A Big Data-Based Intelligent Monitoring System and Method for Medical Equipment Service Status

Abstract

The application discloses a kind of medical equipment service state intelligent monitoring system and method based on big data, it is related to medical equipment monitoring technical field, through the corresponding relationship of the fault information of medical equipment in medical equipment fault maintenance record and fault finding process, establish fault project database, when feedback normal value information in medical equipment is in the time that does not use state satisfies time threshold or medical equipment enables prediction value satisfies condition threshold, medical equipment is detected, by comparing with fault project database, the steps of obtaining detection abnormal feedback, the fault type of judging abnormal feedback, after medical equipment receives enable information, the operating state of each component of medical equipment is tested, the stability of each component operating state is calculated, and the component of unstable operating state is alarmed, whether the safety protection device in medical equipment is enabled is detected, and the safety protection device without enabling is alarmed.

Description

Technical Field

[0001] This invention relates to the field of medical equipment monitoring technology, specifically to an intelligent monitoring system and method for the service status of medical equipment based on big data. Background Technology

[0002] Medical equipment refers to medical instruments used for diagnosis and treatment, designed to obtain information about the human body and provide certain effects. Primarily targeting patients, these devices often operate in a restricted, vulnerable, or even unconscious state, rendering them unaware of potential dangers during treatment. Therefore, when monitoring the condition of medical equipment, its safety is as crucial as its effectiveness. Common safety issues with medical equipment include electrical leaks, fluid leaks, and gas leaks.

[0003] With technological advancements, devices undergo system self-testing processes before entering operational status, such as the Power On Self Test (POST). This refers to the testing of components like the CPU, motherboard, basic memory, extended memory, and system ROM BIOS after a computer system is powered on. If errors are detected, the system provides prompts or warnings to the operator. However, these self-testing processes often lack checks on the safety of the device's hardware. Therefore, even after a system self-test in medical equipment, the safety of the medical device cannot be guaranteed. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent monitoring system and method for the service status of medical devices based on big data, so as to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a method for intelligent monitoring of the service status of medical equipment based on big data, the method comprising:

[0006] Step S100: Obtain fault repair records from the historical operation and maintenance data of medical equipment, and establish a fault item database by matching the fault information of medical equipment with the fault finding process in the fault repair records;

[0007] Step S200: Detect and feedback normal value information. When the time that the medical device is in an unused state meets the time threshold or the predicted value of the medical device being activated meets the condition threshold, the medical device is detected.

[0008] Step S300: Obtain abnormal feedback information during the medical equipment testing process, compare it with the fault item database, obtain the steps for abnormal feedback, execute the steps, and determine the fault type of the abnormal feedback;

[0009] Step S400: After the medical device receives the activation information, the operating status of each component of the medical device is tested, the stability of the operating status of each component is calculated, and an alarm is issued for components with unstable operating status.

[0010] Step S500: Detect whether the safety protection devices in the medical device are enabled, and issue an alarm for any disabled safety protection devices.

[0011] Furthermore, step S100 includes:

[0012] Step S101: Obtain the records of equipment maintenance personnel searching for faults in the historical operation and maintenance data of medical equipment. In the records of equipment maintenance personnel searching for faults, obtain the detection steps of the maintenance personnel in detecting faults in medical equipment, and obtain the detection items included in each fault detection step and the detection process corresponding to each detection item.

[0013] Step S102: Obtain the detection process information for each detection process. One detection process information includes: the detection signal of the equipment maintenance personnel, the detection location, the detection feedback location, and the detection feedback result. The detection feedback result includes: normal detection feedback information and abnormal detection feedback information. The normal detection feedback information represents the range of values ​​when the detection feedback location is in normal feedback. The abnormal detection feedback information represents the difference between the abnormal value and the range of values ​​when the detection feedback location is abnormal.

[0014] The detection record of a device fault includes several fault detection steps, and each fault detection step includes several detection items. To detect a certain detection item, a detection signal needs to be input at the signal input terminal of the component. The output signal of the corresponding signal output terminal is detected at the signal input terminal, and the normality of the detection item is determined based on the output signal.

[0015] Step S103: Record the fault finding process and the corresponding detection process information of the medical equipment fault information, and collect all records to establish a fault item database.

