Medical instrument-oriented intelligent operation management system and method thereof

Abstract

The invention provides an intelligent operation management system and method for medical instruments. The system comprises an operation management middle table, a data acquisition module, a load intelligent analysis module, a health intelligent evaluation module, a node object generation module and an intelligent operation management module. The data acquisition module acquires operation data and historical use data of a target medical instrument; the load intelligent analysis module outputs load data through the load prediction model; the intelligent health assessment module outputs a health assessment result through a health assessment model; the node object generation module generates a storage object result based on the health assessment result; and the intelligent operation management module stores the storage object result as a node to a preset operation management tree, and carries out intelligent operation management on the target medical device. According to the invention, the health assessment result is intelligently output through the load prediction model and the health assessment model, and then the health assessment result is managed through the operation management tree, so that the efficiency and accuracy of operation management of the medical apparatus are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an intelligent operation and management system for medical devices. Background Art

[0002] The existing operation and management methods for medical devices still mainly rely on manual recording methods, that is, manually recording and storing the maintenance status, usage status, health status and other related information of medical devices through simple electronic spreadsheets. However, as the management complexity of medical devices increases, manual recording methods will lead to errors in the recording results, resulting in low accuracy in the operation and management of medical devices. Furthermore, when users need to query relevant information about medical devices, they need to obtain relevant information through query forms, resulting in low efficiency in information query of medical devices, thereby resulting in low efficiency in the operation and management of medical devices. Summary of the invention

[0003] The present invention provides an intelligent operation management system and method for medical devices, aiming to improve the efficiency and accuracy of operation management of medical devices.

[0004] In a first aspect, the present invention provides an intelligent operation management system for medical devices, comprising an operation management middle platform, a data acquisition module, a load intelligent analysis module, a health intelligent assessment module, a node object generation module and an intelligent operation management module; the operation management middle platform is respectively connected to the data acquisition module, the load intelligent analysis module, the health intelligent assessment module, the node object generation module and the intelligent operation management module to store and manage the data of each module;

[0005] A data acquisition module, used to collect operating data and historical usage data of the target medical device; the operating data includes temperature data, pressure data and operating time data of the target medical device, and the historical usage data includes historical maintenance data and usage frequency data of the target medical device;

[0006] A load intelligent analysis module, used for inputting the temperature data, the pressure data and the operation time data into a load prediction model to obtain the load data output by the load prediction model; wherein the load prediction model is trained based on preset load data and its corresponding sample temperature data, sample pressure data and sample time data;

[0007] A health intelligent assessment module, used for inputting the load data, the historical maintenance data and the usage frequency data into a health assessment model to obtain a health assessment result output by the health assessment model; wherein the health assessment model is trained based on a preset health result and its corresponding preset load data, sample historical maintenance data and sample usage frequency data;

[0008] A node object generation module, used to generate a storage object result based on the health assessment result;

[0009] The intelligent operation management module is used to store the storage object results as nodes in a preset operation management tree to achieve intelligent operation management of the target medical device.

[0010] In a second aspect, the present invention further provides an intelligent operation management method for medical devices, which is applied to the intelligent operation management system for medical devices described in the first aspect, and the intelligent operation management method for medical devices includes:

[0011] Collecting operation data and historical usage data of the target medical device; the operation data includes temperature data, pressure data and operation time data of the target medical device, and the historical usage data includes historical maintenance data and usage frequency data of the target medical device;

[0012] Inputting the temperature data, the pressure data and the operation time data into a load prediction model to obtain the load data output by the load prediction model; the load prediction model is trained based on the preset load data and its corresponding sample temperature data, sample pressure data and sample time data;

[0013] Input the load data, the historical maintenance data and the usage frequency data into a health assessment model to obtain a health assessment result output by the health assessment model; wherein the health assessment model is trained based on a preset health result and its corresponding preset load data, sample historical maintenance data and sample usage frequency data;

[0014] generating a storage object result based on the health assessment result;

[0015] The storage object result is stored as a node in a preset operation management tree to achieve intelligent operation management of the target medical device.

[0016] According to the intelligent operation management method for medical devices provided by an embodiment of the present invention, the load prediction model includes a load factor prediction layer, a response load prediction layer and a load calculation layer; the load calculation layer is connected to the load factor prediction layer and the response load prediction layer respectively;

[0017] The step of inputting the temperature data, the pressure data and the operation time data into a load forecasting model to obtain load data output by the load forecasting model includes:

[0018] Inputting the temperature data and pressure data into the load factor prediction layer to obtain the temperature load factor and pressure load factor output by the load factor prediction layer;

[0019] Inputting the temperature data, the pressure data and the operation time data into the response load prediction layer to obtain the load prediction value output by the response load prediction layer;

[0020] The temperature load factor, the pressure load factor and the load prediction value are input into the load calculation layer to obtain the load data output by the load calculation layer.

[0021] According to the intelligent operation management method for medical devices provided by an embodiment of the present invention, the loss function of the load forecasting model is:

[0022] Loss1={[xlogf T (T θ )+(1-x)logf P (P θ )+x 2 logf t (t θ )]→A};

[0023]

[0024] f t (t θ ) = t θ *e c ;

[0025] Among them, Loss1 represents the loss function of the load forecasting model, A represents the preset load data, T θ Represents sample temperature data, P θ represents the sample pressure data, t θ represents the sample duration data, x represents the preset weight coefficient, and f T (T θ ) represents the temperature operation function, λ represents the temperature weight attenuation parameter, ||·|| represents the two-norm calculation, logf P (P θ ) represents the pressure operation function, ρ represents the pressure weight attenuation parameter, represents the preset smoothing parameter, f t (t θ ) represents the duration operation function, e represents the base of the exponential function, and c represents the duration weight attenuation parameter.

