Fall prevention method, system and device and storage medium

Abstract

The invention relates to the technical field of medical treatment. The invention discloses a tumble prevention method, system and device and a storage medium, which can improve the applicability of the tumble prevention method and effectively prevent the occurrence of tumble events of hospitalized patients. The fall prevention method comprises the following steps: acquiring lower limb muscle force information, balance capability information and gait information of an inpatient based on a time sequence; generating a muscle strength grade based on the lower limb muscle strength information; generating balance curve information based on the balance capability information; inputting the muscle strength level, the balance curve information and the gait information into a fall risk prediction model for analysis and processing, and outputting a fall risk level; and generating first tumble early warning information based on the tumble risk level to prevent the hospitalized patient from tumble.

Description

Technical Field

[0001] The present application relates to the field of medical technology. More specifically, the present application relates to a fall prevention method, system, device and storage medium. Background Art

[0002] Falls of inpatients are a high incidence of adverse events in hospitals, which can have a serious impact on the physical and mental health of inpatients. In addition, the injuries caused by falls will increase the economic burden of treatment and the cost of family care for inpatients. To this end, researchers have developed a traditional fall prevention method, which includes obtaining the movement path information of inpatients as spare movement path information; if it is determined that the number of spare movement path information exceeds a preset threshold, clustering the spare movement path information using a preset clustering algorithm to determine the current common path information; determining the fall risk value based on the common path information; using the fall risk level corresponding to each current common path information, and then pushing the fall risk warning to the inpatient according to the fall risk level to prevent falls. That is, the method relies on the common path information of inpatients to prevent falls. However, some inpatients may fall before they start walking. In this case, the method is not suitable for such inpatients who fall before walking, and still cannot prevent the occurrence of falls in inpatients, thereby causing more serious injuries to inpatients. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a fall prevention method, system, device and storage medium, which can improve the applicability of the fall prevention method and effectively prevent the occurrence of fall events in hospitalized patients. The embodiments of the present application are mainly implemented through the following technical solutions:

[0004] A first aspect of an embodiment of the present application provides a fall prevention method, comprising:

[0005] Obtain lower limb muscle strength information, balance ability information and gait information of hospitalized patients based on time series;

[0006] generating a muscle strength level based on the lower limb muscle strength information;

[0007] generating balance curve information based on the balance capability information;

[0008] Inputting the muscle strength level, the balance curve information and the gait information into a fall risk prediction model for analysis and processing, and outputting a fall risk level;

[0009] First fall warning information is generated based on the fall risk level to prevent the hospitalized patient from falling.

[0010] According to one embodiment of the present application, the step of acquiring lower limb muscle strength information, balance ability information and gait information of an inpatient based on time sequence includes:

[0011] When the force sensor in the fall prevention system detects movement of the hospitalized patient, acquiring the lower limb muscle strength information at a first preset time;

[0012] After the lower limb muscle strength information is acquired, acquiring the balance ability information at a second preset time;

[0013] After the balance ability information is acquired, the gait information is acquired at a third preset time.

[0014] According to an embodiment of the present application, the step of generating balance curve information based on the balance ability information includes:

[0015] Perform grayscale and denoising processing on all first images in the balancing capability information to obtain a first feature map corresponding to each first image;

[0016] Arrange and identify all the first feature maps horizontally to obtain feature points corresponding to each of the first feature maps;

[0017] All the characteristic points are connected to obtain the balance curve information.

[0018] According to one embodiment of the present application, the training step of the fall risk prediction model includes:

[0019] Obtain a training data set and a true label set, wherein each true label in the true label set has a one-to-one correspondence with one of the training data in the training data set;

[0020] Inputting target training data into the Transformer model to obtain a prediction level, wherein the target training data is any training data in the training data set;

[0021] Calculating a loss function based on the true label corresponding to the target training data and the predicted grade;

[0022] The model parameters of the Transformer model are adjusted based on the loss function to obtain the fall risk prediction model.

[0023] According to an embodiment of the present application, after the step of generating first fall warning information based on the fall risk level, the fall prevention method further includes:

[0024] Obtain inpatient information from mobile electronic medical record systems in a falls prevention system;

[0025] The inpatient information and the first fall warning information are displayed on the HIS (Hospital Information System) system, the nurse station smart screen and / or the ward smart screen in the fall prevention system.

