Medical equipment intelligent management system and method based on data model analysis

Through the intelligent management system of medical equipment based on data model analysis, the use of sensor data and neural network models to optimize the maintenance plan of medical equipment, the problem of inefficiency of traditional management methods is solved, efficient and intelligent management of medical equipment is realized, and operational costs are reduced. Resource waste has improved the quality of medical services.

CN119028552AInactive Publication Date: 2024-11-26SHANDONG PROVINCE FIRST REHABILITATION HOSPITAL +1
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411069359.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional medical equipment management methods lack real-time and personalization, resulting in inefficiency, inability to effectively utilize data, and difficulty in timely procurement or maintenance based on equipment needs, resulting in high operating costs, waste of resources, and affecting the quality and continuity of medical services.

Method used

An intelligent medical equipment management system based on data model analysis can collect data in real time through sensors, build a risk assessment neural network model, calculate maintenance time correction coefficient, optimize maintenance plan, realize equipment level division and personalized maintenance, monitor energy consumption, and perform secondary Optimize maintenance time to ensure the equipment is operating in the best condition.

Benefits of technology

It improves the operating efficiency and maintenance efficiency of medical equipment, reduces operating costs, ensures the safety and reliability of equipment, extends the service life of equipment, optimizes energy consumption, and improves the quality and continuity of medical services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119028552A_ABST
    Figure CN119028552A_ABST
Patent Text Reader

Abstract

The invention relates to the field of data analysis, in particular to a medical equipment intelligent management system and method based on data model analysis, and the method comprises the steps: collecting the related data information of medical equipment in real time through a sensor installed on the medical equipment, carrying out the preprocessing operation, and constructing a medical equipment risk assessment neural network model; calculating a correction coefficient of the maintenance duration of the medical equipment according to the failure rate and the use frequency of the medical equipment; comparing the correction coefficient of the maintenance duration of the medical equipment with a predefined correction coefficient contrast index of the maintenance duration, and correcting the maintenance duration of the medical equipment according to a comparison result; and obtaining a maintenance effect of the medical equipment according to the optimized maintenance duration of the medical equipment, and calculating to obtain an update period of the medical equipment, thereby realizing intelligent management of the medical equipment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to a medical equipment intelligent management system and method based on data model analysis. Background Art

[0002] With the continuous development of medical technology, the types and quantity of medical equipment used in hospitals have increased dramatically, and the management and maintenance of these equipment have become increasingly complex. Traditional medical equipment management methods mainly rely on manual inspection and maintenance, which lacks real-time and personalization, is inefficient and prone to errors. Therefore, traditional management methods are difficult to meet the requirements of modern hospitals for efficiency and safety.

[0003] At the same time, modern technology is developing rapidly. In the management of modern medical equipment, the existing technology still has the following problems: as medical equipment becomes more diversified and complicated, it is impossible to effectively utilize the huge data generated and accurately locate and divide the medical equipment; it is impossible to purchase or maintain the medical equipment in a timely manner according to the real-time demand and consumption of the medical equipment, making it difficult to reduce operating costs and improve economic benefits; the medical equipment is not maintained according to its actual situation, resulting in a waste of medical resources, reducing the quality and continuity of medical services, and further exacerbating cost losses.

[0004] Therefore, there is a need for an intelligent management system and method for medical equipment based on data model analysis. Summary of the invention

[0005] The medical equipment intelligent management system and method based on data model analysis provided by the present invention aims to improve the operating efficiency of medical equipment, reduce operating costs, and realize standardized and refined intelligent management of medical equipment.

[0006] The technical solution of the present invention is specifically as follows:

[0007] The intelligent management method of medical equipment based on data model analysis includes the following steps:

[0008] Step S1. Using sensors installed on medical equipment, collect relevant data information of medical equipment in real time, perform preprocessing operations, and build a neural network model for medical equipment risk assessment;

[0009] Step S2. Calculate the correction factor of the maintenance time of the medical equipment according to the failure rate and usage frequency of the medical equipment;

[0010] Step S3. Compare the correction coefficient of the medical equipment maintenance time with the predefined correction coefficient control index of the maintenance time, and correct the maintenance time of the medical equipment according to the comparison result;

[0011] Step S4. Obtain the maintenance effect of the medical equipment according to the optimized maintenance time of the medical equipment, calculate and obtain the update cycle of the medical equipment, and realize intelligent management of the medical equipment.

