A medical device monitoring method, device and apparatus based on device logs

Abstract

The application discloses a medical equipment monitoring method and device based on equipment logs and equipment. The method comprises the following steps: obtaining to-be-evaluated state data of a candidate medical equipment from a cloud server; determining a state data threshold of the candidate medical equipment according to a candidate equipment type and historical state data of the candidate medical equipment based on a threshold dynamic generation model; determining a current running state of the candidate medical equipment and a state data trend chart according to the to-be-evaluated state data and the state data threshold, and feeding back the current state data and the state data trend chart to a client; if it is identified that there is a candidate medical equipment with an abnormal state as the current running state, the candidate medical equipment is determined as an abnormal medical equipment, a device abnormality report of the abnormal medical equipment is determined according to an abnormal equipment type, abnormal state data and a state data threshold of the abnormal medical equipment, and the device abnormality report is sent to the client. The above technical scheme improves the reliability of remote detection of medical equipment.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of medical equipment, in particular to the technical field of medical equipment management, and specifically to a medical equipment monitoring method and device based on equipment logs and a medical equipment monitoring device. BACKGROUND

[0002] The conventional daily maintenance and repair process of medical equipment is generally as follows: medical equipment is used by personnel of a department on a daily basis; problems are found and reported to the equipment department; the equipment department inspects the equipment and finds that the problem cannot be solved, and then contacts professional maintenance personnel; the professional maintenance personnel perform performance inspection, safety inspection, and fault repair, etc.

[0003] However, the conventional daily maintenance and repair process cannot allow the equipment to be checked at any time and any place, and cannot allow the medical equipment in an abnormal state to be found in a timely manner. To solve this problem, existing solutions generally take remote monitoring measures to monitor the running state of each medical equipment in real time. Although the real-time detection of the state of the equipment is achieved, the data to be detected and the determination of the abnormal state of each medical equipment are different in a medical environment where multiple types of medical equipment coexist. At this time, the conventional remote monitoring is prone to misjudgment of the abnormal state of the equipment. SUMMARY

[0004] The present application provides a medical equipment monitoring method and device based on equipment logs and a medical equipment monitoring device to improve the accuracy and reliability of the determination of the current state of each medical equipment in a medical environment where multiple types of medical equipment coexist.

[0005] According to an aspect of the present application, a medical equipment monitoring method based on equipment logs is provided. The method is applied to a data management center of a medical equipment management system. The medical equipment management system further includes a data acquisition device, a cloud server, a client, and at least two candidate medical equipment of different types. The cloud server is in communication connection with the data acquisition device and the data management center. The data management center is in communication connection with the client. The data acquisition device is in communication connection with the at least two candidate medical equipment. The method includes:

[0006] acquiring and storing the to-be-evaluated state data of the candidate medical equipment from the cloud server, wherein the to-be-evaluated state data is determined by the cloud server according to the candidate equipment type and the current state data of the candidate medical equipment; the current state data is obtained by the data acquisition device by collecting the running data of the candidate medical equipment within a preset time period and uploading to the cloud server;

[0007] determine, based on a candidate device type and historical state data of the candidate medical device, a state data threshold of the candidate medical device according to a threshold dynamic generation model, wherein the threshold dynamic generation model is obtained by improving a recurrent neural network according to the candidate device type;

[0008] determine, based on the to-be-evaluated state data and the state data threshold, a current running state and a state data trend graph of the candidate medical device, and feed back the current state data and the state data trend graph to the client;

[0009] If it is identified that there is a candidate medical device with an abnormal state, the candidate medical device is determined as an abnormal medical device, and a device abnormality report of the abnormal medical device is determined according to an abnormal device type, abnormal state data and a state data threshold of the abnormal medical device, and the device abnormality report is sent to the client.

[0010] According to another aspect of the present application, a medical device monitoring device based on device logs is provided, which is configured in a data management center of a medical device management system; the medical device management system further comprises a data acquisition device, a cloud server, a client and at least two candidate medical devices of different types; the cloud server is in communication connection with the data acquisition device and the data management center respectively; the data management center is in communication connection with the client; the data acquisition device is in communication connection with at least two candidate medical devices; the device comprises:

[0011] a data acquisition module, configured to acquire to-be-evaluated state data of the candidate medical device from the cloud server and store the to-be-evaluated state data; wherein the to-be-evaluated state data is determined by the cloud server according to a candidate device type and current state data of the candidate medical device; the current state data is obtained by the data acquisition device by acquiring running data of the candidate medical device in a preset time period and uploaded to the cloud server;

[0012] a threshold determination module, configured to determine, based on a threshold dynamic generation model, a state data threshold of the candidate medical device according to a candidate device type and historical state data of the candidate medical device; wherein the threshold dynamic generation model is obtained by improving a recurrent neural network according to the candidate device type;

[0013] a state determination module, configured to determine, based on the to-be-evaluated state data and the state data threshold, a current running state and a state data trend graph of the candidate medical device, and feed back the current state data and the state data trend graph to the client;

[0014] an abnormality feedback module, configured to: if it is identified that there is a candidate medical device in the abnormal state, determine the candidate medical device as an abnormal medical device; and according to an abnormal device type, abnormal state data and state data threshold of the abnormal medical device, determine a device abnormality report of the abnormal medical device, and send the device abnormality report to a client.