[0016] Furthermore, step S200 includes:

[0017] Step S201: Obtain the maintenance records in time period T0 from the historical maintenance records of the medical equipment. Extract the number of fault detection steps, fault maintenance time, and interval with the next fault maintenance record from each fault maintenance record in time period T0. Calculate the fault maintenance index for each historical fault. The fault maintenance index for the b-th fault maintenance record in time period T0 is IN. b IN b =(n b / T b1 ) × Tb2 , where n b T represents the number of testing steps performed by the maintenance personnel in the fault repair record corresponding to the b-th fault repair record. b1 T represents the fault repair time corresponding to the b-th fault repair record. b2 This indicates the time interval between the b-th fault repair record and the next fault repair record;

[0018] Step S202: Sum the m fault maintenance indices corresponding to the m fault repair records in time period T0 to obtain the total fault maintenance index IN0 for time period T0, and calculate the time threshold T. sc T sc = γ*IN0 / m, where γ is the time conversion coefficient;

[0019] For example, if there are m+1 maintenance records in the T0 time period, the first m maintenance records are taken for operation and maintenance index calculation according to the time order. Since the interval between the m+1th maintenance record and the next fault maintenance record is unknown, the operation and maintenance index is not calculated for the m+1th maintenance record.

[0020] Step S203: Obtain all patient treatment records of a certain department in the hospital, set a medical device in the department as the target device, set the patients treated by medical staff using the target device as the target patients, obtain the treatment process of all patients, extract all patient information diagnosed by the diagnostic method from the patient treatment records, remove the target patients from all patients diagnosed by the diagnostic method and set the target patients as control patients, and perform feature annotation on the target patients and control patients respectively.

[0021] Step S204: Denote the diagnostic method as d y , obtain diagnostic method d y The previous diagnostic method d x The system acquires patient classification information under the DX diagnostic method, sets the patient category including the target patient as the target patient category, and sets the patient category excluding the target patient as the control patient category. It performs feature annotation on patients in the target patient category and patients in the control patient category, respectively, and marks the diagnostic method with features. The features of the diagnostic method are set as key node location information. The system trains the patient feature labels and key node location information through the data model to obtain a prediction model for patients using the target device. By collecting the feature labels of patients and the doctor's diagnostic information during the patient's medical treatment process, the system predicts the probability that the doctor will use the target device for the patient at the end of each diagnostic method used by the doctor for the current patient, and obtains the medical device activation prediction value of the target device.

[0022] The process of a doctor diagnosing a patient can be viewed as a process of labeling features between the doctor and the patient. After several diagnoses, the doctor uses a target device on the target patient and records the characteristics of these patients. Some patients have similar characteristics to the target patients, but the doctor does not use the target device on them. The classification process during the doctor's diagnosis is also recorded. The data model learns from the doctor's classification process and calculates the patient's need for the target device during the patient's visit. When certain conditions are met, the detection of the target device is initiated.

[0023] The data model, for example, is a decision tree model. The patient's expectation of the target device after each diagnosis and treatment process can be regarded as a decision point, and the doctor's diagnosis process can be regarded as the pruning process of the decision tree.

[0024] For example, learning can be done through classification models, such as K-nearest neighbor (KNN), support vector machines, and logistic regression models. By learning the labels on different patients and the classification methods of doctors, the probability of doctors using the target device can be predicted.

[0025] Step S205: When the duration of the medical device's unused state is greater than or equal to the time threshold, the time threshold is met. The probability threshold is set as the condition threshold. When the predicted value of the target device's medical device activation is greater than the condition threshold, the condition threshold is met. The calculation start time of the duration of the medical device's unused state includes: the time when the medical device stops being used and the end time of one detection of the medical device in the unused state.

[0026] Furthermore, step S300 includes:

[0027] Step S301: Detect each of the detection feedback locations recorded in the fault item database, record the location information where there is abnormal detection feedback, and set the location information with abnormal detection feedback as abnormal feedback location;

[0028] Step S302: Compare the abnormal feedback location with the detection feedback location in the fault item database to obtain the detection feedback result that is the same as the abnormal value of the abnormal feedback location. Obtain the detection step corresponding to the detection feedback result. Send a set of first test signals to the relevant components in the medical device according to the detection steps. Obtain the first detection feedback information sequence corresponding to the first test signal. When the first detection feedback information sequence is the same as the detection feedback result sequence of the corresponding fault information in the fault item database, confirm the fault information and issue an alarm to the relevant management personnel.

[0029] Step S303: When the detection step of a certain abnormal location information A2 includes the abnormal location information A1, retrieve the feedback value when there is no fault at A1 during the detection of A2 from the fault item database, and generate a simulated test signal based on the feedback value when there is no fault at A1 and input it into the connection circuit between A1 and A2.