[0012] Further, step S1 specifically includes:

[0013] Medical devices are classified into different levels according to the output results of the medical device risk assessment neural network model and the technical complexity of the medical devices, and the maintenance time Mat of the medical devices is set based on the classification.

[0014] Furthermore, the medical device risk assessment neural network model includes an input layer, an evaluation layer, an adjustment layer, and an output layer; the input layer is fully connected to the evaluation layer, and the input layer transmits the input data information to the evaluation layer. The specific process is as follows:

[0015] ID P =ω 12 *OE1+b P

[0016]

[0017] Among them, OE1 represents the output of the input layer; ω1 represents the connection weight of the neurons in the input layer; b1 represents the bias of the input layer; ID P represents the input of the evaluation layer; OE2 represents the output of the evaluation layer; ω 12 represents the connection weight between the input layer and the evaluation layer; b P represents the bias of the evaluation layer; T0 represents the duration when the abnormal situation occurs; α1 represents the first adjustment parameter; α2 represents the second adjustment parameter; T represents the total duration of the historical operation data record; S t Indicates the temperature of the medical device at time t; W S Indicates the impact weight of different temperatures occurring in medical equipment; Indicates the average pressure when the medical device is working normally; ID P_0 represents the neuron state of the evaluation layer; Q represents the number of neurons in the evaluation layer; β represents the pressure warning threshold of the medical equipment.

[0018] Further, step S2 specifically includes:

[0019]

[0020] Among them, Mat_AG represents the correction coefficient of the maintenance time of medical equipment; cost represents the cost incurred when maintaining medical equipment; Gz represents the failure rate of medical equipment; θ1 represents the influence coefficient; SC represents the frequency of use of medical equipment; D1 represents the coefficient of variation of the number of times different medical equipment is used; D2 represents the stability coefficient of the failure of medical equipment; μ represents the correction factor; Vor represents the impact of the external environment on the operation of medical equipment.

[0021] Further, step S3 specifically includes:

[0022] According to the energy consumption information obtained during the operation of medical equipment, the average energy consumption E of medical equipment is calculated. mu ;

[0023]

[0024] Among them, E mu represents the average energy consumption of medical equipment; T represents the total duration of historical operation data recording; E(t) represents the energy consumption of medical equipment at time t; Indicates the impact weight of energy consumption of medical equipment during peak hours; represents the impact weight of medical equipment energy consumption during off-peak hours; Inf(Gz) represents the impact function of failures during the operation of medical equipment; P br Indicates the output power of medical equipment during normal operation; represents the output power of the medical device at time t0; ρ represents the attenuation factor; de_E represents the total energy demand of the medical device during the recording time; tal_E represents the total energy that can be obtained; σ represents the energy consumption balance coefficient.

[0025] Further, step S3 specifically includes:

[0026] The average energy consumption of medical equipment is compared with the preset average energy consumption of medical equipment E mu 'Conduct a comparison, and determine whether to perform secondary optimization on the revised maintenance time of the medical equipment according to the comparison results;

[0027] If E mu ≤E mu ', it means that the use and working status of the medical equipment are normal, and there is no need to optimize the maintenance time of the corrected medical equipment again;

[0028] If E mu >E mu ', it means that the use or working status of the medical equipment is abnormal, and it is necessary to optimize the maintenance time of the corrected medical equipment again.

[0029] Further, step S4 specifically includes:

[0030] Now define the medical equipment maintenance effect function as X(Mat), the equipment performance degradation function as L(T), and the medical equipment update cycle as T update , T update =argmin T (L(T)-X(Mat)).