[0015] According to another aspect of the present application, an electronic device is provided, the electronic device comprising:

[0016] one or more processors;

[0017] a memory for storing one or more programs;

[0018] When the one or more programs are executed by the one or more processors, the one or more processors implement any one of the medical device monitoring methods based on device logs provided by the embodiments of the present application.

[0019] According to another aspect of the present application, a computer readable storage medium is provided, having stored thereon a computer program, which, when executed by a processor, implements any one of the medical device monitoring methods based on device logs provided by the embodiments of the present application.

[0020] According to another aspect of the present application, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements any one of the medical device monitoring methods based on device logs provided by the embodiments of the present application.

[0021] The application obtains the to-be-evaluated state data of the candidate medical device from the cloud server and stores it; wherein the to-be-evaluated state data is determined by the cloud server according to the candidate device type and the current state data of the candidate medical device; the current state data is obtained by collecting the running data of the candidate medical device in a preset time period by the data collection device and uploaded to the cloud server; a threshold dynamic generation model is generated based on the threshold, and the state data threshold of the candidate medical device is determined according to the candidate device type and the historical state data of the candidate medical device; wherein the threshold dynamic generation model is improved according to the candidate device type based on the recurrent neural network; the current running state of the candidate medical device and the state data trend chart are determined according to the to-be-evaluated state data and the state data threshold, and the current state data and the state data trend chart are fed back to the client; if it is identified that there is a candidate medical device with an abnormal state, the candidate medical device is determined as an abnormal medical device, and the device abnormal report of the abnormal medical device is determined according to the abnormal device type, the abnormal state data and the state data threshold of the abnormal medical device, and the device abnormal report is sent to the client. The above technical scheme, by using the device type adaptive analysis combined with the threshold dynamic generation model, helps to improve the accuracy and reliability of the current state determination of each medical device in a medical environment where multiple types of medical devices coexist. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 is a flow chart of a medical device monitoring method based on device logs according to an embodiment of the application;

[0023] Figure 2 is a flow chart of a medical device monitoring method based on device logs according to an embodiment of the application;

[0024] Figure 3 is a structural schematic diagram of a medical device monitoring device based on device logs according to an embodiment of the application;

[0025] Figure 4 is a structural schematic diagram of an electronic device implementing a medical device monitoring method based on device logs according to an embodiment of the application. DETAILED DESCRIPTION

[0026] In order to enable persons skilled in the art to better understand the application scheme, the technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by persons skilled in the art without creative labor should be within the scope of protection of the application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and in the above drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] In addition, it should also be noted that in the technical solutions of the present application, the collection, storage, use, processing, transmission, provision and disclosure of related data such as the to-be-evaluated state data and the current state data, etc. comply with the relevant legal regulations and do not violate public order and good customs.

[0029] Embodiment one

[0030] Figure 1 is a flowchart of a medical device monitoring method based on device logs according to the first embodiment of the present application. The present embodiment can be applied to the real-time detection and remote maintenance of the running state of each medical device in a medical environment where multiple types of medical devices coexist. It can be executed by a medical device monitoring device based on device logs. The medical device monitoring device based on device logs can be realized in the form of hardware and / or software. The medical device monitoring device based on device logs can be configured in a computer device, such as a data management center of a medical device management system. The medical device management system further includes a data acquisition device, a cloud server, a client and at least two candidate medical devices of different types. The cloud server is in communication connection with the data acquisition device and the data management center respectively. The data management center is in communication connection with the client. The data acquisition device is in communication connection with the at least two candidate medical devices. As shown in Figure 1 the method comprises:

[0031] S110, obtaining to-be-evaluated state data of the candidate medical device from the cloud server and storing; wherein the to-be-evaluated state data is determined by the cloud server according to the candidate device type and the current state data of the candidate medical device; the current state data is obtained by the data acquisition device collecting the running data of the candidate medical device in a preset time period and uploading to the cloud server.

