CN117789954A

CN117789954A - Rehabilitation and nursing equipment data management method and platform

Info

Publication number: CN117789954A
Application number: CN202410204973.0A
Authority: CN
Inventors: 朱冠华; 王芳芳; 陈秀华
Original assignee: People's Liberation Army Navy Navy Qingdao Special Service Sanatorium
Current assignee: People's Liberation Army Navy Navy Qingdao Special Service Sanatorium
Priority date: 2024-02-26
Filing date: 2024-02-26
Publication date: 2024-03-29

Abstract

The invention relates to the technical field of rehabilitation and nursing equipment data management, in particular to a rehabilitation and nursing equipment data management method and a platform. The method comprises the following steps: collecting rehabilitation and nursing equipment data from different data sources, and updating the equipment state of the rehabilitation and nursing equipment data to obtain equipment state updating data; performing frequency of use feature extraction and load state feature extraction on the rehabilitation and nursing equipment data according to the equipment state updating data to obtain frequency of use feature data and load state feature data; performing equipment gap calculation on the using frequency characteristic data and the load state characteristic data according to the rehabilitation and nursing equipment data to obtain rehabilitation and nursing equipment gap data; and performing equipment calling plan generation on the rehabilitation and nursing equipment data according to the rehabilitation and nursing equipment gap data to obtain the rehabilitation and nursing equipment calling plan data. The invention optimizes equipment configuration and use, discovers equipment gaps in time, and makes an effective equipment calling plan.

Description

Rehabilitation and nursing equipment data management method and platform

Technical Field

The invention relates to the technical field of rehabilitation and nursing equipment data management, in particular to a rehabilitation and nursing equipment data management method and a platform.

Background

The rehabilitation nursing equipment data management method refers to a method for effectively collecting, storing, processing and analyzing the related data of the rehabilitation nursing equipment (such as a walking aid, an orthosis and the like), and aims to improve the efficiency and the quality of rehabilitation nursing so as to better meet the rehabilitation requirements of patients. The conventional method is used for simply collecting and storing the data of the rehabilitation and nursing equipment, visualizing the data, analyzing and utilizing the data to a low degree, and not fully mining the potential value of the data, so that potential waste and underutilization of the rehabilitation and nursing equipment are caused.

Disclosure of Invention

The invention provides a rehabilitation and nursing equipment data management method and platform for solving at least one of the technical problems.

The application provides a rehabilitation and nursing equipment data management method, which comprises the following steps:

step S1: collecting rehabilitation and nursing equipment data from different data sources, and updating the equipment state of the rehabilitation and nursing equipment data to obtain equipment state updating data;

step S2: performing frequency of use feature extraction and load state feature extraction on the rehabilitation and nursing equipment data according to the equipment state updating data to obtain frequency of use feature data and load state feature data;

Step S3: performing equipment gap calculation on the using frequency characteristic data and the load state characteristic data according to the rehabilitation and nursing equipment data to obtain rehabilitation and nursing equipment gap data;

step S4: and performing equipment calling plan generation on the rehabilitation and nursing equipment data according to the rehabilitation and nursing equipment gap data to obtain the rehabilitation and nursing equipment calling plan data so as to perform rehabilitation and nursing equipment calling operation.

The invention collects and updates the state information of the rehabilitation and nursing equipment in real time, including the use frequency, the load state and the like, and knows the use condition of the equipment in time and discovers potential problems and abnormal conditions in time. Based on the frequency of use and the load state characteristic data, the demand and the service condition of the rehabilitation and nursing equipment can be evaluated more accurately, the configuration of the equipment is optimized, the resources are reasonably distributed, and the service efficiency of the rehabilitation and service equipment is improved. Through step S3, the gap data of the rehabilitation and nursing equipment can be calculated according to the actual use condition, wherein the gap data comprises the gap between the equipment demand and the actual supply, the shortage problem of the rehabilitation and nursing equipment can be found and solved in time, and the smooth proceeding of rehabilitation and nursing is ensured. Based on the rehabilitation and care equipment gap data, an effective equipment call plan can be formulated (step S4), including supplementing the equipment in shortage and adjusting the use plan of the equipment.

Preferably, step S1 is specifically:

step S11: collecting rehabilitation and care equipment data from different data sources;

step S12: extracting equipment availability, maintenance requirement and service condition of the rehabilitation and nursing equipment data to obtain equipment availability data, maintenance requirement data and service condition data;

step S13: and updating the equipment state according to the equipment availability data, the maintenance demand data and the service condition data to obtain equipment state updating data.

In the invention, step S11 ensures the comprehensiveness and diversity of the data by collecting the rehabilitation and nursing equipment data from different data sources, so that the subsequent analysis is more accurate and comprehensive. Step S12 extracts the rehabilitation and nursing equipment data in multiple aspects, wherein the key information comprises equipment availability, maintenance requirements, service conditions and the like, so that the subsequent data processing is more accurate and targeted. And step S13, updating the equipment state according to the equipment availability data, the maintenance demand data and the use condition data, so that timely updating and reflecting of the equipment state are ensured, and an accurate data basis is provided for subsequent analysis and decision. The use condition and the maintenance requirement of the rehabilitation and nursing equipment can be better known by timely updating the equipment state, so that resources and equipment allocation can be planned more effectively, and the resource utilization efficiency is improved. Updating the equipment state in time and extracting the maintenance requirement data are helpful for finding and processing the fault and loss conditions of the equipment in time, and reducing the interruption or delay of rehabilitation treatment caused by equipment problems.

Preferably, the step of extracting the usage in step S12 includes the steps of:

according to the equipment type data in the rehabilitation nursing equipment data, carrying out data sorting and grouping processing on the rehabilitation nursing equipment data to obtain rehabilitation nursing equipment grouping data;

and carrying out use condition calculation on the grouped data of the rehabilitation nursing equipment to obtain use condition data, wherein the use condition data comprises use times data, use duration data and use frequency data.