[0031] The intelligent management system of medical equipment based on data model analysis includes the following contents:

[0032] Data acquisition and processing unit, medical equipment risk assessment unit, medical equipment classification unit, maintenance time correction unit, medical equipment energy consumption unit, maintenance time secondary optimization unit, medical equipment update decision unit;

[0033] Data acquisition and processing unit, responsible for collecting data from various medical devices and sensors and performing pre-processing operations;

[0034] Medical equipment risk assessment unit, which establishes a medical equipment risk assessment neural network model based on the collected data to conduct risk assessment on medical equipment;

[0035] The medical equipment classification unit classifies medical equipment according to the output of the medical equipment risk assessment neural network model and the technical complexity of the medical equipment, and defines the maintenance time;

[0036] The maintenance duration correction unit corrects the maintenance duration according to the equipment operation status and maintenance history;

[0037] The medical equipment energy consumption unit monitors and analyzes the energy consumption of the medical equipment based on the energy consumption information obtained during the operation of the medical equipment;

[0038] The maintenance time secondary optimization unit compares the average energy consumption of medical equipment with the preset average energy consumption of medical equipment, and determines whether to optimize based on the revised maintenance time according to the comparison result;

[0039] The medical equipment update decision unit manages the medical equipment based on the optimized medical equipment maintenance time, medical equipment maintenance effect function, and equipment performance degradation function.

[0040] Beneficial effects:

[0041] 1. The present invention can provide objective and accurate decision-making through the risk assessment model, improve management efficiency and the scientific nature of decision-making, thereby identifying potential safety risks, taking corresponding measures to ensure the safe operation of medical equipment and the safety of patients, optimizing equipment maintenance plans, and concentrating resources on the most needed equipment, thereby improving maintenance efficiency and reducing maintenance costs; by comprehensively grading medical equipment according to risk assessment results and technical complexity, it is possible to formulate personalized maintenance plans for each device, effectively ensure the normal operation of the equipment, and reduce unexpected downtime; by setting the maintenance time according to the equipment level, maintenance resources can be accurately allocated, and high-risk equipment and equipment with high technical complexity can obtain more frequent and in-depth maintenance, thereby reducing the possibility of equipment failure and improving equipment reliability; formulating a reasonable maintenance plan according to the equipment level can ensure the stability and reliability of medical equipment, thereby improving the quality and continuity of medical services.

[0042] 2. By considering the failure rate and frequency of use, the present invention can formulate a personalized maintenance plan for each medical device to meet the actual needs of the device and extend the service life of the device; accurately calculating the correction coefficient of the maintenance time can avoid excessive or insufficient maintenance, thereby reducing unnecessary maintenance costs and improving maintenance efficiency and the overall performance of the medical equipment; adjusting the maintenance time according to the correction coefficient can more effectively allocate maintenance resources. Devices with high failure rates and high usage frequencies may require more frequent maintenance, while devices with low failure rates and low usage frequencies can reduce the number of maintenance times and save maintenance costs.

[0043] 3. The present invention can find the difference between actual maintenance needs and expectations by comparing the correction coefficients. Correcting the maintenance time can more accurately meet the actual maintenance needs of the equipment, avoid unnecessary maintenance or equipment failures caused by delayed maintenance, help find equipment problems in advance and perform maintenance, ensure the reliability and stability of the equipment, and ensure the continuity of medical services. By comparing the actual energy consumption with the expected energy consumption, the energy efficiency performance of the equipment can be evaluated, and it can be considered whether to perform secondary optimization on the maintenance time to improve the energy efficiency performance of the equipment and reduce energy consumption; secondary optimization of maintenance time can help medical institutions use resources more effectively, avoid unnecessary energy waste, and help reduce negative impacts on the environment; by adjusting the maintenance time according to energy consumption, operating costs can be reduced. Reducing energy consumption not only helps to reduce operating costs, but also reduces equipment wear and tear and improves equipment reliability and stability.

