Intelligent follow-up management system for doctor-patient rehabilitation
Through the rehabilitation detection, association qualitative and follow-up arrangement module of the intelligent follow-up management system, the problem of rigid rehabilitation follow-up model of traditional Chinese medicine patients has been solved, and intelligent monitoring and dynamic adjustment of the patient's rehabilitation process has been realized, and follow-up efficiency and accuracy have been improved. Spend.
Patent Information
- Application Number
- CN202410630186.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-21
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-05-21
AI Technical Summary
The current doctor-patient rehabilitation follow-up model is relatively rigid, and it is impossible to fully understand the patient's rehabilitation status and dynamic adjustments, making it difficult for doctors to understand the patient's problems in a timely manner and it is difficult for patients to consult doctors frequently.
An intelligent follow-up management system for doctor-patient rehabilitation was designed, including a rehabilitation detection module, an association qualitative module and a follow-up arrangement module. By periodically obtaining rehabilitation videos, analyzing rehabilitation exercise values, marking abnormal exercises, dynamically adjusting the follow-up period, and Doctors sort and display patient information to improve follow-up efficiency and accuracy.
Intelligent monitoring and dynamic adjustment of the patient's rehabilitation process are achieved, the efficiency and accuracy of doctors' follow-up are improved, and the patient's rehabilitation process is effectively managed.
Smart Images

Figure CN118609752B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of doctor-patient communication, and more specifically, to an intelligent follow-up management system for doctor-patient rehabilitation. Background Art
[0002] Follow-up refers to an observation method in which doctors understand the patient's condition changes and guide the patient's rehabilitation through communication or other means after the patient is discharged from the hospital. Currently, doctors will customize corresponding rehabilitation training for patients before they are discharged, and inform them of the time of the next follow-up in advance before they are discharged. This follow-up model is relatively rigid. During the follow-up period, doctors cannot fully understand the patient's recovery status and problems encountered during the rehabilitation process. At the same time, it is inconvenient for patients to see doctors frequently. Therefore, how to provide a dynamic and accurate follow-up management system is an issue that urgently needs a solution. Summary of the invention
[0003] In view of the deficiencies in the prior art, the object of the present invention is to provide an intelligent follow-up management system for doctor-patient rehabilitation.
[0004] To achieve the above object, the present invention provides the following technical solutions:
[0005] Intelligent follow-up management system for medical and patient rehabilitation, including rehabilitation detection module, correlation qualitative module, and follow-up arrangement module;
[0006] The rehabilitation detection module is used to periodically obtain rehabilitation videos of multiple rehabilitation exercises during the patient's rehabilitation training, obtain the rehabilitation exercise value of each rehabilitation exercise, and then mark the patient's abnormal rehabilitation exercise;
[0007] The association qualitative module is used to obtain the knowledge graph between various rehabilitation exercises of the patient, and obtain the follow-up management value of the patient through the association of abnormal rehabilitation exercises, mark the follow-up patients according to the follow-up management value, and dynamically adjust the acquisition cycle of the rehabilitation video;
[0008] The follow-up scheduling module is used to display the follow-up patient information in order to the doctor, and the doctor arranges the follow-up time for the follow-up patients in sequence according to the order of the order.
[0009] Furthermore, rehabilitation videos of multiple rehabilitation exercises during the patient's rehabilitation training are periodically obtained, and then the rehabilitation exercise value of each rehabilitation exercise is obtained, specifically:
[0010] Based on the H cycle interval, at each cycle node, the patient uploads multiple rehabilitation exercise videos in the rehabilitation training, converts the rehabilitation exercise videos into rehabilitation video frames, and marks them as SZi, where i is the sequence number of the rehabilitation video frames, i=1, 2, ..., N, and N is a positive integer. The rehabilitation video frames are used as input data of the rehabilitation training analysis model of the rehabilitation exercise to obtain the rehabilitation training analysis value, extract the facial expression of the patient in the rehabilitation video frame, match the facial expression of the patient with the patient expression library, and obtain the training emotion score;
[0011] Generate a rehabilitation training log for the patient, obtain the rehabilitation fixed value of the rehabilitation training log, and then obtain the rehabilitation exercise value of the rehabilitation exercise;
[0012] A rehabilitation exercise threshold is set. When the rehabilitation exercise value is greater than or equal to the rehabilitation exercise threshold, the rehabilitation exercise is marked as an abnormal rehabilitation exercise.
