Fault self-repair method, device and equipment for medical equipment

Abstract

The present invention provides a method, device and equipment for self-repairing faults of medical equipment, which include: obtaining full-dimensional data of medical equipment; obtaining the fault type probability corresponding to at least one fault type of the medical equipment and the potential fault information corresponding to at least one potential fault of the medical equipment according to the full-dimensional data; wherein each fault type includes at least one potential fault; and repairing the medical equipment according to the full-dimensional data, the fault type probability and the potential fault information. The medical equipment can be maintained predictively, does not rely on regular inspections or repairs after a fault, has a fast response speed, and has low maintenance costs, thus avoiding delays in patient treatment plans.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a fault self-repair method, device and equipment for medical equipment. Background Art

[0002] As the variety and complexity of medical equipment continue to increase, traditional equipment maintenance methods can no longer meet the needs of the modern medical industry. For example, in large hospitals, the frequent use of high-end medical equipment such as CT machines and MRI machines has led to an increasing demand for their maintenance. However, traditional equipment maintenance methods mainly rely on regular inspections or repairs after failures. This model is not only prone to unexpected equipment downtime, affecting the continuity of medical services, but may also cause delays in patient treatment plans. In addition, slow response speed is also a significant problem. When a device fails, professional engineers are usually required to go to the site for diagnosis and repair, which not only increases downtime but may also delay emergency medical treatment. For example, if an anesthesia machine used for emergency surgery suddenly fails and engineers cannot arrive at the site immediately, it may have a serious impact on the patient's health. High maintenance costs are also an issue that cannot be ignored, including equipment downtime losses, personnel dispatch costs, and maintenance spare parts reserve costs. These costs are often further increased due to information asymmetry. For example, a hospital may need to reserve a large number of spare parts to deal with sudden failures, but this will lead to increased inventory costs. In addition, medical equipment usually generates a large amount of operating data, but this data is not fully utilized, making it difficult to form valuable predictive maintenance information. For example, a CT machine generates a large amount of operation logs during each scan, but this data is usually only used for troubleshooting, and potential problems cannot be discovered in advance through data analysis. Summary of the invention

[0003] The purpose of the present invention is to provide a method, device and equipment for self-repair of medical equipment faults, which is used to solve the problem that the maintenance method of medical equipment in the prior art mainly relies on regular inspection or repair after a fault, has slow response speed and high maintenance cost, causing delays in patient treatment plans.

[0004] To achieve the above object, an embodiment of the present invention provides a fault self-repair method for medical equipment, which includes:

[0005] Obtain full-dimensional data of medical equipment;

[0006] According to the full-dimensional data, a fault type probability corresponding to at least one fault type of the medical device and potential fault information corresponding to at least one potential fault of the medical device are obtained; wherein each of the fault types includes at least one potential fault;

[0007] The medical device is repaired according to the full-dimensional data, the fault type probability and the potential fault information.

[0008] Optionally, the method, wherein obtaining a failure type probability corresponding to at least one failure type of the medical device includes:

[0009] Input the full-dimensional data into a rule engine to obtain abnormal data; wherein the rule engine is based on the historical full-dimensional data of the medical device and industry standard information acquisition;

[0010] The fault type probability is obtained according to the abnormal data.

[0011] Optionally, the method, wherein obtaining potential fault information corresponding to at least one potential fault of the medical device includes:

[0012] Inputting the full-dimensional data into a pre-acquired fault prediction model to obtain potential fault information corresponding to at least one potential fault of the medical device;

[0013] The method for obtaining the fault prediction model includes:

[0014] Acquire historical full-dimensional data and historical fault information of the medical device; wherein the historical fault information is fault information corresponding to the historical full-dimensional data;

[0015] Inputting the historical full-dimensional data into a first prediction model to obtain predicted historical fault information; wherein the first prediction model is constructed based on a long short-term memory network, a time series, a Markov chain model, and a joint classification model;

[0016] The predicted historical fault information is compared with the historical fault information, the first prediction model is adjusted, and a fault prediction model is obtained.