[0044] 4. Based on the maintenance effect function and the equipment performance degradation function, the present invention can help medical institutions to rationally plan the equipment update and replacement cycle, more accurately evaluate the service life of the equipment, and avoid updating the equipment too early or too late; optimizing the maintenance time can improve the maintenance effect of the equipment, extend the service life of the equipment, and reduce the maintenance cost of the equipment. Based on the calculated update cycle, medical institutions can implement intelligent decision support and formulate more scientific and reasonable equipment update plans. The medical equipment intelligent management system can help medical institutions better manage equipment based on real-time data and analysis results, ensure that the equipment operates in the best condition, and improve service levels and medical quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of the medical equipment intelligent management method based on data model analysis of the present invention;

[0046] Figure 2 This is a module diagram of the medical equipment intelligent management system based on data model analysis of the present invention. DETAILED DESCRIPTION

[0047] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should also be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0048] See attached Figure 1 This embodiment provides a medical equipment intelligent management method based on data model analysis, comprising the following steps:

[0049] S1. Through the sensors installed on the medical equipment, relevant data information of the medical equipment is collected in real time, including information related to the working status, environment, maintenance records, energy consumption, and frequency of use. Information related to the working status includes but is not limited to data such as temperature, pressure, current, and vibration; information related to the environment includes but is not limited to data such as temperature, humidity, and air pressure; information related to maintenance records includes but is not limited to data such as the maintenance history, maintenance frequency, and maintenance consumables usage of the medical equipment; information related to energy consumption includes but is not limited to data such as the energy usage, energy demand, and energy stability of the medical equipment; information related to frequency of use includes but is not limited to data such as the frequency of use of the medical equipment, the time period of use, and the number of times of use. The collected raw data is cleaned, normalized, and standardized to eliminate noise and outliers and ensure data quality.

[0050] Based on the historical medical device data obtained, a medical device risk assessment neural network model is constructed, in which the assessed risk situation is a comprehensive situation, including but not limited to the degree of risk to patient safety. The historical operation data characteristics of medical equipment are used as training samples and input into the medical device risk assessment neural network model. The medical device risk assessment neural network model includes an input layer, an evaluation layer, an adjustment layer, and an output layer.

[0051] Define the sample input data of medical equipment historical operation data as Data, Data = {data1, data2, ..., data N}, N represents the number of input sample data sets, where data n Represents any set of sample data information input, n∈[1,N]. The input layer is fully connected to the evaluation layer, and the input layer passes the input data information to the evaluation layer. The specific process is as follows:

[0052] OE1=ω1*data n +b1

[0053] ID P =ω 12 *OE1+b P

[0054]

[0055] Among them, OE1 represents the output of the input layer; ω1 represents the connection weight of the neurons in the input layer; b1 represents the bias of the input layer; ID P represents the input of the evaluation layer; OE2 represents the output of the evaluation layer; ω 12 represents the connection weight between the input layer and the evaluation layer; b P represents the bias of the evaluation layer; T0 represents the duration when the abnormal situation occurs; α1 represents the first adjustment parameter; α2 represents the second adjustment parameter; T represents the total duration of the historical operation data record; S t Indicates the temperature of the medical device at time t; W S Indicates the impact weight of different temperatures occurring in medical equipment; Indicates the average pressure when the medical device is working normally; ID P_0 represents the neuron state of the evaluation layer; Q represents the number of neurons in the evaluation layer; β represents the pressure warning threshold of the medical equipment.

[0056] The assessment layer transmits the risk assessment of medical devices to the adjustment layer, where the assessment results of the model are improved. The specific process is as follows:

[0057] ID S =ω 23 *OE2+b S

[0058]

[0059] Among them, ID S Represents the input of the adjustment layer; ω 23 represents the connection weight between the evaluation layer and the adjustment layer; b S Indicates the bias of the adjustment layer; Vb indicates the adjustment fusion factor; G u Represents the evaluation score of the u-th medical device.

[0060] The adjustment layer passes the optimized results to the output layer, which outputs the final medical device risk assessment results. The specific process is as follows:

[0061]

[0062] Among them, Y represents the output result of the output layer; ω Y represents the weight of the output layer; b Y Represents the bias of the output layer.

[0063] In the embodiment of the present invention, the first risk threshold of the medical device is defined as ε1, the second risk threshold is defined as ε2, and ε1>ε2;

[0064] if It means that the medical device is at high risk; if ε2<γ* The medical device is at medium risk. It means that the medical device is at low risk; where γ represents the evaluation coefficient.

