on the original monitoring data and environmental influence parameter data to obtain preprocessed data, and transmitting the preprocessed data to the CPU reprocessing module for further analysis;

[0120] S3, comprehensively analyzing the data through the CPU reprocessing module to detect the faults and predict the state of the medical device during operation, and generating fault detection and prediction results, and further generating repair requests and alarm information;

[0121] S4, obtaining the analysis results and alarm information in the CPU reprocessing module, converting them into XML data format and performing AES encryption processing, and then transmitting them to the interactive interface module of the remote monitoring terminal through the wireless network HTTP protocol to display the data;

[0122] S5, the user interacts on the interactive interface module of the remote monitoring terminal according to the provided user interaction entrance and operation interface, combines the display of the running state of the medical equipment, the fault detection result and the alarm information to interact, including checking the equipment state and the alarm information, and submitting a maintenance request, at the same time, the maintenance personnel receive the repair request, handle the fault, and feedback the processing result.

[0123] The use method of the bidirectional interactive medical equipment intelligent repair system provided by the embodiment of the application is realized by the bidirectional interactive medical equipment intelligent repair system, and the specific method and process of the use method of the bidirectional interactive medical equipment intelligent repair system are described in the embodiment of the bidirectional interactive medical equipment intelligent repair system, which will not be described here.

[0124] The above formulas are all dimensionless values, and the formulas are obtained by software simulation of a large amount of data to obtain a formula of the nearest real situation, and the preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0125] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized in the form of a computer program product wholly or partially. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another by wire or wireless (such as infrared, wireless, microwave, etc.). The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center and the like containing one or more available medium sets. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD) or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0126] It should be understood that in various embodiments of the application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the application.

[0127] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0128] The above description is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A two-way interactive medical equipment intelligent repair system, characterized in that, The medical device sensor module, the data acquisition and processing module, the environment monitoring module, the CPU reprocessing module, the remote monitoring communication module and the interactive interface module are included. The medical device sensor module continuously monitors the real-time running state of the medical device, acquires the original monitoring data of the medical device, and sends the acquired original monitoring data of the running state of the medical device to the data acquisition and processing module. The data acquisition and processing module uses data cleaning, noise filtering and statistical integration preprocessing algorithms to preprocess the original monitoring data received in the medical device sensor module, generates preprocessed data, and sends the processed data to the CPU reprocessing module. The environment monitoring module monitors the state signal of the environment in which the medical device is running in real time, obtains environmental influence parameter data, establishes a multivariate analysis model, and performs compensation calculation on the environmental influence parameter data to evaluate and correct the influence of the environmental parameters on the running of the medical device. The environmental influence parameter data is transmitted to the data acquisition and processing module for preprocessing, and the algorithm logic of the multivariate analysis model is transmitted to the CPU reprocessing module for compensation calculation. The CPU reprocessing module receives and comprehensively analyzes the preprocessed data of the medical device sensor module and the environment monitoring module, uses high-level machine learning algorithms and establishes a time series analysis model for fault detection and prediction, and generates fault detection and prediction results. The remote monitoring communication module obtains analysis results and alarm information according to the fault detection and prediction results in the CPU reprocessing module, performs AES encryption processing on the analysis results and alarm information, and transmits and interacts the results to the interactive interface module of the remote monitoring terminal in real time through a wireless network. The interactive interface module establishes an interface display and user interaction model, uses data visualization tools, displays the medical device running state analysis results and alarm information obtained from the CPU reprocessing module through the remote monitoring communication module, and provides an interactive entrance and operation interface for users. It can record and store all data and analysis results, and provide historical data query and analysis functions. The influence evaluation step of the multivariate analysis model on the environmental influence parameter data is as follows: Collect environmental impact parameter data At the same time, the operating status of medical equipment is collected and pre-processed data is collected. , as the response variable; The correlation analysis is used to evaluate the correlation between each environmental parameter and the equipment operation state, and a multivariate analysis model is fitted using a multivariate linear regression algorithm, wherein a calculation formula of the multivariate linear regression algorithm is , and , wherein is an intercept, is a regression coefficient corresponding to environmental influence parameter data , and , respectively, are regression coefficients of environmental temperature , environmental humidity , and electromagnetic interference intensity . Specifically, the environmental impact parameter data The input multivariate analysis model, through the model output predicted medical equipment running state changes, assesses the degree of influence of the environmental parameters on the equipment operation, while calculating the compensation amount of the environmental parameters on the equipment running state, and correcting the running state data of the medical equipment through environmental compensation calculation. The calculation formula of the compensation amount is , and , wherein The compensation amount for the running state of the medical equipment is represented by the environmental impact parameter data The compensation amount for the running state of the medical equipment is represented by the environmental impact parameter data The environmental temperature , the environmental humidity , and the electromagnetic interference intensity The degree of influence of the environmental parameters on the running state of the medical equipment in the multivariate analysis model, The correction value for applying the compensation amount to the running state data of the medical equipment is represented by the environmental impact parameter data The fitting goodness R² and mean square error MSE values of the multivariate analysis model are re-evaluated, and the multivariate analysis model is tested using a validation data set to evaluate the prediction accuracy of the multivariate analysis model. The fault detection logic of the machine learning algorithm for the running state of the medical device is as follows: Preprocess the data The training set is divided into 70% and the test set is divided into 30%. The support vector machine model in the machine learning algorithm is used to input the training set for training. The training calculation formula of the support vector machine model is: , where Represented as preprocessed data The training results, Represented as preprocessed data The weight vector of Represented as transpose, Expressed as the bias of the support vector machine; The accuracy performance of the support vector machine model is evaluated using the test set, and the trained support vector machine model is applied to the fault detection of the medical device running state, and the fault detection result is output and fault judgment is performed. The calculation formula of the accuracy performance is , wherein is the preprocessed data The accuracy when performing fault detection, is the preprocessed data The true positive, true negative, false positive and false negative when performing fault detection; When the output of the fault detection result indicates that the current medical device has a fault, a repair request and an alarm information are generated. The alarm information is determined using an alarm threshold, and the repair request is generated using a degree diagnosis result customized for the alarm signal. The prediction step of the time series analysis model for the running state of the medical device is as follows: Organize and preprocess data Time series data is decomposed and standardized using the time series decomposition and standardization calculation formula of the time series standardization is: , where Represented as preprocessed data The time series normalized value of Expressed as time Preprocess data The original value of Represented as preprocessed data The time series mean of Represented as preprocessed data The time series standard deviation of Then use the autoregressive integrated moving average ARIMA model to analyze the operating status of medical equipment Time series normalized values Make predictions and generate prediction results. The calculation formula of the ARIMA model is: , where Expressed as time Normalized value of the time series The predicted value of Expressed as ARIMA model constant, They are respectively represented as the autoregressive coefficients of the ARIMA model, They are respectively expressed as the sliding mean coefficients of the ARIMA model, Expressed as time Normalized value of the time series The error term, Respectively expressed as time On the time; The model parameter is adjusted by using a mean square error loss function to obtain a trained time series analysis model, and the trained time series analysis model is applied to the current medical equipment to predict the running state. A calculation formula of the mean square error loss function is , wherein represents a loss value of the mean square error, represents a time series standardized value of the preprocessed data , represents a predicted value of the time series standardized value , respectively represents a sample quantity of the preprocessed data and a data in the sample . By analyzing the prediction output result of the time series prediction model, it is determined whether the medical device will fail in the next time period during operation. When the prediction output result indicates that a fault will occur at the next time point, a warning information is generated.

