A medical instrument fault early warning method and system based on endogenous diagnosis

Abstract

The present application relates to the technical field of equipment failure analysis, more particularly to a medical equipment failure early warning method and system based on endogenous diagnosis. The scheme includes setting a 2-time detection directory of medical equipment; setting a corresponding grouping backup mechanism according to the 2-time detection directory; receiving 2 online monitoring data in a remote data center and issuing a first abnormality early warning according to the 2 online monitoring data; setting all data in a to-be-processed database in three storage paths, selecting monitoring data; obtaining all data of a cloud data center, performing historical data analysis, and determining whether to issue a second information early warning. The scheme completes endogenous safety transformation of medical equipment online based on endogenous safety diagnosis. The transformation process includes two stages. The first stage is a grouping backup mechanism, and the second stage is an endogenous monitoring mode, achieving safe and reliable equipment failure diagnosis and information recovery.

Description

Technical Field

[0001] This invention relates to the field of medical device failure analysis technology, and more specifically, to a medical device failure early warning method and system based on endogenous diagnosis. Background Technology

[0002] Medical device malfunctions may manifest as the inability to print or display ultrasound images, data corruption, or discontinuous, jumpy, blurry, or ghosting images during patient examinations. Common causes of medical device malfunctions include: failure to perform examinations according to prescribed times and methods; use of other medical devices causing interference; external injuries or foreign objects entering the machine; unexpected events during the examination, such as sudden power outages, unstable power supply, or damaged cable insulation; and operator error, such as improper machine adjustments.

[0003] Prior to this invention, existing technologies required manual troubleshooting to redo medical device malfunctions, which often caused inconvenience, reduced the safety of the examination, and prevented patients from obtaining timely information about their actual examinations. Summary of the Invention

[0004] In view of the above problems, this invention proposes a medical device fault early warning method and system based on endogenous diagnosis. By using endogenous safety diagnosis, the endogenous safety modification of medical devices can be completed online. The modification process includes two stages: the first stage is a group backup mechanism, and the second stage is an endogenous monitoring method, so as to realize safe and reliable device fault diagnosis and information recovery.

[0005] According to a first aspect of the present invention, a method for early warning of medical device malfunctions based on endogenous diagnostics is provided.

[0006] In one or more embodiments, preferably, the medical device fault early warning method based on endogenous diagnostics includes:

[0007] Establish a catalog of medical devices for two tests;

[0008] Set up a corresponding group backup mechanism based on the two detection directories;

[0009] Receive two online monitoring data points from a remote data center and issue the first anomaly warning based on the two online monitoring data points;

[0010] Configure three storage paths for all data in the database to be processed;

[0011] Retrieve three data points from three independent storage locations and select the monitoring data accordingly;

[0012] Obtain all data from the cloud data center, perform historical data analysis, and determine whether to issue a second warning.

[0013] In one or more embodiments, preferably, setting the two-stage testing catalog for the medical device specifically includes:

[0014] Obtain the total amount of data to be tested and determine the number of times each data point can be tested by medical devices in the preset complementary medical device library.

[0015] The current total amount of data to be detected is judged. If it meets the first calculation formula, it is included in the second detection catalog; otherwise, no processing is performed.

[0016] The first calculation formula is:

[0017] A+B≥2

[0018] Where A represents the number of times the data can be tested by medical devices in the preset complementary medical device library, and B represents the number of times the data can be tested by the current medical device.

[0019] In one or more embodiments, preferably, the step of setting a corresponding group backup mechanism based on the two detection directories specifically includes:

[0020] Obtain the two detection catalogs, and set up two identical sets of sensing and monitoring devices for each monitoring quantity in the two detection catalogs;

[0021] Online data monitoring was conducted, generating two sets of online monitoring data.

[0022] One of the two online monitoring data is randomly selected online and sent to the database to be processed;

[0023] Two online monitoring data points are transmitted to a remote data center via an IoT module.