[0017] Optionally, the method, wherein repairing the medical device according to the full-dimensional data, the fault type probability and the potential fault information, comprises:

[0018] Acquire a repair strategy according to the full-dimensional data, the fault type probability and the potential fault information;

[0019] The medical device is repaired according to the repair strategy.

[0020] Optionally, in the method, the repairing the medical device according to the repair strategy comprises:

[0021] In the case where the repair strategy includes adjusting parameters, adjusting the operating status data of the full-dimensional data of the medical device;

[0022] In the case where the repair strategy includes repairing a hardware module, enabling a standby module, isolating and repairing the faulty module;

[0023] In the case where the repair strategy includes repairing the software module, the critical code is reloaded through the over-the-air download technology OTA.

[0024] Optionally, the method further comprises:

[0025] Send fault self-repair report to the client;

[0026] Recording the full-dimensional data, the fault type probability, the potential fault information and the fault self-repair report;

[0027] The fault self-repair report includes one or more of the following:

[0028] Real-time monitoring charts;

[0029] List of medical devices;

[0030] Historical data trend chart;

[0031] Failure probability assessment;

[0032] Fault list and parts purchase order;

[0033] Performance indicator trends.

[0034] Optionally, in the method, the full-dimensional data includes one or more of the following:

[0035] Equipment production data;

[0036] Operation status data;

[0037] Environmental data;

[0038] Behavior data, wherein the behavior data is data of operation behavior collected when the user operates the medical device.

[0039] Optionally, in the method, the potential fault information includes one or more of the following:

[0040] Potential failure probability;

[0041] Potential causes of failure;

[0042] Preset repair methods for potential faults;

[0043] The preset repair probability of a potential fault; wherein the preset repair probability of a potential fault is the repair probability corresponding to the preset repair method of the potential fault.

[0044] In order to achieve the above-mentioned object, an embodiment of the present invention further provides a fault self-repair device for medical equipment, which includes:

[0045] A first acquisition module is used to acquire full-dimensional data of medical equipment;

[0046] A second acquisition module is used to acquire, according to the full-dimensional data, a fault type probability corresponding to at least one fault type of the medical device and potential fault information corresponding to at least one potential fault of the medical device; wherein each of the fault types includes at least one potential fault;

[0047] The first processing module is used to repair the medical device according to the full-dimensional data, the fault type probability and the potential fault information.

[0048] In order to achieve the above-mentioned purpose, an embodiment of the present invention also provides an electronic device, including: a processor, a memory, and a program or instruction stored in the memory and executable on the processor; wherein, when the processor executes the program or instruction, the fault self-repair method of the medical device as described above is implemented.

[0049] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a readable storage medium on which a program or instruction is stored, wherein the program or instruction, when executed by a processor, implements the steps in the fault self-repair method of the medical device as described above.

[0050] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a computer program product, which includes computer instructions, and when the computer instructions are executed by a processor, the steps of the fault self-repair method of the medical device as described above are implemented.

[0051] The beneficial effects of the above technical solution of the present invention are as follows:

[0052] The embodiments of the present invention obtain the failure type probability of the failure type and the potential failure information of the potential failure in the failure type through the full-dimensional data of the medical equipment, so as to repair the medical equipment. The medical equipment can be maintained predictively without relying on regular inspections or repairs after failures. The response speed is fast and the maintenance cost is low, so as to avoid delays in patient treatment plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A schematic diagram of a fault self-repair method for a medical device according to an embodiment of the present invention;

[0054] Figure 2 A flowchart of a fault self-repair method for a medical device according to an embodiment of the present invention;

[0055] Figure 3It is a schematic diagram of a fault self-repairing device of a medical device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0057] It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present invention. Therefore, the references to "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0058] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0059] Additionally, the terms "system" and "network" are often used interchangeably herein.