[0065] Medical equipment is graded according to the output results of the medical equipment risk assessment neural network model and the technical complexity of the medical equipment, and the maintenance time Mat of the medical equipment is set in combination with the grade classification. The grade classification of medical equipment includes: first-level medical equipment, second-level medical equipment, and third-level medical equipment;

[0066] If it is a first-level medical device, it means that the medical device is at low risk and is a medical device with simple technology, easy to operate and maintain; set the initial medical device maintenance time Mat1,

[0067] If it is a secondary medical device, it means that the medical device is at medium risk and has a certain technical complexity, which requires training before operation and maintenance; set the initial medical device maintenance time Mat1,

[0068] If it is a Class III medical device, it means that the medical device is at high risk and is a medical device with complex technology, high operating requirements, and difficult maintenance. Set the initial medical device maintenance time Mat1. Among them, Mat0 represents the standard maintenance time of medical equipment, and δ1, δ2, and δ3 represent the corresponding control parameters respectively.

[0069] Through the risk assessment model, the present invention can provide objective and accurate decisions, improve management efficiency and the scientific nature of decisions, thereby identifying potential safety risks, taking corresponding measures, ensuring the safe operation of medical equipment and the safety of patients, optimizing equipment maintenance plans, and concentrating resources on the most needed equipment, thereby improving maintenance efficiency and reducing maintenance costs; by comprehensively grading medical equipment according to risk assessment results and technical complexity, it is possible to formulate personalized maintenance plans for each device, effectively ensuring the normal operation of the equipment and reducing unexpected downtime; by setting the maintenance duration according to the equipment level, maintenance resources can be accurately allocated, and high-risk equipment and equipment with high technical complexity can obtain more frequent and in-depth maintenance, thereby reducing the possibility of equipment failure and improving equipment reliability; formulating a reasonable maintenance plan according to the equipment level can ensure the stability and reliability of medical equipment, thereby improving the quality and continuity of medical services.

[0070] S2. Calculate the correction factor for the maintenance time of medical equipment based on the failure rate and frequency of use of the medical equipment.

[0071] According to the failure rate and usage frequency of medical equipment, the correction factor of the maintenance time of medical equipment is calculated. The specific process is as follows:

[0072]

[0073] Among them, Mat_AG represents the correction coefficient of the maintenance time of medical equipment; cost represents the cost incurred when maintaining medical equipment; Gz represents the failure rate of medical equipment; θ1 represents the influence coefficient; SC represents the frequency of use of medical equipment; D1 represents the coefficient of variation of the number of times different medical equipment is used; D2 represents the stability coefficient of the failure of medical equipment; μ represents the correction factor; Vor represents the impact of the external environment on the operation of medical equipment.

[0074] By considering the failure rate and usage frequency, the present invention can formulate personalized maintenance plans for each medical device to meet the actual needs of the device and extend its service life; accurately calculating the correction factor of the maintenance duration can avoid over-maintenance or under-maintenance, thereby reducing unnecessary maintenance costs, improving maintenance efficiency and the overall performance of medical devices; adjusting the maintenance duration according to the correction factor can more effectively allocate maintenance resources. Devices with high failure rates and high usage frequencies may require more frequent maintenance, while devices with low failure rates and low usage frequencies can reduce the number of maintenance times and save maintenance costs.

[0075] S3. Compare the correction factor of the medical device maintenance duration with the predefined correction factor control index for the maintenance duration of the medical device, and correct the maintenance duration of the medical device based on the comparison result.