According to the invention, through data sorting and grouping processing according to the equipment types in the rehabilitation nursing equipment data, personalized data processing can be carried out aiming at different types of equipment, and the service condition of each type of equipment can be known more accurately. The use condition of the rehabilitation nursing equipment can be accurately estimated by calculating the use condition of the grouping data of the rehabilitation nursing equipment to obtain the data such as the use times, the use duration, the use frequency and the like, and the information including the use frequency, the duration and the like can be accurately estimated. After knowing the service condition of the rehabilitation nursing equipment, the resource allocation and management can be better carried out, the sufficient supply of the common equipment is ensured, and the efficiency and quality of rehabilitation therapy are improved. By monitoring the use condition of the rehabilitation nursing equipment, equipment with larger use amount or higher use frequency can be found in time, so that the equipment is preferentially maintained and maintained, the normal operation of the equipment is ensured, and the quality and stability of rehabilitation service are improved. According to the service condition data, a targeted equipment use strategy can be formulated, including measures such as adjusting equipment use time and enhancing maintenance of common equipment, so as to exert the utility and value of the equipment to the greatest extent.

Preferably, step S2 is specifically:

step S21: generating equipment use time window data according to the rehabilitation nursing equipment data and the equipment state updating data;

step S22: performing frequency of use feature extraction on the rehabilitation and nursing equipment data according to the equipment use time window data to obtain frequency of use feature data;

step S23: and carrying out load state characteristic extraction on the rehabilitation and nursing equipment data according to the equipment state updating data to obtain load state characteristic data.

In the invention, step S21 generates the equipment use time window data according to the rehabilitation nursing equipment data and the equipment state updating data, and divides the use condition of the rehabilitation nursing equipment into different time periods, so that the analysis is more targeted and accurate. The use frequency characteristics are extracted according to the equipment use time window data in the step S22, so that the use frequency of the rehabilitation nursing equipment in different time periods can be known, and the utilization rate and the demand of the equipment can be better estimated. Step S23 is to extract load state characteristics of the rehabilitation and nursing equipment data according to the equipment state updating data, so that the load state of the rehabilitation and nursing equipment can be evaluated, the load state comprises information such as the work load and maintenance requirement of the equipment, and accurate data support is provided for subsequent resource allocation and maintenance. The use condition and the working state of the rehabilitation and nursing equipment can be more accurately evaluated by extracting the use frequency characteristic and the load state characteristic, and support can be provided for more accurate resource management decision, including aspects of equipment allocation, maintenance, updating and the like. By timely knowing the use frequency and the load state of the rehabilitation and nursing equipment, the use time and the maintenance plan of the equipment are reasonably arranged, and the use efficiency and the quality of the rehabilitation and nursing equipment are improved.

Preferably, the equipment usage time window data includes first equipment usage time window data and second equipment usage time window data, and step S21 is specifically:

generating a time window according to equipment type data in the rehabilitation and nursing equipment data to obtain primary time window data;

weighting calculation is carried out on the primary time window data according to the equipment state updating data to obtain first equipment using time window data;

performing rehabilitation and nursing use prediction according to equipment type data in rehabilitation and nursing equipment data to obtain rehabilitation stage use prediction data;

and generating an event trigger window according to the estimated data used in the rehabilitation stage to obtain second equipment use time window data.

According to the invention, through the step S21, the time window is generated according to the equipment type data in the rehabilitation and nursing equipment data, so that the primary time window data is obtained, the time window data can be customized according to different equipment types, and the use condition of different types of equipment can be better adapted. The weighting calculation in the step S21 carries out the weighting calculation on the primary time window data according to the equipment state updating data, so that the actual use condition of equipment can be reflected more accurately, the use frequency and the load state in different time periods are considered, and the accuracy and the reliability of the time window data are improved. The rehabilitation stage use prediction is carried out according to the rehabilitation care equipment data to obtain rehabilitation stage use prediction data, so that the use condition of equipment can be predicted and planned according to the staged requirements of rehabilitation treatment, and the waste condition caused by improper configuration of the rehabilitation treatment equipment can be reduced. The event trigger window in step S21 is generated, and according to the estimated data of the rehabilitation stage use, the second equipment use time window data can be generated, and the use and preparation of the equipment are triggered at a specific event or stage, so that the pertinence and the efficiency of the use of the rehabilitation equipment are improved. The resource allocation and the use planning of the rehabilitation nursing equipment can be planned and optimized better through the customized time window data and the rehabilitation stage use prediction, the use time and the maintenance plan of the equipment are reasonably arranged according to the actual requirements and the treatment stage, and the resource utilization efficiency is improved.

Preferably, step S22 is specifically:

performing frequency of use feature extraction on the rehabilitation and nursing equipment data according to the equipment use time window data to obtain first frequency of use feature data;

carrying out average calculation on the first frequency of use characteristic data according to the equipment type data in the rehabilitation and nursing equipment data to obtain second frequency of use characteristic data;

and carrying out moving average line processing on the second using frequency characteristic data according to the equipment using time window data to obtain the using frequency characteristic data.