[0030] Step S304: After the analog test signal is input into the connection circuit between A1 and A2, it is detected whether the first detection feedback information at A2 is different from the normal detection feedback information. When the first detection feedback information at A2 changes from a state of difference from the normal detection feedback information to a state of no difference from the normal detection feedback information compared with before the analog test signal is input, it is determined that there is no fault at A2. When the first detection feedback information at A2 is still different from the normal detection feedback information after the analog test signal is input, A2 is regarded as the location information of the detection feedback abnormality, and the process returns to step S302 for further detection.

[0031] Furthermore, step S400 includes:

[0032] Step S401: Obtain the operating parameters from the historical operating records of each component in the medical device, obtain the historical maximum and minimum values ​​of the component input signals, generate a periodic detection signal between the historical maximum and minimum values ​​of the input signals corresponding to each component, and set the periodic detection signal as the second detection signal;

[0033] Step S402: Perform several cycles of detection on each component using the second detection signal to obtain several sets of corresponding second feedback signals. Sample the second feedback signals output by each component, calculate the dispersion of each set of corresponding second feedback signals output by each component, set a dispersion management threshold, and issue an alarm for components whose second feedback signal sampling values ​​have a dispersion greater than the dispersion management threshold.

[0034] Furthermore, step S500 includes:

[0035] Step S501: Obtain the safety protection devices that the target device needs to be activated according to relevant regulations, check the activated safety protection devices of the target device, and issue an alarm for any safety protection measures that are not activated.

[0036] Step S502: Obtain the trigger conditions corresponding to each safety protection device, generate the corresponding third test signal according to the activation conditions of the safety protection device, send the third test signal to the corresponding safety protection device to enable the safety protection device, and issue an alarm for the safety protection device that is not enabled.

[0037] The safety protection device is connected to the corresponding sensor. The third test signal simulates the sensor's acquisition results. For example, the sensor acquires environmental changes and converts them into electrical signals. The third test signal simulates the electrical signals acquired by the sensor and transmits them to the safety protection device to test whether the safety protection device plays a protective role.

[0038] Step S503: Reset the safety protection devices activated during the safety test.

[0039] To better implement the above methods, a big data-based intelligent monitoring system for the service status of medical equipment is also proposed. The system includes:

[0040] The system includes a detection signal generation module, a medical device static detection module, a medical device safety detection module, and an alarm module. The detection signal generation module generates test signals for corresponding detection items. The medical device static detection module analyzes the first detection feedback corresponding to the first test signal input to the components of the medical device when the medical device is not in use and meets the detection conditions. It then compares the first detection feedback information with the detection items in the fault item database to obtain fault alarm information. The medical device safety detection module calculates the stability of the operating status of each component of the medical device and detects whether the safety protection devices are enabled. The alarm module collects alarm information and issues alarms to relevant management personnel.

[0041] Furthermore, the detection signal generation module includes: a historical maintenance record management unit, a first test signal generation unit, an operating parameter management module, a second test signal generation unit, a safety protection device management unit, and a third test signal production unit. The historical maintenance record management unit manages fault maintenance records in the medical equipment's operation and maintenance data; the first test signal generation unit generates the first test signal; the operating parameter management module manages the operating parameter records of each component in the medical equipment; the second test signal generation unit generates the second test signal; the safety protection device management unit manages information about safety protectors in the medical equipment; and the third test signal production unit generates the third test signal.

[0042] Furthermore, the static testing module for medical devices includes: a testing sequence management unit, a time threshold management unit, a condition threshold management unit, and a first testing feedback management unit. The testing sequence management unit is used to manage the testing sequence of each component in the medical device, the time threshold management unit is used to determine whether the time threshold condition is met, the condition threshold management unit is used to perform condition threshold judgment, and the first testing feedback management unit is used to compare the first testing feedback information with the information in the fault item database.

[0043] Furthermore, the medical device safety testing module includes: a second feedback signal sampling unit, a medical device operating status judgment unit, a safety protection device detection unit, and a reset unit. The second feedback signal sampling unit is used to sample the second feedback signal, the medical device operating status judgment unit is used to judge the stability of the medical device operating status, the safety protection device detection unit is used to detect the safety protectors in the medical device, and the reset unit is used to reset the safety protection devices activated during the safety test.