[0032] In this embodiment, the cloud server refers to a server that provides data storage, processing and computing capabilities on a cloud computing platform, and users can remotely access and use its resources through the network. The candidate medical device refers to a medical device that needs to be monitored in real time in the current medical environment; for example, the medical device can be a CT device, an MR device, a ventilator, etc. The to-be-evaluated state data refers to the device state data that needs to be checked in the process of evaluating the current running state of the device, which usually includes various performance indicators and running data of the device; it should be noted that the to-be-evaluated state data is time series data. The candidate device type refers to the type or category of the medical device, which can be classified based on the function, technical specifications, etc. of the device. The current state data refers to the real-time running data of the device within a certain time period, such as the ball tube heat capacity parameter, the liquid helium pressure value, the valve opening and closing frequency, etc.; it should be noted that the current state data is time series data. The data acquisition device refers to a hardware device for collecting device running data, which usually has sensor functions and can monitor the state of the device in real time.

[0033] For example, the current state data can be determined by the following method: collecting data from the candidate medical device through the data acquisition device to obtain key data, thereby monitoring the state of the relevant part of the medical device; for example, the collected key data is the log file data of the CT device, thereby monitoring the number of ignitions of the core spare part ball tube; for example, the collected key data is the data information of the sensor on the magnet in the MR device, thereby monitoring the liquid helium level, the liquid helium pressure, etc.; sorting the collected data information in chronological order of event occurrence, and then encapsulating the sorted data information; uploading the encapsulated data information to the cloud server for storage.

[0034] For example, taking the candidate medical device as a CT device, an MR device and a ventilator, the to-be-evaluated state data can be the value of the key data of the medical device; correspondingly, the to-be-evaluated state data can be determined by the following method: in a mixed environment of simultaneously monitoring the CT device, the MR device and the ventilator: CT device analysis: identifying the medical device whose device type is a CT device, loading the system log analysis template, extracting the ball tube heat capacity parameter, and normalizing it to the [0, 1] interval value; MR device analysis: identifying the medical device whose device type is an MR device, loading the sensor data analysis template, extracting the liquid helium pressure value, and filtering abnormal jump points; ventilator analysis: identifying the medical device whose device type is a ventilator, loading the custom event log template, counting the valve opening and closing frequency (times / minute), and aggregating in a 5-second window. Further, the events in the unencapsulated data information are converted into timestamps, and each data value is stored in the database corresponding to the timestamp; each data value is calculated to obtain the value of the key data within a certain time range.

[0035] S120, based on the threshold value dynamic generation model, according to the candidate equipment type and the historical state data of the candidate medical equipment, determine the state data threshold of the candidate medical equipment; wherein the threshold value dynamic generation model is improved according to the candidate equipment type and the historical state data of the candidate medical equipment.

[0036] In this embodiment, the threshold value dynamic generation model refers to a model that dynamically generates the running state threshold of the equipment based on the candidate equipment type and the historical state data, by improving the recurrent neural network. The recurrent neural network refers to a type of neural network that is good at processing time series data, can keep the information of the previous state, and can capture the dependency in the sequence data through the loop structure. The historical state data refers to the running data of the equipment in the past period of time, including various performance indicators and operating states of the equipment. The state data threshold refers to the limit value for judging whether the equipment running state is normal; exceeding this threshold usually means that the equipment is in an abnormal state.

[0037] For example, taking the CT device ball firing scene as an example: the standard recurrent neural network model generally inputs 72-hour firing frequency sequence, and the threshold is fixed at 100 times / day; the threshold value dynamic generation model of the present application inputs historical state data at the same time, and splices the candidate equipment type; the attention layer gives the equipment type a weight of 0.83 and the sensor data a weight of 0.17; the output dynamic threshold (workday threshold = 118 times, holiday threshold = 76 times); compared with the standard recurrent neural network model, the false positive rate of the threshold value dynamic generation model adopted by the present application is reduced from 28% to 9%, and the early warning accuracy is improved by 27%.

[0038] S130, according to the to-be-evaluated state data and the state data threshold, determine the current running state and the state data trend chart of the candidate medical equipment, and feed back the current state data and the state data trend chart to the client.

[0039] In this embodiment, the current running state refers to the current working state of the equipment, which can be "normal" or "abnormal", etc. The state data trend chart refers to a chart that represents the change of the equipment state data over time, which is usually used to observe the change trend of the equipment running state. The client refers to the equipment or software operated and controlled by the end user.

[0040] For example, after the data management center receives and stores the data information, it compares each data value corresponding to the equipment type with the threshold value corresponding to each data value in the data management center, to obtain the current running state of the candidate medical equipment; the data management center draws the corresponding data trend chart according to the received data information, and stores the data trend chart in the data management center, and sends it to the client or can be requested to view as needed, so as to facilitate the professional maintenance personnel to review and analyze the data later.

