Method and system for determining motion state based on data analysis model

Abstract

The invention provides a method and system for determining a motion state based on a data analysis model, and belongs to the technical field of rehabilitation motion analysis. The method for determining the motion state based on the data analysis model comprises the steps of obtaining patient motion data and a patient rehabilitation motion plan of a cloud platform; based on the rehabilitation exercise plan of the patient, screening the exercise data of the patient to obtain actual exercise time and actual exercise postures; analyzing motion trend data according to the actual motion time and the standard motion time; motion standard degree data are analyzed according to the actual motion posture and the standard rehabilitation motion posture; calculating rehabilitation degree data of the patient according to the motion trend data and the motion standard degree data; through the mode, the rehabilitation exercise state of the patient can be determined, the rehabilitation exercise condition of the patient can be analyzed, and then the rehabilitation condition of the patient can be evaluated, so that the good rehabilitation trend of the patient is ensured, the patient is helped to better complete a rehabilitation plan, and the body function recovery of the patient is promoted.

Description

Technical Field

[0001] The present application relates to the technical field of rehabilitation motion analysis, and in particular to a method and system for determining motion status based on a data analysis model. Background Art

[0002] Rehabilitation exercise is exercise training during the rehabilitation treatment process; rehabilitation exercise is usually guided by a rehabilitation physician and designed according to the patient's condition and rehabilitation goals. Rehabilitation exercise includes multiple exercise postures, such as squats, jumping jacks, etc. Each exercise posture contains multiple movement characteristics. For example, squats are first lowered and then raised. The six-axis sensor can detect that the patient is performing the squat posture; when the patient is performing rehabilitation exercise, he or she performs each posture in turn according to the rehabilitation exercise plan, and each posture has at least one group, and each group has a fixed number of exercises; at this time, the patient's motion data can be collected through six-axis sensors, position sensors and other equipment; then the motion data carrying the patient's label will be uploaded to the cloud platform for storage, and the motion data will be matched with the patient based on the patient label; by analyzing the patient's motion data in the cloud platform, the patient's motion status can be determined and the patient's rehabilitation status can be comprehensively judged. Summary of the invention

[0003] The present application provides a method and system for determining motion status based on a data analysis model, which can analyze and process the motion data of patients in a cloud platform, judge the patient's rehabilitation status, give corresponding rehabilitation exercise suggestions, help patients better complete rehabilitation exercises, and promote the recovery of patients' physical functions.

[0004] In a first aspect, the present application provides a method for determining motion state based on a data analysis model.

[0005] The method comprises:

[0006] Acquire patient motion data and patient rehabilitation exercise plans on the cloud platform; the patient motion data includes patient motion time and patient motion posture; the patient rehabilitation exercise plan includes standard motion quantity, standard motion sequence and standard motion time for standard rehabilitation motion postures; the standard motion quantity includes the standard motion group number of each standard rehabilitation motion posture performed by the patient and the standard motion number included in each standard motion group number; the standard motion time represents the motion time spent on performing a standard rehabilitation motion posture;

[0007] Based on the patient rehabilitation exercise plan, the patient's exercise data is screened to obtain actual exercise time and actual exercise posture; the actual exercise posture is a patient's exercise posture whose similarity to the standard rehabilitation action posture is not less than a preset similarity threshold; the actual exercise time is the patient's exercise time consumed in executing the actual exercise posture;

[0008] Analyze the motion trend data according to the actual motion time and the standard motion time; analyze the motion standard data according to the actual motion posture and the standard rehabilitation motion posture; the motion trend data is associated with the actual motion time; the motion standard data is associated with the actual motion posture;

[0009] The patient's recovery degree data is calculated according to the motion trend data and the action standard degree data; the patient's recovery degree data is used to indicate the patient's recovery status.

[0010] Further, analyzing the motion trend data according to the actual motion time and the standard motion time; analyzing the motion standard data according to the actual motion posture and the standard rehabilitation motion posture includes:

[0011] Based on the actual movement time corresponding to each standard rehabilitation movement posture, the single movement time consumed by the patient to perform the actual movement posture;

[0012] Corresponding to each standard rehabilitation action posture, calculating first time difference data between the single action time and the standard action time;

[0013] Calculate first average time difference data according to the first time difference data;

[0014] Determining a single rehabilitation time for each rehabilitation exercise performed by the patient based on the actual exercise time;

[0015] Determining a standard rehabilitation time for each rehabilitation exercise performed by the patient based on the standard exercise time and the patient rehabilitation exercise plan;

[0016] Calculate the second time difference data by calculating the single recovery time and the standard recovery time;

[0017] Calculate second average time difference data according to the second time difference data;

[0018] The motion trend data is analyzed according to the first average time difference data and the second average time difference data.