According to the invention, through the step S22, the use frequency characteristic extraction is carried out on the rehabilitation nursing equipment data according to the equipment use time window data, so that the first use frequency characteristic data is obtained, the use frequency of each equipment in a specific time period can be accurately known, and accurate data support is provided for subsequent analysis and decision. In step S22, the average calculation is performed on the first usage frequency characteristic data according to the equipment type data in the rehabilitation and nursing equipment data, so as to be helpful to consider the differences among different equipment types and obtain more objective and comprehensive usage frequency characteristic data. In step S22, the second usage frequency characteristic data is processed by moving an average line according to the equipment usage time window data, so that the usage frequency characteristic data can be smoothed, the fluctuation of the data is reduced, and the usage trend and the change rule of the rehabilitation and nursing equipment are better reflected. By carrying out average calculation and smoothing processing on the frequency characteristic data, the stability and reliability of the data can be improved, errors and deviations caused by data fluctuation can be reduced, and more reliable basis is provided for subsequent analysis and decision. The actual use condition and trend of the equipment can be better known through accurately extracting and processing the use frequency characteristic data, the resource allocation and the use planning are facilitated to be optimized, the maintenance and the update of the equipment are reasonably arranged, and the resource utilization efficiency and the rehabilitation effect are improved.

Preferably, step S23 is specifically:

step S231: extracting maintenance requirements of the equipment state update data to obtain maintenance requirement data, wherein the maintenance requirement data is one of required maintenance data or unnecessary maintenance data;

step S232: when the maintenance requirement data is determined to be the data to be maintained, carrying out load state characteristic extraction on the rehabilitation and nursing equipment data according to the equipment type data in the rehabilitation and nursing equipment data to obtain first load state characteristic data;

step S233: when the maintenance requirement data is determined to be maintenance-free data, carrying out load state feature extraction on the rehabilitation and nursing equipment data to obtain second load state feature data;

the step S232 specifically includes:

when the equipment type data in the rehabilitation nursing equipment data is determined to be sports equipment type data, performing motion trail feature extraction on the rehabilitation nursing equipment data to obtain equipment motion feature data;

when the equipment type data in the rehabilitation nursing equipment data is determined to be the pressure equipment type data, performing motion trail feature extraction on the rehabilitation nursing equipment data to obtain equipment pressure feature data;

and when the equipment type data in the rehabilitation nursing equipment data is determined to be the temperature equipment type data, performing motion trail feature extraction on the rehabilitation nursing equipment data to obtain equipment temperature feature data.

According to the invention, through step S23, the corresponding load state characteristic extraction method is selected according to different conditions of maintenance requirement data, so that the load state of the rehabilitation and nursing equipment, including the working characteristics and the service condition of the equipment, can be accurately known. In step S232, corresponding load state feature extraction is performed according to the equipment type data in the rehabilitation and nursing equipment data, including movement features, pressure features, temperature features and the like, so that different types of rehabilitation and nursing equipment can be processed in a targeted manner, and individuation and accuracy of data processing are improved. By combining the maintenance requirement data with the load state feature extraction, the relevance between the maintenance requirement and the load state of the equipment can be better evaluated, potential problems can be found in time, and corresponding measures can be taken for processing. Corresponding load state characteristics are extracted according to different equipment types, the working state and the service condition of equipment can be estimated more accurately, maintenance planning and resource allocation of the equipment are optimized, and the maintenance efficiency and quality of the equipment are improved. Through accurately extracting load state characteristics and correlating maintenance requirement data, the running condition of the rehabilitation nursing equipment can be better known, planning and execution of rehabilitation nursing service can be optimized, and the effect and quality of rehabilitation therapy can be improved.

Preferably, step S3 is specifically:

step S31: acquiring demand data of rehabilitation and nursing equipment;

step S32: estimating the service life of equipment according to the frequency characteristic data and the load state characteristic data to obtain estimated service life data of the equipment;

step S33: dynamically labeling the rehabilitation and nursing equipment data according to the equipment life estimated data to obtain rehabilitation and nursing equipment labeling data;

step S34: carry out the breach calculation according to recovered care equipment demand data and recovered care equipment mark data, obtain recovered care equipment breach data, including recovered care equipment no breach data, recovered care equipment positive breach data and recovered care equipment negative breach data, recovered care equipment positive breach data is less than recovered care equipment demand data for recovered care equipment mark data, recovered care equipment negative breach data is greater than recovered care equipment demand data for recovered care equipment mark data.

According to the invention, through the acquisition and marking of the demand data of the rehabilitation and nursing equipment in the step S3 and the combination of the equipment life prediction data, the demand and supply relation of the rehabilitation and nursing equipment can be comprehensively evaluated, the actual demand condition of the equipment can be known, corresponding adjustment and planning can be made, and the smooth running of the rehabilitation and nursing service can be ensured. The service life of the rehabilitation nursing equipment can be estimated by estimating the service life of the equipment through the frequency characteristic data and the load state characteristic data in the step S32, so that the service life of the equipment can be prolonged, the maintenance plan and the updating strategy can be timely adjusted, the maintenance cost can be reduced, and the resource utilization efficiency can be improved. And the dynamic labeling in the step S33 is used for labeling the rehabilitation and nursing equipment according to the equipment life estimated data, so that the use condition of the equipment can be monitored and managed dynamically. And the notch calculation in the step S34 can calculate the notch condition of the equipment according to the demand data and the labeling data of the rehabilitation and nursing equipment, wherein the notch condition comprises a positive notch and a negative notch, and the purchasing and the allocation plan of the equipment are timely adjusted, so that the sufficient supply of the rehabilitation and nursing equipment is ensured, and the requirement of rehabilitation and treatment is met. The resource allocation and the use planning of the rehabilitation nursing equipment can be optimized by comprehensively considering the equipment requirements, the service life forecast and the gap conditions, so that the reasonable utilization and maintenance of the equipment are ensured, and the efficiency and the quality of the rehabilitation nursing service are improved.

Preferably, step S33 is specifically:

performing equipment use load hierarchical mapping on the rehabilitation and nursing equipment data according to the rehabilitation and nursing equipment demand data to obtain equipment use load hierarchical mapping data;

weighting calculation is carried out on the equipment life estimated data according to the equipment use load hierarchical mapping data to obtain equipment life estimated weighted data;

labeling the rehabilitation and nursing equipment data according to the equipment life prediction weighting data to obtain rehabilitation and nursing equipment labeling data.

