Joint rehabilitation evaluation system and method based on multi-modal data fusion

Abstract

The invention discloses a joint rehabilitation evaluation system and method based on multi-modal data fusion, and the system comprises a controller, the controller is connected in series with a detection module through a circuit, the detection module is connected in series with a collection module through a circuit, and the controller is connected in series with a setting module through a circuit. The setting module is connected in series with an input module through electric power, the controller is connected in series with a comparison module through a circuit, the comparison module is connected in series with a grading module through a circuit, the grading module is connected in series with a fusion module through a circuit, and the fusion module is connected in series with an evaluation module through a circuit. The controller is connected in series with a storage module through a circuit, the storage module is connected in series with a reading module through a circuit, the reading module is connected in series with a networking module through a circuit, and the comparison module is connected in parallel with the storage module through a circuit; the rehabilitation state can be judged in time, assessment is made, the rehabilitation process can be adjusted in time, the rehabilitation effect is improved, and matched use is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of joint rehabilitation, and more specifically, to a joint rehabilitation assessment system and method based on multimodal data fusion. Background Art

[0002] Artificial hip replacement is a relatively mature and effective method for treating severe hip joint diseases and fractures in the elderly. This method can effectively relieve patients' pain, restore joint function, and improve their quality of life. The recovery time of patients after hip replacement is relatively long. Effective rehabilitation management is an important means to ensure the recovery of patients' hip joint function and the independence of the elderly. However, the widespread promotion of rapid rehabilitation in clinical practice has shortened the average hospital stay after hip replacement, and the time for patients to recover in the hospital is limited. Patients who have undergone hip replacement surgery need to undergo a certain degree of rehabilitation training before they can return to a normal life. However, the traditional rehabilitation training process is no longer carried out in the hospital, resulting in a lack of scientific guidance for the patient's own rehabilitation training, resulting in unsatisfactory rehabilitation results.

[0003] Based on the management needs of joint rehabilitation, the results of joint rehabilitation should be evaluated to form the treatment results and rehabilitation processes at different stages. It is necessary to propose a joint rehabilitation evaluation system and method based on multimodal data fusion to solve real practical problems. Summary of the invention

[0004] In view of the problems existing in the prior art, the purpose of the present invention is to provide a joint rehabilitation assessment system and method based on multimodal data fusion, which connects various modules through a controller to form a composite rehabilitation assessment system, and performs data monitoring and collection on the joint parts to form real-time data for grading and comparison, and then performs modal fusion according to the actual nodes and needs of rehabilitation, thereby ensuring the accuracy of the data and the accuracy of the comparison, facilitating timely judgment of the rehabilitation status, thereby making an evaluation, facilitating timely adjustment of the rehabilitation process, improving the rehabilitation effect, and facilitating matching use.

[0005] To solve the above problems, the present invention adopts the following technical solutions.

[0006] A joint rehabilitation assessment system and method based on multimodal data fusion, comprising a controller, wherein the controller is connected in series with a detection module through a circuit, the detection module is connected in series with a collection module through a circuit, the controller is connected in series with a setting module through a circuit, the setting module is connected in series with an input module through power, the controller is connected in series with a comparison module through a circuit, the comparison module is connected in series with a classification module through a circuit, the classification module is connected in series with a fusion module through a circuit, the fusion module is connected in series with an assessment module through a circuit, the controller is connected in series with a storage module through a circuit, the storage module is connected in series with a reading module through a circuit, the reading module is connected in series with a networking module through a circuit, and the comparison module is connected in parallel with the storage module through a circuit;

[0007] The evaluation method includes the following steps:

[0008] S1. Integrate the controller into the device frame and connect it to the display through a transmission line;

[0009] S2, attaching the collection module to the joint rehabilitation part of the patient, distinguishing the attachment position and angle according to the type, and collecting data of the joint rehabilitation part;

[0010] S3, the collected data is detected and analyzed by the detection module, transmitted to the controller, and stored in the storage module to form dynamic data;

[0011] S4, networking through the reading module and the networking module, reading the database data, and forming static data;

[0012] S5, manually operate the input module, and combine with the setting module to set the standard to form evaluation data;

[0013] S6. Read the static data and the dynamic data through the comparison module, and compare the dynamic data and the static data with the evaluation data as a reference point to form a comparison result;

[0014] S7, classifying the comparison results through a classification module to form multi-modal separation data;

[0015] S8. Based on the actual needs and real-time status of joint rehabilitation, the separated data are fused through the fusion module to form a fusion result;

[0016] S9. Match the actual rehabilitation status with the theoretical status, and evaluate the fusion result through the evaluation module based on the actual matching degree.