[0019] Further, analyzing the motion trend data according to the actual motion time and the standard motion time; analyzing the motion standard data according to the actual motion posture and the standard rehabilitation motion posture includes:

[0020] Determine the average movement time for the patient to perform each standard rehabilitation action posture based on the actual movement time;

[0021] Calculate first standard degree data according to the average exercise time and the standard exercise time;

[0022] Determining similarity data between each of the actual movement postures and the corresponding standard rehabilitation movement posture;

[0023] Calculating second standard data; the second standard data is average similarity data of all actual motion postures;

[0024] The motion standard data is analyzed according to the first standard data and the second standard data. Further, the method for calculating the patient's rehabilitation degree data includes:

[0025] R=M×K1+S×K2

[0026] Wherein, R is the patient's recovery degree data, M is the movement trend data, S is the movement standard data; K1 and K2 are the preset first weight and the preset second weight respectively.

[0027] Further, K1+K2=1.

[0028] In a second aspect, the present application provides a system for determining a motion state based on a data analysis model, the system comprising:

[0029] An acquisition module is used to acquire patient motion data and patient rehabilitation motion plans from a cloud platform; the patient motion data includes patient motion time and patient motion posture; the patient rehabilitation motion plan includes a standard motion number, a standard motion sequence and a standard motion time for a standard rehabilitation motion posture; the standard motion number includes a standard motion group number for each standard rehabilitation motion posture performed by the patient and a standard motion number included in each standard motion group number; the standard motion time represents the motion time spent on performing a standard rehabilitation motion posture;

[0030] A screening module is used to screen the patient's movement data based on the patient's rehabilitation movement plan to obtain actual movement time and actual movement posture; the actual movement posture is a patient's movement posture whose similarity with the standard rehabilitation movement posture is not less than a preset similarity threshold; the actual movement time is the patient's movement time consumed by executing the actual movement posture;

[0031] An analysis module is used to analyze the movement trend data according to the actual movement time and the standard movement time; analyze the movement standard data according to the actual movement posture and the standard rehabilitation movement posture; the movement trend data is associated with the actual movement time; the movement standard data is associated with the actual movement posture;

[0032] A calculation module is used to calculate patient recovery degree data based on the motion trend data and the action standard degree data; the patient recovery degree data is used to represent the patient's recovery status.

[0033] Furthermore, the analysis module is further configured to analyze the movement trend data according to the actual movement time and the standard movement time; and analyze the movement standard data according to the actual movement posture and the standard rehabilitation movement posture, including:

[0034] Based on the actual movement time corresponding to each standard rehabilitation movement posture, the single movement time consumed by the patient to perform the actual movement posture;

[0035] Corresponding to each standard rehabilitation action posture, calculating first time difference data between the single action time and the standard action time;

[0036] Calculate first average time difference data according to the first time difference data;

[0037] Determining a single rehabilitation time for each rehabilitation exercise performed by the patient based on the actual exercise time;

[0038] Determining a standard rehabilitation time for each rehabilitation exercise performed by the patient based on the standard exercise time and the patient rehabilitation exercise plan;

[0039] Calculate the second time difference data by calculating the single recovery time and the standard recovery time;

[0040] Calculate second average time difference data according to the second time difference data;

[0041] The motion trend data is analyzed according to the first average time difference data and the second average time difference data.

[0042] Furthermore, the analysis module is further configured to analyze the movement trend data according to the actual movement time and the standard movement time; and analyze the movement standard data according to the actual movement posture and the standard rehabilitation movement posture, including:

[0043] Determine the average movement time for the patient to perform each standard rehabilitation action posture based on the actual movement time;

[0044] Calculate first standard degree data according to the average exercise time and the standard exercise time;

[0045] Determining similarity data between each of the actual movement postures and the corresponding standard rehabilitation movement posture;

[0046] Calculating second standard data; the second standard data is average similarity data of all actual motion postures;

[0047] The action standard data is analyzed based on the first standard data and the second standard data.

[0048] Furthermore, the calculation module is further configured such that the calculation method of the patient recovery degree data includes:

[0049] R=M×K1+S×K2

[0050] Wherein, R is the patient's recovery degree data, M is the movement trend data, S is the movement standard data; K1 and K2 are the preset first weight and the preset second weight respectively.