[0024] In one or more embodiments, preferably, the step of receiving two online monitoring data points in a remote data center and issuing a first anomaly warning based on the two online monitoring data points specifically includes:

[0025] Read two online monitoring data points at the current moment from the remote data center and determine whether they meet the second calculation formula;

[0026] If the second calculation formula is met, a first anomaly warning is issued and the data is stored.

[0027] If the second calculation formula is not met, the first abnormality warning will not be issued, and the data will be stored.

[0028] The second calculation formula is:

[0029] C1-C2>D×(0.5AVG1+0.5AVG2)

[0030] Wherein, C1 is the first data point among the two online monitoring data points, C2 is the second data point among the two online monitoring data points, D is the preset comparison margin coefficient, AVG1 is the historical average of the first data point among the two online monitoring data points, and AVG2 is the historical average of the second data point among the two online monitoring data points.

[0031] In one or more embodiments, preferably, the setting of the three storage paths for all data in the database to be processed specifically includes:

[0032] Once the database to be processed has obtained the data, determine the processing method for the corresponding data.

[0033] Each piece of data is processed separately using three different CPUs;

[0034] Each data point is assigned a separate transmission path and sampling frequency, and after processing, it is stored in three independent storage locations.

[0035] In one or more embodiments, preferably, the step of acquiring three data points from three independent storage locations and selecting the monitoring data specifically includes:

[0036] Retrieve three data points from three independent storage locations, and set a random integer E between 1 and 3;

[0037] When E is 1, the data corresponding to the first of the three independent storage locations is used as the monitoring data;

[0038] When E is 2, the data corresponding to the second location among the three independent storage locations will be used as the monitoring data;

[0039] When E is 3, the data corresponding to the third location among the three independent storage locations will be used as the monitoring data;

[0040] Data that was not selected for monitoring and data that was selected for monitoring from three independent storage locations are sent together to a remote data center via the Internet of Things.

[0041] In one or more embodiments, preferably, the step of acquiring all data from the cloud data center, performing historical data analysis, and determining whether to issue a second information warning specifically includes:

[0042] Obtain all historical data from the cloud data center, and use the third calculation formula to calculate the estimated data to be collected for each data point.

[0043] The volatility index is calculated using the fourth calculation formula based on the estimated collected data.

[0044] Determine whether the volatility index satisfies the fifth calculation formula;

[0045] If the conditions are met, a second warning will be issued, and all current monitoring data will be displayed in the monitoring report.

[0046] If the conditions are not met, all data from the three independent storage locations will be displayed in the monitoring report;

[0047] The third calculation formula is:

[0048] G = (F1 + F2 + F3) ÷ 3

[0049] Wherein, G is the estimated collected data, F1 is the data corresponding to the first position among the three independent storage locations, F2 is the data corresponding to the first position among the three independent storage locations, and F3 is the data corresponding to the first position among the three independent storage locations.

[0050] The fourth calculation formula is:

[0051] Z = (maxT(G) - minT(G)) ÷ G

[0052] Where Z is the volatility index, maxT(G) is the maximum value of G within a preset time range T, and minT(G) is the maximum value of G within a preset time range T.

[0053] The fifth calculation formula is:

[0054] Z <Y

[0055] Where Y represents the volatility comparison margin.

[0056] According to a second aspect of the present invention, a medical device fault early warning system based on endogenous diagnostics is provided.

[0057] In one or more embodiments, preferably, the medical device fault early warning system based on endogenous diagnostics includes:

[0058] The catalog setting module is used to set the catalog for the second testing of medical devices;

[0059] The backup design module is used to set the corresponding group backup mechanism based on the two detection directories;

[0060] The first early warning module is used to receive two online monitoring data points in a remote data center and issue the first abnormality warning based on the two online monitoring data points;

[0061] The storage settings module is used to configure the three storage paths for all data in the database to be processed;

[0062] The monitoring selection module is used to acquire three data points from three independent storage locations and select the monitoring data.

[0063] The second early warning module is used to acquire all data from the cloud data center, perform historical data analysis, and determine whether to issue a second early warning.

[0064] According to a third aspect of the present invention, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the method as described in any one of the first aspects of the present invention.

