Intelligent system and method for matching and selecting female runner equipment

Abstract

The invention relates to the technical field of running equipment matching and selection, in particular to an intelligent system and method for female runner equipment matching and selection, and the system comprises a data collection module, a data processing module, a data analysis module, a data transmission module, a data storage module and a control management module. By analyzing and processing various data, the running state of a user can be conveniently and comprehensively known, and a personalized running plan and a running equipment matching and selecting scheme are appointed for the user, so that the running plan and the running equipment matching and selecting scheme are more suitable for the user; different data are analyzed and processed through multiple neural networks, and then plans and schemes are customized, so that the analysis efficiency and precision of the data are improved; through extraction of data features, data sharing is realized, continuous learning of a neural network is realized, and protection of user privacy is also realized.

Description

Technical Field

[0001] This invention relates to the technical field of running equipment selection, and in particular to an intelligent system and method for selecting equipment for female runners. Background Technology

[0002] Running is a simple and efficient aerobic exercise that can improve people's cardiopulmonary function and burn a lot of calories to achieve weight loss. However, improper running arrangements and inappropriate running equipment can cause burdens and even injuries. Therefore, people generally monitor their condition and maintain a suitable state by using invention patents such as the novel foot movement monitoring system disclosed in patent announcement number CN104490398B and the wireless control system for smart bracelets disclosed in patent announcement number CN119488274B.

[0003] However, existing monitoring systems are limited in function, only able to monitor during running. They are not capable of accurately customizing running plans and equipment selection schemes based on the female user's recent condition and running environment before running, as well as providing emergency measures. This results in poor practicality. Therefore, there is an urgent need for an intelligent system and method for selecting equipment for female runners to improve the above-mentioned problems. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides an intelligent system and method for selecting equipment for female runners. This system analyzes and processes various types of data to gain a comprehensive understanding of a user's running status, providing personalized running plans and equipment selection schemes that are more suitable for the user. Furthermore, it utilizes multiple neural networks to analyze and process different data before customizing plans and schemes, improving the efficiency and accuracy of data analysis. By extracting data features, it achieves both data sharing and continuous learning of neural networks, while also protecting user privacy.

[0005] The present invention provides an intelligent system for selecting equipment for female runners, comprising: Data acquisition module: Collects data on the user's running posture, foot pressure, breast movement, menstrual cycle, running route environment, geographical environment, and weather. Data processing module: preprocesses the collected data, aligns the data in time, performs noise reduction, and converts the images to grayscale to reduce the burden on the data analysis module. Data analysis module: Analyzes the processed data and customizes personalized running plans and running equipment selection schemes for users based on the analysis results; Data transmission module: Performs feature extraction processing on the data, transmits only the image data of the user's joint area to the cloud server, and transmits the complete data to the data storage module to protect the user's privacy; Data storage module: Classifies and stores the received data; Control and Management Module: Provides an interaction platform for users and the system, verifies user identities, and centrally manages the data acquisition module, data processing module, data analysis module, data transmission module, and data storage module.

[0006] Preferably, the data acquisition module includes: Running posture data acquisition unit: collects the user's running posture data; Foot pressure data acquisition unit: collects static and dynamic pressure distribution data of the user's feet; Breast sway data acquisition unit: By attaching position sensors to different positions on the user's breasts, it collects breast sway data when the user is running; Menstrual cycle data collection unit: Users manually upload their own menstrual cycle data; Running route environment data acquisition unit: Users manually upload image data of their running route environment; Weather data collection unit: Collects weather data at the user's running location; Geographic environment data acquisition unit: Collects data on the user's location and altitude.

[0007] Preferably, the data processing module includes: Timestamp alignment unit: Time-aligns running posture data, breast swing data, and dynamic distribution data of foot pressure; Denoising processing unit: performs noise reduction processing on the collected data; Grayscale processing unit: Performs grayscale processing on image data, reducing the burden on the data analysis module and improving the analysis efficiency of the data analysis module.

[0008] Preferably, the data analysis module includes: 3D Convolutional Neural Network: Analyzes the user's running posture to determine whether the user's running posture is correct; Spatiotemporal graph neural network: Analyzes the static and dynamic pressure distribution of a user's foot; Long Short-Term Memory Network: Analyzing changes in a user's breasts while running; Convolutional Neural Network: Analyzes images of the running route environment to predict potential dangers while running in that environment; Recurrent Neural Networks: Based on the analysis results of 3D convolutional neural networks, spatiotemporal graph neural networks, long short-term memory networks, and convolutional neural networks, as well as the physiological data uploaded by users and the acquired weather and geographical environment data, suitable running programs are customized for users, bad postures during running are corrected, and running equipment selection programs are customized for users. At the same time, based on the analysis and processing of potential dangerous situations, emergency measures are customized to ensure that users can exercise safely, comfortably, and efficiently through running.

[0009] Preferably, the data transmission module includes: Feature extraction unit: Uses a convolutional neural network to extract joint positions from the image; Transmission Unit: Transmits the extracted image data of the user's joint positions to the cloud server, so that the cloud service can optimize the neural network based on the image data uploaded by different users, and transmits the completed image to the data storage module for local storage.

[0010] Preferably, the control management module includes: Classification unit: Classifies the received data; Management Unit: Adjusts the data storage period and deletes data that has exceeded the storage period to ensure that the storage unit has sufficient storage space. Storage unit: Stores the categorized data.