[0060] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0061] For ease of understanding, some contents involved in the embodiments of the present invention are described below:

[0062] like Figure 1 As shown, a fault self-repair method of a medical device according to an embodiment of the present invention includes:

[0063] S10, obtaining full-dimensional data of medical equipment;

[0064] It should be noted that if Figure 2 As shown, in step S10, the medical device ( Figure 2 Deploy high-precision sensors (such as medical devices in the Figure 2Optical sensors in the equipment) and cameras are used to collect real-time operating status data of medical equipment, including key parameters such as temperature, humidity, vibration, current, power consumption, and operating time. These sensors need to have high sensitivity and high reliability to adapt to the complex operating environment of medical equipment. In addition, it also includes fault log data: recording key events and abnormal signals in the operation of the medical equipment; user operation behavior data: collecting user's equipment operation records; environmental parameters: including humidity, dust concentration, etc., to predict equipment loss caused by the environment. Use edge computing nodes to perform preliminary data processing and upload key information to the cloud via Modbus (a serial communication protocol). In such Figure 2 The industrial big data technology section shown uses TimescaleDB (a time series database) to store the relevant data of the data acquisition module, data cleaning and processing module, and data storage module. The full-dimensional data uploaded above is received by the data acquisition module, and then the full-dimensional data is cleaned and preprocessed by the data cleaning and processing module: 1. Denoising and smoothing, using improved Kalman filtering and Savitzky-Golay smoothing filtering to remove noise from device signals: in is the current predicted device state, z k is the actual measured device status, P k-1 , Q, R are noise covariance matrices, K k is the Kalman gain, which is used to adjust the weight of state estimation. 2. Anomaly detection, using the DBSCAN (density clustering) algorithm to locate abnormal points in the data: Where p and q are two data points, p i and q i is the value of each dimension, and n is the number of dimensions. By calculating the distances of these data points, we can effectively identify data points that are out of the normal range, determine noise points, and trigger abnormal alarms.

[0065] S20, acquiring, based on the full-dimensional data, a fault type probability corresponding to at least one fault type of the medical device, and potential fault information corresponding to at least one potential fault of the medical device; wherein each of the fault types includes at least one potential fault;

[0066] It should be noted that if Figure 2As shown, in step S20, the rule engine, fault prediction model and behavior data model related data are stored through clickhouse (a columnar database management system) in the computing model section. Through the rule engine, fault prediction model and behavior data model, according to the full-dimensional data, the fault type and the corresponding fault type probability of the medical device, as well as the potential fault and the corresponding potential fault information are obtained. Among them, the data flow between the industrial big data technology section and the computing model section adopts the message queue (MQTT) technology to complete the communication between the device and the cloud with low latency and high reliability.

[0067] S30, repairing the medical device according to the full-dimensional data, the fault type probability and the potential fault information;

[0068] It should be noted that if Figure 2 As shown, the calculation model module communicates with the platform control center and the client through https (Hypertext Transfer Protocol Secure) and TCP (Transmission Control Protocol), so as to achieve the purpose of repairing the medical device according to the full-dimensional data, the fault type probability and the potential fault information.

[0069] In this embodiment, the fault type probability of the fault type and the potential fault information of the potential fault in the fault type are obtained through the full-dimensional data of the medical device, so as to repair the medical device. The medical device can be maintained predictively without relying on regular inspections or post-fault repairs, with fast response speed and low maintenance cost, avoiding delays in patient treatment plans.

[0070] Optionally, in the method, step S20 includes:

[0071] Input the full-dimensional data into a rule engine to obtain abnormal data; wherein the rule engine is based on the historical full-dimensional data of the medical device and industry standard information acquisition;

[0072] The fault type probability is obtained according to the abnormal data.

[0073] In this embodiment, the dynamic rule base in the rule engine is constructed based on the historical full-dimensional data of the medical device and the industry standard information, including: hardware anomaly rules (such as motor overheating, current overlimit). Environmental rules (such as temperature and humidity exceeding the standard). Data deviation rules (such as abnormal vibration amplitude). The rule optimization mechanism is dynamically adjusted through expert knowledge combined with real-time feedback. Then, the Bayesian network is combined with the probability prediction of historical data to perform rule matching: Among them, H represents the fault type, and E is the evidence collected by the device (abnormal data obtained through the dynamic rule base). The probability of the occurrence of potential fault type H is predicted through known conditions (equipment evidence). Therefore, after the establishment of the rule engine, the abnormal data is obtained based on the full-dimensional data, and the probability of the fault type is obtained through the abnormal data. The fault type can be electrical fault, network fault, hardware fault, software fault, and human operation fault, etc.