[0041] S140, if it is identified that there is a candidate medical device in an abnormal state, the candidate medical device is determined as an abnormal medical device, and a device abnormality report of the abnormal medical device is determined according to the abnormal device type of the abnormal medical device, the abnormal state data and the state data threshold, and the device abnormality report is sent to the client.

[0042] In this embodiment, the abnormal state refers to a state in which the device operating state deviates from the normal preset range. The abnormal medical device refers to a medical device that detects an abnormal state, which may have a fault or performance problem. The abnormal device type refers to the type of device with a fault or abnormal state. The abnormal state data refers to the state data to be evaluated of the abnormal device. The device abnormality report refers to a detailed record and analysis report of the device abnormal state, which usually includes device fault type, occurrence time, possible cause and other information.

[0043] For example, the device abnormality report can be a warning information; accordingly, if the data value exceeds the threshold value, the management center client automatically generates the corresponding warning information, and stores the warning information; wherein the warning information at least includes the warning generation time and the warning reason; for example, a certain warning information is: 2022-02-0312:34:12 the number of times of tube firing exceeds the threshold value; according to the client request or according to the set push time, the warning information is automatically sent to the client; for example, the user terminal is a mobile phone, the user can view the information or send an application request to view the required information through a browser or an applet, or the management center client publishes the information on a public number regularly, and the user can access the public number to view the information.

[0044] Optionally, the data management center is in communication connection with at least two candidate medical devices, and accordingly, after sending the device abnormality report to the client, if a parameter modification instruction for the abnormal medical device sent by the client is identified, the current use of the abnormal medical device is detected to obtain the current working state of the abnormal medical device; wherein the current working state includes an idle state and a using state; if the current working state is the using state, a modification prohibition warning is sent to the client, and in the case that the current working state of the abnormal medical device changes to the idle state, the parameter modification instruction is executed.

[0045] In this embodiment, the parameter modification instruction refers to an instruction sent by the client to the device, used to modify the working parameters or configuration of the device. The current usage refers to whether the device is currently in use, reflecting whether the device is in an idle state or a working state. The current working state refers to the actual running state of the device at present; the current working state of the device determines whether the modification operation can be performed, avoiding parameter changes that may cause faults when the device is working. The idle state refers to that the device is not used at the current time, and is in a standby or standby operation state. The in-use state refers to that the device is being operated or used, and is in an active state; modifying the device parameters in this state may cause device failure or performance problems, so restrictions need to be taken. The modification prohibition warning refers to a warning information sent to the client when the device is in the "in-use state", informing the user that the device parameter modification cannot be performed at present; the purpose of the warning is to protect the safety of the device, prevent the adjustment of the parameters of the device when it is running, and avoid possible risks.

[0046] The embodiment of the application obtains the to-be-evaluated state data of the candidate medical device from the cloud server and stores it; wherein the to-be-evaluated state data is determined by the cloud server according to the candidate device type and the current state data of the candidate medical device; the current state data is obtained by collecting the running data of the candidate medical device in a preset time period by the data collection device and uploaded to the cloud server; a threshold dynamic generation model is generated based on the threshold, and the state data threshold of the candidate medical device is determined according to the candidate device type and the historical state data of the candidate medical device; wherein the threshold dynamic generation model is improved according to the candidate device type and the recurrent neural network; according to the to-be-evaluated state data and the state data threshold, the current running state and the state data trend chart of the candidate medical device are determined, and the current state data and the state data trend chart are fed back to the client; if it is identified that there is a candidate medical device with an abnormal state, the candidate medical device is determined as an abnormal medical device, and the device abnormal report of the abnormal medical device is determined according to the abnormal device type, the abnormal state data and the state data threshold of the abnormal medical device, and the device abnormal report is sent to the client. The above technical solution, by combining the device type adaptive analysis with the threshold dynamic generation model, helps to improve the accuracy and reliability of the current state determination of each medical device in a medical environment where multiple types of devices coexist.

[0047] Embodiment two

[0048] Figure 2This is a flowchart of a medical device monitoring method based on device logs according to Embodiment 2 of this application. Based on the technical solutions of the above embodiments, this embodiment refines the step of "determining the status data threshold of a candidate medical device based on the candidate device type and historical status data of the candidate medical device using a dynamic threshold generation model" to "converting the candidate device type of the candidate medical device into a binary vector to obtain the candidate type code of the candidate medical device; determining the status data threshold of the candidate medical device based on the candidate type code and historical status data of the candidate medical device using a dynamic threshold generation model." It should be noted that for parts not detailed in this embodiment, please refer to the relevant descriptions in other embodiments. Figure 2 As shown, the method includes:

[0049] S210. Obtain and store the evaluation status data of candidate medical devices from the cloud server.

[0050] S220. Convert the candidate device type of the candidate medical device into a binary vector to obtain the candidate type code of the candidate medical device.