According to the invention, the equipment use load level is mapped according to the rehabilitation nursing equipment demand data, so that the use condition and the load degree of each equipment can be accurately estimated, the estimation of the service life of the equipment is more accurate, and the problem that all equipment is identical in vision in the traditional method is avoided, thereby causing the problem of waste caused by coarser equipment use. The service life prediction data of the equipment is weighted according to the service load level mapping data of the equipment, the service life prediction of the equipment can be adjusted in a personalized mode according to the importance and influence degrees of different load levels, the condition of the equipment in actual use can be reflected better, and the accuracy and reliability of service life prediction are improved. By marking the rehabilitation and nursing equipment data according to the equipment life prediction weighted data, the life state and the prediction condition of each equipment can be clearly known, more detailed information is provided, and better planning and maintenance strategies of equipment allocation are facilitated, so that the utilization efficiency and the service quality of the rehabilitation and nursing equipment are improved.

Preferably, the present application further provides a rehabilitation and care equipment data management platform for performing the rehabilitation and care equipment data management method as described above, the rehabilitation and care equipment data management platform comprising:

the equipment state updating module is used for acquiring rehabilitation and nursing equipment data from different data sources, and updating the equipment state of the rehabilitation and nursing equipment data to obtain equipment state updating data;

the rehabilitation and nursing equipment characteristic extraction module is used for carrying out frequency of use characteristic extraction and load state characteristic extraction on the rehabilitation and nursing equipment data according to the equipment state updating data to obtain frequency of use characteristic data and load state characteristic data;

the equipment gap calculation module is used for calculating equipment gaps according to the frequency of use characteristic data and the load state characteristic data of the rehabilitation and nursing equipment data to obtain rehabilitation and nursing equipment gap data;

and the equipment calling plan generation module is used for generating equipment calling plans for the rehabilitation care equipment data according to the rehabilitation care equipment gap data to obtain the rehabilitation care equipment calling plan data so as to carry out rehabilitation care equipment calling operation.

The invention has the beneficial effects that: by collecting data from different data sources and updating the state of the equipment, the state of the rehabilitation and nursing equipment can be monitored in real time, so that a user can more effectively utilize the existing equipment resources, and waste and idling of the resources are avoided. Through frequency characteristic and load state characteristic extraction, the actual use frequency and load state of the equipment can be known in depth, and the use condition of the equipment can be accurately estimated. By applying the equipment gap calculating method, supply and demand gaps of the rehabilitation and nursing equipment, including positive gaps and negative gaps of the equipment, can be found in time, so that an organization can be helped to adjust the purchasing plan and the allocation strategy of the equipment in time, and the use continuity and quality of the rehabilitation and nursing equipment are ensured. The equipment calling plan is generated according to the notch data of the rehabilitation nursing equipment, so that the use and the scheduling of the equipment can be planned more effectively, the equipment can be called as required, and poor rehabilitation treatment effect or resource waste caused by equipment shortage or surplus is avoided. By combining the measures, the management and the dispatch of the rehabilitation and nursing equipment can be optimized, and the service efficiency and the service quality are improved. By maintaining, updating and reasonably scheduling the equipment resources in time.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting implementations made with reference to the following drawings in which:

FIG. 1 illustrates a flow chart of steps of a method of rehabilitation and care device data management of an embodiment;

FIG. 2 is a flow chart illustrating the steps of a fixture status update data generation method of an embodiment;

FIG. 3 is a flow chart illustrating steps of a method for feature extraction of rehabilitation and care device data according to one embodiment;

fig. 4 is a flowchart showing steps of a device usage time window data generation method of an embodiment.

Detailed Description

The following is a clear and complete description of the technical method of the present patent in conjunction with the accompanying drawings, and it is evident that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.

Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.

It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

Referring to fig. 1 to 4, the present application provides a rehabilitation and care device data management method, which includes the following steps:

specifically, the sensor equipment and the data acquisition system are used for acquiring the data such as the service condition, the working state and the like of the rehabilitation and nursing equipment into the system in real time. And analyzing and processing the acquired data through set rules and algorithms, updating the state information of equipment, such as working state, availability and the like, and storing the state information as equipment state updating data.

Specifically, a series of rules are set to define the operational status and availability of the equipment. For example: if the runtime of the device exceeds a certain threshold, it is marked as "in-service" state. If the device is not used for a number of consecutive days, it is marked as "standby" state. If the device fails, the maintenance time is exceeded, it is marked as a "failed" condition. Algorithms are designed to analyze and process the collected data according to rules. For example: time series analysis is used to detect patterns and trends in the usage of the device to determine operational status and availability. Machine learning algorithms (such as neural network algorithms and spanning decision tree algorithms) are used to identify abnormal behavior or failure modes of a device, as well as to predict future states of the device. And updating the state information of each rehabilitation and nursing equipment according to the results of the rule and algorithm analysis, wherein the state information comprises working states, availability and the like.

Specifically, a medical institution has a plurality of rehabilitation and nursing devices, including a running machine, a body-building vehicle, a chest expander and the like. By installing the sensors and the data acquisition system, the running time, the using frequency and fault information of each device can be collected in real time. Based on these data, the following rules and algorithms are formulated to update the fixture's status information: rule 1: if the device has run for more than 8 hours per day, it is marked as "on the fly". Rule 2: if the device is not used for 3 consecutive days, it is marked as "standby" state. Rule 3: if the device fails and the maintenance time exceeds 48 hours, it is marked as "failed". For these rules, the following algorithm is designed to update the state information: the time series analysis was used to monitor the run time of the device, with the portion exceeding 8 hours marked as "on the fly" status. The frequency of use of the device was analyzed and the device that was not used for 3 consecutive days was marked as "standby" state. A machine learning algorithm is used to identify failure modes of the device, predicting whether the repair time exceeds 48 hours. Finally, the state information of the rehabilitation and care equipment is updated according to the rules and algorithms and stored as equipment state update data for subsequent management and maintenance work.

specifically, using machine learning or statistical analysis methods, usage frequency characteristics and load state characteristics are extracted based on the fixture state update data. The frequency of use characteristics can comprise indexes such as the number of times of use per day, the duration of use and the like; the load status characteristics may include indicators of load size, load stability, etc. of the equipment.