[0051] Furthermore, the calculation module is further configured as follows: K1+K2=1.

[0052] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0054] Figure 1 A flow chart of a method for determining a motion state based on a data analysis model in an embodiment of the present application is shown;

[0055] Figure 2 A block diagram of a system for determining motion status based on a data analysis model in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0058] The present application provides a method and system for determining exercise status based on a data analysis model, which can help patients better complete rehabilitation exercises and promote the recovery of patients' physical functions.

[0059] In a first aspect, the present application provides a method for determining a motion state based on a data analysis model. Figure 1 The specific steps included in the method are as follows.

[0060] Step S110: Acquire the patient's motion data and patient rehabilitation exercise plan from the cloud platform; the patient's motion data includes the patient's motion time and the patient's motion posture; the patient's rehabilitation exercise plan includes the standard number of exercises, standard sequence of exercises and standard time for standard rehabilitation postures; the standard number of exercises includes the standard number of exercise groups for each standard rehabilitation posture performed by the patient and the number of standard exercises included in each standard number of exercise groups; the standard exercise time represents the exercise time spent on performing a standard rehabilitation posture.

[0061] It is understandable that the patient movement data stored in the cloud platform carries patient tags, such as patient name, patient bed number, and other tags that can indicate the patient's identity; based on the patient tags and the rehabilitation exercise plan pre-stored in the cloud platform, the rehabilitation exercise plan corresponding to the patient can be found; in the rehabilitation exercise plan, the specific plan for the patient to perform rehabilitation exercises is marked, such as the patient needs to do three sets of squats, ten in each set, and the standard time is 15 seconds for one squat, etc.; it should be noted that the patient movement time and the patient's movement posture are based on the data collected by the sensor; therefore, the patient's movement time will correspond to each patient's movement posture; when the patient's movement posture changes, the patient's movement time will mark a node; therefore, based on the patient's movement time and the patient's movement posture, the patient's performance in the rehabilitation exercise process can be reflected.

[0062] It can be understood that different standard rehabilitation postures contain motion features of different dimensions. Motion feature refers to the sensor detection data characterized by the patient's movement. For example, if the patient is jogging, the position sensor will output detection data. One of the motion feature quantities contained in the jogging posture is the position data. The motion feature quantity is the patient's motion data actually uploaded to the cloud platform. When analyzing the patient's posture, based on the established standard motion feature quantity for each motion posture, the motion feature quantity in the actual patient motion data is matched to determine each motion posture of the patient and the exercise time corresponding to each motion posture.

[0063] Step S120: Based on the patient rehabilitation exercise plan, the patient exercise data is screened to obtain the actual exercise time and the actual exercise posture; the actual exercise posture is a patient exercise posture whose similarity with the standard rehabilitation movement posture is not less than a preset similarity threshold; the actual exercise time is the patient exercise time consumed in executing the actual exercise posture.

[0064] It is understandable that in order to analyze whether the patient's rehabilitation movements and postures are standard during the rehabilitation exercise, thereby reflecting the patient's attitude towards rehabilitation exercises and the help that rehabilitation exercises bring to the patient's physical recovery, it is necessary to screen the patient's movement data corresponding to each standard healthy movement posture; for patients in actual rehabilitation exercises, their movements are not standard due to various reasons, but their body movement trends during exercise should be the same as those of standard healthy movement postures; for example, in the standard healthy movement posture, when squatting, the six-axis sensor will have acceleration in the specified direction. Similarly, when the patient squats in actual exercise, there will also be corresponding acceleration data; the similarity between the two can be obtained by calculating the ratio of the actual acceleration data to the standard acceleration data.

[0065] Step S130: analyzing the movement trend data according to the actual movement time and the standard movement time; analyzing the movement standardization data according to the actual movement posture and the standard rehabilitation movement posture; the movement trend data is associated with the actual movement time; and the movement standardization data is associated with the actual movement posture.

[0066] In an embodiment of the present application, the motion trend data is analyzed according to the actual motion time and the standard motion time; the motion standard data is analyzed according to the actual motion posture and the standard rehabilitation action posture, specifically including: based on the actual motion time corresponding to each standard rehabilitation action posture, the single action time consumed by the patient to perform the actual motion posture; corresponding to each standard rehabilitation action posture, calculating the first time difference data of the single action time and the standard motion time; calculating the first average time difference data according to the first time difference data; determining the single rehabilitation time for each rehabilitation exercise performed by the patient based on the actual motion time; determining the standard rehabilitation time for each rehabilitation exercise performed by the patient based on the standard motion time and the patient's rehabilitation exercise plan; calculating the second time difference data by calculating the single rehabilitation time and the standard rehabilitation time; calculating the second average time difference data according to the second time difference data; analyzing the motion trend data according to the first average time difference data and the second average time difference data.