[0074] Optionally, in the method, step S20 further includes:

[0075] Inputting the full-dimensional data into a pre-acquired fault prediction model to obtain potential fault information corresponding to at least one potential fault of the medical device;

[0076] The method for obtaining the fault prediction model includes:

[0077] Acquire historical full-dimensional data and historical fault information of the medical device; wherein the historical fault information is fault information corresponding to the historical full-dimensional data;

[0078] Inputting the historical full-dimensional data into a first prediction model to obtain predicted historical fault information; wherein the first prediction model is constructed based on a long short-term memory network, a time series, a Markov chain model, and a joint classification model;

[0079] The predicted historical fault information is compared with the historical fault information, the first prediction model is adjusted, and a fault prediction model is obtained.

[0080] In this embodiment, the first prediction model includes multivariate time series analysis, joint classification model and Markov chain-based fault probability assessment model. Among them, the multivariate time series analysis uses an improved LSTM (long short-term memory network) to process the device status data in the full-dimensional data, combined with the time series fault trend: h t =f(W h h t-1 +W x x t +b), y t =σ(W hy ht +b y ), h t represents the hidden state at the current moment, x t is the input data at the current moment. h ,W x ,W hy is the weight matrix, b and b y is the bias term. σ is the activation function, usually Sigmoid or Tanh. By capturing long-term dependencies, the historical potential faults in the predicted historical fault information are obtained. At the same time, the fault probability assessment model based on Markov chain is used to predict the change of equipment state and the possibility of failure. The Markov chain model can simulate the transition of equipment from one state to another and is suitable for continuous modeling of equipment state changes. Prediction of fault evolution process based on Markov chain: P(X t+1 |X t )=P(X t )·T, where T is the state transition matrix, which represents the probability of changing from the current device state to the next state. This formula can be used to evaluate the probability of a device failure based on the current device state. Next, the random forest and deep learning models are combined through the two classification models for fault cause analysis: y = majority vote (h1(x), h2(x), ..., h n (x)), where x is the historical potential fault, thus obtaining the historical potential fault cause y. Then the output probability correction is performed through logistic regression: z=ω T x+b, where y is the predicted fault type, x is the input historical potential fault data, z is the fault result, and P(y|x) is the repair probability corresponding to the preset repair method for solving the potential historical potential fault. For example, when the historical potential faults are a temperature increase of 10 degrees, excessive current, and increased power consumption, the corresponding historical fault result is a loose screw. There are multiple preset repair methods for historical potential faults: adding gaskets, tightening screws, and replacing screws, etc. The output probability correction is performed through logistic regression to obtain the probabilities corresponding to multiple preset repair methods. The fault prediction model is obtained by training the above-mentioned first prediction model.

[0081] Optionally, in the method, step S30 includes:

[0082] Acquire a repair strategy according to the full-dimensional data, the fault type probability and the potential fault information;

[0083] The medical device is repaired according to the repair strategy.

[0084] In this embodiment, the potential faults of the medical device are repaired through the repair strategy, thereby solving the problem before the fault alarm is generated, effectively reducing maintenance costs, and improving the operating efficiency and reliability of the equipment.

[0085] Optionally, in the method, the step of repairing the medical device according to the repair strategy comprises:

[0086] In the case where the repair strategy includes adjusting parameters, adjusting the operating status data of the full-dimensional data of the medical device;

[0087] In the case where the repair strategy includes repairing a hardware module, enabling a standby module, isolating and repairing the faulty module;

[0088] In the case where the repair strategy includes repairing the software module, the critical code is reloaded through the over-the-air download technology OTA.