[0051] In this embodiment, a binary vector refers to a format for representing data, typically a vector composed of 0s and 1s. Candidate type encoding refers to converting candidate device types into binary codes that can be used for calculation and analysis; each device type is represented as a specific binary vector.

[0052] S230. Based on the threshold dynamic generation model, determine the status data threshold of the candidate medical device according to the candidate type code and historical status data of the candidate medical device.

[0053] Optionally, the threshold dynamic generation model includes an input layer, a long short-term memory layer, an attention layer, and an output layer. Correspondingly, the input layer concatenates candidate type encoding and historical state data to obtain fused state data of candidate medical devices, and transmits this fused state data to the long short-term memory layer. The long short-term memory layer extracts features from the fused state data to obtain hidden state data of the candidate medical devices, and sends this hidden state data to the attention layer. The attention layer adjusts the weights of the hidden state data based on the correlation between device type and state data, and uses the adjusted weights to perform weighted processing on the hidden state data to obtain target state data, which is then sent to the output layer. The output layer uses an activation function to determine the state data threshold of the candidate medical devices based on the target state data.

[0054] In this embodiment, the fusion state data refers to data obtained by splicing or merging the type code of the candidate device and the historical state data, aiming to provide more comprehensive device information. The hidden state data is used to represent the internal characteristics and information of the input data. The target state data refers to data obtained by attention layer weighting processing, representing the current state information of the device and being used to determine the state threshold. The activation function is a mathematical function in the neural network, used to determine the output of a node,

[0055] For example, in the input layer, the candidate type code and the historical state data are spliced together to form a comprehensive input vector, i.e., the fusion state data. This vector contains the identification information of the device type and the real-time device running data. The long short-term memory layer receives the comprehensive input vector from the input layer. In the long short-term memory layer, the input vector is processed by three gates (forget gate, input gate, and output gate), which determine which information needs to be retained and which needs to be forgotten. The hidden state data of the device at the current time step is obtained, which contains the short-term and long-term running trends of the device. The output of the long short-term memory layer (i.e., the hidden state) is transmitted to the attention layer. The attention mechanism calculates the correlation between the device type and the time series data, and assigns different weights to different time steps (i.e., historical data), finally obtaining a weighted hidden state, i.e., the target state data. In the output layer, the model generates a dynamic threshold related to the device type through the activation function.

[0056] S240, according to the to-be-evaluated state data and the state data threshold, determining the current running state and the state data trend graph of the candidate medical device, and feeding back the current state data and the state data trend graph to the client.

[0057] Optionally, the to-be-evaluated state data and the state data threshold are compared numerically to obtain a numerical comparison result; according to the numerical comparison result, the current running state of the candidate medical device is determined; according to the to-be-evaluated state data, the numerical comparison result, and the state data threshold, the state data trend graph of the candidate medical device is determined.

[0058] Further, if the numerical comparison result does not satisfy the state abnormal condition, the current running state of the candidate medical device is determined as a normal state; if the numerical comparison result satisfies the state abnormal condition, the current running state of the candidate medical device is determined as an abnormal state.

[0059] In this embodiment, the numerical comparison result refers to the numerical comparison result of the to-be-evaluated state data and the state data threshold. The state abnormal condition is artificially pre-set according to actual conditions or empirical values, which is not limited in the embodiment of the application; the state abnormal condition can be that the to-be-evaluated state data is greater than the state data threshold.

[0060] For example, if the to-be-evaluated state data is greater than the state data threshold, the current running state of the candidate medical device is determined as an abnormal state; if the to-be-evaluated state data is less than or equal to the state data threshold, the current running state of the candidate medical device is determined as a normal state.

[0061] S250, if it is identified that there is a candidate medical device with an abnormal state, the candidate medical device is determined as an abnormal medical device, and a device abnormality report of the abnormal medical device is determined according to the abnormal device type, the abnormal state data and the state data threshold of the abnormal medical device, and the device abnormality report is sent to the client.

[0062] The embodiment of the present application obtains the to-be-evaluated state data of the candidate medical device from the cloud server and stores it; converts the candidate device type of the candidate medical device into a binary vector to obtain the candidate type code of the candidate medical device; dynamically generates a threshold value based on a model, determines the state data threshold of the candidate medical device according to the candidate type code and the historical state data of the candidate medical device; determines the current running state and the state data trend chart of the candidate medical device according to the to-be-evaluated state data and the state data threshold, and feeds back the current state data and the state data trend chart to the client; if it is identified that there is a candidate medical device with an abnormal state, the candidate medical device is determined as an abnormal medical device, and a device abnormality report of the abnormal medical device is determined according to the abnormal device type, the abnormal state data and the state data threshold of the abnormal medical device, and the device abnormality report is sent to the client. The above technical solution, by using the device type adaptive analysis and the threshold value dynamic generation model, helps to improve the accuracy and reliability of the current state determination of each medical device in a medical environment where multiple types of devices coexist.