[0044] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: The present invention divides the status monitoring of medical devices into normal detection in the unused state and safety detection after the preparation for use is completed. On the one hand, it makes up for the shortcomings of the traditional technical solution that only detects the power-on process of the medical device system, which is insufficient in terms of the hardware performance and safety of the medical device. On the other hand, it utilizes the time when the medical device is not in use to perform safety detection on the medical device, reducing the device detection time during the preparation for use, so that the medical device can respond quickly under the condition of ensuring safety, saving valuable time for doctors and patients. Attached Figure Description

[0045] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0046] Figure 1 This is a schematic diagram of the intelligent monitoring system for the service status of medical equipment based on big data, which is the subject of this invention patent.

[0047] Figure 2 This is a flowchart illustrating the intelligent monitoring method for the service status of medical equipment based on big data, which is a patent of this invention.

[0048] Figure 3 This is a patient classification diagram of the intelligent monitoring method for the service status of medical equipment based on big data, which is a patented invention. Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] Please see Figure 1 , Figure 2 and Figure 3 The present invention provides the following technical solution:

[0051] The methods include:

[0052] Step S100: Obtain fault repair records from the historical operation and maintenance data of medical equipment, and establish a fault item database by matching the fault information of medical equipment with the fault finding process in the fault repair records;

[0053] Step S100 includes:

[0054] Step S101: Obtain the records of equipment maintenance personnel searching for faults in the historical operation and maintenance data of medical equipment. In the records of equipment maintenance personnel searching for faults, obtain the detection steps of the maintenance personnel in detecting faults in medical equipment, and obtain the detection items included in each fault detection step and the detection process corresponding to each detection item.

[0055] Step S102: Obtain the detection process information for each detection process. One detection process information includes: the detection signal of the equipment maintenance personnel, the detection location, the detection feedback location, and the detection feedback result. The detection feedback result includes: normal detection feedback information and abnormal detection feedback information. The normal detection feedback information represents the range of values ​​when the detection feedback location is in normal feedback. The abnormal detection feedback information represents the difference between the abnormal value and the range of values ​​when the detection feedback location is abnormal.

[0056] Step S103: Record the fault finding process and the corresponding detection process information of the medical equipment fault information, and collect all records to establish a fault item database.

[0057] For example, a single record in the fault project database is: {trouble1, step1, step2, step3}, where trouble1 represents the first fault type, and step1, step2, and step3 represent the first, second, and third steps required to find the first fault type, respectively.

[0058] Step 1 includes proj11, proj12, and proj13; Step 2 includes proj21 and proj22; and Step 3 includes proj31, proj32, proj33, and proj34.

[0059] proj11, proj12, and proj13 represent the first, second, and third detection items included in step 1, respectively; proj21 and proj22 represent the first and second detection items included in step 2, respectively; and proj31, proj32, proj33, and proj34 represent the first, second, third, and fourth detection items included in step 1, respectively.

[0060] Among them, proj11 includes signal11 and position. t 11. position r 11 and rec11, signal11 represent the detection signal and position in proj11. t 11 represents the detection position in proj11. r 11 represents the detection feedback position in proj11, and rec11 represents the detection feedback result in proj11;

[0061] Step S200: Detect and feedback normal value information. When the time that the medical device is in an unused state meets the time threshold or the predicted value of the medical device being activated meets the condition threshold, the medical device is detected.

[0062] Step S200 includes:

[0063] Step S201: Obtain the maintenance records in time period T0 from the historical maintenance records of the medical equipment. Extract the number of fault detection steps, fault maintenance time, and interval with the next fault maintenance record from each fault maintenance record in time period T0. Calculate the fault maintenance index for each historical fault. The fault maintenance index for the b-th fault maintenance record in time period T0 is IN. b IN b =(n b / T b1 ) × T b2 , where n b T represents the number of testing steps performed by the maintenance personnel in the fault repair record corresponding to the b-th fault repair record. b1 T represents the fault repair time corresponding to the b-th fault repair record. b2 This indicates the time interval between the b-th fault repair record and the next fault repair record;

[0064] Step S202: Sum the m fault maintenance indices corresponding to the m fault repair records in time period T0 to obtain the total fault maintenance index IN0 for time period T0, and calculate the time threshold T. sc , among which, T sc = γ*IN0 / m, where γ is the time conversion coefficient;

[0065] For example, the four fault repair records in time period T0 include: the first fault repair record includes: number of detection steps n1=4, fault repair time T. 11 = 5h, the interval T between the first fault repair record and the second fault repair record 12=168h, where h represents the number of hours. The second fault repair record includes: number of inspection steps n2=2, fault repair time T. 21 =3h, the interval T between the second and third fault repair records. 22 = 240h, the third fault repair record includes: number of inspection steps n3=8, fault repair time T 31 = 7h, the interval T between the 3rd and 4th fault repair records 32 = 288h;