[0017] Preferably, the acquisition module comprises a acquisition unit and a summarizing unit, the summarizing unit is connected in series to the acquisition unit via a circuit, and the acquisition unit is connected in series to the acquisition module via a circuit.

[0018] Preferably, the summary unit is connected in parallel with the patch unit, the angle unit, the tightness unit and the confirmation unit through a circuit, and the patch unit, the angle unit, the tightness unit and the confirmation unit are all combined with the acquisition module through the circuit.

[0019] Preferably, the patch unit, angle unit, tightness unit and confirmation unit are based on the type distinction in S2 and perform data collection.

[0020] Preferably, the setting module includes a setting unit, a parameter unit, a graphic unit, a control unit, a standard unit and a sample unit, the parameter unit, the graphic unit, the control unit, the standard unit and the sample unit are connected in parallel to the setting unit through a circuit, and the setting unit is connected to the setting module through a circuit.

[0021] Preferably, the parameter unit, the graphic unit, the control unit, the standard unit and the sample unit are connected in parallel with a marking unit via a circuit, and the marking unit is connected in series with a locking unit via a circuit.

[0022] Preferably, the parameter unit, graphic unit, control unit, standard unit, sample unit, marking unit and locking unit are applied to the standard setting in S5.

[0023] Preferably, the grading module is connected in parallel with a grading unit through a circuit, the grading unit is connected in parallel with a computing unit, a matching unit, a model unit, a separation unit and an arrangement unit through a circuit, and the computing unit, matching unit, model unit, separation unit and arrangement unit are connected in parallel with a mirror unit through a circuit.

[0024] Preferably, the mirror unit is connected in parallel to the grading unit via a circuit, and mirrors the data to the grading unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a system principle block diagram of the present invention;

[0026] Figure 2 It is a structural block diagram of the acquisition module of the present invention;

[0027] Figure 3 It is a structural block diagram of the setting module of the present invention;

[0028] Figure 4 It is a structural block diagram of the grading module of the present invention.

[0029] Description of the numbers in the figure:

[0030] 1 controller, 11 detection module, 12 acquisition module, 13 setting module, 14 input module, 15 comparison module, 16 classification module, 17 fusion module, 18 evaluation module, 2 storage module, 21 reading module, 22 networking module, 23 acquisition unit, 24 summary module, 25 patch unit, 26 angle unit, 27 tightness unit, 28 confirmation unit, 3 setting unit, 31 parameter unit, 32 control unit, 33 control unit, 34 standard unit, 35 sample unit, 36 marking unit, 37 locking unit, 4 classification unit, 41 calculation unit, 42 matching unit, 43 model unit, 44 separation unit, 45 arrangement unit, 46 mirror unit. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention; it is obvious that the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments, and all other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making creative work are within the scope of protection of the present invention.

[0032] See also Figure 1 , Figure 2 , Figure 3 and Figure 4 A joint rehabilitation assessment system and method based on multimodal data fusion, comprising a controller 1, the controller 1 is connected in series with a detection module 11 through a circuit, the detection module 11 is connected in series with a collection module 12 through a circuit, the controller 1 is connected in series with a setting module 13 through a circuit, the setting module 13 is connected in series with an input module 14 through power, the controller 1 is connected in series with a comparison module 15 through a circuit, the comparison module 15 is connected in series with a classification module 16 through a circuit, the classification module 16 is connected in series with a fusion module 17 through a circuit, the fusion module 17 is connected in series with an assessment module 18 through a circuit, the controller 1 is connected in series with a storage module 2 through a circuit, the storage module 2 is connected in series with a reading module 21 through a circuit, the reading module 21 is connected in series with a networking module 22 through a circuit, and the comparison module 15 is connected in parallel with the storage module 2 through a circuit;

[0033] The evaluation method includes the following steps:

[0034] S1, integrate the controller 1 into the device frame and connect it to the display through a transmission line;

[0035] S2, attaching the acquisition module 12 to the joint rehabilitation part of the patient, distinguishing the attachment position and angle according to the type, and collecting data of the joint rehabilitation part;

[0036] S3, the collected data is detected and analyzed by the detection module 11, transmitted to the controller 1, and stored in the storage module 2 to form dynamic data;

[0037] S4, networking through the reading module 21 and the networking module 22, reading the database data, and forming static data;