[0026] According to one embodiment of the present application, after the step of displaying the inpatient information and the first fall warning information in the HIS system, the nurse station smart screen and / or the ward smart screen in the fall prevention system, the fall prevention method further includes:

[0027] Obtaining heart rate information of the hospitalized patient;

[0028] Optimizing the fall risk level based on the heart rate information to obtain an optimized level;

[0029] A second fall warning information is generated based on the optimization level. A second aspect of an embodiment of the present application provides a fall prevention system, comprising:

[0030] An acquisition module, used for acquiring lower limb muscle strength information, balance ability information and gait information of hospitalized patients based on time series;

[0031] A muscle strength level generating module, used for generating a muscle strength level based on the lower limb muscle strength information;

[0032] A balance curve information generating module, used to generate balance curve information based on the balance capability information;

[0033] A fall risk level output module, used for inputting the muscle strength level, the balance curve information and the gait information into a fall risk prediction model for analysis and processing, and outputting a fall risk level;

[0034] The first fall warning information generating module is used to generate the first fall warning information based on the fall risk level to prevent the inpatient from falling.

[0035] The third aspect of the embodiment of the present application provides a fall prevention system, including a medical information system, a force sensor, a mobile electronic medical record system, a HIS system, a smart screen at the nurse station, and a smart screen in the ward, wherein the medical information system is used to implement the steps of the fall prevention method provided in the first aspect of the embodiment of the present application, and the medical information system is respectively communicated with the force sensor, the mobile electronic medical record system, the HIS system, the smart screen at the nurse station, and the smart screen in the ward.

[0036] In a fourth aspect of an embodiment of the present application, a terminal device is provided, including a processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the steps of the fall prevention method provided in the first aspect of the embodiment of the present application.

[0037] According to a fifth aspect of the embodiments of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store a computer program, wherein the computer program enables a computer to execute the steps of the fall prevention method provided in the first aspect of the embodiments of the present application.

[0038] The beneficial effects of the embodiments of the present application include at least:

[0039] The embodiment of the present application uses lower limb muscle strength information, balance ability information and gait information to replace the traditional common walking path information, so that the fall prevention method is more suitable for the actual situation of hospitalized patients. Specifically, the present application analyzes and processes the muscle strength level generated by the lower limb muscle strength information, the balance curve information generated by the balance ability information, and the gait information through a fall risk prediction model, thereby outputting the fall risk level of the hospitalized patient, and then, using the fall risk level to generate the first fall warning information to prevent the hospitalized patient from falling. Therefore, compared with the prior art, the embodiment of the present application does not rely on the common walking path information or ordinary walking path information of the hospitalized patient. Therefore, the fall prevention method provided by the present application can be applicable to hospitalized patients with a variety of different physical fitness, thereby improving the applicability of the fall prevention method and effectively preventing the occurrence of fall events in hospitalized patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A flow chart of a fall prevention method of the present application in some embodiments;

[0042] Figure 2 A reference diagram for horizontal arrangement of all first characteristic diagrams in this application;

[0043] Figure 3 A reference diagram for horizontal arrangement of all first characteristic diagrams in this application;

[0044] Figure 4 A reference diagram for horizontal arrangement of all first characteristic diagrams in this application;

[0045] Figure 5 is a principle block diagram of the fall prevention system of the present application in some embodiments;

[0046] Figure 6 is a principle block diagram of the fall prevention system of the present application in some other embodiments;

[0047] Figure 7 This is a functional block diagram of the terminal device of the present application in some embodiments. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific embodiments disclosed below.

[0049] It should be noted that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0050] The terms "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0051] The terms "comprises," "includes," or any other variations thereof are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a series of steps or elements is not necessarily limited to those steps or elements explicitly listed but may include other steps or elements not explicitly listed or inherent to such process, method, product, or apparatus.

[0052] Unless otherwise defined, all technical and scientific terms used in the specification of this application have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used in the specification of this application includes any and all combinations of one or more related listed items.