[0067] It can be understood that by analyzing the difference between the actual time consumed by the patient and the standard time when performing each standard rehabilitation posture, and then calculating the first average time difference data, the patient's rehabilitation status when performing each action can be reflected; then for the overall rehabilitation exercise, the patient's total time is compared with the standard time to calculate the second average time difference; these two sets of data can reflect the patient's rehabilitation status from a time perspective; in this solution, the above-mentioned differences are all calculated in the form of negative numbers. Whether the actual time is greater than the standard time or less than the standard time, it indicates that there are certain problems with the patient's rehabilitation exercise. Therefore, the exercise trend data here is to characterize the negative impact brought about by the patient's failure to meet the standards in actual exercise; specifically, the exercise trend data = first average time difference data * 50% + second average time difference data * 50%.

[0068] Furthermore, based on the actual movement time, the average movement time of the patient to perform each standard rehabilitation movement posture is determined; the first standard data is calculated according to the average movement time and the standard movement time; the similarity data between each actual movement posture and the corresponding standard rehabilitation movement posture is determined; the second standard data is calculated; the second standard data is the average similarity data of all actual movement postures; the movement standard data is analyzed according to the first standard data and the second standard data.

[0069] It can be understood that when calculating the above similarity, the TensorFlow open source PoseNet model can be used to analyze the similarity of each posture, and then the average value can be calculated to obtain the average similarity data; the difference between the average movement time and the standard movement time is obtained by calculation, and the difference represents the standard degree of movement time of one of the standard rehabilitation movement postures; the first standard degree data can be obtained by summing the difference of each standard rehabilitation movement posture and then calculating the average value; the movement standard degree data here = first standard degree data * second standard degree data; it should be noted that the movement standard degree data here participates in subsequent calculations as a negative value; since the difference represents a deviation in the patient's movement, this value has a negative impact on the patient's rehabilitation.

[0070] Step S140: calculating the patient's rehabilitation degree data according to the motion trend data and the action standard degree data; the patient's rehabilitation degree data is used to represent the patient's rehabilitation status.

[0071] In the embodiment of the present application, the method for calculating the patient recovery degree data specifically includes:

[0072] R=M×K1+S×K2

[0073] Wherein, R is the patient's recovery degree data, M is the movement trend data, and S is the movement standard data; K1 and K2 are the preset first weight and the preset second weight respectively; wherein, K1+K2=1.

[0074] It is understandable that the final rehabilitation degree data is a negative value, and the larger the value, the smaller the deviation, that is, the patient's recovery trend is good; the smaller the value, the larger the deviation, that is, the patient's recovery trend is poor, and the specific rehabilitation plan, rehabilitation movements, etc. need to be adjusted.

[0075] In this scheme, K1 and K2 are taken as 0.5 and 0.5 respectively.

[0076] It can be understood that this program is actually a machine learning model. Through the analysis of the patient's motion data, the patient's movement status is determined, the patient's rehabilitation status is reflected based on the patient's rehabilitation degree data, and the patient's rehabilitation plan is periodically and adaptively adjusted according to the deviation of the rehabilitation results, to help patients better complete rehabilitation training and promote the recovery of patients' physical functions.

[0077] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0078] In a second aspect, the present application provides a system for determining motion state based on a data analysis model. Figure 2As shown, the system includes an acquisition module 210, which is used to acquire patient motion data and patient rehabilitation exercise plans on a cloud platform; the patient motion data includes patient motion time and patient motion posture; the patient rehabilitation exercise plan includes a standard number of exercises, a standard sequence of exercises and a standard motion time for standard rehabilitation action postures; the standard number of exercises includes the number of standard exercise groups for each standard rehabilitation action posture performed by the patient and the number of standard exercises included in each standard exercise group; the standard exercise time represents the exercise time spent on performing a standard rehabilitation action posture; a screening module 220 is used to screen the patient motion data based on the patient rehabilitation exercise plan to obtain actual exercise time and actual exercise posture; the actual The actual motion posture is a patient motion posture whose similarity with the standard rehabilitation motion posture is not less than a preset similarity threshold; the actual motion time is the patient motion time consumed in executing the actual motion posture; the analysis module 230 is used to analyze the motion trend data according to the actual motion time and the standard motion time; the motion standardization data is analyzed according to the actual motion posture and the standard rehabilitation motion posture; the motion trend data is associated with the actual motion time; the motion standardization data is associated with the actual motion posture; the calculation module 240 is used to calculate the patient rehabilitation degree data according to the motion trend data and the motion standardization data; the patient rehabilitation degree data is used to represent the patient's rehabilitation status.