[0076] In the embodiment of the present invention, the predefined correction factor control index for the maintenance duration of the first medical device is AG1, and AG1 > 0;

[0077] If Mat_AG ≥ AG1, then set the maintenance duration of the corrected medical device to Mat2,

[0078] If 0 ≤ Mat_AG < AG1, then set the maintenance duration of the corrected medical device to Mat2,

[0079] If Mat_AG < 0, then set the maintenance duration of the corrected medical device to Mat2,

[0080] According to the obtained energy consumption-related information during the operation of the medical device, calculate the average energy consumption of the medical device. The specific process is as follows:

[0081]

[0082] Among them, E mu represents the average energy consumption of the medical device; T represents the total duration of the historical operation data record; E(t) represents the energy consumption of the medical device at time t; represents the weight of the energy consumption impact of the medical device during peak hours; represents the weight of the energy consumption impact of the medical device during off-peak hours; Inf(Gz) represents the impact function of the faults during the operation of the medical device; P brIt represents the output power of the medical equipment during normal operation; Pt0 represents the output power of the medical equipment at time t0; ρ represents the attenuation factor; de_E represents the total energy demand of the medical equipment during the recording time; tal_E represents the total energy that can be obtained; σ represents the energy consumption balance coefficient.

[0083] Compare the average energy consumption of medical equipment with the preset average energy consumption of medical equipment E mu 'Conduct a comparison and determine whether to perform a secondary optimization on the revised maintenance time of the medical equipment based on the comparison results.

[0084] If E mu ≤E mu ', it means that the use and working status of the medical equipment are normal, and there is no need to optimize the maintenance time of the corrected medical equipment again;

[0085] If E mu >E mu ', it means that the use or working status of the medical equipment is abnormal, and the maintenance time of the corrected medical equipment needs to be optimized again. The specific process is as follows:

[0086] In the embodiment of the present invention, E is calculated mu With E mu ', that is, ΔE=E mu -E mu '; Define the first preset energy consumption difference as ΔE1, the second preset energy consumption difference as ΔE2, and ΔE1>ΔE2;

[0087] If ΔE>ΔE1, the maintenance time of the medical equipment after secondary optimization is Mat3.

[0088] If ΔE2≤ΔE≤ΔE1, the maintenance time of the medical equipment after secondary optimization is Mat3.

[0089] If ΔE>ΔE1, the maintenance time of the medical equipment after secondary optimization is Max3. Among them, τ1, τ2, and τ3 represent the optimization coefficients in different situations respectively.

[0090] By comparing the correction coefficients, the present invention can find the difference between the actual maintenance needs and the expected ones. The correction of the maintenance time can more accurately meet the actual maintenance needs of the equipment, avoid unnecessary maintenance or equipment failure caused by delayed maintenance, help to find equipment problems in advance and perform maintenance, reduce equipment failure rate and unnecessary maintenance costs, ensure the reliability and stability of the equipment, and ensure the continuity of medical services. By comparing the actual energy consumption with the expected energy consumption, the energy efficiency performance of the equipment can be evaluated, and it can be considered whether to perform secondary optimization on the maintenance time to improve the energy efficiency performance of the equipment and reduce energy consumption; secondary optimization of maintenance time can help medical institutions use resources more effectively, avoid unnecessary energy waste, and help reduce negative impacts on the environment; by adjusting the maintenance time according to energy consumption, energy costs can be saved and operating costs can be reduced; reducing energy consumption not only helps to reduce operating costs, but also reduces equipment wear and tear and improves equipment reliability and stability.

[0091] S4. According to the optimized maintenance time of medical equipment, the maintenance effect of medical equipment can be obtained. The maintenance effect function of medical equipment is now defined as X(Mat), the equipment performance degradation function is L(T), and the update cycle of medical equipment is T update , the specific process is as follows:

[0092] L(T)=L0-r·In(1+b*T)

[0093]

[0094] T update =argmin T (L(T)-X(Mat))

[0095] Where L0 represents the initial performance of the medical device; r represents the device performance degradation rate; b represents the constant coefficient; X max represents the most ideal maintenance effect of medical equipment; k represents the constant coefficient of maintenance effect; represents the average cost requirement during the maintenance period; λ represents the contribution parameter of medical equipment maintenance effect; tom represents the minimum cost generated by different types of maintenance, and j represents the number of maintenance types.