[0013] Furthermore, the rehabilitation training analysis model is obtained in the following manner: collecting multiple rehabilitation video frames of the same rehabilitation exercise, extracting the patient's limb movements in the rehabilitation video frames, assigning different labels to different rehabilitation video frames according to different limb movements, the labels being the subsequent rehabilitation training analysis values, dividing the patient's limb movements in the rehabilitation video frames into a training set and a validation set, and obtaining the rehabilitation training analysis model through iterative training of a neural network. The numerical range of the rehabilitation training analysis value is (1~3). The larger the numerical value of the rehabilitation training analysis value, the more non-standard the patient's limb movements in the rehabilitation exercise, and the smaller the numerical value of the rehabilitation training analysis value, the more standard the patient's limb movements in the rehabilitation exercise.
[0014] Furthermore, the rehabilitation training log includes the name of the rehabilitation exercise item, the number of the rehabilitation video frame, the rehabilitation training analysis value, and the training emotion score.
[0015] Furthermore, the rehabilitation fixed frame value of the rehabilitation training log is obtained by marking the rehabilitation training analysis value of the rehabilitation training log as CWZ, marking the training emotion score of the rehabilitation training log as GBN, and using the formula The rehabilitation fixed value KPB of the rehabilitation training log is obtained, wherein a1 is the rehabilitation training analysis value coefficient, and a2 is the training emotion score coefficient.
[0016] Further, the rehabilitation exercise value of the rehabilitation exercise is obtained by the following method: obtaining the name of the rehabilitation exercise project of the rehabilitation training log, summing up the rehabilitation fixed frame values of all rehabilitation training logs with the same rehabilitation exercise project name, obtaining the total rehabilitation fixed frame value, and marking it as DGZ;
[0017] Set a rehabilitation freeze threshold, and when the rehabilitation freeze value of a rehabilitation training log is greater than or equal to the rehabilitation freeze threshold, mark the rehabilitation training log as an abnormal rehabilitation training log;
[0018] The rehabilitation training abnormality logs with the same rehabilitation exercise project name are sorted in the order of rehabilitation video frame numbers. The rehabilitation video frame numbers of two adjacent rehabilitation training abnormality logs after sorting are calculated to obtain the rehabilitation abnormality continuous value, which is marked as YCP. The total number of rehabilitation training abnormality logs with the same rehabilitation exercise project name is obtained and marked as RBU. The formula is used The rehabilitation exercise value FLM of the rehabilitation exercise is obtained, wherein b1 is the total value coefficient of rehabilitation, b2 is the continuous value coefficient of rehabilitation abnormality, and b3 is the coefficient of the number of rehabilitation training abnormal logs.
[0019] Furthermore, the knowledge graph between the various rehabilitation exercises of the patient is obtained, and the follow-up management value of the patient is obtained through the association of abnormal rehabilitation exercises, specifically:
[0020] When the rehabilitation exercise is marked as an abnormal rehabilitation exercise, the knowledge graph between the rehabilitation exercises is obtained, and other rehabilitation exercises related to the abnormal rehabilitation exercise are obtained and marked as associated rehabilitation exercises. When the associated rehabilitation exercise is marked as an abnormal rehabilitation exercise, the abnormal association times are increased by one, and all abnormal association times of the patient are summed up to obtain the total abnormal association times, which are marked as BNM;
[0021] The rehabilitation exercise values of all rehabilitation exercises of the patient are summed up to obtain the total rehabilitation exercise value, which is marked as SWK. The follow-up management value JBC of the patient is obtained, where c1 is the total number of abnormal association coefficients and c2 is the total value coefficient of rehabilitation exercise.
[0022] Furthermore, the follow-up patients are marked according to the follow-up management value, and the acquisition cycle of the rehabilitation video is dynamically adjusted, specifically: the follow-up management upper value and the follow-up management lower value are set, and when the follow-up management value of the patient is greater than the follow-up management upper value, the patient is marked as a follow-up patient;
[0023] When the patient's follow-up management value is between the upper follow-up management value and the lower follow-up management value, the follow-up management value is calculated by ratio with the upper follow-up management value to obtain the rehabilitation detection index SK. At periodic intervals, multiple rehabilitation exercise videos of the patient's rehabilitation training at the next periodic node are collected.