[0026] According to the intelligent operation management method for medical devices provided by an embodiment of the present invention, the health assessment model includes a life prediction layer and a health assessment layer;

[0027] The step of inputting the load data, the historical maintenance data and the usage frequency data into a health assessment model to obtain a health assessment result output by the health assessment model includes:

[0028] Inputting the historical maintenance data and the usage frequency data into the life prediction layer to obtain a life prediction result output by the life prediction layer;

[0029] The load data and the life prediction result are input into the health assessment layer to obtain the health assessment result output by the health assessment layer.

[0030] According to the intelligent operation management method for medical devices provided by an embodiment of the present invention, the loss function of the health assessment model is:

[0031]

[0032] f H (H θ )=σ r log(H θ )+(1-σ c )log(H θ );

[0033] f H (U θ )=σ c log(U θ )+(1-σ r )log(U θ );

[0034] Among them, Loss2 represents the loss function of the health assessment model, B represents the preset health result, σ r represents the weight of the life prediction layer, σ c represents the weight of the health assessment layer, A represents the preset load data, H θ Represents sample historical maintenance data, U θ Indicates the sample usage frequency data, f H (H θ ) represents the maintenance operation function, f H (U θ ) represents the frequency operation function.

[0035] According to the intelligent operation and management method for medical devices provided by an embodiment of the present invention, the device information of the target medical device includes the device registration number, device model and device manufacturer number; the medical device type includes diagnostic device type, therapeutic device type and monitoring device type;

[0036] The generating a storage object result based on the health assessment result includes:

[0037] Obtaining device information and medical device type of the target medical device;

[0038] Determining a coding method of the target medical device based on the type of the medical device;

[0039] Encoding the device registration number, the device model number and the device manufacturer number based on the encoding method to obtain encoding information of the target medical device;

[0040] The storage object result is generated based on the encoding information and the health assessment result.

[0041] According to the intelligent operation management method for medical devices provided by an embodiment of the present invention, storing the storage object result as a node in a preset operation management tree to implement intelligent operation management of the target medical device includes:

[0042] Determine a root node, a parent node, and a child node based on the storage object result;

[0043] Determine a target storage link of the storage object result in the operation management tree based on the root node, the parent node and the child node;

[0044] The storage object result is stored in the operation management tree using the target storage link to implement intelligent operation management of the target medical device.

[0045] In a third aspect, the present invention further provides an electronic device, comprising: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby implementing any of the above-mentioned intelligent operation and management methods for medical devices.

[0046] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, wherein the storage medium stores a computer software program, and when the computer software program is executed by a processor, the intelligent operation and management method for medical devices as described in any one of the above-mentioned methods is implemented.

[0047] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-described intelligent operation and management methods for medical devices.

[0048] The intelligent operation and management system for medical devices provided by the embodiment of the present invention uses the load prediction model in the load intelligent analysis module and the health assessment model in the health intelligent assessment module to intelligently output the health assessment results in combination with the operation data and historical usage data, without the need for manual recording, thus avoiding the occurrence of recording errors, thereby improving the accuracy of the operation and management of medical devices. At the same time, the health assessment results are stored as nodes in the operation and management tree. When it is necessary to query the relevant information of the medical device, the health assessment results of the medical device can be queried through the nodes in the operation and management tree, without the need to query through electronic spreadsheets, which speeds up the query efficiency of the relevant information of the medical device and improves the efficiency of the operation and management of the medical device. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a structural diagram of the intelligent operation and management system for medical devices provided by the present invention;

[0050] Figure 2 It is a flowchart of the intelligent operation management method for medical devices provided by the present invention;

[0051] Figure 3 It is one of the structural diagrams of the operation management tree provided by the present invention;

[0052] Figure 4 This is the second structural diagram of the operation management tree provided by the present invention;

[0053] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0055] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0056] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0057] Optional, see Figure 1 As shown, Figure 1 It is a structural diagram of the intelligent operation management system for medical devices provided by the present invention, which includes an operation management middle platform, a data acquisition module, a load intelligent analysis module, a health intelligent assessment module, a node object generation module and an intelligent operation management module. Among them, the operation management middle platform in the embodiment of the present invention is respectively connected with the data acquisition module, the load intelligent analysis module, the health intelligent assessment module, the node object generation module and the intelligent operation management module to store and manage the data of each module.

[0058] Optionally, the data acquisition module can be understood as a data acquisition device, such as a sensor, which can be installed on a medical device. Therefore, the data acquisition module can collect the operating data and historical usage data of the target medical device, wherein the operating data includes the temperature data, pressure data and operating time data of the target medical device, and the historical usage data includes the historical maintenance data and usage frequency data of the target medical device.

[0059] Optionally, the load intelligent analysis module inputs temperature data, pressure data and operating time data into a load prediction model to obtain load data output by the load prediction model. The load prediction model is trained based on preset load data and its corresponding sample temperature data, sample pressure data and sample time data.

[0060] Optionally, the health intelligent assessment module inputs the load data, historical maintenance data and usage frequency data into the health assessment model to obtain a health assessment result output by the health assessment model, wherein the health assessment model is trained based on preset health results and their corresponding preset load data, sample historical maintenance data and sample usage frequency data.