[0089] In this embodiment, when the repair strategy includes adjusting parameters, the equipment operating parameters (such as power, voltage, cooling wind speed, etc.) are dynamically adjusted: α is the learning rate, is the gradient of the performance function, reflecting the impact of the device operating parameters on the fault. When the repair strategy includes repairing the hardware module, the faulty module is isolated and repaired by enabling the backup module. The process is as follows: detect the hardware module abnormality and trigger the backup module to take over. When the repair strategy includes repairing the software module, reload the key code and redeploy the software repair strategy through OTA (over-the-air update). Figure 2 As shown, multiple configurations are performed in the platform control center, such as communication protocol configuration, communication interface configuration, model definition configuration, alarm threshold configuration, adaptive rule configuration, self-repair strategy configuration, etc. It also includes self-repair optimization: using reinforcement learning algorithms (such as DQN) to dynamically generate repair strategies. Reinforcement learning enables the system to continuously adjust and optimize repair strategies during operation: Where Q(s, a) is the value function of state s and action a, r is the reward value, γ is the discount factor, s ′ is the next state, and a′ is the next action. The self-repair mechanism optimizes the operating parameters of the equipment through gradient descent and modular repair, and triggers the repair strategy through real-time fault data to ensure that the equipment can automatically repair or switch to the backup module when a fault occurs, thus ensuring the normal operation of the equipment. Adaptive rule adjustment: Optimize the rule base through recursive neural network (RNN): R t =R t-1 +ΔR, where R tis the adjusted rule, and ΔR is the adjustment amount based on real-time data feedback. The continuously improved rule engine uses the Bayesian network to dynamically adjust the operation rules of the equipment, and optimizes the operation strategy of the equipment by combining the equipment production data, operation status data and historical fault data.

[0090] Optionally, the method further comprises:

[0091] Send fault self-repair report to the client;

[0092] Recording the full-dimensional data, the fault type probability, the potential fault information and the fault self-repair report;

[0093] The fault self-repair report includes one or more of the following:

[0094] Real-time monitoring charts;

[0095] List of medical devices;

[0096] Historical data trend chart;

[0097] Failure probability assessment;

[0098] Fault list and parts purchase order;

[0099] Performance indicator trends.

[0100] In this embodiment, if Figure 2 As shown, the fault self-repair report is sent to the client, and the full-dimensional data, the fault type probability, the potential fault information and the fault self-repair report are recorded to enrich the database of the rule engine, thereby enhancing the rule matching function and improving the prediction accuracy and repair success rate. Users can view the operation of the equipment in real time through an intuitive graphical interface on the client, obtain fault warnings and maintenance suggestions, and take timely measures to ensure the normal operation of the equipment. The client also supports multi-terminal access, which is convenient for medical staff to monitor the status of the equipment anytime and anywhere.

[0101] Optionally, in the method, the full-dimensional data includes one or more of the following:

[0102] Equipment production data;

[0103] Operation status data;

[0104] Environmental data;

[0105] Behavior data, wherein the behavior data is data of operation behavior collected when the user operates the medical device.

[0106] In this embodiment, the equipment production data is the relevant data recorded when the medical equipment is produced, the operating status data includes key parameters such as temperature, humidity, vibration, current, etc., the environmental data includes humidity, dust concentration, etc., and the environmental data is user operation data.

[0107] Optionally, in the method, the potential fault information includes one or more of the following:

[0108] Potential failure probability;

[0109] Potential causes of failure;

[0110] Preset repair methods for potential faults;

[0111] The preset repair probability of a potential fault; wherein the preset repair probability of a potential fault is the repair probability corresponding to the preset repair method of the potential fault.