[0024] Furthermore, the follow-up patient information is displayed to the doctor in sorted order, and the doctor arranges follow-up time for the follow-up patients according to the sorting order. Specifically, the follow-up patient information is sent to the terminal device of the doctor to which it belongs, and the names of the follow-up patients are displayed on the doctor's terminal device in descending order according to the follow-up management value, and the doctor arranges follow-up time for the follow-up patients according to the sorting order.
[0025] Compared with the prior art, the present invention has the following beneficial effects:
[0026] 1. Set up a rehabilitation detection module to periodically analyze the patient's rehabilitation training video, intelligently analyze the patient's abnormal rehabilitation movement according to the rehabilitation movement value of each rehabilitation movement, customize a three-dimensional and comprehensive rehabilitation monitoring mode for the patient, and ensure effective supervision of the patient's rehabilitation process before follow-up;
[0027] 2. Set up a correlation qualitative module and a follow-up arrangement module. Through correlation analysis of the patient's abnormal rehabilitation movements, intelligently analyze whether the patient needs follow-up in advance, and dynamically adjust the rehabilitation video acquisition cycle according to the patient's rehabilitation movement status. After determining that the patient needs follow-up, the follow-up sequence is intelligently provided to the doctor to improve the doctor's follow-up efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 A flowchart for marking abnormal rehabilitation movements;
[0029] Figure 2 A flowchart for displaying follow-up patient information to doctors in a prioritized manner. DETAILED DESCRIPTION
[0030] Reference Figure 1-Figure 2 , an intelligent follow-up management system for doctor-patient rehabilitation, including rehabilitation detection module, correlation qualitative module, and follow-up arrangement module.
[0031] The rehabilitation detection module: based on H cycle intervals, at each cycle node, the patient uploads multiple rehabilitation exercise videos in rehabilitation training, and then obtains the rehabilitation exercise value of each rehabilitation exercise.
[0032] The rehabilitation exercise value of each rehabilitation exercise is obtained in the following way:
[0033] The rehabilitation exercise video is converted into rehabilitation video frames (the rehabilitation exercise video can be converted into rehabilitation video frames by frame extraction), and marked as SZi, where i is the sequential number of the rehabilitation video frame, i=1, 2, ..., N, and N is a positive integer. The rehabilitation video frame is used as the input data of the rehabilitation training analysis model of the rehabilitation exercise to obtain the rehabilitation training analysis value, extract the patient's facial expression in the rehabilitation video frame, match the patient's facial expression with the patient expression library, and obtain the training emotion score.
[0034] Generate a rehabilitation training log for the patient, which includes the name of the rehabilitation exercise project, the number of the rehabilitation video frame, the rehabilitation training analysis value, and the training emotion score.
[0035] The rehabilitation training analysis model is obtained by the following method: collecting multiple rehabilitation video frames of the same rehabilitation exercise, the rehabilitation video frames can be rehabilitation training frames of patients in actual rehabilitation training, or rehabilitation training frames of patients simulated by computer, extracting the patient's limb movements in the rehabilitation video frames, assigning different labels to different rehabilitation video frames according to different limb movements, and the labels are the subsequent rehabilitation training analysis values, dividing the patient's limb movements in the rehabilitation video frames into a training set and a validation set, and obtaining the rehabilitation training analysis model through iterative training of a neural network. The numerical range of the rehabilitation training analysis value is (1~3), the larger the numerical value of the rehabilitation training analysis value, the less standard the patient's limb movements in the rehabilitation exercise, and the smaller the numerical value of the rehabilitation training analysis value, the more standard the patient's limb movements in the rehabilitation exercise.
[0036] The patient expression library is a collection of facial expressions and their corresponding emotional polarity. The emotional polarity of facial expressions includes pain and relaxation. Pain and relaxation are used to represent the emotional polarity of facial expressions. Each facial expression in the patient expression library is associated with a training emotional score. The training emotional score of the facial expression related to pain is close to 1, and the training emotional score of the facial expression related to relaxation is close to -1. Pain indicates that the patient is severely uncomfortable when performing rehabilitation exercises, and the rehabilitation exercises cause irritation to the patient. Relaxation indicates that the patient does not feel discomfort when performing rehabilitation exercises, and the rehabilitation exercises do not cause irritation to the patient.