[0053] The specific implementation of the present application is further described below in conjunction with the accompanying drawings.

[0054] <How to prevent falls>

[0055] like Figure 1 FIG. 1 is a flow chart of a fall prevention method provided in the first aspect of the embodiment of the present application. Figure 1 In the method, the fall prevention method comprises:

[0056] S1. Obtain lower limb muscle strength information, balance ability information and gait information of hospitalized patients based on time series.

[0057] The lower limb muscle strength information is obtained by a force sensor in the fall prevention system. Exemplarily, the force sensor can be attached to the lower leg of the hospitalized patient to monitor in real time whether the hospitalized patient's leg moves.

[0058] The balance ability information is a set of image information, including a plurality of first images. The balance ability information is acquired by an image acquisition device in the fall prevention system. The image acquisition device can be installed at any position in the ward where the inpatient is located, but the position must meet the condition that all activities of the inpatient in the ward can be captured.

[0059] The gait information is a set of image information, including a plurality of second images. The gait information is also acquired by the image acquisition device. The gait information is an image of the inpatient's walking posture.

[0060] Furthermore, the S1 step includes:

[0061] S11. When the force sensor in the fall prevention system detects that the hospitalized patient is moving, the lower limb muscle strength information is obtained at a first preset time.

[0062] In the embodiment of the present application, the timing is divided into three parts, namely, the first preset time, the second preset time and the third preset time.

[0063] S12: After the lower limb muscle strength information is obtained, the balance ability information is obtained at a second preset time.

[0064] S13: After the balance ability information is acquired, the gait information is acquired at a third preset time.

[0065] S2. Generate a muscle strength level based on the lower limb muscle strength information.

[0066] Exemplarily, the muscle strength level is divided into four levels, including the first level, the second level, the third level and the fourth level. When the lower limb muscle strength information is 1 Newton to 3 Newtons, the muscle strength level is the first level; when the lower limb muscle strength information is 4 Newtons to 6 Newtons, the muscle strength level is the second level; when the lower limb muscle strength information is 7 Newtons to 8 Newtons, the muscle strength level is the third level; when the lower limb muscle strength information is 9 Newtons to 10 Newtons, the muscle strength level is the fourth level. When the muscle strength level is the first level, the physical condition of the hospitalized patient may be that the limbs can move on the horizontal plane of the bed, but cannot resist their own gravity, that is, cannot be lifted off the bed; when the muscle strength level is the second level, the physical condition of the hospitalized patient may be that the limbs can be lifted off the bed, but cannot resist external resistance; when the muscle strength level is the third level, the physical condition of the hospitalized patient may be that the limbs can be lifted off the bed and can resist part of the external resistance; when the muscle strength level is the fourth level, the physical condition of the hospitalized patient may be that the limbs can be lifted off the bed and can completely resist external resistance, and the patient has normal muscle strength.

[0067] In other embodiments, the specific classification of the muscle strength level can be set by those skilled in the art according to actual needs.

[0068] S3. Generate balance curve information based on the balance capability information.

[0069] The balance curve information is a curve.

[0070] Furthermore, the S3 step includes:

[0071] S31. Perform grayscale and denoising processing on all first images in the balancing capability information to obtain a first feature map corresponding to each first image.

[0072] S32: Arrange and identify all the first feature maps horizontally to obtain feature points corresponding to each of the first feature maps.

[0073] Specifically, refer to Figure 2 As shown, all the first feature graphs A are arranged horizontally. The content of each of the first feature graphs A at least includes the inpatient B.

[0074] Regarding the feature point, for example, the top of the hospitalized patient's head can be identified as the feature point. Figure 3 As shown, in Figure 3 In the figure, dot C is the feature point corresponding to each of the first feature graphs A. In other embodiments, other body parts of the hospitalized patient may be used as the feature points, which are determined by those skilled in the art according to actual needs.

[0075] S33, connecting all the characteristic points to obtain the balance curve information.

[0076] In actual application, the balance curve information can refer to the following example:

[0077] Example 1, reference Figure 3 , is an example of the inpatient B sitting on bed D and standing up and walking forward without falling tendency, Figure 3 The balance curve information S1 obtained from all feature points is a curve with an arc and tends to be stable.