[0096] Based on the maintenance effect function and the equipment performance degradation function, the present invention can help medical institutions to rationally plan the equipment update and replacement cycle, more accurately evaluate the service life of the equipment, and avoid updating the equipment too early or too late; optimizing the maintenance time can improve the maintenance effect of the equipment, extend the service life of the equipment, and reduce the maintenance cost of the equipment. Based on the calculated update cycle, medical institutions can implement intelligent decision support and formulate more scientific and reasonable equipment update plans. The intelligent management system for medical equipment can help medical institutions better manage equipment based on real-time data and analysis results, ensure that the equipment operates in the best condition, and improve service levels and medical quality.

[0097] See attached Figure 2 This embodiment provides a medical equipment intelligent management system based on data model analysis, including the following contents:

[0098] Data acquisition and processing unit, medical equipment risk assessment unit, medical equipment classification unit, maintenance time correction unit, medical equipment energy consumption unit, maintenance time secondary optimization unit, medical equipment update decision unit;

[0099] Data acquisition processing unit, responsible for collecting data from various medical devices and sensors, including equipment operating status, maintenance records, energy consumption data, etc.;

[0100] Medical equipment risk assessment unit, which establishes a medical equipment risk assessment neural network model based on the collected data to conduct risk assessment on medical equipment and identify potential failure risks and safety hazards;

[0101] A medical device classification unit that classifies medical devices according to the output of the medical device risk assessment neural network model and the technical complexity of the medical devices;

[0102] The maintenance time correction unit corrects the maintenance time according to the equipment operation status and maintenance history to improve maintenance efficiency and accuracy;

[0103] Medical equipment energy consumption unit, which monitors and analyzes the energy consumption of medical equipment, helps save energy and reduce emissions, and optimizes energy utilization;

[0104] The maintenance time secondary optimization unit compares the average energy consumption of medical equipment with the preset average energy consumption of medical equipment, and determines whether to further optimize the plan based on the revised maintenance time according to the comparison results to ensure the timeliness and effectiveness of equipment maintenance;

[0105] The medical equipment update decision unit manages the medical equipment based on the optimized medical equipment maintenance time, medical equipment maintenance effect function, and equipment performance degradation function to ensure that the equipment is in the best condition.

[0106] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0107] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0108] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0109] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0110] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A medical equipment intelligent management method based on data model analysis, characterized in that: The following steps are involved: Step S1. Using sensors installed on medical equipment, collect relevant data information of medical equipment in real time, perform preprocessing operations, and build a neural network model for medical equipment risk assessment; Step S2. Calculate the correction factor of the maintenance time of the medical equipment according to the failure rate and usage frequency of the medical equipment; Step S3. Compare the correction coefficient of the medical equipment maintenance time with the predefined correction coefficient control index of the maintenance time, and correct the maintenance time of the medical equipment according to the comparison result; Step S4. Obtain the maintenance effect of the medical equipment according to the optimized maintenance time of the medical equipment, calculate and obtain the update cycle of the medical equipment, and realize intelligent management of the medical equipment.

2. The medical equipment intelligent management method based on data model analysis according to claim 1 is characterized in that: The step S1 specifically includes: Medical devices are classified into different levels according to the output results of the medical device risk assessment neural network model and the technical complexity of the medical devices, and the maintenance time Mat of the medical devices is set based on the classification.

3. The medical equipment intelligent management method based on data model analysis according to claim 1 is characterized in that: The medical device risk assessment neural network model includes an input layer, an evaluation layer, an adjustment layer, and an output layer; the input layer is fully connected with the evaluation layer, and the input layer transmits the input data information to the evaluation layer. The specific process is as follows: ID P =ω 12 *OE1+b P Among them, OE1 represents the output of the input layer; ω1 represents the connection weight of the neurons in the input layer; b1 represents the bias of the input layer; IDp represents the input of the evaluation layer; OE2 represents the output of the evaluation layer; ω 12 represents the connection weight between the input layer and the evaluation layer; b P represents the bias of the evaluation layer; T0 represents the duration when the abnormal situation occurs; α1 represents the first adjustment parameter; α2 represents the second adjustment parameter; T represents the total duration of the historical operation data record; S t Indicates the temperature of the medical device at time t; W S Indicates the impact weight of different temperatures occurring in medical equipment; Indicates the average pressure when the medical device is working normally; ID P_0 represents the neuron state of the evaluation layer; Q represents the number of neurons in the evaluation layer; β represents the pressure warning threshold of the medical equipment.