[0079] The analysis module 230 is further configured to analyze the movement trend data according to the actual movement time and the standard movement time; analyze the movement standard data according to the actual movement posture and the standard rehabilitation movement posture, including, based on the actual movement time corresponding to each standard rehabilitation movement posture, the single movement time consumed by the patient to perform the actual movement posture; corresponding to each standard rehabilitation movement posture, calculate the first time difference data of the single movement time and the standard movement time; calculate the first average time difference data according to the first time difference data; determine the single rehabilitation time for each rehabilitation exercise performed by the patient based on the actual movement time; determine the standard rehabilitation time for each rehabilitation exercise performed by the patient based on the standard movement time and the patient's rehabilitation exercise plan Complex time; calculate the second time difference data by calculating the single rehabilitation time and the standard rehabilitation time; calculate the second average time difference data according to the second time difference data; analyze the motion trend data according to the first average time difference data and the second average time difference data; determine the average motion time for the patient to perform each standard rehabilitation action posture based on the actual motion time; calculate the first standard degree data according to the average motion time and the standard motion time; determine the similarity data between each actual motion posture and the corresponding standard rehabilitation action posture; calculate the second standard degree data; the second standard degree data is the average similarity data of all actual motion postures; analyze the motion standard degree data according to the first standard degree data and the second standard degree data.

[0080] The calculation module 240 is further configured to calculate the patient recovery degree data by:

[0081] R=M×K1+S×K2

[0082] Wherein, R is the patient's recovery degree data, M is the movement trend data, and S is the movement standard data; K1 and K2 are the preset first weight and the preset second weight respectively; wherein, K1+K2=1.

[0083] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described device can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0084] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A method for determining motion state based on a data analysis model, characterized in that: include: Acquire patient motion data and patient rehabilitation exercise plans on the cloud platform; the patient motion data includes patient motion time and patient motion posture; the patient rehabilitation exercise plan includes standard motion quantity, standard motion sequence and standard motion time for standard rehabilitation motion postures; the standard motion quantity includes the standard motion group number of each standard rehabilitation motion posture performed by the patient and the standard motion number included in each standard motion group number; the standard motion time represents the motion time spent on performing a standard rehabilitation motion posture; Based on the patient rehabilitation exercise plan, the patient's exercise data is screened to obtain actual exercise time and actual exercise posture; The actual movement posture is a patient movement posture whose similarity to the standard rehabilitation movement posture is not less than a preset similarity threshold; The actual movement time is the patient's movement time consumed in performing the actual movement posture; Analyzing the exercise trend data according to the actual exercise time and the standard exercise time; Analyze the movement standard degree data according to the actual movement posture and the standard rehabilitation movement posture; the movement trend data is associated with the actual movement time; The action standard data is associated with the actual movement posture; Calculating patient rehabilitation degree data according to the motion trend data and the action standard degree data; The patient recovery degree data is used to indicate the patient's recovery status.

2. The method for determining motion state based on a data analysis model according to claim 1, characterized in that: analyzing the exercise trend data according to the actual exercise time and the standard exercise time; Analyzing the movement standard data according to the actual movement posture and the standard rehabilitation movement posture includes: Based on the actual movement time corresponding to each standard rehabilitation movement posture, the single movement time consumed by the patient to perform the actual movement posture; Corresponding to each standard rehabilitation action posture, calculating first time difference data between the single action time and the standard action time; Calculate first average time difference data according to the first time difference data; Determining a single rehabilitation time for each rehabilitation exercise performed by the patient based on the actual exercise time; Determining a standard rehabilitation time for each rehabilitation exercise performed by the patient based on the standard exercise time and the patient rehabilitation exercise plan; Calculate the second time difference data by calculating the single recovery time and the standard recovery time; Calculate second average time difference data according to the second time difference data; The motion trend data is analyzed according to the first average time difference data and the second average time difference data.