Specifically, the machine learning or statistical analysis method is used to extract usage frequency features from the equipment status update data, the features including: number of daily use: the number of uses per day for each device was counted. The use time is long: the daily use time of each device is calculated. Frequency of use: the frequency of use per day, i.e. the number of uses divided by the length of use, is calculated for each device.

Extracting load status features from the fixture status update data using machine learning or statistical analysis methods, the features comprising: load size of the equipment: the load size is estimated according to the operating state and the use time of the device. For example, longer operating times of the device are subjected to greater loads. Load stability: and evaluating the stability of the load according to the change condition of the working state of the equipment. For example, a device that is continuously operated for a longer period of time and that is stable in state has a higher load stability.

Specifically, there are multiple treadmills and daily operating conditions and usage time data for each treadmill are collected.

The data are analyzed by using a machine learning model or a statistical analysis method, and characteristics such as daily use times, use duration, use frequency and the like of each running machine are extracted. Meanwhile, according to the working state and the service time data of each running machine, the characteristics of the load of each running machine, the load stability and the like are estimated. The resulting feature data may be used for further analysis and modeling, such as predicting the risk of failure of the device, optimizing the usage schedule of the device, etc.

specifically, according to the frequency of use characteristic data and the load state characteristic data, the supply and demand gap of the equipment is calculated by combining the demand condition of the rehabilitation and nursing equipment of the mechanism. For example, by comparing actual usage with expected demand, the gap condition of the fixture is determined, including a positive gap and a negative gap.

Specifically, the usage frequency characteristic data includes indexes such as the number of times of use per day, the duration of use, and the like. The load state characteristic data comprise indexes such as load size, load stability and the like of the equipment. The expected demand of each type of equipment is determined according to the rehabilitation and nursing requirement of the institution, for example, how many running machines, spinning and the like are required every day. According to the frequency of use characteristic data and the load state characteristic data, the actual use amount, namely the actual use times, the use duration and the like of each type of equipment are calculated. And comparing the actual usage amount with the expected demand amount, and calculating the supply and demand gap of each type of equipment. The positive notch indicates that the actual usage amount is lower than the expected demand amount, namely the number of equipment needs to be increased to meet the demand; the negative notch indicates that the actual usage is higher than the expected demand, i.e., the number of equipment needs to be reduced to avoid wastage.

Specifically, a rehabilitation and nursing center is provided with 10 running machines and 5 spinning, and according to analysis of the using frequency characteristic data and the load state characteristic data, the actual using amount is obtained by using 8 running machines and 3 spinning on average every day. The rehabilitation and nursing requirement situation of the center shows that at least 10 running machines and 5 spinning units are needed to be used every day. According to the actual use condition and the expected demand, the number of the positive notches of the running machine is calculated to be 2, the number of the positive notches of the spinning is calculated to be 2, and the center needs to be additionally provided with 2 running machines and 2 spinning to meet the demand.

Specifically, based on the notch data of the rehabilitation and nursing equipment, a reasonable calling plan is designed, and timely allocation and use of the rehabilitation and nursing equipment are ensured. For example, according to the gap condition and the priority, plans such as purchasing, maintaining, updating and the like of the equipment are formulated so as to meet the requirements of rehabilitation equipment. Meanwhile, the scheduling plan is optimized in consideration of resource utilization efficiency and cost control, so that reasonable use and management of rehabilitation and nursing equipment are ensured.

Specifically, the indentations of the rehabilitation and care equipment are ordered according to the degree of urgency and importance to determine the type of equipment to be preferentially allocated. For the equipment with the gap, a purchase plan is formulated, including the purchase quantity, the purchase time, the supplier and the like. And (3) formulating a reasonable purchasing plan according to the budget and the actual situation of the suppliers, and ensuring timely replenishment of the gap. An update plan is formulated for equipment with serious aging or damage, including determining update time, update quantity, update mode and the like. And the scheduling is optimized by combining the gap condition and the resource utilization efficiency of the rehabilitation nursing equipment. By reasonably arranging purchasing, maintaining and updating plans, the cost is reduced as much as possible, and the resource utilization efficiency is improved.

A rehabilitation center finds that 10 running machines are used frequently, but only 8 running machines can meet the requirements, so that a purchasing plan is established, and 2 new running machines are planned to be purchased in one month. Meanwhile, 5 spinning is found to be required to be maintained, a maintenance plan is formulated, maintenance is conducted at the beginning of the next month, and timely use is ensured after maintenance is completed. For some severely aged equipment, such as 3 severely aged treadmills, it is decided to update in the next quarter to ensure the performance and safety of the equipment. Through the optimization of the calling plan, reasonable allocation and management of the rehabilitation and nursing equipment are ensured.

Preferably, step S1 is specifically:

specifically, the sensor device and the data acquisition system are used for acquiring various data of the rehabilitation and nursing equipment from different data sources, including but not limited to information such as the working state, the use frequency and the use duration of the equipment. The data sources include sensors, equipment records, management systems for medical facilities, and the like.

specifically, data processing and feature extraction are performed on the collected rehabilitation and nursing equipment data. For example, the availability of the equipment is extracted, and whether the equipment is available or not is judged according to the running state, maintenance condition and other information of the equipment; extracting maintenance requirements, and judging whether maintenance is needed according to information such as working time, running conditions and the like of equipment; and extracting the use condition, and evaluating the actual use condition of the equipment according to the use frequency, the use duration and other information of the equipment.