[0065] According to a fourth aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in any one aspect of the present invention.

[0066] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0067] In this invention, for the most critical or irreproducible single important detection results, two detection paths are set up. Powered by different power supplies, different monitoring devices perform replication detection completely independently of the original monitoring device, forming a group backup of key information. This ensures that there is sufficient monitoring data in each monitoring, avoiding the situation where the detection result cannot be reproduced. The grouping process relies on a random allocation method to ensure the reliability and credibility of the main result.

[0068] In this invention, three independent data processing channels are used in the data analysis and processing process. Three sets of different analytical data detection results are obtained through the three processing channels. During each detection process, one set of detection results is automatically acquired. For highly fluctuating data, all information of the three sets of detection results is displayed at the same time, which effectively supplements the key information. At the same time, since a unique data processing method is not used, failures caused by system errors of medical devices are avoided.

[0069] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0070] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0071] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0072] Figure 1 This is a flowchart of a medical device fault early warning method based on endogenous diagnosis, according to an embodiment of the present invention.

[0073] Figure 2 This is a flowchart illustrating the setting of a two-stage testing catalog for a medical device in a medical device fault early warning method based on endogenous diagnostics, according to an embodiment of the present invention.

[0074] Figure 3 This is a flowchart of a medical device fault early warning method based on endogenous diagnosis according to an embodiment of the present invention, which sets up a corresponding group backup mechanism according to the two detection catalogs.

[0075] Figure 4 This is a flowchart illustrating a medical device fault early warning method based on endogenous diagnostics according to an embodiment of the present invention, which involves receiving two online monitoring data points in a remote data center and issuing a first abnormality warning based on the two online monitoring data points.

[0076] Figure 5 This is a flowchart illustrating the setup of three storage paths for all data in the database to be processed in a medical device fault early warning method based on endogenous diagnosis, according to an embodiment of the present invention.

[0077] Figure 6 This is a flowchart illustrating the process of acquiring three data points from three independent storage locations and selecting monitoring data in a medical device fault early warning method based on endogenous diagnostics according to an embodiment of the present invention.

[0078] Figure 7 This is a flowchart illustrating a medical device fault early warning method based on endogenous diagnosis according to an embodiment of the present invention, which involves obtaining all data from a cloud data center, performing historical data analysis, and determining whether to issue a second information warning.

[0079] Figure 8 This is a structural diagram of a medical device fault early warning system based on endogenous diagnosis, according to an embodiment of the present invention.

[0080] Figure 9 This is a structural diagram of an electronic device according to one embodiment of the present invention. Detailed Implementation

[0081] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0082] 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.

[0083] Medical device malfunctions may manifest as the inability to print or display ultrasound images, data corruption, or discontinuous, jumpy, blurry, or ghosting images during patient examinations. Common causes of medical device malfunctions include: failure to perform examinations according to prescribed times and methods; use of other medical devices causing interference; external injuries or foreign objects entering the machine; unexpected events during the examination, such as sudden power outages, unstable power supply, or damaged cable insulation; and operator error, such as improper machine adjustments.

[0084] Prior to this invention, existing technologies required manual troubleshooting to redo medical device malfunctions, which often caused inconvenience, reduced the safety of the examination, and prevented patients from obtaining timely information about their actual examinations.

[0085] This invention provides a method and system for early warning of medical device faults based on endogenous diagnostics. This solution utilizes endogenous safety diagnostics to perform online endogenous safety modifications to medical devices. The modification process includes two stages: the first stage is a group backup mechanism, and the second stage is an endogenous monitoring method, achieving safe and reliable device fault diagnosis and information recovery.

[0086] According to a first aspect of the present invention, a method for early warning of medical device malfunctions based on endogenous diagnostics is provided.

[0087] Figure 1This is a flowchart of a medical device fault early warning method based on endogenous diagnosis, according to an embodiment of the present invention.