[0061] Optionally, the node object generation module generates a storage object result based on the health assessment result, specifically: obtaining the device information and medical device type of the target medical device, and generating a storage object result based on the device information and the medical device type.

[0062] Optionally, the intelligent operation management module stores the storage object results as nodes in a preset operation management tree to realize intelligent operation management of the target medical device, specifically: determining the root node, parent node and child node based on the storage object results, and then determining the storage path of the storage object results in the operation management tree based on the root node, parent node and child node.

[0063] The intelligent operation and management system for medical devices provided by the embodiment of the present invention uses the load prediction model in the load intelligent analysis module and the health assessment model in the health intelligent assessment module to intelligently output the health assessment results in combination with the operation data and historical usage data, without the need for manual recording, thus avoiding the occurrence of recording errors, thereby improving the accuracy of the operation and management of medical devices. At the same time, the health assessment results are stored as nodes in the operation and management tree. When it is necessary to query the relevant information of the medical device, the health assessment results of the medical device can be queried through the nodes in the operation and management tree, without the need to query through electronic spreadsheets, which speeds up the query efficiency of the relevant information of the medical device and improves the efficiency of the operation and management of the medical device.

[0064] Optional, see Figure 2 , Figure 2 It is a flow chart of the intelligent operation management method for medical devices provided by the present invention. The execution subject of the intelligent operation management method for medical devices in the embodiment of the present invention is the intelligent operation management system. Therefore, the intelligent operation management method for medical devices includes:

[0065] Step 10: Collect the operating data and historical usage data of the target medical device.

[0066] Among them, each medical device is installed with a sensor, which can collect the operating data of the medical device. The sensor is connected and communicated with the intelligent operation management system through wired communication or wireless communication.

[0067] Optionally, the intelligent operation management system can collect operating data of the target medical device through sensors, where the sensors may include temperature sensors, pressure sensors, and operating time sensors. Therefore, the intelligent operation management system can collect temperature data, pressure data, and operating time data of the target medical device through sensors. The target medical device is any medical device.

[0068] Optionally, the intelligent operation management system may call a usage record sheet of the target medical device, and obtain historical usage data of the target medical device through the usage record sheet, wherein the historical usage data includes historical maintenance data and usage frequency data of the target medical device.

[0069] Step 20, inputting the temperature data, pressure data and operation time data into the load prediction model to obtain the load data output by the load prediction model.

[0070] In an embodiment of the present invention, a load prediction model and a health assessment model are trained in the intelligent operation management system, wherein the load prediction model is trained based on preset load data and its corresponding sample temperature data, sample pressure data and sample duration data, and the health assessment model is trained based on preset health results and their corresponding preset load data, sample historical maintenance data and sample usage frequency data.

[0071] Optionally, the intelligent operation management system inputs the temperature data, pressure data and operation duration data into the load forecasting model, processes the temperature data, pressure data and operation duration data through the load forecasting model, and obtains the load data output by the load forecasting model.

[0072] Step 30, input the load data, historical maintenance data and usage frequency data into the health assessment model to obtain the health assessment result output by the health assessment model.

[0073] Optionally, the intelligent operation management system inputs the load data, historical maintenance data and usage frequency data into the health assessment model, processes the load data, historical maintenance data and usage frequency data through the health assessment model, and obtains the health assessment results output by the health assessment model.

[0074] Step 40: Generate a storage object result based on the health assessment result.

[0075] Step 50, storing the storage object result as a node in a preset operation management tree to achieve intelligent operation management of the target medical device.

[0076] Optionally, the intelligent operation management system generates a storage object result based on the health assessment result, specifically: obtaining the device information and medical device type of the target medical device, and generating a storage object result based on the device information and medical device type. The intelligent operation management system stores the storage object result as a node in a preset operation management tree to achieve intelligent operation management of the target medical device, specifically: determining the root node, parent node and child node based on the storage object result, and then determining the storage path of the storage object result in the operation management tree based on the root node, parent node and child node.

[0077] The embodiment of the present invention uses a load prediction model and a health assessment model, and combines operation data and historical usage data to intelligently output health assessment results, without the need for manual recording, thereby avoiding the occurrence of recording errors, thereby improving the accuracy of medical device operation management. At the same time, the health assessment results are stored as nodes in the operation management tree. When it is necessary to query the relevant information of the medical device, the health assessment results of the medical device can be queried through the nodes in the operation management tree, without the need to query through electronic spreadsheets, which speeds up the query efficiency of the relevant information of the medical device and improves the efficiency of the operation management of the medical device.

[0078] In one embodiment, the load prediction model includes a load factor prediction layer, a response load prediction layer and a load calculation layer, wherein the load calculation layer is connected to the load factor prediction layer and the response load prediction layer respectively. The function of the load factor prediction layer is to match the corresponding temperature load factor and pressure load factor by calling the factor matching function and the load factor matching table. The function of the response load prediction layer is to match the corresponding load prediction value by calling the load prediction table. The function of the load calculation layer is to calculate the load prediction value by calling the load calculation function. Therefore, step 20 inputs the temperature data, pressure data and operation time data into the load prediction model to obtain the load data output by the load prediction model, including:

[0079] Step 201, input temperature data and pressure data into the load factor prediction layer to obtain the temperature load factor and pressure load factor output by the load factor prediction layer.