[0066] IN0 / m = ((4 / 5)×168+(2 / 3)×240+ (8 / 7)×288) / 3≈207;

[0067] Preferably, γ is taken as hours / unit, and the time threshold T under the current example conditions is calculated. sc It is 207h;

[0068] Step S203: Obtain all patient treatment records of a certain department in the hospital, set a medical device in the department as the target device, set the patients treated by medical staff using the target device as the target patients, obtain the treatment process of all patients, extract all patient information diagnosed by the diagnostic method from the patient treatment records, remove the target patients from all patients diagnosed by the diagnostic method and set the target patients as control patients, and perform feature annotation on the target patients and control patients respectively.

[0069] Step S204: Denote the diagnostic method as d y , obtain diagnostic method d y The previous diagnostic method d x The system acquires patient classification information under the DX diagnostic method, sets the patient category including the target patient as the target patient category, and sets the patient category excluding the target patient as the control patient category. It performs feature annotation on patients in the target patient category and patients in the control patient category, respectively, and marks the diagnostic method with features. The features of the diagnostic method are set as key node location information. The system trains the patient feature labels and key node location information through the data model to obtain a prediction model for patients using the target device. By collecting the feature labels of patients and the doctor's diagnostic information during the patient's medical treatment process, the system predicts the probability that the doctor will use the target device for the patient at the end of each diagnostic method used by the doctor for the current patient, and obtains the medical device activation prediction value of the target device.

[0070] Figure 3This represents an example of patient classification: P1, P2, P3, ..., P10 represent the medical records of the 1st, 2nd, 3rd, ..., 10th patients in a set of patient medical records, respectively; H1, H2, H3, H4, and H5 represent the sets consisting of the medical records of the 1st, 2nd, 3rd, 4th, and 5th patients, respectively; and d1, d2, and d3 represent the 1st, 2nd, and 3rd diagnostic methods, respectively.

[0071] Among them, the patient's medical record P5 includes the usage information of the target device, while the patient's medical records P1, P2, P3, ... and P10 do not include the usage information of the target device except for P5;

[0072] Among them, H1 includes P1, P2, P3, ..., P10; H2 includes P3, P5, P6, P7 and P8; H3 includes P1, P2, P4, P9 and P10; H4 includes P5 and P7; and H5 includes P3, P6 and P8.

[0073] Step S205: When the duration of the medical device's unused state is greater than or equal to the time threshold, the time threshold is met. The probability threshold is set as the condition threshold. When the predicted value of the target device's medical device activation is greater than the condition threshold, the condition threshold is met. The calculation start time of the duration of the medical device's unused state includes: the time when the medical device stops being used and the end time of one detection of the medical device in the unused state.

[0074] Step S300: Obtain abnormal feedback information during the medical equipment testing process, compare it with the fault item database, obtain the steps for abnormal feedback, execute the steps, and determine the fault type of the abnormal feedback;

[0075] Step S300 includes:

[0076] Step S301: Detect each of the detection feedback locations recorded in the fault item database, record the location information where there is abnormal detection feedback, and set the location information with abnormal detection feedback as abnormal feedback location;

[0077] Step S302: Compare the abnormal feedback location with the detection feedback location in the fault item database to obtain the detection feedback result that is the same as the abnormal value of the abnormal feedback location. Obtain the detection step corresponding to the detection feedback result. Send a set of first test signals to the relevant components in the medical device according to the detection steps. Obtain the first detection feedback information sequence corresponding to the first test signal. When the first detection feedback information sequence is the same as the detection feedback result sequence of the corresponding fault information in the fault item database, confirm the fault information and issue an alarm to the relevant management personnel.

[0078] Step S303: When the detection step of a certain abnormal location information A2 includes the abnormal location information A1, retrieve the feedback value when there is no fault at A1 during the detection of A2 from the fault item database, and generate a simulated test signal based on the feedback value when there is no fault at A1 and input it into the connection circuit between A1 and A2.

[0079] Step S304: After the analog test signal is input into the connection circuit between A1 and A2, it is detected whether the first detection feedback information at A2 is different from the normal detection feedback information. When the first detection feedback information at A2 changes from a state of difference from the normal detection feedback information to a state of no difference from the normal detection feedback information compared with before the analog test signal is input, it is determined that there is no fault at A2. When the first detection feedback information at A2 is still different from the normal detection feedback information after the analog test signal is input, A2 is regarded as the location information of the detection feedback abnormality, and the process returns to step S302 for further detection.