[0088] In one or more embodiments, preferably, the medical device fault early warning method based on endogenous diagnostics includes:

[0089] S101. Establish a catalog of medical devices for two tests;

[0090] S102. Set up a corresponding group backup mechanism based on the two detection directories;

[0091] S103. Receive two online monitoring data points in the remote data center and issue the first anomaly warning based on the two online monitoring data points;

[0092] S104. Setting the three storage paths for all data in the database to be processed;

[0093] S105. Obtain three data points from three independent storage locations and select the monitoring data.

[0094] S106. Obtain all data from the cloud data center, perform historical data analysis, and determine whether to issue a second information warning.

[0095] In this embodiment of the invention, two detection channels are set to detect information, two detection synchronizations are arranged, and a group backup mechanism is set. Based on the group backup, it is confirmed that there is abnormal information of key data. Then, three different types of data processing methods are set, one of the data is selected as the monitoring result, and some of the data is set as high fluctuation data.

[0096] Figure 2 This is a flowchart illustrating the setting of a two-stage testing catalog for a medical device in a medical device fault early warning method based on endogenous diagnostics, according to an embodiment of the present invention.

[0097] like Figure 2 As shown, in one or more embodiments, preferably, setting the two-stage testing catalog for the medical device specifically includes:

[0098] S201. Obtain the total amount of data to be tested, and determine the number of times each data can be tested by medical devices in the preset complementary medical device library.

[0099] S202. Judge all the data to be detected. If the data meets the first calculation formula, it is included in the second detection catalog; otherwise, no processing is performed.

[0100] The first calculation formula is:

[0101] A+B≥2

[0102] Where A represents the number of times the data can be tested by medical devices in the preset complementary medical device library, and B represents the number of times the data can be tested by the current medical device.

[0103] In this embodiment of the invention, among the detection devices of the same type, which of the corresponding detection information is irreplaceable? This irreplaceable information is the path that the device needs to perform two detections. In order to realize this two-detection setting process, it is first determined which path detection information needs to be set to two detections. The most common way to do this screening process is to judge by calculation formula. When the first calculation formula is not met, it is considered that the corresponding two-detection path needs to be set.

[0104] Figure 3 This is a flowchart of a medical device fault early warning method based on endogenous diagnosis according to an embodiment of the present invention, which sets up a corresponding group backup mechanism according to the two detection catalogs.

[0105] like Figure 3 As shown, in one or more embodiments, preferably, the step of setting a corresponding group backup mechanism based on the two detection directories specifically includes:

[0106] S301. Obtain the two detection catalogs, and set up two identical sets of sensing and monitoring devices for each monitoring quantity in the two detection catalogs;

[0107] S302. Online data monitoring is performed, generating two sets of online monitoring data;

[0108] S303. Randomly select one of the two online monitoring data and send it to the database to be processed.

[0109] S304. Transmit the two online monitoring data to the remote data center via the Internet of Things module.

[0110] In this embodiment of the invention, by randomly selecting data during each detection process and uploading the associated data to a remote data center via the network, the corresponding data can be backed up in groups. The backup data can be analyzed online in the remote database. However, the random transmission method may lead to the risk of systemic errors if the data forms inspection results.

[0111] Figure 4 This is a flowchart illustrating a medical device fault early warning method based on endogenous diagnostics according to an embodiment of the present invention, which involves receiving two online monitoring data points in a remote data center and issuing a first abnormality warning based on the two online monitoring data points.

[0112] like Figure 4As shown, in one or more embodiments, preferably, the step of receiving two online monitoring data points in a remote data center and issuing a first anomaly warning based on the two online monitoring data points specifically includes:

[0113] S401. Read the two online monitoring data points at the current time from the remote data center and determine whether they meet the second calculation formula;

[0114] S402. If the second calculation formula is satisfied, a first abnormality warning is issued and the data is stored.

[0115] S403. If the second calculation formula is not met, the first abnormality warning will not be issued, and the data will be stored.

[0116] The second calculation formula is:

[0117] C1-C2>D×(0.5AVG1+0.5AVG2)

[0118] Wherein, C1 is the first data point among the two online monitoring data points, C2 is the second data point among the two online monitoring data points, D is the preset comparison margin coefficient, AVG1 is the historical average of the first data point among the two online monitoring data points, and AVG2 is the historical average of the second data point among the two online monitoring data points.