[0080] Optionally, the intelligent operation management system inputs the temperature data and pressure data into the load factor prediction layer. In the load factor prediction layer, the load factor is matched by calling the temperature factor matching function and the pressure factor matching function to obtain the temperature load factor and pressure load factor output by the load factor prediction layer.

[0081] The expression of the temperature factor matching function is:

[0082] M T (T) = [T] + [Tmod10]

[0083] Among them, M T (T) represents the temperature load factor, [T] represents the load factor corresponding to the range of the temperature data T, and [Tmod10] represents the load factor corresponding to the remainder obtained by taking the temperature data T modulo 10.

[0084] The expression of the pressure factor matching function is:

[0085] M P (P) = [P] + [Pmod20]

[0086] Among them, MP (P) represents the pressure load factor, [P] represents the load factor corresponding to the range of the pressure data P, and represents the load factor corresponding to the remainder obtained after the pressure data P is divided by 20.

[0087] In one embodiment, the load factor prediction layer can call the load factor matching table, and perform load factor matching through the temperature factor matching function and the pressure factor matching function combined with the load factor matching table to obtain the temperature load factor corresponding to the temperature data and the pressure load factor corresponding to the pressure data.

[0088] In a specific embodiment, the temperature load factor matching table is shown in Table 1, and the pressure load factor matching table is shown in Table 2. The temperature data T is 45°C (degrees Celsius), the pressure data P is 114Pa (Pascals), T=45°C is in the range of 40≤T<50, the load factor corresponding to the range of the temperature data T is a5, the remainder after T=45°C mod 10 is 5, and the load factor corresponding to the remainder obtained after the temperature data T is taken as 10 is b2. Therefore, the temperature load factor obtained by matching the temperature factor matching function in combination with the temperature load factor matching table is a5+b2. P=114Pa is in the range of 100≤P<120, the load factor corresponding to the range of the pressure data P is c4, the remainder after P=114Pa mod 20 is 14, and the load factor corresponding to the remainder obtained after the pressure data P is taken as 20 is d3. Therefore, the pressure load factor obtained by matching the pressure factor matching function in combination with the pressure load factor matching table is c4+d3.

[0089] It should be noted that the purpose of setting the load factor corresponding to the range and the load factor corresponding to the remainder in the embodiment of the present invention is to reduce errors and improve the accuracy of the load factor.

[0090] Table 1 Temperature load factor matching table

[0091]

[0092]

[0093] Table 2 Pressure load factor matching table

[0094] Pressure range(Pa) Load Factor Pressure Residual(Pa) Load Factor 0≤P＜40 c1 (0，10) d1 40≤P＜80 c2 10 d2 80≤P＜100 c3 (10，20) d3 100≤P＜120 c4 120≤P＜140 c5 140≤P＜160 c6

[0095] Step 202: input the temperature data, pressure data and operation time data into the response load prediction layer to obtain the load prediction value output by the response load prediction layer.

[0096] Optionally, the intelligent operation management system inputs the temperature data, pressure data and operation time data into the response load prediction layer, and the load prediction layer matches by calling the load prediction table to obtain the load prediction value output by the response load prediction layer.

[0097] In one embodiment, the load prediction table is shown in Table 3. It should be noted that Table 3 only shows part of the data, not all of the data. The temperature data T is 40°C, the pressure data P is 100Pa, the operating time data t is 5 hours, and the matched load prediction value is Q4.

[0098] Table 3 Load forecast table

[0099] Temperature range (℃) Pressure range(Pa) Running time data (h) Load forecast value (kW) 40≤T＜50 0≤P＜40 5 Q1 40≤T＜50 40≤P＜80 5 Q2 40≤T＜50 80≤P＜100 5 Q3 40≤T＜50 100≤P＜120 5 Q4 40≤T＜50 120≤P＜140 5 Q5 40≤T＜50 140≤P＜160 5 Q6

[0100] Step 203, input the temperature load factor, the pressure load factor and the load prediction value into the load calculation layer to obtain the load data output by the load calculation layer.

[0101] Optionally, the intelligent operation management system inputs the temperature load factor, pressure load factor and load prediction value into the load calculation layer, and the load calculation layer calls the load calculation function to perform calculations based on the temperature load factor, pressure load factor and load prediction value to obtain the load data output by the load calculation layer.

[0102] The load calculation function can be expressed as: F = e X*Y *Q

[0103] Among them, F represents the load prediction value, e represents the base of the exponential function, Q represents the load prediction value, X represents the temperature load factor, and Y represents the pressure load factor.

[0104] In a specific embodiment, the temperature data T is 45°C, the pressure data P is 110Pa, and the operation time data t is 5 hours. Therefore, the load prediction value is Q4, the temperature load factor is a5+b2, and the pressure load factor is c4+d2. Therefore, the load prediction value F=e (a5+b2)*(c4+d2) *Q4.

[0105] In one embodiment, the loss function of the load forecasting model in the embodiment of the present invention is:

[0106] Loss1={[xlogf T (T θ )+(1-x)logf P (P θ )+x 2 logf t (t θ )]→A};

[0107]

[0108] f t (t θ ) = t θ *e c ;

[0109] Among them, Loss1 represents the loss function of the load forecasting model, A represents the preset load data, T θ Represents sample temperature data, P θ represents the sample pressure data, t θ represents the sample duration data, x represents the preset weight coefficient, and f T (T θ ) represents the temperature operation function, λ represents the temperature weight attenuation parameter, ||·|| represents the two-norm calculation, logf P (P θ ) represents the pressure operation function, ρ represents the pressure weight attenuation parameter, represents the preset smoothing parameter, f t (t θ ) represents the duration operation function, e represents the base of the exponential function, and c represents the duration weight attenuation parameter.