[0080] Step S400: After the medical device receives the activation information, the operating status of each component of the medical device is tested, the stability of the operating status of each component is calculated, and an alarm is issued for components with unstable operating status.

[0081] Step S400 includes:

[0082] Step S401: Obtain the operating parameters from the historical operating records of each component in the medical device, obtain the historical maximum and minimum values ​​of the component input signals, generate a periodic detection signal between the historical maximum and minimum values ​​of the input signals corresponding to each component, and set the periodic detection signal as the second detection signal;

[0083] Step S402: Perform several cycles of detection on each component using the second detection signal to obtain several sets of corresponding second feedback signals. Sample the second feedback signals output by each component, calculate the dispersion of each set of corresponding second feedback signals output by each component, set a dispersion management threshold, and issue an alarm for components whose second feedback signal sampling values ​​have a dispersion greater than the dispersion management threshold.

[0084] Step S500: Detect whether the safety protection devices in the medical equipment are enabled, and issue an alarm for any disabled safety protection devices;

[0085] Step S500 includes:

[0086] Step S501: Obtain the safety protection devices that the target device needs to be activated according to relevant regulations, check the activated safety protection devices of the target device, and issue an alarm for any safety protection measures that are not activated.

[0087] The safety protection device is used to protect against potential risks to medical equipment, such as circuit breakers, protective switches, and shut-off valves. The safety protection device is connected to a sensor, which converts environmental information such as temperature, humidity, and charge into electrical signals for the safety protection device to make judgments. When the threshold value of the safety protection device is reached, the safety protection device automatically activates.

[0088] Step S502: Obtain the trigger conditions corresponding to each safety protection device, generate the corresponding third test signal according to the activation conditions of the safety protection device, send the third test signal to the corresponding safety protection device to enable the safety protection device, and issue an alarm for the safety protection device that is not enabled.

[0089] Step S503: Reset the safety protection devices activated during the safety test.

[0090] The system includes:

[0091] The system includes a detection signal generation module, a medical device static detection module, a medical device safety detection module, and an alarm module. The detection signal generation module generates test signals for corresponding detection items. The medical device static detection module analyzes the first detection feedback information corresponding to the first test signal input to the components of the medical device when the medical device is not in use and meets the detection conditions. It then compares the first detection feedback information with the detection items in the fault item database to obtain fault alarm information. The medical device safety detection module calculates the stability of the operating status of each component of the medical device and detects whether the safety protection devices are enabled. The alarm module collects alarm information and issues alarms to relevant management personnel.

[0092] The detection signal generation module includes: a historical maintenance record management unit, a first test signal generation unit, an operating parameter management module, a second test signal generation unit, a safety protection device management unit, and a third test signal production unit. The historical maintenance record management unit manages fault maintenance records in the medical equipment operation and maintenance data. The first test signal generation unit generates the first test signal. The operating parameter management module manages the operating parameter records of each component in the medical equipment. The second test signal generation unit generates the second test signal. The safety protection device management unit manages the information of the safety protectors in the medical equipment. The third test signal production unit generates the third test signal.

[0093] The medical device static testing module includes: a testing sequence management unit, a time threshold management unit, a condition threshold management unit, and a first testing feedback management unit. The testing sequence management unit manages the testing sequence of each component in the medical device; the time threshold management unit determines whether time threshold conditions are met; the condition threshold management unit performs condition threshold judgments; and the first testing feedback unit compares the first testing feedback information with information in the fault item database.