[0078] Example 2, reference Figure 4 , which is an example of the inpatient B sitting on bed D and standing up to walk forward, but his body sways and he tends to fall. Figure 4 The balance curve information S2 obtained from all feature points is an irregular curve.

[0079] S4. Input the muscle strength level, the balance curve information and the gait information into a fall risk prediction model for analysis and processing, and output a fall risk level.

[0080] In the embodiment of the present application, the fall risk level is selected from one of a low risk level, a medium risk level and a high risk level.

[0081] Furthermore, the training steps of the fall risk prediction model include:

[0082] S41, obtaining a training data set and a real label set, wherein each real label in the real label set has a one-to-one correspondence with one of the training data in the training data set.

[0083] Each of the training data includes lower limb strength training information, balance ability training information and gait training information.

[0084] The lower limb muscle strength training information has the same data type as the lower limb muscle strength information, the balance ability training information has the same data type as the balance ability information, and the gait training information has the same data type as the gait information.

[0085] Both the training data set and the real label set are real data collected from most inpatients in the hospital.

[0086] S42: Input the target training data into the Transformer model to obtain a prediction level, wherein the target training data is any training data in the training data set.

[0087] S43: Calculate a loss function based on the true label corresponding to the target training data and the predicted grade.

[0088] S44. Adjust the model parameters of the Transformer model based on the loss function to obtain the fall risk prediction model.

[0089] Furthermore, the calculation formula of the loss function is as follows:

[0090]

[0091] Where N is the number of training data sets, y i is the i-th true label, g i is the i-th prediction level.

[0092] It should be understood that the number of the training data sets is the same as the number of the true label sets.

[0093] S5. Generate first fall warning information based on the fall risk level to prevent the hospitalized patient from falling.

[0094] The first fall warning information may be a color pattern or a warning symbol.

[0095] In the above technical scheme, the embodiment of the present application does not rely on the usual walking path information or ordinary walking path information of the hospitalized patients. Therefore, the fall prevention method provided by the present application can be applicable to hospitalized patients with various physical fitness, thereby improving the applicability of the fall prevention method and effectively preventing the occurrence of fall incidents in hospitalized patients.

[0096] In some embodiments, after the step of generating first fall warning information based on the fall risk level, the fall prevention method further includes:

[0097] S61. Obtain inpatient information from the mobile electronic medical record system in the fall prevention system.

[0098] The inpatient information includes at least the inpatient's name, gender, disease details, allergy history and other information.

[0099] S62. Display the inpatient information and the first fall warning information on the HIS system, the nurse station smart screen and / or the ward smart screen in the fall prevention system.

[0100] In some embodiments, after the step S62, the fall prevention method further includes:

[0101] S71. Obtain the heart rate information of the hospitalized patient.

[0102] In an embodiment of the present application, the heart rate information is obtained through a smart mattress in the fall prevention system.

[0103] The smart mattress is provided by the hospital to inpatients with a high risk of falling.

[0104] In other embodiments, the smart mattress can also be used to obtain activity information of the hospitalized patient, that is, to detect whether the hospitalized patient has left the bed through the smart mattress.

[0105] S72: Optimize the fall risk level based on the heart rate information to obtain an optimized level.

[0106] When the inpatient's heart rate increases or the inpatient gets out of bed (that is, the inpatient's body position changes due to getting up and moving), the fall risk level is modified according to the heart rate information and / or the getting out of bed activity to obtain the optimized level.

[0107] For example, when the heart rate information shows that the heart rate is accelerating very quickly, this acceleration may cause the hospitalized patient to have a potential risk of fainting, thereby changing the fall risk level that was originally at a "medium risk level" to a "high risk level."

[0108] S73: Generate second fall warning information based on the optimization level.

[0109] The second fall warning information is used to prevent the inpatient from falling. The second fall warning information can be a color pattern or a warning symbol.

[0110] In some embodiments, after the step S73, the fall prevention method further includes:

[0111] S74. Display the inpatient information and the second fall warning information on the HIS system, the nurse station smart screen and / or the ward smart screen.