Specifically, the equipment status is updated according to the equipment availability data, the maintenance requirement data, and the usage data extracted in step S12. For example, if the maintenance requirement data of a certain rehabilitation and nursing equipment shows that maintenance is needed, the state of the equipment is updated to be 'maintenance needed'; if the usage data of the appliance indicates that the frequency of usage is low, the status of the appliance is updated to "low frequency of usage". The updated equipment status data may be used for subsequent data analysis and decision making.

In particular, one of the treadmills is used less frequently, but the sensor data indicates that it is running for a long time, malfunctions or requires maintenance. Based on this information, the system updates its status to "maintenance needed". Meanwhile, the use frequency of the other spinning is very high, and the state is normal. Thus, the user can allocate resources in time according to the actual condition of the equipment.

Preferably, the step of extracting the usage in step S12 includes the steps of:

specifically, first, the rehabilitation and care equipment data is sorted and grouped according to the equipment type data in the rehabilitation and care equipment data. For example, the same type of rehabilitation and care equipment data is classified, and the same type of equipment data is put together, so that subsequent use condition calculation is facilitated.

Specifically, the usage calculation is performed on rehabilitation and care equipment group data. And calculating indexes such as the use times, the use duration, the use frequency and the like of different equipment according to the requirements. For example, for the number of uses, counting the number of uses of each type of equipment over a period of time; for the use duration, calculating the accumulated use duration of each type of equipment; for the frequency of use, the number of uses is compared with the time of use to obtain the average frequency of use for each type of equipment.

Preferably, step S2 is specifically:

specifically, the usage time window data of the equipment is generated according to the rehabilitation nursing equipment data and the equipment state updating data, the size of the time window is determined by setting a time period or according to specific requirements, and then the equipment usage condition in each time window is determined according to the equipment usage condition and the state updating data. For example, a day is divided into a plurality of time periods, and the use condition of equipment in each time period is counted to obtain the use condition data of each time window.

specifically, according to the generated equipment use time window data, the use frequency characteristic extraction is carried out on the rehabilitation and nursing equipment data. And counting the use times of each equipment in different time windows, and calculating the characteristics of average use times, maximum use times and the like. These features can reflect the frequency of use and the activity of the equipment and help to understand the actual use of the equipment.

Specifically, load state feature extraction is performed on rehabilitation and care equipment data according to the equipment state update data. And extracting load state characteristics according to the information such as the working state, the load size and the like of the equipment. For example, for sports rehabilitation equipment, load state characteristics are extracted according to indexes such as the movement speed, the load size and the like of the equipment; for the pressure rehabilitation equipment, the load state characteristics are extracted according to the pressure of the equipment, the using pressure interval and other indexes.

Specifically, the load state characteristics of the running machine are extracted according to the equipment state updating data, and the load size is calculated according to the running speed, the inclination angle, the weight of the user and other information of the equipment. For example, if the running speed of the treadmill is faster and the incline is greater while the user's weight is also higher, the load size is greater; and if the running speed of the running machine is slower and the inclination is smaller, the user is lighter in weight, and the load is smaller.

And extracting the load state characteristics of the rowing machine according to the equipment state updating data. The load is calculated based on the rowing speed, resistance and weight of the user. For example, if the rowing speed of the rowing machine is high and the resistance is high, while the user's weight is high, the load size is high; and if the rowing speed of the rowing machine is slower and the resistance is smaller, the user is lighter, and the load is smaller.

For a pressure bed, load state features are extracted from the pressure magnitudes and the use pressure intervals recorded in the equipment state update data. For example, if the pressure bed is used at a higher pressure and for a longer duration, the load condition is greater; whereas if the pressure bed is used at a lower pressure and for a shorter duration, the load conditions are smaller.

A running machine is subjected to load state feature extraction, and according to analysis of equipment state updating data, the running speed of the running machine in the past week is high, the gradient is high, and the weight of a user is high. Based on this information, the system extracts that the load status of the treadmill is characterized as "high load".

step S211: generating a time window according to equipment type data in the rehabilitation and nursing equipment data to obtain primary time window data;

specifically, primary time window data is generated according to equipment type data in the rehabilitation and nursing equipment data, time windows are divided by setting fixed time intervals, for example, each day, each week or each month is used as a time window, and then the rehabilitation and nursing equipment data are classified according to the time windows, so that the use condition of various equipment in each time window is obtained.

Step S212: weighting calculation is carried out on the primary time window data according to the equipment state updating data to obtain first equipment using time window data;

specifically, according to the primary time window data and the equipment state updating data, weighting calculation is carried out on the primary time window data, so that first equipment using time window data is obtained. For example, the equipment data in different time windows is weighted according to the maintenance requirement condition, the use frequency and other information in the equipment state update data so as to reflect the actual use condition in the different time windows.

In a certain time window, the maintenance requirement condition of the running machine is lower, the use frequency is higher, and then higher weight is given to the running machine data in the time window; in the same time window, the maintenance requirement of the rowing machine is higher, the use frequency is lower, and then lower weight is given to the rowing machine data in the time window.

Step S213: performing rehabilitation and nursing use prediction according to equipment type data in rehabilitation and nursing equipment data to obtain rehabilitation stage use prediction data;

specifically, the rehabilitation and nursing use prediction is performed according to the equipment type data in the rehabilitation and nursing equipment data, and the use condition of the rehabilitation stage is predicted by analyzing information such as historical data, patient conditions, medical requirements and the like. For example, the frequency and duration of use of different equipment at different rehabilitation stages is estimated based on the patient's rehabilitation program and medical regimen.

Step S214: and generating an event trigger window according to the estimated data used in the rehabilitation stage to obtain second equipment use time window data.