2. The two-way interactive medical device intelligent repair system according to claim 1, wherein, The medical device sensor module acquires the raw monitoring data as follows: In medical devices, it is necessary to collect information of temperature, vibration, current, voltage and running time of the medical device in real time, wherein the temperature information collection is through the circuit topology in the device, using thermocouple or thermistor as temperature sensor, directly measuring the analog voltage signal of the internal temperature of the medical device during operation, after amplification, filtering and analog-digital conversion ADC processing, obtaining digital signal, that is, obtaining the actual temperature value that the data acquisition processing module can process, and calibrating to ; The vibration information collection is to directly measure the analog signal of the vibration amplitude and frequency of the medical equipment by using the accelerometer or piezoelectric sensor, to obtain the digital signal after amplification, filtering and analog-digital conversion ADC processing, and to extract the vibration amplitude and frequency characteristic signal capable of being processed by the data collection and processing module by using the fast Fourier transform FFT algorithm, and to calibrate it as ; Current information acquisition is to use Hall effect sensor or shunt resistor in the circuit topology of medical device, directly measure the analog signal of current through the medical device, get digital signal after amplification, filtering and analog-digital conversion ADC processing, and then convert the digital signal to actual current value by using the calibration model of Hall effect or shunt resistor, and calibrate it to ; Voltage information collection is to use a resistance voltage divider as a sensor in the circuit topology of a medical device, directly measure the voltage analog signal of the medical device, obtain a digital signal after amplification, filtering and analog-digital conversion ADC processing, and then convert the digital signal to an actual voltage value by using the calibration curve of the voltage sensor, and calibrate it to ; The runtime information acquisition is to use a timing circuit in the circuit topology in the medical device, adopt an accumulated timing algorithm to directly acquire the runtime of the medical device, and calibrate it to ; The original monitoring data is calibrated as , and includes information of temperature , vibration , current , voltage and running time , i.e. .