[0063] Embodiment Three

[0064] Figure 3 is a structural schematic diagram of a medical device monitoring device based on device logs provided by the embodiment three of the present application, which can be applicable to the case of real-time detection and remote maintenance of the running state of each medical device in a medical environment where multiple types of medical devices coexist. The medical device monitoring device based on device logs can be realized in the form of hardware and / or software, and can be configured in a computer device, such as a data management center of a medical device management system; the medical device management system further includes a data acquisition device, a cloud server, a client and at least two candidate medical devices of different types; the cloud server is in communication connection with the data acquisition device and the data management center; the data management center is in communication connection with the client; the data acquisition device is in communication connection with the at least two candidate medical devices. As shown in the figure, the device includes: Figure 3 ​

[0065] The data acquisition module 310 is configured to acquire and store the to-be-evaluated state data of the candidate medical device from the cloud server, wherein the to-be-evaluated state data is determined by the cloud server according to the candidate device type and the current state data of the candidate medical device; the current state data is obtained by collecting the running data of the candidate medical device within a preset time period by the data acquisition device and uploaded to the cloud server.

[0066] The threshold determination module 320 is configured to determine the state data threshold of the candidate medical device based on a threshold dynamic generation model according to the candidate device type and the historical state data of the candidate medical device; wherein the threshold dynamic generation model is obtained by improving a recurrent neural network according to the candidate device type.

[0067] The state determination module 330 is configured to determine the current running state and the state data trend chart of the candidate medical device according to the to-be-evaluated state data and the state data threshold, and feed back the current state data and the state data trend chart to the client.

[0068] The abnormality feedback module 340 is configured to determine the candidate medical device as an abnormal medical device if it is identified that there is a candidate medical device with an abnormal state, and determine a device abnormality report of the abnormal medical device according to the abnormal device type, the abnormal state data and the state data threshold of the abnormal medical device, and send the device abnormality report to the client.

[0069] The embodiments of the present application acquire and store the to-be-evaluated state data of the candidate medical device from the cloud server, wherein the to-be-evaluated state data is determined by the cloud server according to the candidate device type and the current state data of the candidate medical device; the current state data is obtained by collecting the running data of the candidate medical device within a preset time period by the data acquisition device and uploaded to the cloud server; a threshold dynamic generation model is used to determine the state data threshold of the candidate medical device according to the candidate device type and the historical state data of the candidate medical device, wherein the threshold dynamic generation model is obtained by improving a recurrent neural network according to the candidate device type; the current running state and the state data trend chart of the candidate medical device are determined according to the to-be-evaluated state data and the state data threshold, and the current state data and the state data trend chart are fed back to the client; if it is identified that there is a candidate medical device with an abnormal state, the candidate medical device is determined as an abnormal medical device, and a device abnormality report of the abnormal medical device is determined according to the abnormal device type, the abnormal state data and the state data threshold of the abnormal medical device, and the device abnormality report is sent to the client. The above technical solution uses the device type adaptive analysis in combination with the threshold dynamic generation model, which helps to improve the accuracy and reliability of the current state determination of each medical device in a medical environment where multiple types of devices coexist.

[0070] Optionally, the threshold determination module 330 comprises:

[0071] a type conversion unit, configured to convert the candidate device type of the candidate medical device into a binary vector to obtain a candidate type code of the candidate medical device;

[0072] a threshold determination unit, configured to determine, based on a threshold dynamic generation model, the state data threshold of the candidate medical device according to the candidate type code of the candidate medical device and the historical state data.

[0073] Optionally, the threshold dynamic generation model comprises an input layer, a long short-term memory layer, an attention layer and an output layer; correspondingly, the threshold determination unit 330 is specifically configured to:

[0074] concatenate the candidate type code and the historical state data through the input layer to obtain fusion state data of the candidate medical device, and transmit the fusion state data to the long short-term memory layer;

[0075] extract features of the fusion state data through the long short-term memory layer to obtain hidden state data of the candidate medical device, and send the hidden state data to the attention layer;

[0076] adjust the weight of the hidden state data based on the relevance between the device type and the state data through the attention layer, and perform weighted processing on the hidden state data by using the adjusted weight to obtain target state data, and send the target state data to the output layer;

[0077] determine, through the output layer by using an activation function, the state data threshold of the candidate medical device according to the target state data.