[0038] S5, manually operate the input module 14, and combine with the setting module 13 to perform standard setting to form evaluation data;

[0039] S6, reading the static data and the dynamic data through the comparison module 15, taking the evaluation data as a reference point, comparing the dynamic data and the static data to form a comparison result;

[0040] S7, classifying the comparison results through the classification module 16 to form multi-modal separation data;

[0041] S8, based on the actual needs and real-time status of joint rehabilitation, the separated data are fused through the fusion module 17 to form a fusion result;

[0042] S9. Match the actual rehabilitation state with the theoretical state, and evaluate the fusion result through the evaluation module 18 based on the actual matching degree.

[0043] See also Figure 1 and Figure 2 The collection module 12 includes a collection unit 23 and a summary unit 24. The summary unit 24 is connected in series to the collection unit 23 through a circuit. The collection unit 23 is connected in series to the collection module 12 through a circuit. The summary unit 24 is connected in parallel with a patch unit 25, an angle unit 26, a tightness unit 27 and a confirmation unit 28 through a circuit. The patch unit 25, the angle unit 26, the tightness unit 27 and the confirmation unit 28 are all combined with the collection module 12 through a circuit. The patch unit 25, the angle unit 26, the tightness unit 27 and the confirmation unit 28 are based on the type distinction in S2, and data collection is performed. The patch unit 25 is attached to the joint part to collect data, and the angle unit 26 can be attached to both ends of the joint, so that the joint can be moved to detect the movement angle of the joint, which is convenient for real-time detection of data. The tightness unit 27 is combined to detect the tightness of the joint during movement. The patient confirms the pain through the confirmation unit 28, thereby confirming the maximum angle to ensure safety and accuracy.

[0044] See also Figure 1 and Figure 3The setting module 13 includes a setting unit 3, a parameter unit 31, a graphic unit 32, a comparison unit 33, a standard unit 34 and a sample unit 35. The parameter unit 31, the graphic unit 32, the comparison unit 33, the standard unit 34 and the sample unit 35 are connected in parallel with the setting unit 3 through a circuit. The setting unit 3 is connected to the setting module 13 through a circuit. The parameter unit 31, the graphic unit 32, the comparison unit 33, the standard unit 34 and the sample unit 35 are connected in parallel with a marking unit 36 ​​through a circuit. The marking unit 36 ​​is connected in series with a locking unit 37 through a circuit. The recording unit 36 ​​and the locking unit 37 are applied to the standard setting in S5. In the manual operation in S3, manual input is performed through the input module (14), and manual setting is performed in combination with the setting unit 31. Various rehabilitation parameters are classified through the parameter unit 31 and input item by item. The graphics unit 31 draws graphics, thereby performing manual comparison, reducing item errors and omissions, and ensuring accuracy. After reading static data through the sample unit 35, a sample result is formed, and the control unit 33 is combined to perform data comparison to ensure that the standard setting of each item meets the specification. The rehabilitation standard is formed in combination with the standard unit 34, thereby completing the manually set standard and having a beard result evaluation.

[0045] See also Figure 1 and Figure 4 The grading module 16 is connected in parallel with the grading unit 4 through a circuit. The grading unit 4 is connected in parallel with the calculation unit 41, the matching unit 42, the model unit 43, the separation unit 44 and the arrangement unit 45 through a circuit. The calculation unit 41, the matching unit 42, the model unit 43, the separation unit 44 and the arrangement unit 45 are connected in parallel with the mirror unit 46 through a circuit. The mirror unit 46 is connected in parallel with the grading unit 4 through a circuit, and the data is mirrored and copied to the grading unit 4. In actual use, based on the operation of S7, the dynamic data is graded by the grading unit 4, and the collected data is calculated by the calculation unit 41, so that the matching unit 42 and the corresponding data in the static data are matched and transmitted to the model unit 43 to establish a dynamic model. Based on model extrusion, the data is separated by the separation unit 44 to form rehabilitation data of a separate project, and arranged in combination with the arrangement data. Multiple groups of data can be separated according to different projects to form separated data.