[0119] In this embodiment of the invention, in the data center, anomaly analysis based on a calculation formula is performed on the two obtained detection synchronization information to form the first wave of information warning.

[0120] Figure 5 This is a flowchart illustrating the setup of three storage paths for all data in the database to be processed in a medical device fault early warning method based on endogenous diagnosis, according to an embodiment of the present invention.

[0121] like Figure 5 As shown, in one or more embodiments, preferably, the setting of the three storage paths for all data in the database to be processed specifically includes:

[0122] S501. After the database to be processed obtains data, determine the processing method for the corresponding data;

[0123] S502: Each data item is processed separately using three different CPUs.

[0124] S503. Set a separate transmission path and sampling frequency for each data, and store it in three independent storage locations after processing.

[0125] In this embodiment of the invention, for the same type of data, three CPUs, three transmission lines, and three different sampling frequencies are used to complete the storage of three sets of processing and calculation results.

[0126] Figure 6 This is a flowchart illustrating the process of acquiring three data points from three independent storage locations and selecting monitoring data in a medical device fault early warning method based on endogenous diagnostics according to an embodiment of the present invention.

[0127] like Figure 6 As shown, in one or more embodiments, preferably, the step of acquiring three data points from three independent storage locations and selecting the monitoring data specifically includes:

[0128] S601. Obtain three data points from three independent storage locations and set a random integer E between 1 and 3;

[0129] S602. When E is 1, the data corresponding to the first location among the three independent storage locations is used as the monitoring data.

[0130] S603. When E is 2, the data corresponding to the second location among the three independent storage locations is used as the monitoring data.

[0131] S604. When E is 3, the data corresponding to the third location among the three independent storage locations is used as the monitoring data.

[0132] S605: Send the unselected and selected monitoring data from three independent storage locations together to a remote data center via the Internet of Things.

[0133] In this embodiment of the invention, the stored data is selected online by random selection, and the unselected data and the selected data are simultaneously placed in the cloud.

[0134] Figure 7 This is a flowchart illustrating a medical device fault early warning method based on endogenous diagnosis according to an embodiment of the present invention, which involves obtaining all data from a cloud data center, performing historical data analysis, and determining whether to issue a second information warning.

[0135] like Figure 7 As shown, in one or more embodiments, preferably, the step of acquiring all data from the cloud data center, performing historical data analysis, and determining whether to issue a second information warning specifically includes:

[0136] S701. Obtain all historical data from the cloud data center and use the third calculation formula to calculate the estimated data to be collected for each data point.

[0137] S702. Calculate the fluctuation index using the fourth calculation formula based on the estimated collected data.

[0138] S703. Determine whether the volatility index satisfies the fifth calculation formula;

[0139] S704. If the conditions are met, a second warning will be issued, and all current monitoring data will be displayed in the monitoring report.

[0140] S705. If not satisfied, all data from the three independent storage locations will be displayed in the monitoring report.

[0141] The third calculation formula is:

[0142] G = (F1 + F2 + F3) ÷ 3

[0143] Wherein, G is the estimated collected data, F1 is the data corresponding to the first position among the three independent storage locations, F2 is the data corresponding to the first position among the three independent storage locations, and F3 is the data corresponding to the first position among the three independent storage locations.

[0144] The fourth calculation formula is:

[0145] Z = (maxT(G) - minT(G)) ÷ G

[0146] Where Z is the volatility index, maxT(G) is the maximum value of G within a preset time range T, and minT(G) is the maximum value of G within a preset time range T.

[0147] The fifth calculation formula is:

[0148] Z <Y

[0149] Where Y represents the volatility comparison margin.

[0150] In this embodiment of the invention, the core idea for the second anomaly analysis is to determine which data belongs to high volatility based on specific historical fluctuation information. If it belongs to high volatility data, it is automatically processed, while for non-high volatility data, a second information warning is required.