[0078] Optionally, the state determination module 330 comprises:

[0079] a numerical comparison unit, configured to perform numerical comparison on the to-be-evaluated state data and the state data threshold to obtain a numerical comparison result;

[0080] a state determination unit, configured to determine, according to the numerical comparison result, the current running state of the candidate medical device;

[0081] a trend chart determination unit, configured to determine, according to the to-be-evaluated state data, the numerical comparison result and the state data threshold, a state data trend chart of the candidate medical device.

[0082] Optionally, the state determination unit is specifically configured to:

[0083] if the numerical comparison result does not satisfy the state abnormal condition, determine the current running state of the candidate medical device as a normal state;

[0084] If the numerical comparison result satisfies the state abnormal condition, the current running state of the candidate medical device is determined as an abnormal state.

[0085] Optionally, the data management center is in communication connection with at least two candidate medical devices, and correspondingly, the apparatus further comprises a parameter modification module; the parameter modification module is used for:

[0086] After sending the device abnormal report to the client, if the parameter modification instruction for the abnormal medical device sent by the client is identified, the current use condition of the abnormal medical device is detected to obtain the current working state of the abnormal medical device; wherein the current working state comprises an idle state and a using state.

[0087] If the current working state is the using state, a modification prohibition warning is sent to the client, and in the case that the current working state of the abnormal medical device changes to the idle state, the parameter modification instruction is executed.

[0088] The device log-based medical device monitoring apparatus provided in the embodiments of the present application can execute the device log-based medical device monitoring method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of executing each device log-based medical device monitoring method.

[0089] According to the embodiments of the present application, the present application further provides an electronic device, a readable storage medium and a computer program product.

[0090] Embodiment Four

[0091] Figure 4 FIG. 4 is a structural schematic diagram of an electronic device 410 for implementing the device log-based medical device monitoring method according to the embodiments of the present application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections, and their functions, as well as the software implemented by the electronic device, are merely examples and are not intended to limit the present application described and / or claimed herein.

[0092] As Figure 4As shown, the electronic device 410 includes at least one processor 411, and a memory, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, and the like, connected to the at least one processor 411 in communication. The memory stores a computer program that can be executed by the at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or loaded from the storage unit 418 into the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other through a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0093] Various components in the electronic device 410 are connected to the I / O interface 415, including an input unit 416, such as a keyboard, a mouse, and the like, an output unit 417, such as various types of displays, a speaker, and the like, a storage unit 418, such as a magnetic disk, an optical disk, and the like, and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0094] The processor 411 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, and the like. The processor 411 performs various methods and processes described above, such as the device log-based medical device monitoring method.

[0095] In some embodiments, the device log-based medical device monitoring method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 418. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the device log-based medical device monitoring method described above can be performed. Alternatively, in other embodiments, the processor 411 can be configured as the device log-based medical device monitoring method by any other appropriate means, such as by means of firmware.

[0096] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0097] Computer programs used to implement the methods of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a general purpose computer, special purpose computer, or other programmable processing apparatuses to produce a machine, such that the computer program, when executed, implements the functions / operations specified in the flowcharts and / or block diagrams. The computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package, partly on a machine and partly on a remote machine or entirely on a remote machine or server.

[0098] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0100] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0101] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0102] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0103] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and scope of the disclosure. Any further modifications, equivalents, and / or alternatives come within the scope of the present disclosure as described in the following claims.

Claims

1. A method for monitoring medical devices based on device logs, characterized in that, A data management center is used in a medical device management system; the medical device management system also includes a data acquisition device, a cloud server, a client, and at least two different types of candidate medical devices; the cloud server is communicatively connected to the data acquisition device and the data management center respectively; The data management center and the client communicate with each other. The data acquisition device is communicatively connected to at least two candidate medical devices; the method includes: The cloud server retrieves and stores the candidate medical device's status data to be evaluated; wherein, the status data to be evaluated is determined by the cloud server based on the candidate device type and current status data of the candidate medical device; the current status data is obtained by the data acquisition device collecting the operating data of the candidate medical device within a preset time period and uploading it to the cloud server; Based on the threshold dynamic generation model, the state data threshold of the candidate medical device is determined according to the candidate device type and historical state data of the candidate medical device; wherein, the threshold dynamic generation model is obtained by improving the recurrent neural network according to the candidate device type; the threshold dynamic generation model includes an input layer, a long short-term memory layer, an attention layer and an output layer; Based on the status data to be evaluated and the status data threshold, the current operating status and status data trend chart of the candidate medical device are determined, and the current status data and the status data trend chart are fed back to the client. If a candidate medical device is identified as having an abnormal current operating state, the candidate medical device is identified as an abnormal medical device, and an abnormal medical device report is determined based on the abnormal device type, abnormal state data, and state data threshold of the abnormal medical device, and the abnormal medical device report is sent to the client. The threshold-based dynamic generation model, which determines the status data threshold of the candidate medical devices based on their candidate device types and historical status data, includes: The candidate device type of the candidate medical device is converted into a binary vector to obtain the candidate type code of the candidate medical device; The candidate type encoding and the historical state data are concatenated by the input layer to obtain the fused state data of the candidate medical device, and the fused state data is transmitted to the long short-term memory layer. The long short-term memory layer extracts features from the fused state data to obtain the hidden state data of the candidate medical device, and then sends the hidden state data to the attention layer. The attention layer adjusts the weights of the hidden state data based on the correlation between device type and state data, and uses the adjusted weights to perform weighted processing on the hidden state data to obtain the target state data, which is then sent to the output layer. The output layer employs an activation function to determine the threshold value of the candidate medical device's state data based on the target state data.