3. The method for determining motion state based on a data analysis model according to claim 2, characterized in that: analyzing the exercise trend data according to the actual exercise time and the standard exercise time; Analyzing the movement standard data according to the actual movement posture and the standard rehabilitation movement posture includes: Determine the average movement time for the patient to perform each standard rehabilitation action posture based on the actual movement time; Calculate first standard degree data according to the average exercise time and the standard exercise time; Determining similarity data between each of the actual movement postures and the corresponding standard rehabilitation movement posture; Calculating second standard data; the second standard data is average similarity data of all actual motion postures; The action standard data is analyzed based on the first standard data and the second standard data.

4. The method for determining motion state based on a data analysis model according to claim 3, characterized in that: The method for calculating the patient's recovery degree data includes: R=M×K1+S×K2 Wherein, R is the patient's recovery degree data, M is the movement trend data, S is the movement standard data; K1 and K2 are the preset first weight and the preset second weight respectively.

5. The method for determining motion state based on a data analysis model according to claim 4, characterized in that: K1+K2=1.

6. A system for determining motion state based on a data analysis model, characterized in that: include: An acquisition module (210) is used to acquire patient movement data and patient rehabilitation movement plans from a cloud platform; the patient movement data includes patient movement time and patient movement posture; the patient rehabilitation movement plan includes a standard movement number, a standard movement sequence and a standard movement time for a standard rehabilitation movement posture; the standard movement number includes a standard movement group number for each standard rehabilitation movement posture performed by the patient and a standard movement number included in each standard movement group number; the standard movement time represents the movement time spent on performing a standard rehabilitation movement posture; A screening module (220), configured to screen the patient's exercise data based on the patient's rehabilitation exercise plan to obtain actual exercise time and actual exercise posture; The actual movement posture is a patient movement posture whose similarity to the standard rehabilitation movement posture is not less than a preset similarity threshold; The actual movement time is the patient's movement time consumed in performing the actual movement posture; An analysis module (230), configured to analyze the exercise trend data according to the actual exercise time and the standard exercise time; Analyze the movement standard degree data according to the actual movement posture and the standard rehabilitation movement posture; the movement trend data is associated with the actual movement time; The action standard data is associated with the actual movement posture; A calculation module (240), used for calculating patient rehabilitation degree data according to the motion trend data and the action standard degree data; The patient recovery degree data is used to indicate the patient's recovery status.

7. The system for determining motion state based on a data analysis model according to claim 6, characterized in that: The analysis module (230) is further configured to analyze the exercise trend data according to the actual exercise time and the standard exercise time; Analyzing the movement standard data according to the actual movement posture and the standard rehabilitation movement posture includes: Based on the actual movement time corresponding to each standard rehabilitation movement posture, the single movement time consumed by the patient to perform the actual movement posture; Corresponding to each standard rehabilitation action posture, calculating first time difference data between the single action time and the standard action time; Calculate first average time difference data according to the first time difference data; Determining a single rehabilitation time for each rehabilitation exercise performed by the patient based on the actual exercise time; Determining a standard rehabilitation time for each rehabilitation exercise performed by the patient based on the standard exercise time and the patient rehabilitation exercise plan; Calculate the second time difference data by calculating the single recovery time and the standard recovery time; Calculate second average time difference data according to the second time difference data; The motion trend data is analyzed according to the first average time difference data and the second average time difference data.

8. The system for determining motion state based on a data analysis model according to claim 7, characterized in that: The analysis module (230) is further configured to analyze the exercise trend data according to the actual exercise time and the standard exercise time; Analyzing the movement standard data according to the actual movement posture and the standard rehabilitation movement posture includes: Determine the average movement time for the patient to perform each standard rehabilitation action posture based on the actual movement time; Calculate first standard degree data according to the average exercise time and the standard exercise time; Determining similarity data between each of the actual movement postures and the corresponding standard rehabilitation movement posture; Calculating second standard data; the second standard data is average similarity data of all actual motion postures; The action standard data is analyzed based on the first standard data and the second standard data.

9. The system for determining motion state based on a data analysis model according to claim 8, characterized in that: The calculation module (240) is further configured such that the method for calculating the patient recovery degree data includes: R=M×K1+S×K2 Wherein, R is the patient's recovery degree data, M is the movement trend data, S is the movement standard data; K1 and K2 are the preset first weight and the preset second weight respectively.

10. The system for determining motion state based on a data analysis model according to claim 9, characterized in that: The calculation module (240) is further configured such that K1+K2=1.

Images