[0037] Before the patient is discharged from the hospital, the doctor will customize rehabilitation training for the patient. The customized rehabilitation training includes a variety of rehabilitation exercises. After the patient is discharged from the hospital, he needs to undergo rehabilitation treatment based on the rehabilitation exercises in the rehabilitation training.
[0038] Patients need to regularly upload their latest rehabilitation training videos to the system. Since rehabilitation training includes multiple rehabilitation exercises, multiple rehabilitation exercise videos will be uploaded. Usually, rehabilitation training will not cause discomfort to patients and will not cause stimulation or damage to patients.
[0039] The rehabilitation training analysis value of the rehabilitation training log is marked as CWZ, and the training emotion score of the rehabilitation training log is marked as GBN. The rehabilitation fixed value KPB of the rehabilitation training log is obtained, where a1 is the rehabilitation training analysis value coefficient, a2 is the training emotion score coefficient, the value of a1 is 0.81, and the value of a2 is 1.92.
[0040] The rehabilitation exercise item name of the rehabilitation training log is obtained, and the rehabilitation fixed frame values of all rehabilitation training logs with the same rehabilitation exercise item name are summed up to obtain the total rehabilitation fixed frame value, which is marked as DGZ.
[0041] Set the recovery freeze threshold. The recovery freeze threshold is the system setting threshold and can be modified according to actual needs.
[0042] When the rehabilitation freeze value of the rehabilitation training log is greater than or equal to the rehabilitation freeze threshold, the rehabilitation training log is marked as an abnormal rehabilitation training log.
[0043] When the rehabilitation freeze value of the rehabilitation training log is less than the rehabilitation freeze threshold, no corresponding processing is performed.
[0044] The rehabilitation training abnormality logs with the same rehabilitation exercise project name are sorted in the order of rehabilitation video frame numbers. The rehabilitation video frame numbers of two adjacent rehabilitation training abnormality logs after sorting are calculated to obtain the rehabilitation abnormality continuous value, which is marked as YCP. The total number of rehabilitation training abnormality logs with the same rehabilitation exercise project name is obtained and marked as RBU. The formula is used The rehabilitation exercise value FLM of the rehabilitation exercise is obtained, where b1 is the total rehabilitation fixed value coefficient, b2 is the rehabilitation abnormal continuous value coefficient, and b3 is the rehabilitation training abnormal log quantity coefficient. The value of b1 is 0.57, the value of b2 is 0.98, and the value of b3 is 0.42.
[0045] Set the rehabilitation exercise threshold. The rehabilitation exercise threshold is the system setting threshold and can be modified according to actual needs.
[0046] When the rehabilitation exercise value is greater than or equal to the rehabilitation exercise threshold, the rehabilitation exercise is marked as an abnormal rehabilitation exercise.
[0047] When the rehabilitation exercise value is less than the rehabilitation exercise threshold, no corresponding processing is performed.
[0048] A rehabilitation detection module is set up to conduct periodic analysis of the patient's rehabilitation training videos, intelligently analyze the patient's abnormal rehabilitation movements based on the rehabilitation movement value of each rehabilitation movement, customize a three-dimensional and comprehensive rehabilitation monitoring mode for the patient, and ensure effective supervision of the patient's rehabilitation process before follow-up.
[0049] The association qualitative module: when the rehabilitation exercise is marked as an abnormal rehabilitation exercise, the knowledge graph between the various rehabilitation exercises is obtained, and other rehabilitation exercises that are related to the abnormal rehabilitation exercise are obtained and marked as associated rehabilitation exercises. When the associated rehabilitation exercise is marked as an abnormal rehabilitation exercise, the abnormal association times are increased by one, and all abnormal association times of the patient are summed up to obtain the total abnormal association times, which is marked as BNM;
[0050] Each rehabilitation exercise is represented in the form of a knowledge graph. For example, the relationship in the knowledge graph represents the association between rehabilitation exercises, such as rehabilitation position relationships, etc., to ensure that the knowledge graph can accurately reflect the relationship between various rehabilitation exercises.
[0051] The rehabilitation exercise values of all rehabilitation exercises of the patient are summed up to obtain the total rehabilitation exercise value, which is marked as SWK. The follow-up management value JBC of the patient was obtained, where c1 is the total number of abnormal association coefficients, c2 is the total coefficient of rehabilitation exercise, the value of c1 is 5.67, and the value of c2 is 1.19.
[0052] Set the upper and lower values for follow-up management. The upper and lower values for follow-up management are greater than the lower and both are greater than 0. Both are system-set thresholds and can be modified according to actual needs.
[0053] When the patient's follow-up management value is greater than the follow-up management upper value, the patient is marked as a follow-up patient;
[0054] When the patient's follow-up management value is less than the lower value of follow-up management, no corresponding treatment will be performed;
[0055] When the patient's follow-up management value is between the upper follow-up management value and the lower follow-up management value, the follow-up management value is calculated by ratio with the upper follow-up management value to obtain the rehabilitation detection index SK. At periodic intervals, multiple rehabilitation exercise videos of the patient's rehabilitation training at the next periodic node are collected.
[0056] Follow-up arrangement module: The follow-up patient information is sent to the terminal device of the doctor to whom it belongs. The names of the follow-up patients are displayed on the doctor's terminal device in descending order according to the follow-up management value. The doctor arranges follow-up time for the follow-up patients according to the sorting order.
[0057] A correlation qualitative module and a follow-up arrangement module are set up to intelligently analyze whether the patient needs early follow-up through correlation analysis of the patient's abnormal rehabilitation movements, and dynamically adjust the rehabilitation video acquisition cycle according to the patient's rehabilitation movement status. After determining that the patient needs follow-up, the follow-up sequence is intelligently provided to the doctor to improve the doctor's follow-up efficiency and accuracy.
[0058] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0059] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0060] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0061] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0062] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0063] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0064] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.
[0065] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. Intelligent follow-up management system for doctor-patient rehabilitation, characterized by: It includes rehabilitation detection module, association qualitative module, and follow-up arrangement module; The rehabilitation detection module is used to periodically obtain rehabilitation videos of multiple rehabilitation exercises during the patient's rehabilitation training, obtain the rehabilitation exercise value of each rehabilitation exercise, and then mark the patient's abnormal rehabilitation exercise; The association qualitative module is used to obtain the knowledge graph between various rehabilitation exercises of the patient, and obtain the follow-up management value of the patient through the association of abnormal rehabilitation exercises, mark the follow-up patients according to the follow-up management value, and dynamically adjust the acquisition cycle of the rehabilitation video; The follow-up scheduling module is used to display the follow-up patient information to the doctor in order, and the doctor arranges the follow-up time for the follow-up patient in descending order according to the follow-up management value; Periodically obtain rehabilitation videos of multiple rehabilitation exercises during the patient's rehabilitation training, and then obtain the rehabilitation exercise value of each rehabilitation exercise, specifically: Based on the H cycle interval, at each cycle node, the patient uploads multiple rehabilitation exercise videos in the rehabilitation training, converts the rehabilitation exercise videos into rehabilitation video frames, and marks them as SZi, where i is the sequence number of the rehabilitation video frames, i=1, 2, ..., N, and N is a positive integer. The rehabilitation video frames are used as input data of the rehabilitation training analysis model of the rehabilitation exercise to obtain the rehabilitation training analysis value, extract the facial expression of the patient in the rehabilitation video frame, match the facial expression of the patient with the patient expression library, and obtain the training emotion score; Generate a rehabilitation training log for the patient, obtain the rehabilitation fixed value of the rehabilitation training log, and then obtain the rehabilitation exercise value of the rehabilitation exercise; Set a rehabilitation exercise threshold. When the rehabilitation exercise value is greater than or equal to the rehabilitation exercise threshold, mark the rehabilitation exercise as an abnormal rehabilitation exercise. The rehabilitation training analysis model is obtained in the following manner: collecting multiple rehabilitation video frames of the same rehabilitation exercise, extracting the patient's limb movements in the rehabilitation video frames, assigning different labels to different rehabilitation video frames according to different limb