[0110] Therefore, it can be understood that in the process of training the load forecasting model, multiple model training is required so that after multiple model training, [xlogf T (T θ )+(1-x)logf P (P θ )+x 2 logf t (t θ )] tends to A infinitely, that is, when [xlogf T (T θ )+(1-x)logf P (P θ )+x 2 logf t (t θ )] and A is less than or equal to a preset value, indicating that the load forecasting model training is completed, wherein the preset value, such as 0.01, 0.05, 0.1, etc., is set according to the required accuracy.

[0111] The embodiment of the present invention uses a load prediction model to combine operating data to intelligently output load data, providing a data basis for the subsequent output of health assessment results, so that the entire process does not require manual recording, avoiding recording errors, and thus improving the accuracy of medical device operation management.

[0112] In one embodiment, the health assessment model includes a life prediction layer and a health assessment layer. The life prediction layer is used to predict the corresponding life prediction result by calling the life prediction function. The health assessment layer is used to match the corresponding health assessment result by calling a preset health score mapping table.

[0113] Therefore, step 30 inputs the load data, historical maintenance data and usage frequency data into the health assessment model to obtain the health assessment results output by the health assessment model, including:

[0114] Step 301, inputting historical maintenance data and usage frequency data into the life prediction layer to obtain the life prediction result output by the life prediction layer.

[0115] Optionally, the intelligent operation management system inputs the historical maintenance data and the usage frequency data into the life prediction layer, and calculates the life prediction result output by the life prediction layer by combining the historical maintenance data and the usage frequency data through the life prediction function in the life prediction layer.

[0116] The life prediction function can be shown as:

[0117]

[0118] D=e -λt

[0119] Where, L represents the life prediction result (in hours); N m Represents historical maintenance data, that is, the number of historical maintenance times; R m Indicates the service life restored after each repair, that is, the number of hours extended by the repair; N u Represents the usage frequency data, that is, the number of times or hours used per unit time; R u It represents the influence factor of each unit frequency of use on the life, such as the reduction of life due to overload use; C represents the correction coefficient, which is used to adjust the influence of maintenance on the frequency of use; D represents the depreciation factor, e represents the base of the exponential function, λ represents the attenuation rate, and t represents the usage time data; E represents the environmental factor factor, and U represents the usage condition factor. In a specific embodiment, the environmental factor factor E is 0.5-0.8, and the usage condition factor U is 0.8-1.2.

[0120] Step 302: input the load data and the life prediction result into the health assessment layer to obtain the health assessment result output by the health assessment layer.

[0121] Optionally, the intelligent operation management system inputs the load data and the life prediction result into the health assessment layer, and the health assessment layer matches the load data and the life prediction result in a preset health score mapping table to obtain a health score. In one embodiment, part of the data in the health score mapping table is, for example: {(load data F1, life prediction result L1, health score s1), (load data F2, life prediction result L2, health score s2), (load data F3, life prediction result L3, health score s3)}. When the load data is F1 and the life prediction result is L1, the health score is s1.

[0122] Furthermore, the health assessment layer determines the range of the health score and outputs the health assessment result according to the range, thereby obtaining the health assessment result output by the health assessment layer.

[0123] In one embodiment, if the health score is greater than 0.8, the output health assessment result is a healthy state; if the health score is between 0.5 and 0.79, the output health assessment result is a state requiring attention; if the health score is less than 0.5, the output health assessment result is an unhealthy state.

[0124] In one embodiment, the loss function of the health assessment model in the embodiment of the present invention is:

[0125]

[0126] f H (H θ )=σ r log(H θ )+(1-σ c )log(H θ );

[0127] f H (U θ )=σ c log(U θ )+(1-σ r )log(U θ );

[0128] Among them, Loss2 represents the loss function of the health assessment model, B represents the preset health result, σ r represents the weight of the life prediction layer, σ c represents the weight of the health assessment layer, A represents the preset load data, H θ Represents sample historical maintenance data, U θ Indicates the sample usage frequency data, f H (H θ ) represents the maintenance operation function, f H (U θ ) represents the frequency operation function.

[0129] Therefore, it can be understood that in the process of training the health assessment model, multiple model trainings are required so that after multiple model trainings, The result tends to B infinitely, that is, when When the difference between A and B is less than or equal to a preset value, it indicates that the training of the health assessment model is completed, wherein the preset value, such as 0.01, 0.05, 0.1, etc., is set according to the required accuracy.

[0130] The embodiment of the present invention intelligently outputs the health assessment results by combining the load data, historical maintenance data and usage frequency data through the health assessment model. Therefore, the entire process does not need to be recorded manually, thus avoiding the occurrence of recording errors, thereby improving the accuracy of the operation and management of medical equipment.

[0131] In one embodiment, step 40 generates a storage object result based on the health assessment result, including:

[0132] Step 401, obtaining device information and medical device type of a target medical device;

[0133] Step 402, determining a coding method of a target medical device based on the type of the medical device;

[0134] Step 403, encoding the device registration number, device model and device manufacturer number based on the encoding method to obtain the encoding information of the target medical device;

[0135] Step 404, generating a storage object result based on the encoding information and the health assessment result.

[0136] Optionally, the intelligent operation management system obtains the device information and medical device type of the target medical device. The device information of the target medical device in the embodiment of the present invention includes the device registration number, device model and device manufacturer number, and the medical device type includes diagnostic device type, therapeutic device type and monitoring device type.

