Gait difference identification method and system based on multi-integration of internal and external factors
Through the gait difference identification method of internal and external factors fusion, the problem that gait analysis in the existing technology is not suitable for multiple groups of users, and effective evaluation and gait correction for multiple groups of users are achieved It is recommended to improve the universality of the system and the user scope.
Patent Information
- Application Number
- CN202410591594.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-14
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-05-14
AI Technical Summary
The existing gait analysis technology mainly judges a single individual, lacks universality, and is difficult to support the use of multiple groups of users. The calculation volume is large and the evaluation criteria are not universal.
Using the gait difference identification method based on the multi-fusion of internal and external factors, by collecting personal gait data and user data, the height-step-length scale factor and BMI index are generated, the user group is divided, the group proportion factor and average step frequency are calculated, and the impact is generated. The coefficients are corrected to generate gait index, and gait differences are identified and corrective suggestions are provided.
It improves the universality of the system, is suitable for multiple groups of users, reduces the amount of data collected by a single user, supports multiple groups of users, and provides personalized gait correction suggestions to reduce the impact of bad gait on the body.
Smart Images

Figure CN118490213B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of gait difference recognition methods, and specifically to a gait difference recognition method and system based on multi-factor fusion of internal and external factors. Background Art
[0002] Gait analysis is recognized as an effective evaluation method in the field of human movement research, which can objectify movement behavior. Through gait detection, it is possible to analyze whether the human body's indicators are within the normal range and avoid the impact of bad gait on the human body. However, in the prior art, most of the human gait analysis is aimed at a single individual, and the judgment of its gait is also based on experience. However, due to the different body shapes of each person, even the same gait will cause different burdens on the body. Therefore, the judgment criteria are not universal and have low applicability.
[0003] For example, the gait detection method, electronic device, and storage medium disclosed in Chinese patent publication number CN117860237A can realize the gait detection of users, but it still belongs to the category of individual analysis. The gait problem is still judged by experience. When there are multiple groups of users, the amount of calculation will become very large, which is difficult to support multiple groups of users and is not universal.
[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention
[0005] The purpose of the present invention is to provide a gait difference identification method and system based on multi-factor fusion of internal and external factors to solve the problems raised in the above background technology.
[0006] To achieve the above object, the present invention provides the following technical solutions:
[0007] The gait difference identification method based on the multi-integration of internal and external factors includes the following specific steps:
[0008] S1: Collect personal gait data and user data of each user, and generate corresponding height-step length ratio factor and BMI index according to the personal gait data and user data;
[0009] S2: Users are divided into multiple user groups based on their BMI index. The individual gait data of all users in each user group together constitute the group gait data. The group proportion factor and group average step frequency of each user group are calculated based on the group gait data of each user group.
[0010] S3: generating a first influence coefficient according to the individual's height-step length ratio factor and the group ratio factor of the user group, and generating a second influence coefficient according to the individual average step frequency and the group average step frequency in the individual gait data;
[0011] S4: correcting the first influence coefficient and the second influence coefficient according to the age of each user, analyzing the corrected first influence coefficient and the second influence coefficient, and generating a gait index for each user;
[0012] S5: Identify the gait differences of the user according to the gait index of the user, and provide gait correction suggestions to the user according to the identification results.
[0013] Preferably, the personal gait data includes personal average step length and personal average step frequency, and the user data includes user weight, user height, and user age.
[0014] Preferably, the method of collecting the user's personal gait data and user data and generating the corresponding height-step length ratio factor and BMI index is:
[0015] Collect the user's real-time step length each time they swing their legs and leg swing interval , subscript Indicates the user ID in each user group. , superscript Indicates the number of collections. ;
[0016] According to the real-time step size and leg swing interval Calculate your average stride length and average leg swing interval , the calculation methods are:
[0017]
[0018]
[0019] Average cadence ;
[0020] Height-stride length scaling factor ,BMI index , where , Respectively represent the preset user height and user weight.
[0021] Preferably, users are divided into several groups according to the range of BMI index, and the group ratio factor is calculated. and the group average cadence , the calculation methods are:
[0022]
[0023]
[0024] Subscript The ID that indicates the user group.