[0112] In some technical solutions, after the step S74, the fall prevention method further includes:

[0113] S75. The medical information system in the fall prevention system issues a fall alarm sound and displays a fall warning symbol based on the first fall warning information or the second fall warning information.

[0114] Through the above technical solution, medical staff can discover the condition of hospitalized patients in time and avoid secondary injuries caused by falls, which will increase the economic burden of treatment and the cost of family care.

[0115] In some embodiments, after the step S75, the fall prevention method further includes:

[0116] The pharmacy smart medicine dispensing machine in the fall prevention system is used to mark a fall risk warning symbol on the medicine bag of the inpatient based on the first fall warning information or the second fall warning information.

[0117] The fall risk warning symbol is a word “fall”.

[0118] The warning reminder on the medicine bag can remind hospitalized patients to pay attention to the risk of falling, so as to reduce the probability of falls in hospitalized patients.

[0119] In some implementations, a green button can be added to wristbands for inpatients at high risk levels as a high-risk fall warning, so as to achieve a combination of clinical practice and informatization, and implement health and early warning of fall risks.

[0120] In some embodiments, hospitalized patients may also be assigned smart vests, smart belts, plantar sensors and / or smart helmets to identify when they are about to fall during activities and rehabilitation walking, and to promptly pop out protective bags on the head, waist and hips to prevent serious injuries such as cerebral hemorrhage and fractures.

[0121] In some embodiments, the AI-assisted robot in the fall prevention system can also be used to conduct fall risk education to enhance hospitalized patients' awareness of fall prevention.

[0122] An evaluation function may also be provided on the AI-assisted robot so that hospitalized patients can make an evaluation after watching the relevant content of fall risk education, thereby enabling medical staff to manage and control fall risk education.

[0123] In some embodiments, a standardized fall prevention clinical decision knowledge base can also be established in the form of text, posters, brochures, videos, etc., and the fall prevention clinical decision knowledge base can be maintained in the mobile electronic medical record system and other smart terminals to popularize the risk awareness of fall prevention.

[0124] <Fall Prevention System>

[0125] like Figure 5 , which is a principle block diagram of a fall prevention system provided in the second aspect of the embodiment of the present application. Figure 5 In the embodiment, the fall prevention system 100 comprises:

[0126] An acquisition module 101 is used to acquire lower limb muscle strength information, balance ability information and gait information of an inpatient based on a time sequence;

[0127] A muscle strength level generating module 102, configured to generate a muscle strength level based on the lower limb muscle strength information;

[0128] A balance curve information generating module 103, configured to generate balance curve information based on the balance capability information;

[0129] A fall risk level output module 104, configured to input the muscle strength level, the balance curve information and the gait information into a fall risk prediction model for analysis and processing, and output a fall risk level;

[0130] The first fall warning information generating module 105 is used to generate first fall warning information based on the fall risk level to prevent the inpatient from falling.

[0131] <Fall Prevention System>

[0132] refer to Figure 6 , which is a principle block diagram of a fall prevention system provided by the third aspect of the embodiment of the present application. Figure 6 In the embodiment, the fall prevention system 200 includes a medical information system 201, a force sensor 202, a mobile electronic medical record system 203, a HIS system 204, a nurse station smart screen 205 and a ward smart screen 206, wherein the medical information system 201 is used to implement the steps of the fall prevention method provided in the first aspect of the above-mentioned embodiment of the present application, and the medical information system 201 is respectively communicated with the force sensor 202, the mobile electronic medical record system 203, the HIS system 204, the nurse station smart screen 205 and the ward smart screen 206.

[0133] In some embodiments, the fall prevention system 200 also includes an image acquisition device, a smart mattress, a medical information system, a pharmacy smart medicine dispensing machine, and an AI-assisted robot.

[0134] <Terminal Equipment>

[0135] like Figure 7 , which is a principle block diagram of a terminal device provided in the fourth aspect of the embodiment of the present application. Figure 7 In the embodiment, the terminal device 300 includes a processor 301 and a memory 302, the memory 302 is used to store a computer program, and the processor 301 is used to call and run the computer program stored in the memory 302 to execute the steps of the fall prevention method provided in the first aspect of the embodiment of the present application.