3. The two-way interactive medical device intelligent repair system according to claim 2, wherein, The pre-processing data acquisition logic is as follows: The original monitoring data Data cleaning and filtering denoising are performed, and a calculation formula of the filtering denoising is , wherein, is the filtered output monitoring data, is the input original monitoring data , and each data in the original monitoring data is respectively represented as the filtering window size and the first input data in the original monitoring data . The cleaned and denoised data is used to fill missing data using linear interpolation and smooth the data using moving average method. The calculation formula of linear interpolation is: , where Expressed as time The interpolation of Expressed as time The output monitoring data after known filtering , Expressed as time The output monitoring data after known filtering , are respectively represented as the time of adjacent known data points; the calculation formula for the moving average is , where Expressed as time The moving average of Expressed as time The data points after interpolation are Represented as the filter window size and original monitoring data respectively The Input data; The data after the supplement and smoothing is detected for abnormal values and normalized by using a Z-score method to obtain high-quality preprocessed data of uniform scale, and is calibrated as The calculation formula of the Z-score method is , wherein, is the mean value of the original monitoring data is the standard deviation of the original monitoring data is the mean value of the original monitoring data is the standard deviation of the original monitoring data is the mean value of the original monitoring data is the standard deviation of the original monitoring data 4. The two-way interactive medical device intelligent repair system of claim 3, wherein, The environmental monitoring module acquires environmental impact parameter data as follows: In the operation of medical equipment, it is necessary to monitor the parameter signals of environmental temperature, environmental humidity and electromagnetic interference intensity in the environment where the medical equipment is running in real time. The environmental temperature is an analog signal directly measured by a temperature sensor, is converted into a digital signal after signal amplification by an operational amplifier and noise filtering processing by a low-pass filter of the sensor, and the sensor is calibrated for precision to obtain the actual environmental temperature signal for transmission, which is calibrated as ; The environmental humidity is an analog signal directly measured by a humidity sensor, which is converted into a digital signal after signal amplification by an operational amplifier and noise filtering by a low-pass filter, and the sensor is calibrated for precision to obtain the actual environmental humidity signal for transmission, which is calibrated as ; The electromagnetic interference intensity is an analog signal directly detected by using a Hall effect sensor to detect the electromagnetic interference intensity of the medical equipment in the environment, is amplified by an operational amplifier, is filtered by a low-pass filter of the sensor, is converted into a digital signal, and is calibrated for precision to obtain an actual electromagnetic interference intensity signal transmitted, and is calibrated as ; The environmental impact parameter data is calibrated as , and includes parameter signals of the environmental temperature , the environmental humidity , and the electromagnetic interference intensity , i.e. .

5. The two-way interactive medical device intelligent repair system according to claim 4, wherein, The analysis result and alarm information acquisition steps are as follows: From the CPU reprocessing module, obtain fault detection and prediction results, and extract time stamp, device ID, fault type, and fault severity from the fault detection and prediction results to determine warranty information; According to the fault type and severity, classify and label, analyze the prediction results, and extract time series data that may fail, predicted future time points, predicted fault types, and possibility and severity prediction information; And analyze the prediction data to identify high-risk time points and corresponding fault types, and generate alarm information based on the fault detection and prediction results; The obtained analysis results and alarm information are arranged into XML data format to be encrypted, an AES key is obtained to encrypt the XML data format, and the encrypted data is transmitted in real time to the interactive interface module of the remote monitoring terminal through the wireless network HTTP protocol; Decrypt the data in the interactive interface module and display and interact with it, and provide corresponding operation options for confirming the alarm and requesting maintenance.

6. The two-way interactive medical device intelligent repair system according to claim 5, wherein, The processing steps of the interactive interface and operation interface are as follows: Define a unified data format and communication protocol for all medical devices, i.e., XML data format and wireless communication HTTP protocol; Set up a unified management API gateway and deploy middleware behind the API gateway in the two-way interactive medical device intelligent repair system; Use OpenAPI tools to define standardized interfaces for medical devices; Design a visual user interface and provide an intuitive operation portal that can display the running status of all medical devices and corresponding alarm information.

7. A method for using a two-way interactive medical equipment intelligent repair system, which is implemented by the two-way interactive medical equipment intelligent repair system according to any one of claims 1-6, characterized in that, The steps include: The steps include: S1, real-time monitor the running status data of the medical device through the sensor module of the medical device, and monitor the change parameters of the medical device affected by the environment during operation through the environmental monitoring module, and transmit the acquired raw monitoring data and environmental impact parameter data to the data acquisition and processing module for preprocessing; S2, receive the collected data from the sensor module and environmental monitoring module of the medical device, and after data cleaning, filtering and denoising, and standardization of the raw monitoring data and environmental impact parameter data, obtain pre-processed data, and transmit to the CPU reprocessing module for further analysis; S3, comprehensively analyze the data through the CPU reprocessing module to detect faults and predict the state of the medical device during operation, and generate fault detection and prediction results, and further generate repair requests and alarm information; S4, obtain the analysis results and alarm information in the CPU reprocessing module, convert them into XML data format and perform AES encryption processing, and then transmit them to the interactive interface module of the remote monitoring terminal through the wireless network HTTP protocol to display the data; S5, the user interacts on the interactive interface module of the remote monitoring terminal according to the provided user interaction entrance and operation interface, combines the display of the running state of the medical equipment, the fault detection result and the alarm information to interact, including checking the equipment state and the alarm information, and submitting a maintenance request, at the same time, the maintenance personnel receives the repair request, handles the fault, and feeds back the processing result.

Images