[0025] Preferably, the first influence coefficient and the second influence coefficient are generated according to the group gait data and the individual gait data, and then according to the user's age Make corrections to obtain the corrected first influence coefficient and the second influence coefficient ,in:
[0026]
[0027]
[0028] According to the corrected first influence coefficient and the second influence coefficient Generating gait indices , .
[0029] Preferably, based on the user's BMI index Generate the corresponding identification interval , , Identification interval The upper and lower limits of are calculated as follows:
[0030]
[0031] In the formula is the preset coefficient threshold.
[0032] Preferably, the logic for identifying the gait difference of the user according to the gait index of the user is:
[0033] When the gait index When the user's stride length is short and the cadence is fast, it is suggested that the user increase the stride length and slow down the cadence to reduce joint wear;
[0034] When the gait index When the user's stride length and stride frequency are moderate, the user is advised to maintain the current gait;
[0035] When the gait index When the user's stride length is long and the step frequency is fast, it is recommended that the user shorten the stride length and slow down the step frequency to reduce muscle fatigue and joint wear.
[0036] A gait difference recognition system based on multi-integration of internal and external factors, wherein the recognition system adopts the above-mentioned recognition method, includes:
[0037] A sensor module, which is in communication with the data processing module and is used to collect the user's personal gait data during exercise;
[0038] A user data module, which is in communication with the data processing module and is used to collect user data preset by the user;
[0039] A data processing module, the data processing module is in communication with the data determination module, and is used to generate a gait index for each user based on multiple sets of personal gait data and user data, and send the generated gait index to the data determination module;
[0040] The data determination module is used to identify the user's gait index and generate gait correction suggestions based on the identification results. Compared with the prior art, the beneficial effects of the present invention are:
[0041] The present invention collects personal gait data and user data of users, divides user groups, obtains group gait data suitable for different user groups through a big data collection method, and then compares the personal gait data of users with the group gait data of user groups, thereby realizing the identification of user gait, and finally gives gait correction suggestions to users according to the identification results, so that users can adjust their gait according to the gait correction suggestions to reduce the impact of bad gait on the body. The present invention can be applicable to more different users, improves the universality of the system, and a single user needs to collect and calculate less data, can support multiple groups of users, and also improves the user surface of the system. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 It is a schematic diagram of the overall method flow of the present invention;
[0043] Figure 2 It is a schematic diagram of the module structure of the present invention. DETAILED DESCRIPTION
[0044] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.
[0045] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0046] Example:
[0047] See also Figure 1 , the present invention provides a technical solution:
[0048] The gait difference identification method based on the multi-integration of internal and external factors includes the following specific steps:
[0049] S1: Build a user platform and collect each user's personal gait data and user data. Personal gait data includes personal average stride length and personal average step frequency. User data includes user weight, user height, and user age. Generate corresponding height-step length ratio factor and BMI index based on personal gait data and user data. The height-step length ratio factor reflects the user's relative step length during exercise, which is generally around 0.35~0.45. The specific size is related to personal exercise habits. If the step length is too large, it is easy to cause muscle strain. If the step length is too short, in this case, when the step frequency is low, although the overall pace is slow, it is not easy to cause harm to the body. However, if a faster step frequency is used to maintain a certain overall pace, this gait can easily increase the burden on the knee and ankle joints. Long-term use of this gait can easily lead to excessive wear of the joints. The BMI index reflects the user's fatness or thinness. Since fat and thin people have different habits during exercise, identification can make the results more accurate by dividing user groups.
[0050] S2: Users are divided based on the BMI index. Users with a BMI index less than 18 are classified as thin users, users with a BMI index between 18 and 24 are classified as normal users, and users with a BMI index greater than 24 are classified as fat users. Group gait data for each user group is generated. The group gait data includes a group proportion factor and a group average step frequency. A first influence coefficient and a second influence coefficient are generated based on the group gait data and the individual gait data. A gait index is then generated based on the first influence coefficient and the second influence coefficient. By comparing the individual gait data with the group gait data corresponding to the user group, the user's gait during movement can be identified. Based on big data, it is determined whether the user's gait will affect the health of the body, so as to provide gait correction suggestions to the user.