[0151] According to a second aspect of the present invention, a medical device fault early warning system based on endogenous diagnostics is provided.

[0152] Figure 8 This is a structural diagram of a medical device fault early warning system based on endogenous diagnosis, according to an embodiment of the present invention.

[0153] In one or more embodiments, preferably, the medical device fault early warning system based on endogenous diagnostics includes:

[0154] The catalog setting module 801 is used to set the catalog for the second testing of medical devices;

[0155] Backup design module 802 is used to set a corresponding group backup mechanism according to the two detection directories;

[0156] The first early warning module 803 is used to receive two online monitoring data in a remote data center and issue a first abnormality warning based on the two online monitoring data;

[0157] The storage settings module 804 is used to set the three storage paths for all data in the database to be processed;

[0158] The monitoring selection module 805 is used to acquire three data points from three independent storage locations and select the monitoring data.

[0159] The second early warning module 806 is used to acquire all data from the cloud data center, perform historical data analysis, and determine whether to issue a second early warning.

[0160] In this embodiment of the invention, a system suitable for different structures is realized through a series of modular designs. This system can achieve closed-loop, reliable, and efficient execution through data acquisition, analysis, and control.

[0161] According to a third aspect of the present invention, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the method as described in any one of the first aspects of the present invention.

[0162] According to a fourth aspect of the present invention, an electronic device is provided. Figure 9 This is a structural diagram of an electronic device according to one embodiment of the present invention. Figure 9The illustrated electronic device is a general-purpose medical device fault warning device based on endogenous diagnostics, comprising a general computer hardware architecture, including at least a processor 901 and a memory 902. The processor 901 and memory 902 are connected via a bus 903. The memory 902 is adapted to store instructions or programs executable by the processor 901. The processor 901 can be a standalone microprocessor or a collection of one or more microprocessors. Thus, the processor 901 executes the instructions stored in the memory 902, thereby performing the method flow of the embodiments of the present invention as described above to process data and control other devices. The bus 903 connects the aforementioned components together, and also connects these components to a display controller 904, a display device, and an input / output (I / O) device 905. The input / output (I / O) device 905 can be a mouse, keyboard, modem, network interface, touch input device, motion-sensing input device, printer, and other devices known in the art. Typically, the input / output device 905 is connected to the system via an input / output (I / O) controller 906.

[0163] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0164] In this invention, for the most critical or irreproducible single important detection results, two detection paths are set up. Powered by different power supplies, different monitoring devices perform replication detection completely independently of the original monitoring device, forming a group backup of key information. This ensures that there is sufficient monitoring data in each monitoring, avoiding the situation where the detection result cannot be reproduced. The grouping process relies on a random allocation method to ensure the reliability and credibility of the main result.

[0165] In this invention, three independent data processing channels are used in the data analysis and processing process. Three sets of different analytical data detection results are obtained through the three processing channels. During each detection process, one set of detection results is automatically acquired. For highly fluctuating data, all information of the three sets of detection results is displayed at the same time, which effectively supplements the key information. At the same time, since a unique data processing method is not used, failures caused by system errors of medical devices are avoided.