[0137] Further, the intelligent operation management system matches the medical device type with the preset coding mapping table to obtain the coding method of the target medical device, that is, the arrangement method of the device registration number, device model and device manufacturer number. In one embodiment, the coding mapping table can be {(medical device type: diagnostic device type; coding method: device registration number-device model-device manufacturer number), (medical device type: diagnostic device type; coding method: device registration number-device manufacturer number-device model), (medical device type: therapeutic device type; coding method: device model-device registration number-device manufacturer number), (medical device type: therapeutic device type; coding method: device model-device manufacturer number-device registration number), (medical device type: monitoring device type; coding method: device manufacturer number-device registration number-device model), (medical device type: monitoring device type; coding method: device manufacturer number-device model-device registration number)}. It should be noted that, for the fault tolerance of coding, each medical device type corresponds to two coding methods, and the embodiment of the present invention randomly selects the coding method for each medical device type.

[0138] Furthermore, the intelligent operation management system encodes the device registration number, device model and device manufacturer number according to the coding method to obtain the coding information of the target medical device.

[0139] Furthermore, the intelligent operation management system uses the coding information as prefix information and the health assessment result as suffix information to synthesize and generate a storage object result. In one embodiment, the medical device type of the target medical device W1 is a diagnostic device type, the device registration number is N1, the device model is N2, the device manufacturer number is N3, and the health assessment result is a health status. Therefore, the storage object result of the target medical device W1 is N1-N2-N3-health status, or N1-N3-N2-health status.

[0140] The embodiment of the present invention generates storage object results for the device information and health assessment results of the target medical device in different coding methods according to the medical device type of the target medical device, thereby storing the health assessment results of each type of medical device in a diversified manner, avoiding the storage of health assessment results of multiple types of medical devices in a single manner. Therefore, when performing data query, the health assessment results of different types of medical devices can be quickly queried, thereby improving the efficiency of medical device operation management.

[0141] In one embodiment, the operation management tree can be understood as an N-ary tree, a simple N-ary tree such as a DOM tree. The nodes of the operation management tree in the embodiment of the present invention can be mainly classified into a root node, multiple parent nodes under the root node, multiple child nodes under the parent node, and multiple leaf nodes under the child node, wherein the leaf node can be understood as an attribute node for storing attribute information. In the embodiment of the present invention, the leaf node is used to store health assessment results.

[0142] For the operation management tree, in a specific embodiment, the root node A branch has two parent nodes, namely, parent node a1 and parent node a2. The parent node a1 branch has two child nodes, namely, child node a3 and child node a4. Child node a3 and child node a4 are similar, so a similar connection is established between the two. The leaf nodes of child node a3 and child node a4 are different. The leaf node of child node a3 is a7, and the leaf node of child node a4 is a8. The parent node a2 branch has two child nodes, namely, child node a5 and child node a6. Child node a5 and child node a6 are different. The leaf node of child node a5 is a9, and the leaf node of child node a6 is a10. Leaf node a9 and leaf node a10 are similar, so a similar connection is established between the two. For details, see Figure 3 Therefore, step 50 stores the storage object result as a node in a preset operation management tree to realize intelligent operation management of the target medical device, including:

[0143] Step 501, determining a root node, a parent node, and a child node based on a storage object result;

[0144] Step 502, based on the root node, the parent node and the child node, determine the target storage link of the storage object result in the operation management tree;

[0145] Step 503: Store the storage object result in the operation management tree using the target storage link to implement intelligent operation management of the target medical device.

[0146] Optionally, the intelligent operation management system determines the root node, parent node and child node according to the storage object result. Continuing with the above embodiment, the storage object result of the target medical device W1 is N1-N2-N3-health status. Therefore, it can be determined that the root node of the target medical device W1 is N1, the parent node is N2, the child node is N3, and the leaf node is the health status.

[0147] Furthermore, the intelligent operation management system obtains the first text of each root node in the operation management tree, and obtains the second text of the root node in the storage object result.

[0148] Furthermore, the intelligent operation management system obtains the number of consecutive identical words between the first text and the second text that are greater than a preset length, and the maximum length of consecutive identical words, wherein the preset length is set according to demand, such as a preset length of 2, 3, 4, etc.

[0149] Furthermore, the intelligent operation management system calculates the similarity between the first text and the second text according to the number of consecutive words with the same length greater than the preset length, the maximum length, the total length of the first text and the total length of the second text, wherein the similarity between the first text and the second text can be understood as the similarity between the root node in the storage object result and any root node in the operation management tree, and the specific calculation formula is as follows:

[0150]

[0151] Where WordSim(s,r) represents the similarity between the first text and the second text, s represents the first text, r represents the second text, N w Indicates the number of consecutive words with the same length greater than the preset length, Max w Indicates the maximum length, L s Indicates the total length of the first text, L r Indicates the total length of the second text.

[0152] Furthermore, the intelligent operation management system determines the root node in the operation management tree with the greatest similarity to the root node in the storage object result as the target root node, that is, the parent node of the storage object result is classified under the branch of the target root node.

[0153] Continuing with the above embodiment, the storage object result of the target medical device W1 is N1-N2-N3-health status. The root node N1 has the greatest similarity with the root node A in the operation management tree. Therefore, the root node A is the target root node, and the parent node is N2 classified under the root node A.

[0154] It should be noted that, if there are multiple calculation results of the same maximum similarity, any root node corresponding to the maximum similarity in the operation management tree is selected as the target root node.