[0112] It should be noted that the embodiments of the present invention combine the equipment life cycle data, FMEA (Failure Modes and Effects Analysis) experience library and big data analysis technology to realize the real-time monitoring, fault prediction, remote repair and intelligent self-repair functions of medical equipment, thereby reducing maintenance costs and improving equipment reliability. First, an example is provided, a self-repairing Internet of Things platform for medical equipment. The platform functions include: 1. Predictive maintenance, based on big data analysis and equipment operation status data, predicting potential equipment failures in advance and generating maintenance plans. For example, the platform can predict possible future failures by analyzing the historical operation data of the CT machine, and arrange maintenance in advance, thereby avoiding unexpected equipment downtime; 2. Real-time monitoring and alarm, using Internet of Things technology to realize real-time monitoring of the equipment operation status. When the equipment is abnormal, the platform can issue an alarm and upload relevant data in the first time to ensure timely processing. For example, when the temperature sensor of the MRI machine detects abnormally high temperature, the platform will immediately notify the maintenance personnel to check; 3. Full life cycle data management, each device uploads the full life cycle inspection data and inspection report before leaving the factory as a reference during the operation of the equipment. 4. Self-repair and remote repair: Based on the equipment operation data, rule model and FMEA experience library, the platform automatically generates repair solutions and remote repair instructions. For hardware problems, it generates a fault list and parts purchase recommendation list. For example, when the probe of the ultrasound equipment fails, the platform will generate a detailed fault list and recommend the purchase of corresponding replacement parts. For software or circuit problems, the platform can realize equipment self-repair through instructions. For example, when the software of the electrocardiograph fails, the platform can automatically send repair instructions to guide the equipment to self-repair. 5. Compatibility and scalability: The platform supports all trained medical devices, has strong adaptability, and supports multiple generations of equipment operating environments. Whether it is old equipment or the latest model, the platform can provide effective monitoring and maintenance support. Through this platform, the operating efficiency and maintenance level of the equipment can be fundamentally improved, providing more reliable technical support for medical services.

[0113] like Figure 3 As shown, in order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a fault self-repair device for medical equipment, which includes:

[0114] A first acquisition module 301 is used to acquire full-dimensional data of a medical device;

[0115] A second acquisition module 302 is used to acquire, according to the full-dimensional data, a fault type probability corresponding to at least one fault type of the medical device and potential fault information corresponding to at least one potential fault of the medical device; wherein each of the fault types includes at least one potential fault;

[0116] The first processing module 303 is used to repair the medical device according to the full-dimensional data, the fault type probability and the potential fault information.

[0117] Optionally, in the device, the second acquisition module 302 includes:

[0118] A first acquisition unit, configured to input the full-dimensional data into a rule engine to acquire abnormal data; wherein the rule engine is acquired based on the historical full-dimensional data of the medical device and industry standard information;

[0119] The second acquisition unit is used to acquire the fault type probability according to the abnormal data.

[0120] Optionally, in the device, the second acquisition module 302 includes:

[0121] A third acquisition unit, configured to input the full-dimensional data into a pre-acquired fault prediction model to acquire potential fault information corresponding to at least one potential fault of the medical device;

[0122] The method for obtaining the fault prediction model includes:

[0123] Acquire historical full-dimensional data and historical fault information of the medical device; wherein the historical fault information is fault information corresponding to the historical full-dimensional data;

[0124] Inputting the historical full-dimensional data into a first prediction model to obtain predicted historical fault information; wherein the first prediction model is constructed based on a long short-term memory network, a time series, a Markov chain model, and a joint classification model;

[0125] The predicted historical fault information is compared with the historical fault information, the first prediction model is adjusted, and a fault prediction model is obtained.

[0126] Optionally, in the device, the first processing module 303 includes:

[0127] A fourth acquisition unit, configured to acquire a repair strategy according to the full-dimensional data, the fault type probability and the potential fault information;

[0128] The first processing unit is used to repair the medical device according to the repair strategy.

[0129] Optionally, in the device, the first processing unit includes:

[0130] a first processing component, for adjusting the operation status data of the full-dimensional data of the medical device when the repair strategy includes an adjustment parameter;

[0131] a second processing component, in the case where the repair strategy includes repairing the hardware module, enabling the standby module, isolating and repairing the faulty module;

[0132] The third processing component reloads the critical code through the over-the-air download technology OTA when the repair strategy includes repairing the software module.