[0094] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0095] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A big data-based intelligent monitoring method for the service state of a medical device, characterized in that: The method comprises the following steps: Step S100: obtaining the fault maintenance record in the medical equipment historical operation and maintenance data, establishing a fault item database through the corresponding relationship between the fault information of the medical equipment and the fault finding process in the fault maintenance record; Step S200: detecting the medical equipment when the feedback normal value information meets the time threshold value in the non-use state of the medical equipment or the medical equipment activation prediction value meets the condition threshold value; Step S200: Step S201: Obtain the maintenance records in the T0 period in the historical maintenance records of the medical equipment, extract the fault detection steps, fault maintenance time and interval time with the next fault maintenance record in each fault maintenance record in the T0 period, calculate the fault operation and maintenance index of each historical fault, wherein the fault operation and maintenance index of the bth fault maintenance record in the T0 period is IN b , IN b = (n b / T b1 ) × T b2 , wherein n b represents the number of detection steps made by the maintenance personnel in the fault maintenance record corresponding to the bth fault maintenance record, T b1 represents the fault maintenance time corresponding to the bth fault maintenance record, and T b2 represents the interval time between the bth fault maintenance record and the next fault maintenance record. Step S202: Accumulate the m fault operation and maintenance indexes corresponding to the m times of fault maintenance records in the T0 period to obtain a total fault operation and maintenance index IN0 of the T0 period, and calculate a time threshold T sc , wherein T sc = γ*IN0 / m, γ is a time conversion coefficient; Step S203: obtaining all patient diagnosis and treatment records of a department in a hospital, setting a medical device in the department as a target device, setting a patient diagnosed and treated by a medical staff using the target device as a target patient, obtaining a diagnosis and treatment process of all patients, extracting patient information diagnosed by a diagnosis method from the patient diagnosis and treatment record, setting a patient other than the target patient as a control patient, and labeling the target patient and the control patient with features; Step S204: Denote the diagnostic method as d y , obtain diagnostic method d y The previous diagnostic method d x The system acquires patient classification information under the DX diagnostic method, sets the patient category including the target patient as the target patient category, and sets the patient category excluding the target patient as the control patient category. It performs feature annotation on patients in the target patient category and patients in the control patient category, respectively, and marks the diagnostic method with features. The features of the diagnostic method are set as key node location information. The system trains the patient feature labels and key node location information through the data model to obtain a prediction model for patients using the target device. By collecting the feature labels of patients and the doctor's diagnostic information during the patient's medical treatment process, the system predicts the probability that the doctor will use the target device for the patient at the end of each diagnostic method used by the doctor for the current patient, and obtains the medical device activation prediction value of the target device. Step S205: when the length of the non-use state of the medical equipment is greater than or equal to the time threshold value, setting a probability threshold value as the condition threshold value, when the medical equipment activation prediction value of the target device is greater than the condition threshold value, the condition threshold value is met, and the starting time of the calculation of the length of the non-use state of the medical equipment includes: the time when the medical equipment stops being used and the time when the medical equipment detects once in the non-use state; Step S300: obtaining abnormal feedback information in the detection process of the medical equipment, obtaining the step of detecting abnormal feedback by comparing with the fault item database, executing the step, and judging the fault type of the abnormal feedback; Step S400: testing the running state of each component of the medical equipment after the medical equipment receives the activation information, calculating the stability of the running state of each component, and alarming the component with an unstable running state; Step S500: detecting whether the safety protection device in the medical equipment is activated, and alarming the safety protection device that is not activated.

2. The big data based medical device service condition intelligent monitoring method according to claim 1, characterized in that: Step S100 comprises: Step S101: obtaining the fault finding process record of the equipment operation and maintenance personnel in the medical equipment historical operation and maintenance data, obtaining the detection steps of the operation and maintenance personnel in detecting the medical equipment fault in the fault finding process record, and obtaining the detection items included in each fault detection step and the detection process corresponding to each detection item; Step S102: obtaining the detection process information of each detection process, wherein one piece of detection process information comprises: the detection signal of the equipment operation and maintenance personnel, the detection position, the detection feedback position and the detection feedback result, the detection feedback result comprises: the detection feedback normal value information and the detection feedback abnormal information, the detection feedback normal value information represents the numerical range when the detection feedback position normally feedbacks, and the detection feedback abnormal information represents the difference between the abnormal value and the numerical range when normally feedbacks in the detection feedback position; Step S103: recording the fault finding process of the medical equipment fault information and the detection process information corresponding to the fault finding process, and establishing a fault item database by collecting each record. 3.The big data based medical device service state intelligent monitoring method according to claim 2, characterized in that: Step S300 comprises: Step S301: Detect each of the detection feedback positions recorded in the fault item database, record the position information of the detection feedback abnormality, and set the position information of the detection feedback abnormality as an abnormal feedback position; Step S302: Compare the abnormal feedback position with the detection feedback position in the fault item database, obtain the detection feedback result with the same abnormal value as the abnormal feedback position, obtain the detection step corresponding to the detection feedback result, send a first test signal to the relevant components in the medical equipment according to the detection step, obtain the first detection feedback information sequence corresponding to the first test signal, and confirm the fault information when the first detection feedback information sequence is the same as the detection feedback result sequence of the corresponding fault information in the fault item database, and issue an alarm to the relevant management personnel; Step S303: When the detection step of the position information A2 of the detection feedback abnormality includes the position information A1 of the detection feedback abnormality, obtain the feedback value when A1 is fault-free during the detection of A2 from the fault item database, and generate a simulation test signal input into the connection circuit of A1 and A2 according to the feedback value when A1 is fault-free; Step S304: After the simulation test signal is input into the connection circuit of A1 and A2, detect whether the first detection feedback information at A2 is different from the detection feedback normal value information, and when the first detection feedback information at A2 is different from the detection feedback normal value information before the simulation test signal is input, the state changes from the state of being different from the detection feedback normal value information to the state of being not different from the detection feedback normal value information, it is judged that A2 is fault-free, and when the first detection feedback information at A2 is still different from the detection feedback normal value information after the simulation test signal is input, A2 is taken as a position information of detection feedback abnormality, and the step S302 is returned for further detection. 4.The big data based medical device service state intelligent monitoring method of claim 3, wherein: Step S400 includes: Step S401: Obtain the running parameters in the historical running record of each component in the medical equipment, obtain the historical maximum value and the historical minimum value of the component input signal, generate a period detection signal corresponding to each component between the historical maximum value and the historical minimum value of the input signal, and set the period detection signal as a second detection signal; Step S402: Perform a plurality of period detections on each component through the second detection signal, obtain a plurality of second feedback signals corresponding to the plurality of period detections, sample the second feedback signals output by each component, calculate the dispersion degree of each component output corresponding to each group of second feedback signals, set a dispersion degree management threshold, and alarm the components whose dispersion degree of the second feedback signal sample value is greater than the dispersion degree management threshold.