[0051] S3: Identify the gait differences of the user according to the user's gait index, and provide gait correction suggestions to the user based on the identification results.
[0052] The method of collecting the user's personal gait data and user data and generating the corresponding height-step length ratio factor and BMI index is as follows:
[0053] Collect the user's real-time step length each time they swing their legs and leg swing interval , which can be achieved by placing motion sensors on the user's legs, or by interactively collecting data from portable smart devices with pedometer functions, such as mobile phones, smart watches, etc. Indicates the user ID in each user group. , superscript Indicates the number of collections. ;
[0054] According to the real-time step size and leg swing interval Calculate your average stride length and average leg swing interval , the calculation methods are:
[0055]
[0056]
[0057] Average cadence , height-step length scaling factor ,BMI index , where , They represent the preset user height and user weight respectively, which can be filled in by the user.
[0058] Divide users into several groups according to the range of BMI index and calculate the group ratio factor and the group average cadence , the calculation methods are:
[0059]
[0060]
[0061] Subscript Indicates the number of the user group, and then generates the first influence coefficient based on the group gait data and personal gait data and the second influence coefficient , and then according to the user's age Make corrections to obtain the corrected first influence coefficient and the second influence coefficient ,in:
[0062]
[0063]
[0064] According to the first influence coefficient and the second influence coefficient Generating gait indices , .
[0065] Among them, the first influence coefficient reflects the difference in height-step length ratio between a single user and a user group, and the second influence coefficient reflects the difference in step frequency between a single user and a user group. The greater the difference between the user's height-step length ratio and the user group's group ratio, the greater the absolute value of the first influence coefficient, and the positive or negative value of the first influence coefficient reflects whether the difference is larger or smaller. Similarly, the greater the difference between the user's personal average step frequency and the user group's group average step frequency, the greater the absolute value of the second influence coefficient, and its positive or negative value also reflects whether the difference is larger or smaller. The gait index reflects the overall difference between the two. It can be seen from the calculation formula of the gait index that taking the second influence coefficient as the power of the exponential function makes the impact on the gait index greater than the first influence coefficient. This is because when the step frequency is too fast, the wear and tear on the joints over time is irreversible, which is more serious and more harmful than muscle strain, so it also needs more attention. It is understandable that as the user's age increases, the differences in the same height-step length ratio factor and the differences in step frequency between individual users and user groups will cause more serious consequences. Older users are more likely to suffer from joint wear or muscle strain, so it is necessary to introduce the user's age to correct the first and second influence coefficients. Assuming that the first and second influence coefficients of two users are the same before correction, the gait index generated by the older user will be larger, and it will be more likely to exceed the corresponding identification interval. , thereby sending gait correction suggestions to them.
[0066] According to the user's BMI index Generate the corresponding identification interval , , Identification interval The upper and lower limits of are calculated as follows:
[0067]
[0068] In the formula is the preset coefficient threshold, from the identification interval It can be seen from the calculation formula of the upper and lower limits that the size of the upper and lower limits is inversely proportional to the BMI index. This is because when the weight increases, the burden on the body will also increase at the same step frequency. Therefore, it is necessary to dynamically adjust the recognition intervals of different users according to their BMI index to improve the recognition accuracy.
[0069] The logic of identifying the gait difference of users according to their gait index is:
[0070] When the gait index When the user's stride length is short and the cadence is fast, it is suggested that the user increase the stride length and slow down the cadence to reduce joint wear;
[0071] When the gait index When the user's stride length and stride frequency are moderate, the user is advised to maintain the current gait;
[0072] When the gait index When the user's stride length is long and the step frequency is fast, it is recommended that the user shorten the stride length and slow down the step frequency to reduce muscle fatigue and joint wear.