[0133] Optionally, the device further comprises:

[0134] A first sending module, used to send a fault self-repair report to the client;

[0135] A first recording module, used to record the full-dimensional data, the fault type probability, the potential fault information and the fault self-repair report;

[0136] The fault self-repair report includes one or more of the following:

[0137] Real-time monitoring charts;

[0138] List of medical devices;

[0139] Historical data trend chart;

[0140] Failure probability assessment;

[0141] Fault list and parts purchase order;

[0142] Performance indicator trends.

[0143] Optionally, in the device, the full-dimensional data includes one or more of the following:

[0144] Equipment production data;

[0145] Operation status data;

[0146] Environmental data;

[0147] Behavior data, wherein the behavior data is data of operation behavior collected when the user operates the medical device.

[0148] Optionally, in the device, the potential fault information includes one or more of the following:

[0149] Potential failure probability;

[0150] Potential causes of failure;

[0151] Preset repair methods for potential faults;

[0152] The preset repair probability of a potential fault; wherein the preset repair probability of a potential fault is the repair probability corresponding to the preset repair method of the potential fault.

[0153] In order to achieve the above-mentioned purpose, an embodiment of the present invention also provides an electronic device, including: a processor, a memory, and a program or instruction stored in the memory and executable on the processor; wherein, when the processor executes the program or instruction, the fault self-repair method of the medical device as described above is implemented.

[0154] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a readable storage medium on which a program or instruction is stored, wherein the program or instruction, when executed by a processor, implements the steps in the fault self-repair method of the medical device as described above.

[0155] It should be further explained that the terminals described in this specification include but are not limited to smart phones, tablet computers, etc., and many of the functional components described are called modules in order to more particularly emphasize the independence of their implementation methods.

[0156] In the embodiment of the present invention, module can be implemented with software so that it can be executed by various types of processors. For example, an executable code module of an identification can include one or more physical or logical blocks of computer instructions, for example, it can be constructed as an object, process or function. Nevertheless, the executable code of the identified module does not need to be physically located together, but can include different instructions stored in different positions, and when these instructions are logically combined together, it constitutes a module and realizes the specified purpose of the module.

[0157] In fact, executable code module can be a single instruction or many instructions, and can even be distributed on a plurality of different code segments, distributed among different programs, and distributed across a plurality of memory devices. Similarly, operating data can be identified in the module, and can be implemented and organized in the data structure of any appropriate type according to any appropriate form. The operating data can be collected as a single data set, or can be distributed in different locations (including on different storage devices), and can only be present on a system or network as an electronic signal at least in part.

[0158] When a module can be implemented by software, considering the level of existing hardware technology, a person skilled in the art can build a corresponding hardware circuit to implement the corresponding function of the module that can be implemented by software without considering the cost. The hardware circuit includes a conventional very large scale integration (VLSI) circuit or gate array and existing semiconductors such as logic chips, transistors, or other discrete components. The module can also be implemented by a programmable hardware device, such as a field programmable gate array, a programmable array logic, a programmable logic device, etc.

[0159] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a computer program product, which includes computer instructions, and when the computer instructions are executed by a processor, the steps of the fault self-repair method of the medical device as described above are implemented.

[0160] The above exemplary embodiments are described with reference to the accompanying drawings, and many different forms and embodiments are feasible without departing from the spirit and teachings of the present invention. Therefore, the present invention should not be constructed as a limitation of the exemplary embodiments proposed herein. More specifically, these exemplary embodiments are provided so that the present invention will be perfect and complete, and the scope of the present invention will be conveyed to those who are familiar with the technology. In these figures, the component sizes and relative sizes may be exaggerated for clarity. The terms used here are only based on the purpose of describing specific exemplary embodiments and are not intended to be limiting. As used herein, unless the text clearly indicates otherwise, the singular forms "one", "an" and "the" are intended to include these multiple forms. It will be further understood that the terms "including" and / or "comprising" when used in this specification indicate the presence of the features, integers, steps, operations, components and / or components, but do not exclude the presence or increase of one or more other features, integers, steps, operations, components, components and / or their groups. Unless otherwise indicated, when stated, a range of values ​​includes the upper and lower limits of that range and any subranges therebetween.