[0155] Similarly, the intelligent operation management system determines the target parent node and target child node in the operation management tree according to the above algorithm, and establishes a similar connection between the parent node in the storage object result and the target parent node, and establishes a similar connection between the child node in the storage object result and the target child node, and establishes a similar connection between the operation management tree and the target child node with the same leaf node in the storage object result, to obtain the target storage link of the storage object result in the operation management tree.

[0156] In one embodiment, the storage object result of the target medical device W1 is N1-N2-N3-healthy state. After similarity calculation, the similarity between the root node N1 and the root node A is greater than the similarity between the root node B. Therefore, the parent node N2 is classified into the root node A. Further, after similarity calculation, the similarity between the parent node N2 and the parent node a2 is greater than the similarity between the parent node a1, the similarity between the child node N3 and the child node a6 is greater than the similarity between the child node a5, the leaf node a9 is in an unhealthy state, and the leaf node a10 is in a healthy state. Therefore, after the storage object result of the target medical device W1 is stored in the operation management tree, FIG. Figure 4 As shown, Figure 4 This is the second structural diagram of the operation management tree provided by the present invention.

[0157] Furthermore, the intelligent operation management system stores the storage object results in the operation management tree with the target storage link to realize intelligent operation management of the target medical device.

[0158] The embodiment of the present invention stores the health assessment results as nodes in the operation management tree. When it is necessary to query the relevant information of the medical device, the health assessment results of the medical device can be queried through the nodes in the operation management tree, without the need to query through electronic spreadsheets, which speeds up the query efficiency of the relevant information of the medical device and improves the efficiency of the operation management of the medical device.

[0159] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530 and a communication bus 550, wherein the processor 510, the communications interface 520 and the memory 530 communicate with each other through the communication bus 550. The processor 510 may call the logic instructions in the memory 530 to execute the intelligent operation management method for medical devices, which includes:

[0160] Collecting the operating data and historical usage data of the target medical device; the operating data includes the temperature data, pressure data and operating time data of the target medical device, and the historical usage data includes the historical maintenance data and usage frequency data of the target medical device;

[0161] Inputting temperature data, pressure data and operation time data into the load forecasting model to obtain load data output by the load forecasting model; the load forecasting model is trained based on preset load data and its corresponding sample temperature data, sample pressure data and sample time data;

[0162] Input the load data, historical maintenance data and usage frequency data into the health assessment model to obtain the health assessment result output by the health assessment model; wherein the health assessment model is trained based on the preset health result and its corresponding preset load data, sample historical maintenance data and sample usage frequency data;

[0163] Generate storage object results based on health assessment results;

[0164] The storage object results are stored as nodes in the preset operation management tree to achieve intelligent operation management of the target medical device.

[0165] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0166] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the intelligent operation management method for medical devices provided by the above methods, the method comprising:

[0167] Collecting the operating data and historical usage data of the target medical device; the operating data includes the temperature data, pressure data and operating time data of the target medical device, and the historical usage data includes the historical maintenance data and usage frequency data of the target medical device;

[0168] Inputting temperature data, pressure data and operation time data into the load forecasting model to obtain load data output by the load forecasting model; the load forecasting model is trained based on preset load data and its corresponding sample temperature data, sample pressure data and sample time data;

[0169] Input the load data, historical maintenance data and usage frequency data into the health assessment model to obtain the health assessment result output by the health assessment model; wherein the health assessment model is trained based on the preset health result and its corresponding preset load data, sample historical maintenance data and sample usage frequency data;

[0170] Generate storage object results based on health assessment results;

[0171] The storage object results are stored as nodes in the preset operation management tree to achieve intelligent operation management of the target medical device.

[0172] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the above-mentioned intelligent operation management method for medical devices, the method comprising:

[0173] Collecting the operating data and historical usage data of the target medical device; the operating data includes the temperature data, pressure data and operating time data of the target medical device, and the historical usage data includes the historical maintenance data and usage frequency data of the target medical device;

[0174] Inputting temperature data, pressure data and operation time data into the load forecasting model to obtain load data output by the load forecasting model; the load forecasting model is trained based on preset load data and its corresponding sample temperature data, sample pressure data and sample time data;

[0175] Input the load data, historical maintenance data and usage frequency data into the health assessment model to obtain the health assessment result output by the health assessment model; wherein the health assessment model is trained based on the preset health result and its corresponding preset load data, sample historical maintenance data and sample usage frequency data;

[0176] Generate storage object results based on health assessment results;

[0177] The storage object results are stored as nodes in the preset operation management tree to achieve intelligent operation management of the target medical device.

[0178] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0179] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0180] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent operation management system for medical devices, characterized in that: It includes an operation management center, a data acquisition module, a load intelligent analysis module, a health intelligent assessment module, a node object generation module and an intelligent operation management module; the operation management center is respectively connected to the data acquisition module, the load intelligent analysis module, the health intelligent assessment module, the node object generation module and the intelligent operation management module to store and manage the data of each module; A data acquisition module, used to collect operating data and historical usage data of the target medical device; the operating data includes temperature data, pressure data and operating time data of the target medical device, and the historical usage data includes historical maintenance data and usage frequency data of the target medical device; A load intelligent analysis module, used for inputting the temperature data, the pressure data and the operation time data into a load prediction model to obtain the load data output by the load prediction model; wherein the load prediction model is trained based on preset load data and its corresponding sample temperature data, sample pressure data and sample time data; A health intelligent assessment module, used for inputting the load data, the historical maintenance data and the usage frequency data into a health assessment model to obtain a health assessment result output by the health assessment model; wherein the health assessment model is trained based on a preset health result and its corresponding preset load data, sample historical maintenance data and sample usage frequency data; A node object generation module, used to generate a storage object result based on the health assessment result; The intelligent operation management module is used to store the storage object results as nodes in a preset operation management tree to achieve intelligent operation management of the target medical device.