5. The big data based medical device service state intelligent monitoring method according to claim 4, characterized in that: Step S500 includes: Step S501: Obtain the safety protection devices required to be turned on in the target equipment according to the relevant regulations, check the safety protection devices turned on in the target equipment, and alarm the safety protection measures that are not turned on. Step S502: obtaining the trigger condition corresponding to each safety protection device, generating the third test signal according to the enable condition of the safety protection device, sending the third test signal to enable the safety protection device to the corresponding safety protection device, and alarming the safety protection device which is not enabled; Step S503: resetting the safety protection device which is enabled in the safety test process.

6. The intelligent monitoring system for service state of medical equipment based on big data, applied to the intelligent monitoring method for service state of medical equipment based on big data in any one of claims 1-5, characterized in that, The system comprises the following modules: The detection signal generation module is used to generate the test signal corresponding to the detection item, the medical equipment static detection module is used to analyze the components of the medical equipment by inputting the first test signal when the medical equipment is in the non-use state and the detection condition is met, to feed back the first detection feedback information corresponding to the first test signal, to compare the first detection feedback information with the detection items in the fault item database, and to obtain the fault alarm information, the medical equipment safety detection module is used to calculate the stability of the running state of each component of the medical equipment and to detect whether the safety protection device is enabled, and the alarm module is used to collect the alarm information and to issue an alarm to the relevant management personnel.

7. The big data based medical device service state intelligent monitoring system according to claim 6, characterized in that: The detection signal generation module comprises a historical maintenance record management unit, a first test signal generation unit, a running parameter management module, a second test signal generation unit, a safety protection device management unit and a third test signal production unit, wherein the historical maintenance record management unit is used to manage the fault maintenance record in the medical equipment operation and maintenance data, the first test signal generation unit is used to generate the first test signal, the running parameter management module is used to manage the running parameter record of each component in the medical equipment, the second test signal generation unit is used to generate the second test signal, the safety protection device management unit is used to manage the information of the safety protection device in the medical equipment, and the third test signal production unit is used to generate the third test signal.

8. The big data based medical device service state intelligent monitoring system as claimed in claim 6, wherein: The medical equipment static detection module comprises a detection sequence management unit, a time threshold management unit, a condition threshold management unit and a first detection feedback management unit, wherein the detection sequence management unit is used to manage the detection sequence of each component in the medical equipment, the time threshold management unit is used to determine whether the time threshold condition is met, the condition threshold management unit is used to make the condition threshold judgment, and the first detection feedback management unit is used to compare the first detection feedback information with the information in the fault item database.

9. The big data based medical device service state intelligent monitoring system as claimed in claim 6, wherein: The medical equipment safety detection module comprises a second feedback signal sampling unit, a medical equipment running state judgment unit, a safety protection device detection unit and a reset unit, wherein the second feedback signal sampling unit is used to sample the second feedback signal, the medical equipment running state judgment unit is used to judge the stability of the medical equipment running state, the safety protection device detection unit is used to detect the safety protection device in the medical equipment, and the reset unit is used to reset the safety protection device which is enabled in the safety test process.

Images