Specifically, according to the estimated data of the rehabilitation stage use, an event trigger window is generated, second equipment use time window data is obtained, and the generation of the time window is triggered by setting specific events or conditions, for example, the event trigger window is determined according to factors such as rehabilitation progress of a patient, advice of a doctor, change of a treatment plan and the like. Each time a trigger window is generated, a new time window is generated for monitoring and evaluating the usage of the equipment at a particular event or condition.

Each time the trigger condition is met, a new event trigger window is generated for monitoring and assessing the usage of the rehabilitation and care device at a particular event or condition. For example, when a patient enters a mid-level rehabilitation session from a primary rehabilitation session, a new event-triggered window is generated for monitoring the use of the rehabilitation care device during the mid-level rehabilitation session.

Preferably, step S22 is specifically:

specifically, the frequency of use feature extraction is performed on the rehabilitation and nursing equipment data according to the equipment use time window data, and the frequency of use of various equipment in each time window is counted. For example, for each time window, the number of times of use of each equipment is counted and taken as characteristic data to obtain first frequency of use characteristic data, which reflects the frequency of use of the equipment in each time window.

specifically, the average calculation is performed on the first usage frequency characteristic data according to the equipment type data in the rehabilitation and nursing equipment data, and the average value of the usage frequency of the same equipment in all time windows is calculated. For example, for each fixture, the usage frequency data in all time windows is averaged to obtain an average usage frequency of each fixture, and the second usage frequency feature data is obtained to reflect the average usage frequency of each fixture.

Specifically, the second usage frequency characteristic data is subjected to a moving average line processing according to the equipment usage time window data, and the moving average line processing is realized by calculating a moving average value of the usage frequency data in each time window. For example, a sliding window method is adopted, average values of frequency data used in a plurality of adjacent time windows are calculated, and then the average values are used as new characteristic data to obtain a moving average line of the frequency characteristic data used for smoothing and trend analysis.

Preferably, step S23 is specifically:

specifically, the equipment state update data is analyzed and processed to determine whether the equipment needs maintenance, and the equipment is judged by monitoring information such as the working state, fault record, maintenance history and the like of the equipment. If the system determines that the equipment has failed, is damaged (or has similar problems historically) or exceeds a maintenance period, determining that the data is required to be maintained; and if the equipment operates normally and is in the maintenance period, judging that the maintenance-free data is needed.

specifically, the type of equipment to be maintained is determined based on the equipment type data in the rehabilitation and care equipment data. Then, load state feature extraction is performed for these devices. For example: for exercise equipment type data (exercise equipment such as running machine): and extracting the characteristics of motion trail, motion speed, motion frequency and the like. For pressure equipment type data (pressure equipment such as pressure bed): extracting the characteristics of pressure, pressure change rate and the like. For temperature equipment type data (hot or cold compress device): extracting the characteristics of temperature change, temperature fluctuation and the like.

specifically, the rehabilitation and nursing equipment does not need maintenance, so that load state characteristics of the rehabilitation and nursing equipment data are directly extracted, such as characteristics of running state, load size, load stability and the like of the equipment are extracted.

The step S232 specifically includes:

specifically, the motion trail feature extraction is performed according to the type of equipment data in the rehabilitation and nursing equipment data as the type of the motion equipment data, and the information such as the use condition, the motion trail, the motion speed and the like of the equipment is analyzed to extract the features. For example, for sports equipment such as a running machine, characteristics of a user such as a movement speed, a step frequency, a movement duration, and the like are extracted.

Specifically, pressure characteristic extraction is performed according to the pressure equipment type data as the equipment type data in the rehabilitation and nursing equipment data, and the characteristics are extracted by monitoring information such as the pressure, load, bearing capacity and the like of the equipment through a sensor. For example, for equipment such as a pressure plate, characteristics such as pressure distribution and bearing strength of a user are extracted.

Specifically, according to the fact that the equipment type data in the rehabilitation and nursing equipment data is temperature equipment type data, temperature characteristic extraction is carried out, and characteristics are extracted by monitoring information such as temperature change and heat dissipation conditions of equipment through a temperature sensor. For example, for devices such as foggers, characteristics such as temperature change, heat distribution, etc. of the device surface are extracted.

Preferably, step S3 is specifically:

step S31: acquiring demand data of rehabilitation and nursing equipment;

specifically, the demand data of the rehabilitation and nursing equipment is acquired through a software input interface or control, including demand information of rehabilitation institutions, hospitals and doctors, and personal demand information of rehabilitation patients. The demand data contains information on the type, number, frequency of use and the like of the rehabilitation and nursing equipment.

specifically, the service life of the rehabilitation and nursing equipment is estimated according to the frequency characteristic data and the load state characteristic data, and the method is performed through a machine learning model, statistical analysis and the like. For example, a predictive model is built using historical data and monitoring data to predict the life of the equipment. Based on the characteristics of equipment such as frequency of use, load state and the like, the service life of the equipment is estimated by combining an evaluation model designed by the experience knowledge of field experts.

Historical data of rehabilitation and care equipment is collected, including frequency of use, load status, maintenance records, and the like. The monitoring data of the rehabilitation nursing equipment is obtained from a data system of the rehabilitation institution, and the monitoring data comprise real-time data such as using frequency, load state and the like. And integrating the historical data and the monitoring data, and extracting the frequency of use characteristic and the load state characteristic as input characteristics of the model. And selecting a machine learning algorithm, such as a regression model, a decision tree, a random forest and the like, and establishing a prediction model of the life of the rehabilitation and nursing equipment. The historical data is utilized to train a model, so that the life of the rehabilitation and nursing equipment can be predicted according to the using frequency characteristic and the load state characteristic. And inputting the real-time use frequency and the load state data of the rehabilitation and nursing equipment by using the established prediction model, so that the service life of the equipment can be estimated.

specifically, the rehabilitation and nursing equipment data are dynamically marked according to the equipment life prediction data, and the equipment is marked according to the life state of the equipment, for example, the equipment is divided into different states such as new equipment, normal use equipment, aging equipment and the like.