2. An intelligent operation management method for medical devices, applied to the intelligent operation management system for medical devices as claimed in claim 1, characterized in that: The intelligent operation management method for medical devices includes: Collecting operation data and historical usage data of the target medical device; the operation data includes temperature data, pressure data and operation time data of the target medical device, and the historical usage data includes historical maintenance data and usage frequency data of the target medical device; Inputting the temperature data, the pressure data and the operation time data into a load prediction model to obtain the load data output by the load prediction model; the load prediction model is trained based on the preset load data and its corresponding sample temperature data, sample pressure data and sample time data; Input the load data, the historical maintenance data and the usage frequency data into a health assessment model to obtain a health assessment result output by the health assessment model; wherein the health assessment model is trained based on a preset health result and its corresponding preset load data, sample historical maintenance data and sample usage frequency data; generating a storage object result based on the health assessment result; The storage object result is stored as a node in a preset operation management tree to achieve intelligent operation management of the target medical device.

3. The intelligent operation and management method for medical devices according to claim 2, characterized in that: The load prediction model includes a load factor prediction layer, a response load prediction layer and a load calculation layer; the load calculation layer is connected to the load factor prediction layer and the response load prediction layer respectively; The step of inputting the temperature data, the pressure data and the operation time data into a load forecasting model to obtain load data output by the load forecasting model includes: Inputting the temperature data and pressure data into the load factor prediction layer to obtain the temperature load factor and pressure load factor output by the load factor prediction layer; Inputting the temperature data, the pressure data and the operation time data into the response load prediction layer to obtain the load prediction value output by the response load prediction layer; The temperature load factor, the pressure load factor and the load prediction value are input into the load calculation layer to obtain the load data output by the load calculation layer.

4. The intelligent operation and management method for medical devices according to claim 3 is characterized in that: The loss function of the load forecasting model is: Loss1={[xlogf T (T θ )+(1-x)logf P (P θ )+x 2 logf t (t θ )]→A}; f t (t θ )=t θ *e c ; Among them, Loss1 represents the loss function of the load forecasting model, A represents the preset load data, T θ Represents sample temperature data, P θ represents the sample pressure data, t θ represents the sample duration data, x represents the preset weight coefficient, and f T (T θ ) represents the temperature operation function, λ represents the temperature weight attenuation parameter, ||·|| represents the two-norm calculation, logf P (P θ ) represents the pressure operation function, ρ represents the pressure weight attenuation parameter, represents the preset smoothing parameter, f t (t θ ) represents the duration operation function, e represents the base of the exponential function, and c represents the duration weight attenuation parameter.

5. The intelligent operation and management method for medical devices according to claim 2, characterized in that: The health assessment model includes a life prediction layer and a health assessment layer; The step of inputting the load data, the historical maintenance data and the usage frequency data into a health assessment model to obtain a health assessment result output by the health assessment model includes: Inputting the historical maintenance data and the usage frequency data into the life prediction layer to obtain a life prediction result output by the life prediction layer; The load data and the life prediction result are input into the health assessment layer to obtain the health assessment result output by the health assessment layer.

6. The intelligent operation management method for medical devices according to claim 5, characterized in that: The loss function of the health assessment model is: f H (H θ )=s r log(H θ )+(1-σ c )log(H θ ); f H (IN θ )=σ c log(U θ )+(1-σ r )log(U θ ); Among them, Loss2 represents the loss function of the health assessment model, B represents the preset health result, σ r represents the weight of the life prediction layer, σ c represents the weight of the health assessment layer, A represents the preset load data, H θ Represents sample historical maintenance data, U θ Indicates the sample usage frequency data, f H (H θ ) represents the maintenance operation function, f H (U θ ) represents the frequency operation function.

7. The intelligent operation management method for medical devices according to claim 2, characterized in that: The device information of the target medical device includes the device registration number, device model and device manufacturer number; the medical device type includes diagnostic device type, therapeutic device type and monitoring device type; The generating a storage object result based on the health assessment result includes: Obtaining device information and medical device type of the target medical device; Determining a coding method of the target medical device based on the type of the medical device; Encoding the device registration number, the device model number and the device manufacturer number based on the encoding method to obtain encoding information of the target medical device; The storage object result is generated based on the encoding information and the health assessment result.

8. The intelligent operation management method for medical devices according to claim 2, characterized in that: The storing the storage object result as a node in a preset operation management tree to realize intelligent operation management of the target medical device includes: Determine a root node, a parent node, and a child node based on the storage object result; Determine a target storage link of the storage object result in the operation management tree based on the root node, the parent node and the child node; The storage object result is stored in the operation management tree using the target storage link to implement intelligent operation management of the target medical device.

9. An electronic device, comprising: A memory and a processor, characterized in that a computer software program is stored in the memory, and when the processor reads and executes the computer software program, the intelligent operation and management method for medical devices as described in any one of claims 2 to 8 is implemented.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the intelligent operation and management method for medical devices as described in any one of claims 2 to 8 is implemented.

Images