[0136] <Computer Readable Storage Medium>

[0137] According to a fifth aspect of the embodiments of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store a computer program, wherein the computer program enables a computer to execute the steps of the fall prevention method provided in the first aspect of the embodiments of the present application.

[0138] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0139] The technical features of the above embodiments can be combined without changing the basic principles of the present application. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0140] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the scope of patent protection of the present application shall be subject to the attached claims.

Claims

1. A fall prevention method, characterized in that: include: Obtain lower limb muscle strength information, balance ability information and gait information of hospitalized patients based on time series; generating a muscle strength level based on the lower limb muscle strength information; generating balance curve information based on the balance capability information; Inputting the muscle strength level, the balance curve information and the gait information into a fall risk prediction model for analysis and processing, and outputting a fall risk level; First fall warning information is generated based on the fall risk level to prevent the hospitalized patient from falling.

2. The fall prevention method according to claim 1, characterized in that: The step of acquiring lower limb muscle strength information, balance ability information and gait information of the hospitalized patient based on time sequence comprises: When the force sensor in the fall prevention system detects movement of the hospitalized patient, acquiring the lower limb muscle strength information at a first preset time; After the lower limb muscle strength information is obtained, the balance ability information is obtained at a second preset time; After the balance ability information is acquired, the gait information is acquired at a third preset time.

3. The fall prevention method according to claim 1, characterized in that: The step of generating balance curve information based on the balance ability information comprises: Perform grayscale and denoising processing on all first images in the balancing capability information to obtain a first feature map corresponding to each first image; Arrange and identify all the first feature maps horizontally to obtain feature points corresponding to each of the first feature maps; All the characteristic points are connected to obtain the balance curve information.

4. The fall prevention method according to claim 1, characterized in that: The training steps of the fall risk prediction model include: Obtain a training data set and a true label set, wherein each true label in the true label set has a one-to-one correspondence with one of the training data in the training data set; Inputting target training data into the Transformer model to obtain a prediction level, wherein the target training data is any training data in the training data set; Calculating a loss function based on the true label corresponding to the target training data and the predicted grade; The model parameters of the Transformer model are adjusted based on the loss function to obtain the fall risk prediction model.

5. The fall prevention method according to claim 1, characterized in that: After the step of generating first fall warning information based on the fall risk level, the fall prevention method further includes: Obtain inpatient information from mobile electronic medical record systems in a falls prevention system; The inpatient information and the first fall warning information are displayed on the HIS system, the nurse station smart screen and / or the ward smart screen in the fall prevention system.

6. The fall prevention method according to claim 5, characterized in that: After the step of displaying the inpatient information and the first fall warning information on the HIS system, the nurse station smart screen and / or the ward smart screen in the fall prevention system, the fall prevention method further includes: Obtaining heart rate information of the hospitalized patient; Optimizing the fall risk level based on the heart rate information to obtain an optimized level; Second fall warning information is generated based on the optimization level.

7. A fall prevention system, characterized in that: include: An acquisition module, used for acquiring lower limb muscle strength information, balance ability information and gait information of hospitalized patients based on time series; A muscle strength level generating module, used for generating a muscle strength level based on the lower limb muscle strength information; A balance curve information generating module, used to generate balance curve information based on the balance capability information; A fall risk level output module, used for inputting the muscle strength level, the balance curve information and the gait information into a fall risk prediction model for analysis and processing, and outputting a fall risk level; The first fall warning information generating module is used to generate the first fall warning information based on the fall risk level to prevent the inpatient from falling.

8. A fall prevention system, characterized in that: It includes a medical information system, a force sensor, a mobile electronic medical record system, a HIS system, a smart screen at the nurse station and a smart screen in the ward, wherein the medical information system is used to implement the steps of the fall prevention method described in any one of claims 1 to 6 above, and the medical information system is respectively connected to the force sensor, the mobile electronic medical record system, the HIS system, the smart screen at the nurse station and the smart screen in the ward.

9. A terminal device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the steps of the fall prevention method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein the computer program enables a computer to execute the steps of the fall prevention method according to any one of claims 1 to 6.

Images