[0046] The above is only a preferred specific implementation of the present invention; however, the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solution and its improved conception within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A joint rehabilitation assessment method based on multimodal data fusion, comprising a controller (1), characterized in that: The controller (1) is connected in series with a detection module (11) through a circuit, the detection module (11) is connected in series with a collection module (12) through a circuit, the controller (1) is connected in series with a setting module (13) through a circuit, the setting module (13) is connected in series with an input module (14) through power, the controller (1) is connected in series with a comparison module (15) through a circuit, the comparison module (15) is connected in series with a classification module (16) through a circuit, the classification module (16) is connected in series with a fusion module (17) through a circuit, the fusion module (17) is connected in series with an evaluation module (18) through a circuit, the controller (1) is connected in series with a storage module (2) through a circuit, the storage module (2) is connected in series with a reading module (21) through a circuit, the reading module (21) is connected in series with a networking module (22) through a circuit, and the comparison module (15) is connected in parallel with the storage module (2) through a circuit; The evaluation method includes the following steps: S1, integrating the controller (1) into the device frame and connecting it to the display through a transmission line; S2, attaching the collection module (12) to the joint rehabilitation part of the patient, distinguishing the attachment position and angle according to the type, and collecting data of the joint rehabilitation part; S3, the collected data is detected and analyzed by the detection module (11), transmitted to the controller (1), and stored in the storage module (2) to form dynamic data; S4, networking through the reading module (21) and the networking module (22), reading the database data, and forming static data; S5, manually operate the input module (14), and perform standard setting in combination with the setting module (13) to form evaluation data; S6, reading the static data and the dynamic data through the comparison module (15), using the evaluation data as a reference point, comparing the dynamic data and the static data to form a comparison result; S7, classifying the comparison results through a classification module (16) to form multi-modal separation data; S8, based on the actual needs and real-time status of joint rehabilitation, the separated data are fused through a fusion module (17) to form a fusion result; S9. Match the actual rehabilitation state with the theoretical state, and evaluate the fusion result through the evaluation module (18) based on the actual matching degree.

2. A joint rehabilitation assessment method based on multimodal data fusion according to claim 1, characterized in that: The acquisition module (12) comprises a acquisition unit (23) and a summarizing unit (24); the summarizing unit (24) is connected in series to the acquisition unit (23) via a circuit; and the acquisition unit (23) is connected in series to the acquisition module (12) via a circuit.

3. A joint rehabilitation assessment method based on multimodal data fusion according to claim 2, characterized in that: The summary unit (24) is connected in parallel with a patch unit (25), an angle unit (26), a tightness unit (27) and a confirmation unit (28) through a circuit, and the patch unit (25), the angle unit (26), the tightness unit (27) and the confirmation unit (28) are all combined with the acquisition module (12) through the circuit.

4. The joint rehabilitation assessment method based on multimodal data fusion according to claim 3, characterized in that: The patch unit (25), angle unit (26), tightness unit (27) and confirmation unit (28) are based on the type distinction in S2 and perform data collection.

5. The joint rehabilitation assessment method based on multimodal data fusion according to claim 1, characterized in that: The setting module (13) comprises a setting unit (3), a parameter unit (31), a graphic unit (32), a comparison unit (33), a standard unit (34) and a sample unit (35); the parameter unit (31), the graphic unit (32), the comparison unit (33), the standard unit (34) and the sample unit (35) are connected in parallel to the setting unit (3) via a circuit; and the setting unit (3) is connected to the setting module (13) via a circuit.

6. A joint rehabilitation assessment method based on multimodal data fusion according to claim 5, characterized in that: The parameter unit (31), the graphic unit (32), the control unit (33), the standard unit (34) and the sample unit (35) are connected in parallel with a marking unit (36) via a circuit, and the marking unit (36) is connected in series with a locking unit (37) via a circuit.

7. A joint rehabilitation assessment method based on multimodal data fusion according to claim 6, characterized in that: The parameter unit (31), the graphic unit (32), the control unit (33), the standard unit (34), the sample unit (35), the marking unit (36) and the locking unit (37) are applied to the standard setting in S5.

8. The joint rehabilitation assessment method based on multimodal data fusion according to claim 1, characterized in that: The grading module (16) is connected in parallel with a grading unit (4) via a circuit; the grading unit (4) is connected in parallel with a computing unit (41), a matching unit (42), a model unit (43), a separation unit (44) and an arrangement unit (45) via a circuit; and the computing unit (41), the matching unit (42), the model unit (43), the separation unit (44) and the arrangement unit (45) are connected in parallel with a mirror unit (46) via a circuit.

9. A joint rehabilitation assessment method based on multimodal data fusion according to claim 8, characterized in that: The mirror unit (46) is connected in parallel to the grading unit (4) through a circuit, and mirrors the data to the grading unit (4).

Images