2. The method according to claim 1, characterized in that, Based on the state data to be evaluated and the state data threshold, the current operating status and state data trend chart of the candidate medical device are determined, including: The numerical comparison between the state data to be evaluated and the state data threshold is performed to obtain the numerical comparison result. Based on the numerical comparison results, the current operating status of the candidate medical device is determined; Based on the state data to be evaluated, the numerical comparison results, and the state data threshold, a state data trend chart of the candidate medical device is determined.

3. The method according to claim 2, characterized in that, Based on the numerical comparison results, the current operating status of the candidate medical device is determined, including: If the numerical comparison result does not meet the abnormal state condition, the current operating state of the candidate medical device is determined to be normal. If the numerical comparison result meets the abnormal state condition, then the current operating state of the candidate medical device is determined to be an abnormal state.

4. The method according to claim 1, characterized in that, The data management center communicates with the at least two candidate medical devices. Accordingly, after sending the device anomaly report to the client, the method further includes: If a parameter modification instruction for the abnormal medical device sent by the client is detected, the current usage status of the abnormal medical device is detected to obtain the current working status of the abnormal medical device; wherein, the current working status includes an idle state and a used state; If the current working state is the "in use" state, a warning prohibiting modification is sent to the client, and the parameter modification instruction is executed when the current working state of the abnormal medical device changes to the "idle" state.

5. A medical device monitoring device based on device logs, characterized in that, A data management center is configured within a medical device management system; the medical device management system also includes a data acquisition device, a cloud server, a client, and at least two candidate medical devices of different types; the cloud server is communicatively connected to both the data acquisition device and the data management center. The data management center and the client communicate with each other. The data acquisition device is communicatively connected to at least two candidate medical devices; the device includes: The data acquisition module is used to acquire and store the evaluation status data of the candidate medical device from the cloud server; wherein, the evaluation status data is determined by the cloud server based on the candidate device type and current status data of the candidate medical device; the current status data is obtained by the data acquisition device collecting the operating data of the candidate medical device within a preset time period and uploading it to the cloud server; A threshold determination module is used to determine the state data threshold of the candidate medical device based on the candidate device type and historical state data of the candidate medical device, according to a threshold dynamic generation model; wherein, the threshold dynamic generation model is obtained by improving a recurrent neural network according to the candidate device type; the threshold dynamic generation model includes an input layer, a long short-term memory layer, an attention layer and an output layer; The status determination module is used to determine the current operating status and status data trend chart of the candidate medical device based on the status data to be evaluated and the status data threshold, and to feed the current status data and the status data trend chart back to the client. An anomaly feedback module is used to identify a candidate medical device whose current operating state is abnormal if a candidate medical device is identified as an abnormal medical device, and to determine an anomaly report of the abnormal medical device based on the abnormal device type, abnormal state data and state data threshold of the abnormal medical device, and to send the anomaly report to the client. The threshold determination module includes a type conversion unit and a threshold determination unit; The type conversion unit is used to convert the candidate device type of the candidate medical device into a binary vector to obtain the candidate type code of the candidate medical device. The threshold determination unit is specifically used for: The candidate type encoding and the historical state data are concatenated by the input layer to obtain the fused state data of the candidate medical device, and the fused state data is transmitted to the long short-term memory layer. The long short-term memory layer extracts features from the fused state data to obtain the hidden state data of the candidate medical device, and then sends the hidden state data to the attention layer. The attention layer adjusts the weights of the hidden state data based on the correlation between device type and state data, and uses the adjusted weights to perform weighted processing on the hidden state data to obtain the target state data, which is then sent to the output layer. The output layer employs an activation function to determine the threshold value of the candidate medical device's state data based on the target state data.

6. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the medical device monitoring method based on device logs as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the medical device monitoring method based on device logs as described in any one of claims 1-4.

8. A computer program product comprising a computer program that, when executed by a processor, implements the medical device monitoring method based on device logs according to any one of claims 1-4.

Images