Specifically, labeling is performed according to the life prediction value of the equipment, for example, the equipment is classified into different categories such as normal life prediction, insufficient life prediction and the like.

Specifically, gap calculation is performed according to the demand data and the labeling data of the rehabilitation and nursing equipment, and the gap condition of the rehabilitation and nursing equipment is calculated by comparing the demand data and the labeling data. For example, the demand data is compared with the annotation data to determine which equipment demands are not met and which equipment is superfluous, thereby calculating the gap data, including the number and type of positive and negative gaps.

And comparing the demand data of the rehabilitation and nursing equipment with the actual labeling data to determine the gap condition. For each type of rehabilitation and care equipment, the difference between the actual labeling data and the demand data is calculated to determine the number of positive and negative gaps. If the actual labeling data is smaller than the demand data, indicating that a positive gap exists, and further purchasing or allocating equipment is needed to meet the demand; if the actual labeling data is larger than the demand data, a negative gap exists, and the rehabilitation nursing equipment needs to be redistributed or reduced so as to improve the resource utilization efficiency. And summarizing the gap conditions of each type of rehabilitation and nursing equipment to obtain gap data of the rehabilitation and nursing equipment, wherein the gap data comprises the number and types of the positive gaps and the negative gaps. And (3) making a corresponding allocation plan and a corresponding purchasing plan according to the gap data so as to ensure timely supply and reasonable use of the rehabilitation and nursing equipment.

Preferably, step S33 is specifically:

specifically, the use load levels of the rehabilitation and nursing equipment are mapped according to the demand data of the rehabilitation and nursing equipment, and the rehabilitation and nursing equipment is classified according to different levels of the use load, for example, the levels of high load, medium load, low load and the like. According to different load levels, each equipment is allocated a corresponding load level.

And formulating a load hierarchical division scheme according to the load parameters and the demand data of the rehabilitation and nursing equipment. The load levels are divided according to indexes such as load size, frequency of use, stability and the like, and are divided into three levels of high load, medium load and low load. Specific definitions are made for each load class, for example: high load: equipment with high use frequency, large load and high stability requirement; medium load: equipment with moderate use frequency, general load and general stability requirements; low load: the equipment has low use frequency, small load and lower stability requirement.

Specifically, the equipment life estimated data is weighted according to the equipment using load hierarchy mapping data, and the equipment life estimated data is weighted according to the importance and influence degree of different load hierarchies. For example, for high load equipment, the life estimate may be weighted higher, while for low load equipment, the life estimate may be weighted lower.

Three load levels: high load, medium load and low load, the corresponding weights are 0.4, 0.3 and 0.2, respectively. And respectively carrying out weighted calculation according to the load layers of the life prediction data of each equipment. Assume that life prediction data for a fixture is as follows: life prediction under high load conditions: lifetime estimation under medium load conditions for 1000 hours: 1500 hours, life prediction under low load: 2000 hours. And weighting and calculating the life estimated data according to the weight: weighted life estimation under high load conditions: weighted lifetime estimation under medium load at 1000 x 0.4=400 hours: 1500 x 0.3=450 hours, weighted lifetime estimation under low load: 2000 x 0.2=400 hours, so the overall weighted lifetime of the fixture is estimated to be 400 hours+450 hours+400 hours=1250 hours.

Specifically, labeling the rehabilitation and nursing equipment data according to the equipment life prediction weighting data, and classifying the equipment into different labeling categories such as normal, insufficient life prediction, excessive life prediction and the like according to different thresholds of the weighting data.

There is a batch of rehabilitation and care equipment, and according to the previous steps, the system has performed life prediction weighting calculation on them to obtain weighting data. The system will now label the rehabilitation and care equipment based on these weighted data, classifying them into different labeling categories, such as normal, insufficient life prediction and excessive life prediction. The weighted data is assumed to be as follows: the weight data of the equipment a is 1100 hours, the weight data of the equipment B is 900 hours, the weight data of the equipment C is 1300 hours, and then the weight data are classified and labeled according to a preset threshold value. For example, the following thresholds are set: if the weighted data is greater than 1200 hours, the fixture is marked as over life prediction. If the weighted data is less than 1000 hours, the fixture is marked as having insufficient life prediction. If the weighted data is between 1000 hours and 1200 hours, the fixture is marked as normal. The following labeling is performed according to the threshold and the weighting data set as above: the weighting data for fixture a is 1100 hours, between 1000 hours and 1200 hours, and is therefore labeled normal. The weighted data for fixture B is 900 hours, less than 1000 hours, and is therefore labeled as insufficient life expectancy. The weighted data for fixture C is 1300 hours, greater than 1200 hours, and is therefore labeled as life prediction overage.

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A rehabilitation and care equipment data management method, which is characterized by comprising the following steps:

2. The method according to claim 1, wherein step S1 is specifically:

3. The method according to claim 2, wherein the step of use case extraction in step S12 comprises the steps of:

4. The method according to claim 1, wherein step S2 is specifically:

5. The method of claim 4, wherein the equipment usage time window data includes first equipment usage time window data and second equipment usage time window data, and step S21 is specifically:

6. The method according to claim 4, wherein step S22 is specifically:

7. The method according to claim 4, wherein step S23 is specifically:

the step S232 specifically includes:

8. The method according to claim 1, wherein step S3 is specifically:

step S31: acquiring demand data of rehabilitation and nursing equipment;

9. The method according to claim 8, wherein step S33 is specifically:

10. A rehabilitation and care equipment data management platform for performing the rehabilitation and care equipment data management method of claim 1, the rehabilitation and care equipment data management platform comprising: