Joint flexion and extension monitoring method, device and equipment and storage medium

Abstract

The invention discloses a joint flexion and extension monitoring method, device and equipment and a storage medium, and belongs to the technical field of exercise rehabilitation. According to the method, illness state data of a target patient is obtained, a joint brace is controlled to collect joint movement data of the target patient, and the joint movement data comprises a joint angle and duration time corresponding to joint flexion and extension actions; matching is carried out in a database of illness state rehabilitation models according to the illness state data, an associated target illness state rehabilitation model is obtained, and the illness state rehabilitation model comprises joint rehabilitation motion parameters; predicting a prediction probability corresponding to each adverse reaction of joint rehabilitation according to the target illness state rehabilitation model and the joint movement data; and generating corresponding joint rehabilitation prompt information according to the prediction probability and the joint movement data, thereby reducing complications in the joint rehabilitation process and reducing the rehabilitation time after the joint operation.

Description

Technical Field

[0001] The present invention relates to the field of sports rehabilitation, and particularly to a method, device, equipment and storage medium for monitoring joint flexion and extension. Background Art

[0002] With the development of medical technology, the rehabilitation after joint surgery has gradually become an indispensable part of the treatment of knee joints and elbow joints. Usually, after joint surgery, a joint brace is generally worn on the patient. The joint brace generally has functions such as support and protection, joint movement limitation, and braking and fixation. At present, the use of joint braces often brings a psychological burden to patients, resulting in a lack of corresponding rehabilitation activities during the rehabilitation period when activities are required, and then leading to pathological states such as adhesion and insufficient muscle strength in patients, thus affecting the rehabilitation of patients' joints, and further increasing the rehabilitation time and adverse reactions after joint surgery.

[0003] The above content is only used to assist in understanding the technical solution of the present invention, and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method, device, equipment and storage medium for monitoring joint flexion and extension, aiming to reduce the complications during joint rehabilitation while reducing the rehabilitation time after joint surgery.

[0005] To achieve the above purpose, the present invention provides a method for monitoring joint flexion and extension, which includes the following steps:

[0006] Obtain the condition data of the target patient, and control the joint brace to collect the joint movement data of the target patient. The joint movement data includes: the joint angle and duration corresponding to the joint flexion and extension actions;

[0007] Match the condition data in the database of the condition rehabilitation model to obtain the associated target condition rehabilitation model. The condition rehabilitation model includes: joint rehabilitation movement parameters;

[0008] Predict the prediction probabilities corresponding to each adverse reaction of joint rehabilitation according to the target condition rehabilitation model and the joint movement data;

[0009] Generate corresponding joint rehabilitation prompt information according to the prediction probabilities and the joint movement data.

[0010] Optionally, the step of matching the condition data in the condition rehabilitation model database to obtain the associated target condition rehabilitation model includes:

[0011] Normalize the condition data and generate a corresponding condition vector according to the condition data;

[0012] Calculate the corresponding cosine similarity according to the disease condition vector and the vectors of each disease condition recovery model in the disease condition recovery model database to obtain a plurality of similarity data;

[0013] Determine the target disease condition recovery model according to the plurality of similarity data.

[0014] Optionally, the step of generating a corresponding disease condition vector according to the disease condition data includes:

[0015] Determine the treatment stage corresponding to the target patient at the current moment according to the disease condition data;

[0016] Classify the disease condition data into first-class disease condition data and second-class disease condition data according to the treatment stage;

[0017] Generate a corresponding disease condition vector according to the first-class disease condition data.

[0018] Optionally, the treatment stage includes: immediate postoperative period, early rehabilitation period, mid-rehabilitation period, late rehabilitation period, functional recovery period, and long-term maintenance period, and the immediate postoperative period, the early rehabilitation period, the mid-rehabilitation period, the late rehabilitation period, the functional recovery period, and the long-term maintenance period respectively correspond to different time ranges.

[0019] Optionally, the step of predicting the prediction probability corresponding to each adverse reaction of joint rehabilitation according to the target disease condition recovery model and the joint movement data includes:

[0020] Calculate the corresponding disease condition impact factor according to the standard joint movement data corresponding to the target disease condition recovery model and the joint movement data;

[0021] Determine the prediction probability according to the preset probability of the adverse reaction corresponding to the target disease condition recovery model and the disease condition impact factor.

[0022] Optionally, the step of calculating the corresponding disease condition impact factor according to the standard joint movement data corresponding to the target disease condition recovery model and the joint movement data includes:

[0023] Calculate the movement state deviation value according to the standard joint movement data and the joint movement data;

[0024] Calculate the disease condition impact factor according to the movement state deviation value and the recovery coefficient corresponding to the target disease condition recovery model.

[0025] Optionally, the step of generating a corresponding joint rehabilitation prompt message according to the prediction probability and the joint movement data includes:

[0026] When the predicted probability is within a preset probability interval, it is determined that the joint rehabilitation prompt information indicates that the rehabilitation condition has met the expectation;

[0027] When the predicted probability is outside the preset probability interval and the joint motion data is outside the preset motion data interval, it is determined that the joint rehabilitation prompt information is to suggest adjusting the joint motion condition;

[0028] When the predicted probability is outside the preset probability interval and the joint motion data is within the preset motion data interval, it is determined that the joint rehabilitation prompt information is to suggest a follow-up visit.

[0029] In addition, to achieve the above object, the present invention further provides a joint flexion and extension monitoring device, which includes:

[0030] An acquisition module, configured to acquire the condition data of a target patient and control a joint brace to collect the joint motion data of the target patient, where the joint motion data includes: the joint angle and duration corresponding to the joint flexion and extension movement;

[0031] A matching module, configured to perform matching in a condition rehabilitation model database according to the condition data to obtain an associated target condition rehabilitation model;

[0032] A prediction module, configured to predict the prediction probabilities corresponding to various adverse reactions of joint rehabilitation according to the target condition rehabilitation model and the joint motion data;

[0033] A prompt module, configured to generate corresponding joint rehabilitation prompt information according to the prediction probability and the joint motion data.

[0034] In addition, to achieve the above object, the present invention further provides a joint flexion and extension monitoring device, which includes: a memory, a processor, and a joint flexion and extension monitoring program stored on the memory and executable on the processor, where the joint flexion and extension monitoring program is configured to implement the steps of the joint flexion and extension monitoring method described in any one of the above.

[0035] In addition, to achieve the above object, the present invention further provides a storage medium, on which a joint flexion and extension monitoring program is stored, and when the joint flexion and extension monitoring program is executed by a processor, the steps of the joint flexion and extension monitoring method described in any one of the above are implemented.

[0036] The present invention provides a method for monitoring joint flexion and extension. By matching the disease data in the database of the disease rehabilitation model, the associated target disease rehabilitation model is obtained. Compared with the brace that only limits the position, it can accurately determine the situation of the target patient, and predict the prediction probabilities corresponding to various adverse reactions of joint rehabilitation according to the target disease rehabilitation model and the joint movement data. It realizes determining the occurrence probability of adverse reactions based on the actual movement data during the user's rehabilitation process, and generates corresponding joint rehabilitation prompt information according to the prediction probability and the joint movement data. Thus, the target patient can adjust the use of the knee during rehabilitation according to the joint rehabilitation prompt information, and further reduce complications while reducing the rehabilitation time after joint surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a schematic structural diagram of a joint flexion and extension monitoring device in the hardware operating environment related to the embodiment solution of the present invention;

[0038] Figure 2 is a schematic flowchart of the first embodiment of the method for monitoring joint flexion and extension of the present invention;

[0039] Figure 3 is a schematic flowchart of the second embodiment of the method for monitoring joint flexion and extension of the present invention;

[0040] Figure 4 is a schematic diagram of the specific steps of step S21 in the second embodiment of the method for monitoring joint flexion and extension of the present invention;

[0041] Figure 5 is a schematic flowchart of the third embodiment of the method for monitoring joint flexion and extension of the present invention;

[0042] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0044] Refer to Figure 1 , Figure 1 is a schematic structural diagram of a joint flexion and extension monitoring device in the hardware operating environment related to the embodiment solution of the present invention.

[0045] As Figure 1As shown in the figure, the joint flexion and extension monitoring device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, an interaction device 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The interaction device 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the interaction device 1003 may also be connected to the communication bus through a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wireless-Fidelity (WI-FI) interface). The memory 1005 may be a high-speed Random Access Memory (RAM) or a stable Non-Volatile Memory (NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0046] Those skilled in the art can understand that Figure 1 the structure shown in the figure does not constitute a limitation on the joint flexion and extension monitoring device, and may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0047] As Figure 1 shown, the memory 1005, as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a joint flexion and extension monitoring program.

[0048] In Figure 1 the joint flexion and extension monitoring device shown in the figure, the network interface 1004 is mainly used for data communication with other devices; the interaction device 1003 is mainly used for data interaction with users; the processor 1001 and the memory 1005 in the joint flexion and extension monitoring device of the present invention may be arranged in the joint flexion and extension monitoring device. The joint flexion and extension monitoring device calls the joint flexion and extension monitoring program stored in the memory 1005 through the processor 1001 and executes the joint flexion and extension monitoring method provided by the embodiment of the present invention.

[0049] Furthermore, for the joint flexion and extension monitoring device, the joint flexion and extension monitoring device may be a knee joint brace.

[0050] The embodiment of the present invention provides a joint flexion and extension monitoring method. Referring to Figure 2 , Figure 2 it is a schematic flowchart of the first embodiment of a joint flexion and extension monitoring method of the present invention.

[0051] In this embodiment, the joint flexion and extension monitoring method includes:

[0052] Step S1: Obtain the condition data of the target patient, and control the joint brace to collect the joint movement data of the target patient. The joint movement data includes the joint angle and duration corresponding to the joint flexion and extension actions.

[0053] The condition data here includes: the basic information, medical history, symptom assessment, imaging examination, function assessment, and self-assessment of the patient of the target patient, etc. Among them, the basic information of the patient includes: age, gender, weight, BMI, etc. The medical history here can be various knee joint medical histories and corresponding surgical histories. Common surgical histories include: ACL reconstruction, meniscus repair, total joint replacement, etc. The joint brace here can be a knee joint brace provided with sensors. Preferably, the sensors can include: inertial measurement units, and the inertial measurement units can include accelerometers, gyroscopes, and magnetometers. The position and angle of the knee joint can be determined through the above sensors.

[0054] Step S2: Match in the database of the condition rehabilitation model according to the condition data to obtain the associated target condition rehabilitation model.

[0055] Before step S2 is executed, it also includes: recording the data of patients with various joint diseases at the current moment during the rehabilitation process. Such data reflects the improvement process of the patient's mobility during the rehabilitation period, and the control of the patient by various movement behaviors of the patient in daily life during the rehabilitation process. Optionally, the models in the condition rehabilitation model database are saved in the form of vectors. In addition to the joint rehabilitation exercise parameters, a model often also includes other parameters. Each of the condition rehabilitation models here corresponds to a model under the same or similar conditions of basic information, medical history, symptom assessment, imaging examination, function assessment, and self-assessment of the patient, etc. Specifically, one of the condition rehabilitation models: can be a 26-year-old male with a normal BMI value, right knee ACL reconstruction surgery, normal intraoperative graft tension measurement, the joint range of motion locked in full extension on the 3rd day after surgery, and swelling on the 5th day after surgery, etc. During the matching process, it is necessary to perform a similarity match between the condition data and the condition rehabilitation model to determine the target condition rehabilitation model.

[0056] Step S3: Predict the prediction probabilities corresponding to each adverse reaction of joint rehabilitation according to the target condition rehabilitation model and the joint movement data.

[0057] In this embodiment, after determining the target disease recovery model, it is necessary to use the data corresponding to the model to predict various adverse reactions of the target patient. The adverse reactions here may include: joint adhesion, joint stiffness, limited joint movement, muscle atrophy, venous thrombosis, and pain. Optionally, based on the curve of the recovery process of the target disease recovery model, the prediction probabilities corresponding to the respective adverse reactions are generated. This is because during the recovery process, due to different living conditions of the patient, there may be excessive or insufficient knee movements inadvertently during their life, resulting in an unsatisfactory knee recovery situation.

[0058] Step S4, generate corresponding joint recovery prompt information according to the prediction probability and the joint movement data.

[0059] Specifically, determine the generated prompt type according to the prediction probability, and generate specific joint recovery prompt information based on the joint movement data. The joint recovery prompt information may include: the number of joint movements recommended to be supplemented on the current day, or, it is recommended to stop using or moving the joint after the current time. Thus, the target patient can achieve a refined joint recovery process.

[0060] In this embodiment, by matching the disease data in the database of the disease recovery model, the associated target disease recovery model is obtained. Compared with only using a brace with limited movement, it can accurately determine the situation of the target patient, and predict the prediction probabilities corresponding to various adverse reactions of joint recovery according to the target disease recovery model and the joint movement data. It realizes determining the occurrence probability of adverse reactions based on the actual movement data during the user's recovery process, and generates corresponding joint recovery prompt information according to the prediction probability and the joint movement data. Thus, the target patient can adjust the use of the knee during the recovery process according to the joint recovery prompt information, and thereby can reduce complications while reducing the recovery time after joint surgery.

[0061] Further, based on the first embodiment, a second embodiment of a method for monitoring joint flexion and extension according to the present invention is proposed. In this embodiment, referring to Figure 3 , the step of matching the disease data in the disease recovery model database to obtain the associated target disease recovery model includes:

[0062] Step S21, normalize the disease data, and generate a corresponding disease vector according to the disease data;

[0063] Specifically, the information of the patient is converted into numerical data, including converting text data into structured numerical values, and normalizing each numerical data. Specifically, min-max normalization is used to scale features with larger values to [0, 1]. Different features are combined into a vector according to a preset priority to obtain the disease condition vector. Preferably, the order of surgery history, rehabilitation exercise, weight, BMI, and age is used as the order of decreasing priority.

[0064] Step S22: Calculate the corresponding cosine similarity according to the disease condition vector and the vector of each disease condition rehabilitation model in the disease condition rehabilitation model database to obtain a plurality of similarity data;

[0065] In this embodiment, for target patients in different rehabilitation cycles, since they actually do not experience a complete rehabilitation treatment process, the number of elements in the disease condition vector corresponding to the target patient is less than the number of elements in the vector corresponding to the disease condition rehabilitation model. Specifically, in the process of calculating the corresponding cosine similarity according to the disease condition vector and the vector of each disease condition rehabilitation model in the disease condition rehabilitation model database, when the number of elements in the disease condition vector corresponding to the target patient is less than the number of elements in the vector corresponding to the disease condition rehabilitation model, it is judged whether there is a preset necessary element type in the disease condition vector corresponding to the target patient. Furthermore, when there is a preset necessary element type in the disease condition vector corresponding to the target patient, the elements corresponding to the same element type as the disease condition vector corresponding to the target patient in the vector of the disease condition rehabilitation model in the disease condition rehabilitation model database are selected to form a comparison vector. Calculate the cosine similarity between the comparison vector and the disease condition vector to obtain the similarity data corresponding to the vector of each disease condition rehabilitation model. The way of generating a comparison vector and then making a comparison here is to not modify the disease condition vector of the target patient, so as to realize the comparison with the disease condition rehabilitation model. Compared with the method of filling in missing information with default values or average values, it can ensure that the patient's data is not modified, and only the elements of the matching model are changed.

[0066] Step S23: Determine the target disease condition rehabilitation model according to the plurality of similarity data.

[0067] Select the disease condition rehabilitation model corresponding to the highest value in the plurality of similarity data as the target disease condition rehabilitation model. And it should be noted that in the process of determining the target disease condition rehabilitation model, since in the process of step S22, the disease condition vector may only include preset necessary element types, the number of target disease condition rehabilitation models obtained may be more than one. Optionally, in some other embodiments, only one disease condition rehabilitation model can be selected as the target disease condition rehabilitation model.

[0068] Further, refer toFigure 4 , step S21 can specifically include:

[0069] Step S211, determining the treatment stage corresponding to the current moment of the target patient according to the condition data;

[0070] It should be noted that the determination of the treatment stage here is actually judged by the doctor based on the recovery situation of the target patient, rather than a single fixed time. By extracting the data of the latest updated diagnosis and treatment records in the condition data, the treatment stage determined by the doctor at the current moment is determined.

[0071] Step S212, classifying the condition data into first-class condition data and second-class condition data according to the treatment stage;

[0072] Optionally, the relevance of the first-class condition data to the treatment stage is greater than that of the second-class condition data to the treatment stage. The relevance here can be preset by the doctor, so that the doctor can actively exclude unnecessary data for each different treatment stage. Instead of simply taking all the condition data as vectors. Optionally, the time difference between the time of the first-class condition data and the treatment stage is less than the time difference between the time of the second-class condition data and the treatment stage.

[0073] Step S213, generating a corresponding condition vector according to the first-class condition data.

[0074] In this embodiment, the treatment stage includes: immediate postoperative period, early rehabilitation period, middle rehabilitation period, late rehabilitation period, functional recovery period, and long-term maintenance period, and the immediate postoperative period, the early rehabilitation period, the middle rehabilitation period, the late rehabilitation period, the functional recovery period, and the long-term maintenance period respectively correspond to different time ranges.

[0075] In this embodiment, by normalizing the condition data and generating a corresponding condition vector according to the condition data; calculating the corresponding cosine similarity according to the condition vector and the vector of each condition rehabilitation model in the condition rehabilitation model database, obtaining a plurality of similarity data and determining the target condition rehabilitation model according to the plurality of similarity data, so as to improve the accuracy of determining the rehabilitation state of the current target patient.

[0076] Further, based on the first embodiment or the second embodiment, a third embodiment of the joint flexion and extension monitoring method of the present invention is proposed. In this embodiment, referring to Figure 5 , the step of predicting the prediction probability corresponding to each adverse reaction of joint rehabilitation according to the target condition rehabilitation model and the joint movement data includes:

[0077] Step S31: Calculate the corresponding disease impact factor based on the standard joint motion data corresponding to the target disease rehabilitation model and the joint motion data.

[0078] The disease impact factor here is used to correct the adverse reactions corresponding to the target disease rehabilitation model and the adverse reactions corresponding to the current joint motion data. For example, for the current target disease rehabilitation model, based on the standard joint motion data, the occurrence probability of various adverse reactions is 10%. However, through the disease impact factor, the occurrence probability of the adverse reactions here is no longer directly equal to the preset probability of the adverse reactions corresponding to the target disease rehabilitation model.

[0079] Step S32: Determine the prediction probability based on the preset probability of the adverse reactions corresponding to the target disease rehabilitation model and the disease impact factor.

[0080] The prediction probability is calculated based on the preset probability, the disease impact factor, and a preset calculation formula. The preset calculation formula here may include a coefficient corresponding to the disease impact factor. The calculation formula here corresponds one-to-one with the target disease rehabilitation model.

[0081] In this embodiment, the motion state deviation value is calculated based on the standard joint motion data and the joint motion data; and the disease impact factor is calculated based on the motion state deviation value and the rehabilitation coefficient corresponding to the target disease rehabilitation model, thereby avoiding determining the rehabilitation situation of the target patient solely through the target disease rehabilitation model, but rather determining the rehabilitation situation based on the usage and activity of the joints by the target patient during the rehabilitation process.

[0082] The step of calculating the corresponding disease impact factor based on the standard joint motion data corresponding to the target disease rehabilitation model and the joint motion data includes:

[0083] Calculate the motion state deviation value based on the standard joint motion data and the joint motion data;

[0084] Specifically, calculate the difference between the standard joint motion data and the joint motion data as the motion state deviation value. Optionally, calculate the quotient of the standard joint motion data and the joint motion data as the motion state deviation value.

[0085] Calculate the disease impact factor based on the motion state deviation value and the rehabilitation coefficient corresponding to the target disease rehabilitation model.

[0086] In other embodiments, the motion state deviation value may be used as the disease impact factor.

[0087] In this embodiment, the deviation value of the motion state is calculated according to the standard joint motion data and the joint motion data; the disease impact factor is calculated according to the deviation value of the motion state and the rehabilitation coefficient corresponding to the target disease rehabilitation model, so as to improve the accuracy of the disease impact factor, and further improve the accuracy of the corresponding joint rehabilitation prompt information generated subsequently.

[0088] Further, based on any of the above embodiments, a fourth embodiment of the joint flexion and extension monitoring method of the present invention is proposed. The step of generating the corresponding joint rehabilitation prompt information according to the prediction probability and the joint motion data includes:

[0089] When the prediction probability is within the preset probability interval, it is determined that the joint rehabilitation prompt information is that the rehabilitation condition meets the expectation;

[0090] Specifically, the prediction probability here can be the sum of various adverse reactions, or the prediction probability of a single adverse reaction. The prediction probability can be either the sum of the adverse probabilities including joint adhesion, joint stiffness, limited range of motion, muscle atrophy, etc., or the prediction probability of a single joint adhesion.

[0091] When the prediction probability is outside the preset probability interval and the joint motion data is outside the preset motion data interval, it is determined that the joint rehabilitation prompt information is to suggest adjusting the joint motion condition;

[0092] When the joint motion data is outside the preset motion data interval and the prediction probability of joint adhesion is outside the preset probability interval, it is recommended to increase the frequency and quantity of joint flexion and extension. When the prediction probability of muscle atrophy is outside the preset probability interval, the amount of training can be increased to avoid muscle atrophy. When the prediction probability of deep vein thrombosis of the lower extremities is outside the preset probability interval, the amount of training can be reduced and it is recommended to increase the time of lying in bed to avoid irritation of the lower extremity blood vessels.

[0093] When the prediction probability is outside the preset probability interval and the joint motion data is within the preset motion data interval, it is determined that the joint rehabilitation prompt information is to suggest a follow-up visit.

[0094] In this embodiment, the joint rehabilitation prompt information is jointly determined by the prediction probability of adverse reactions and the joint motion data, so that the target patient can adjust the use of the knee during rehabilitation according to the joint rehabilitation prompt information, and thus can reduce complications while reducing the rehabilitation time after joint surgery.

[0095] In addition, an embodiment of the present invention also proposes a joint flexion and extension monitoring device, and the joint flexion and extension monitoring device includes:

[0096] An acquisition module, configured to acquire the condition data of a target patient and control a joint brace to collect the joint movement data of the target patient, where the joint movement data includes: the joint angle and duration corresponding to the flexion and extension movements of the joint;

[0097] A matching module, configured to perform a match in a condition rehabilitation model database according to the condition data to obtain an associated target condition rehabilitation model;

[0098] A prediction module, configured to predict the prediction probabilities corresponding to each adverse reaction of joint rehabilitation according to the target condition rehabilitation model and the joint movement data;

[0099] A prompting module, configured to generate corresponding joint rehabilitation prompting information according to the prediction probabilities and the joint movement data;

[0100] The joint flexion and extension monitoring device can execute any step in any of the above embodiments.

[0101] In addition, an embodiment of the present invention further provides a joint flexion and extension monitoring device, where the joint flexion and extension monitoring device includes: a memory, a processor, and a joint flexion and extension monitoring program stored on the memory and executable on the processor, and the joint flexion and extension monitoring program is configured to implement the steps of the joint flexion and extension monitoring method described in any one of the above embodiments.

[0102] In addition, an embodiment of the present invention further provides a storage medium, where a joint flexion and extension monitoring program is stored on the storage medium, and when the joint flexion and extension monitoring program is executed by a processor, the steps of the joint flexion and extension monitoring method described in any one of the above embodiments are implemented.

[0103] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or system including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or system including the element.

[0104] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0105] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0106] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be similarly included in the patent protection scope of the present invention.

Claims

1. A method for monitoring joint flexion and extension, characterized in that, The joint flexion and extension monitoring method includes the following steps: Obtain the condition data of the target patient, and control the joint brace to collect the joint movement data of the target patient. The joint movement data includes: the joint angle and duration corresponding to the joint flexion and extension movement; Match according to the condition data in the database of the condition rehabilitation model to obtain the associated target condition rehabilitation model. The condition rehabilitation model includes: joint rehabilitation movement parameters; Predict the prediction probabilities corresponding to each adverse reaction of joint rehabilitation according to the target condition rehabilitation model and the joint movement data; Generate corresponding joint rehabilitation prompt information according to the prediction probability and the joint movement data.

2. The joint flexion and extension monitoring method according to claim 1, wherein, The step of matching according to the condition data in the condition rehabilitation model database to obtain the associated target condition rehabilitation model includes: Normalize the condition data, and generate a corresponding condition vector according to the condition data; Calculate the corresponding cosine similarity according to the condition vector and the vector of each condition rehabilitation model in the condition rehabilitation model database to obtain a plurality of similarity data; Determine the target condition rehabilitation model according to the plurality of similarity data.

3. The joint flexion and extension monitoring method according to claim 2, wherein The step of generating a corresponding condition vector according to the condition data includes: Determine the treatment stage corresponding to the current moment of the target patient according to the condition data; Classify the condition data into the first type of condition data and the second type of condition data according to the treatment stage; Generate a corresponding condition vector according to the first type of condition data.

4. The joint flexion and extension monitoring method according to claim 3, wherein The treatment stage includes: immediate postoperative period, early rehabilitation period, mid-rehabilitation period, late rehabilitation period, functional recovery period, and long-term maintenance period. The immediate postoperative period, the early rehabilitation period, the mid-rehabilitation period, the late rehabilitation period, the functional recovery period, and the long-term maintenance period respectively correspond to different time ranges.

5. The joint flexion and extension monitoring method according to claim 1, characterized in that The step of predicting the prediction probabilities corresponding to each adverse reaction of joint rehabilitation according to the target condition rehabilitation model and the joint movement data includes: Calculate the corresponding condition influence factor according to the standard joint movement data corresponding to the target condition rehabilitation model and the joint movement data; Determine the prediction probability according to the preset probability of the adverse reaction corresponding to the target condition rehabilitation model and the condition influence factor.

6. The joint flexion and extension monitoring method according to claim 5, wherein The step of calculating the corresponding condition influence factor according to the standard joint movement data corresponding to the target condition rehabilitation model and the joint movement data includes: Calculate the movement state deviation value according to the standard joint movement data and the joint movement data; Calculate the condition influence factor according to the movement state deviation value and the rehabilitation coefficient corresponding to the target condition rehabilitation model.

7. The joint flexion and extension monitoring method according to any one of claims 1 to 6, characterized in that, The step of generating corresponding joint rehabilitation prompt information according to the prediction probability and the joint movement data includes: When the prediction probability is within the preset probability interval, determine that the joint rehabilitation prompt information is that the rehabilitation situation meets the expectation; When the prediction probability is outside the preset probability interval and the joint movement data is outside the preset movement data interval, determine that the joint rehabilitation prompt information is to suggest adjusting the joint movement situation; When the predicted probability is outside the preset probability interval and the joint motion data is within the preset motion data interval, determine that the joint rehabilitation prompt information is a suggestion for a follow-up visit.

8. A joint flexion and extension monitoring device, characterized in that, The joint flexion and extension monitoring device includes: An acquisition module, configured to acquire the condition data of a target patient and control a joint brace to collect the joint motion data of the target patient, where the joint motion data includes the joint angle and duration corresponding to the joint flexion and extension actions; A matching module, configured to perform matching in a condition rehabilitation model database according to the condition data to obtain an associated target condition rehabilitation model; A prediction module, configured to predict the prediction probabilities corresponding to various adverse reactions of joint rehabilitation according to the target condition rehabilitation model and the joint motion data; A prompt module, configured to generate corresponding joint rehabilitation prompt information according to the prediction probability and the joint motion data.

9. A joint flexion and extension monitoring device, characterized in that, The joint flexion and extension monitoring device includes: a memory, a processor, and a joint flexion and extension monitoring program stored on the memory and executable on the processor, where the joint flexion and extension monitoring program is configured to implement the steps of the joint flexion and extension monitoring method according to any one of claims 1 to 7.

10. A storage medium, characterized in that, A joint flexion and extension monitoring program is stored on the storage medium, and when the joint flexion and extension monitoring program is executed by a processor, the steps of the joint flexion and extension monitoring method according to any one of claims 1 to 7 are implemented.

Images