movements, the labels are the subsequent rehabilitation training analysis values, dividing the patient's limb movements in the rehabilitation video frames into a training set and a validation set, and obtaining the rehabilitation training analysis model through iterative training of a neural network. The numerical range of the rehabilitation training analysis value is (1-3). The larger the numerical value of the rehabilitation training analysis value, the less standard the patient's limb movements in the rehabilitation exercise, and the smaller the numerical value of the rehabilitation training analysis value, the more standard the patient's limb movements in the rehabilitation exercise. The rehabilitation fixed frame value of the rehabilitation training log is obtained by marking the rehabilitation training analysis value of the rehabilitation training log as CWZ, marking the training emotion score of the rehabilitation training log as GBN, and using the formula The rehabilitation fixed value KPB of the rehabilitation training log is obtained, where a1 is the rehabilitation training analysis value coefficient, and a2 is the training emotion score coefficient; The rehabilitation exercise value of the rehabilitation exercise is obtained in the following manner: obtaining the name of the rehabilitation exercise project in the rehabilitation training log, summing up the rehabilitation fixed frame values of all rehabilitation training logs with the same rehabilitation exercise project name, obtaining the total rehabilitation fixed frame value, and marking it as DGZ; Set a rehabilitation freeze threshold, and when the rehabilitation freeze value of a rehabilitation training log is greater than or equal to the rehabilitation freeze threshold, mark the rehabilitation training log as an abnormal rehabilitation training log; The rehabilitation training abnormality logs with the same rehabilitation exercise project name are sorted in the order of rehabilitation video frame numbers. The rehabilitation video frame numbers of two adjacent rehabilitation training abnormality logs after sorting are calculated to obtain the rehabilitation abnormality continuous value, which is marked as YCP. The total number of rehabilitation training abnormality logs with the same rehabilitation exercise project name is obtained and marked as RBU. The formula is used The rehabilitation exercise value FLM of the rehabilitation exercise is obtained, wherein b1 is the total value coefficient of the rehabilitation set point, b2 is the continuous value coefficient of the rehabilitation abnormality, and b3 is the coefficient of the number of rehabilitation training abnormal logs; Obtain the knowledge graph between the patient's various rehabilitation exercises, and obtain the patient's follow-up management value through the association of abnormal rehabilitation exercises, specifically: When the rehabilitation exercise is marked as an abnormal rehabilitation exercise, the knowledge graph between the rehabilitation exercises is obtained, and other rehabilitation exercises related to the abnormal rehabilitation exercise are obtained and marked as associated rehabilitation exercises. When the associated rehabilitation exercise is marked as an abnormal rehabilitation exercise, the abnormal association times are increased by one, and all abnormal association times of the patient are summed up to obtain the total abnormal association times, which are marked as BNM; The rehabilitation exercise values of all rehabilitation exercises of the patient are summed up to obtain the total rehabilitation exercise value, which is marked as SWK. The follow-up management value JBC of the patient is obtained, where c1 is the total number of abnormal association coefficients, and c2 is the total value coefficient of rehabilitation exercise; Mark the follow-up patients according to the follow-up management value, and dynamically adjust the acquisition cycle of the rehabilitation video, specifically: set the follow-up management upper value and the follow-up management lower value, and when the follow-up management value of the patient is greater than the follow-up management upper value, mark the patient as a follow-up patient; When the patient's follow-up management value is between the upper follow-up management value and the lower follow-up management value, the follow-up management value is calculated by ratio with the upper follow-up management value to obtain the rehabilitation detection index SK. At periodic intervals, multiple rehabilitation exercise videos of the patient's rehabilitation training at the next periodic node are collected.
2. The intelligent follow-up management system for doctor-patient rehabilitation according to claim 1 is characterized in that: The rehabilitation training log includes the name of the rehabilitation exercise project, the number of the rehabilitation video frame, the rehabilitation training analysis value, and the training emotion score.
3. The intelligent follow-up management system for doctor-patient rehabilitation according to claim 1 is characterized in that: The follow-up patient information is displayed to the doctor in sorted order, and the doctor arranges follow-up time for the follow-up patients according to the sorting order. Specifically, the follow-up patient information is sent to the terminal device of the doctor to which it belongs, and the names of the follow-up patients are displayed on the doctor's terminal device in descending order according to the follow-up management value. The doctor arranges follow-up time for the follow-up patients according to the sorting order.