[0166] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0167] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0168] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0169] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0170] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A medical device fault early warning method based on endogenous diagnostics, characterized in that, The method includes: Establish a catalog of medical devices for two tests; Set up a corresponding group backup mechanism based on the two detection directories; Receive two online monitoring data points from a remote data center and issue the first anomaly warning based on the two online monitoring data points; Configure three storage paths for all data in the database to be processed; Retrieve three data points from three independent storage locations and select the monitoring data accordingly; Obtain all data from the cloud data center, perform historical data analysis, and determine whether to issue a second warning. The step of receiving two online monitoring data points in a remote data center and issuing a first anomaly warning based on these two data points specifically includes: Read two online monitoring data points at the current moment from the remote data center and determine whether they meet the second calculation formula; If the second calculation formula is met, a first anomaly warning is issued and the data is stored. If the second calculation formula is not met, the first abnormality warning will not be issued, and the data will be stored. The second calculation formula is: C1-C2>D×(0.5AVG1+0.5AVG2) Wherein, C1 is the first data point among the two online monitoring data points, C2 is the second data point among the two online monitoring data points, D is the preset comparison margin coefficient, AVG1 is the historical average of the first data point among the two online monitoring data points, and AVG2 is the historical average of the second data point among the two online monitoring data points; Specifically, the setting of the three storage paths for all data in the database to be processed includes: Once the database to be processed has obtained the data, determine the processing method for the corresponding data. Each piece of data is processed separately using three different CPUs; Each data point is assigned a separate transmission path and sampling frequency, and after processing, it is stored in three independent storage locations. Specifically, the process of acquiring three data points from three independent storage locations and selecting the monitoring data includes: Retrieve three data points from three independent storage locations, and set a random integer E between 1 and 3; When E is 1, the data corresponding to the first of the three independent storage locations is used as the monitoring data; When E is 2, the data corresponding to the second location among the three independent storage locations will be used as the monitoring data; When E is 3, the data corresponding to the third location among the three independent storage locations will be used as the monitoring data; The unselected and selected monitoring data from three independent storage locations are sent together to a remote data center via the Internet of Things; Specifically, obtaining all data from the cloud data center, performing historical data analysis, and determining whether to issue a second warning includes: The estimated data to be collected is calculated using a third calculation formula by acquiring all historical data from the cloud data center. The volatility index is calculated using the fourth calculation formula based on the estimated collected data. Determine whether the volatility index satisfies the fifth calculation formula; If the conditions are met, a second warning will be issued, and all current monitoring data will be displayed in the monitoring report. If the conditions are not met, all data from the three independent storage locations will be displayed in the monitoring report; The third calculation formula is: G = (F1 + F2 + F3) ÷ 3 Wherein, G is the estimated collected data, F1 is the data corresponding to the first location among the three independent storage locations, F2 is the data corresponding to the second location among the three independent storage locations, and F3 is the data corresponding to the third location among the three independent storage locations; The fourth calculation formula is: Z = (maxT(G) - minT(G)) ÷ G Where Z is the volatility index, maxT(G) is the maximum value of G within a preset time range T, and minT(G) is the minimum value of G within a preset time range T. The fifth calculation formula is: Z>Y Where Y represents the volatility comparison margin; The aforementioned two-stage testing catalog for medical devices specifically includes: Obtain the total amount of data to be tested, and extract the number of times each data point can be tested by medical devices in the preset complementary medical device library; The current total amount of data to be detected is judged. If it meets the first calculation formula, it is included in the second detection catalog; otherwise, no processing is performed. The first calculation formula is: A+B≥2 Where A represents the number of times the data can be tested by medical devices in the preset complementary medical device library, and B represents the number of times the data can be tested by the current medical device. Specifically, the step of setting a corresponding group backup mechanism based on the two detection directories includes: Obtain the two detection catalogs, and set up two identical sets of sensing and monitoring devices for each monitoring quantity in the two detection catalogs; Online data monitoring was conducted, generating two sets of online monitoring data. One of the two online monitoring data is randomly selected online and sent to the database to be processed; Two online monitoring data points are transmitted to a remote data center via an IoT module.

2. A medical device fault early warning system based on endogenous diagnostics, characterized in that, The system is used to implement the method as described in claim 1, the system comprising: The catalog setting module is used to set the catalog for the second testing of medical devices; The backup design module is used to set the corresponding group backup mechanism based on the two detection directories; The first early warning module is used to receive two online monitoring data points in a remote data center and issue the first abnormality warning based on the two online monitoring data points; The storage settings module is used to configure the three storage paths for all data in the database to be processed; The monitoring selection module is used to acquire three data points from three independent storage locations and select the monitoring data. The second early warning module is used to acquire all data from the cloud data center, perform historical data analysis, and determine whether to issue a second early warning.

3. A computer-readable storage medium storing computer program instructions thereon, characterized in that, The computer program instructions, when executed by a processor, implement the method as described in claim 1.

4. An electronic device, comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method as described in claim 1.

Images