[0161] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A fault self-repair method for medical equipment, characterized in that: include: Obtain full-dimensional data of medical equipment; According to the full-dimensional data, a fault type probability corresponding to at least one fault type of the medical device and potential fault information corresponding to at least one potential fault of the medical device are obtained; wherein each of the fault types includes at least one potential fault; The medical device is repaired according to the full-dimensional data, the fault type probability and the potential fault information.

2. The method according to claim 1, characterized in that Obtaining a failure type probability corresponding to at least one failure type of the medical device includes: Input the full-dimensional data into a rule engine to obtain abnormal data; wherein the rule engine is based on the historical full-dimensional data of the medical device and industry standard information acquisition; The fault type probability is obtained according to the abnormal data.

3. The method according to claim 1, characterized in that Acquiring potential fault information corresponding to at least one potential fault of the medical device, including: Inputting the full-dimensional data into a pre-acquired fault prediction model to obtain potential fault information corresponding to at least one potential fault of the medical device; The method for obtaining the fault prediction model includes: Acquire historical full-dimensional data and historical fault information of the medical device; wherein the historical fault information is fault information corresponding to the historical full-dimensional data; Inputting the historical full-dimensional data into a first prediction model to obtain predicted historical fault information; wherein the first prediction model is constructed based on a long short-term memory network, a time series, a Markov chain model, and a joint classification model; The predicted historical fault information is compared with the historical fault information, the first prediction model is adjusted, and a fault prediction model is obtained.

4. The method according to claim 1, characterized in that Repairing the medical device according to the full-dimensional data, the fault type probability and the potential fault information includes: Acquire a repair strategy according to the full-dimensional data, the fault type probability and the potential fault information; The medical device is repaired according to the repair strategy.

5. The method according to claim 4, characterized in that The step of repairing the medical device according to the repair strategy includes: In the case where the repair strategy includes adjusting parameters, adjusting the operating status data of the full-dimensional data of the medical device; In the case where the repair strategy includes repairing a hardware module, enabling a standby module, isolating and repairing the faulty module; In the case where the repair strategy includes repairing the software module, the critical code is reloaded through the over-the-air download technology OTA.

6. The method according to claim 1, characterized in that The method further comprises: Send fault self-repair report to the client; Recording the full-dimensional data, the fault type probability, the potential fault information and the fault self-repair report; The fault self-repair report includes one or more of the following: Real-time monitoring charts; List of medical devices; Historical data trend chart; Failure probability assessment; Fault list and parts purchase order; Performance indicator trends.

7. The method according to claim 1, characterized in that The full-dimensional data includes one or more of the following: Equipment production data; Operation status data; Environmental data; Behavior data, wherein the behavior data is data of operation behavior collected when the user operates the medical device.

8. The method according to claim 1, characterized in that The potential fault information includes one or more of the following: Potential failure probability; Potential causes of failure; Preset repair methods for potential faults; The preset repair probability of a potential fault; wherein the preset repair probability of a potential fault is the repair probability corresponding to the preset repair method of the potential fault.

9. A fault self-repair device for medical equipment, characterized in that: include: A first acquisition module is used to acquire full-dimensional data of medical equipment; A second acquisition module is used to acquire, according to the full-dimensional data, a fault type probability corresponding to at least one fault type of the medical device and potential fault information corresponding to at least one potential fault of the medical device; wherein each of the fault types includes at least one potential fault; The first processing module is used to repair the medical device according to the full-dimensional data, the fault type probability and the potential fault information.

10. An electronic device comprising: A processor, a memory, and a program or instruction stored in the memory and executable on the processor; characterized in that when the processor executes the program or instruction, the fault self-repair method of the medical device as described in any one of claims 1-8 is implemented.

11. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by the processor, the steps in the fault self-repair method of the medical device as described in any one of claims 1-8 are implemented.

12. A computer program product, characterized in that It comprises computer instructions, which, when executed by a processor, implement the steps of the fault self-repair method of the medical device as described in any one of claims 1 to 8.

Images