4. The medical equipment intelligent management method based on data model analysis according to claim 1 is characterized in that: The step S2 specifically includes: Among them, Mat_AG represents the correction coefficient of the maintenance time of medical equipment; cost represents the cost incurred when maintaining medical equipment; Gz represents the failure rate of medical equipment; θ1 represents the influence coefficient; SC represents the frequency of use of medical equipment; D1 represents the coefficient of variation of the number of times different medical equipment is used; D2 represents the stability coefficient of the failure of medical equipment; μ represents the correction factor; Vor represents the impact of the external environment on the operation of medical equipment.

5. The medical equipment intelligent management method based on data model analysis according to claim 1 is characterized in that: The step S3 specifically includes: According to the energy consumption information obtained during the operation of medical equipment, the average energy consumption E of medical equipment is calculated. mu ; Among them, E mu represents the average energy consumption of medical equipment; T represents the total duration of historical operation data recording; E(t) represents the energy consumption of medical equipment at time t; Indicates the impact weight of energy consumption of medical equipment during peak hours; represents the impact weight of medical equipment energy consumption during off-peak hours; Inf(Gz) represents the impact function of failures during the operation of medical equipment; P b r represents the output power of the medical equipment during normal operation; represents the output power of the medical device at time t0; ρ represents the attenuation factor; de_E represents the total energy demand of the medical device during the recording time; tal_E represents the total energy that can be obtained; σ represents the energy consumption balance coefficient.

6. The medical equipment intelligent management method based on data model analysis according to claim 5 is characterized in that: The step S3 specifically includes: The average energy consumption of medical equipment is compared with the preset average energy consumption of medical equipment E mu 'Conduct a comparison, and determine whether to perform secondary optimization on the revised maintenance time of the medical equipment according to the comparison results; If E mu ≤E mu ', it means that the use and working status of the medical equipment are normal, and there is no need to optimize the maintenance time of the corrected medical equipment again; If E mu >E mu ', it means that the use or working status of the medical equipment is abnormal, and it is necessary to optimize the maintenance time of the corrected medical equipment again.

7. The medical equipment intelligent management method based on data model analysis according to claim 1 is characterized in that: The step S4 specifically includes: Now define the medical equipment maintenance effect function as X(Mat), the equipment performance degradation function as L(T), and the medical equipment update cycle as T update , T update =argmin T (L(T)-X(Mat)).

8. A medical equipment intelligent management system based on data model analysis, applied to the medical equipment intelligent management method based on data model analysis according to claim 1, comprising the following contents: Data acquisition and processing unit, medical equipment risk assessment unit, medical equipment classification unit, maintenance time correction unit, medical equipment energy consumption unit, maintenance time secondary optimization unit, medical equipment update decision unit; The data acquisition processing unit is responsible for collecting data from various medical devices and sensors and performing pre-processing operations; The medical device risk assessment unit establishes a medical device risk assessment neural network model based on the collected data to perform risk assessment on the medical device; The medical equipment classification unit classifies the medical equipment according to the output results of the medical equipment risk assessment neural network model and the technical complexity of the medical equipment, and defines the maintenance time; The maintenance duration correction unit corrects the maintenance duration according to the equipment operation status and maintenance history: The medical equipment energy consumption unit monitors and analyzes the energy consumption of the medical equipment based on the energy consumption related information obtained during the operation of the medical equipment; The maintenance time secondary optimization unit compares the average energy consumption of the medical equipment with the preset average energy consumption of the medical equipment, and determines whether to optimize based on the revised maintenance time according to the comparison result; The medical equipment update decision unit manages the medical equipment based on the optimized medical equipment maintenance duration, the medical equipment maintenance effect function, and the equipment performance degradation function.

Citation Information

Cited By

  • Method and system for intelligently generating treatment prescription

    CN120072255A

  • Medical equipment preventive inspection method and system based on dynamic scheduling engine

    CN121122619A