[0073] For example, in the same user group, user A weighs 50KG, the corresponding gait index is 5, and the identification interval is , which is just within the normal range. User B weighs 60KG, and the corresponding gait index is also 5. If the same identification interval is used as user A, user B will also be considered to be within the normal range. However, in fact, since user B weighs more, the burden on the body is greater when exercising with the same step frequency and step length, so the identification interval needs to be adjusted. Assume that the adjusted identification interval is , then user B will be considered to have a longer stride length and a faster cadence, and a reminder will be issued to the user, suggesting that he shorten his stride length and slow down his cadence to avoid muscle strain and reduce joint wear.
[0074] See also Figure 2 The present invention also provides a gait difference recognition system based on multi-factor fusion of internal and external factors, wherein the recognition system adopts the above-mentioned recognition method and comprises:
[0075] A sensor module, which is in communication with the data processing module and is used to collect the user's personal gait data during exercise;
[0076] A user data module, which is in communication with the data processing module and is used to collect user data preset by the user;
[0077] A data processing module, the data processing module is in communication with the data determination module, and is used to generate a gait index for each user based on multiple sets of personal gait data and user data, and send the generated gait index to the data determination module;
[0078] The data determination module is used to identify the user's gait index and generate gait correction suggestions based on the identification results.
[0079] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0080] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.
[0081] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0082] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.
Claims
1. Gait difference identification method based on multi-integration of internal and external factors, It is characterized in that The specific steps include: S1: Collect personal gait data and user data of each user, and generate corresponding height-step length ratio factor and BMI index according to the personal gait data and user data; The personal gait data includes personal average step length and personal average step frequency, and the user data includes user weight, user height, and user age; The method of collecting the user's personal gait data and user data and generating the corresponding height-step length ratio factor and BMI index is as follows: Collect the user's real-time step length each time they swing their legs and leg swing interval , subscript Indicates the user ID in each user group. , superscript Indicates the number of collections. ; According to the real-time step size and leg swing interval Calculate your average stride length and average leg swing interval , the calculation methods are: Average cadence ; Height-stride length scaling factor ,BMI index , where , Respectively represent the preset user height and user weight; S2: Users are divided into multiple user groups based on their BMI index. The individual gait data of all users in each user group together constitute the group gait data. The group proportion factor and group average step frequency of each user group are calculated based on the group gait data of each user group. Divide users into several groups according to the range of BMI index and calculate the group ratio factor and the group average cadence , the calculation methods are: Subscript The number representing the user group; S3: generating a first influence coefficient according to the individual's height-step length ratio factor and the group ratio factor of the user group, and generating a second influence coefficient according to the individual average step frequency and the group average step frequency in the individual gait data; S4: correcting the first influence coefficient and the second influence coefficient according to the age of each user, analyzing the corrected first influence coefficient and the second influence coefficient, and generating a gait index for each user; The first influence coefficient and the second influence coefficient are generated based on the group gait data and the individual gait data, and then based on the user's age Make corrections to obtain the corrected first influence coefficient and the second influence coefficient ,in: According to the corrected first influence coefficient and the second influence coefficient Generating gait index , ; S5: Identify the gait difference of the user according to the gait index of the user, and provide gait correction suggestions to the user according to the identification results; According to the user's BMI index Generate the corresponding identification interval , , Identification interval The upper and lower limits of are calculated as follows: In the formula is the preset coefficient threshold; The logic of identifying the gait difference of users according to their gait index is: When the gait index When the user's stride length is short and the cadence is fast, it is suggested that the user increase the stride length and slow down the cadence to reduce joint wear; When the gait index When the user's stride length and stride frequency are moderate, the user is advised to maintain the current gait; When the gait index When the user's stride length is long and the step frequency is fast, it is recommended that the user shorten the stride length and slow down the step frequency to reduce muscle fatigue and joint wear.
2. Gait difference recognition system based on multi-integration of internal and external factors, Features: The identification system adopts the identification method according to claim 1, comprising: A sensor module, which is in communication with the data processing module and is used to collect the user's personal gait data during exercise; A user data module, which is in communication with the data processing module and is used to collect user data preset by the user; A data processing module, the data processing module is in communication with the data determination module, and is used to generate a gait index for each user based on multiple sets of personal gait data and user data, and send the generated gait index to the data determination module; The data determination module is used to identify the user's gait index and generate gait correction suggestions based on the identification results.