[0011] Preferably, the control management module includes: Human-Computer Interaction Unit: Provides an interaction platform for users and the system, enabling users to operate the system and display data within the system; Authentication unit: Verifies the identity information of logged-in users to ensure the security of user information and the system; Centralized control unit: centrally manages the data acquisition module, data processing module, data analysis module, data transmission module, and data storage module.

[0012] Preferably, the running posture data acquisition unit acquires the user's running posture by using multiple cameras at different angles while the user is exercising on the treadmill.

[0013] Preferably, the foot pressure data acquisition unit uses an insole with a flexible pressure sensor array and a micro-airbag array. After the user wears the insole, an external air pump is connected to it through a hose. The flexible pressure sensor array acquires the pressure at different locations on the user's foot, and the pressure in the micro-airbags at different locations is adjusted according to the dynamic pressure changes on the user's foot until it is adjusted to a comfortable state for the user and suitable for running. This allows the data analysis module to recommend suitable insoles or running shoes to the user based on the final pressure distribution data acquired by the foot pressure data acquisition unit.

[0014] The present invention provides a method for selecting equipment for female runners, comprising the following steps: S1. Collect user running posture, foot pressure, breast movement, menstrual period, running route environment, geographical environment data and weather data through the data acquisition module; S2. The time stamp alignment unit performs time alignment on the running posture data, breast swing data, and dynamic distribution data of foot pressure. The noise reduction unit performs noise reduction on the collected data. The grayscale processing unit performs grayscale processing on the image data, thereby reducing the burden on the data analysis module and improving the analysis efficiency of the data analysis module. S3. Using a 3D convolutional neural network based on the MobileNetV3 architecture and model distillation technology, the system predicts joint angle errors to determine whether the user's running posture is correct. It also analyzes the static and dynamic pressure distribution of the user's feet using a spatiotemporal graph neural network, analyzes the changes in the user's breasts during running using a long short-term memory network, and analyzes the environmental images of the running route using a convolutional neural network to predict the dangers that may occur when running in this environment. S4. Based on the analysis results of 3D convolutional neural networks, spatiotemporal graph neural networks, long short-term memory networks, and convolutional neural networks, as well as the physiological data uploaded by users and the acquired weather and geographical environment data, the system customizes a suitable running plan for users, corrects bad postures during running, and customizes running equipment selection plans for users. At the same time, based on the analysis and processing of potential dangerous situations, the system customizes first aid measures to ensure that users can exercise safely, comfortably, and efficiently through running. S5. The human-computer interaction unit displays customized running plans, running equipment selection plans and first aid measures to the user, enabling the user to reasonably arrange running time and equip appropriate running equipment and first aid items according to the running equipment selection plan and first aid measures. S6. The feature extraction unit uses a convolutional neural network to extract the joint positions in the image. The extracted user joint position image data is transmitted to the cloud server through the transmission unit. This allows the cloud service to optimize the neural network based on the image data uploaded by different users. The completed image is then transmitted to the data storage module for local storage.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. By analyzing and processing various types of data, we can gain a comprehensive understanding of the user's running status and provide personalized running plans and equipment selection options to make them more suitable for the user. 2. By analyzing and processing different data through various neural networks, and then customizing plans and solutions, the efficiency and accuracy of data analysis can be improved; 3. By extracting data features, we can achieve both data sharing and continuous learning of neural networks, while also protecting user privacy. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the intelligent system for selecting equipment for female runners according to the present invention; Figure 2 This is a schematic diagram of the data acquisition module of the present invention; Figure 3 This is a schematic diagram of the data processing module of the present invention; Figure 4 This is a schematic diagram of the data analysis module of the present invention; Figure 5 This is a schematic diagram of the data transmission module of the present invention; Figure 6 This is a schematic diagram of the data storage module of the present invention; Figure 7 This is a schematic diagram of the control and management module of the present invention; Figure 8 This is a schematic diagram of the foot pressure data acquisition unit of the present invention; Figure 9 This is a schematic diagram of the running posture data acquisition unit of the present invention; Figure 10 This is a schematic diagram of the preparation process before using this invention; Figure 11 This is a flowchart illustrating the usage of this invention.

[0017] The attached diagram is labeled as follows: 1. Treadmill; 2. Camera; 11. Insole; 12. Micro-airbag; 13. Flexible pressure sensor. Detailed Implementation

[0018] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. The present invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0019] Example: Figures 1 to 11 As shown, an intelligent system for selecting equipment for female runners includes: Data acquisition module: Collects data on the user's running posture, foot pressure, breast movement, menstrual cycle, running route environment, geographical environment, and weather. Data processing module: preprocesses the collected data, aligns the data in time, performs noise reduction, and converts the images to grayscale to reduce the burden on the data analysis module. Data analysis module: Analyzes the processed data and customizes personalized running plans and running equipment selection schemes for users based on the analysis results; Data transmission module: Performs feature extraction processing on the data, transmits only the image data of the user's joint area to the cloud server, and transmits the complete data to the data storage module to protect the user's privacy; Data storage module: Classifies and stores the received data; Control and Management Module: Provides an interaction platform for users and the system, verifies user identities, and centrally manages the data acquisition module, data processing module, data analysis module, data transmission module, and data storage module; The data acquisition module includes: Running posture data acquisition unit: collects the user's running posture data; Foot pressure data acquisition unit: collects static and dynamic pressure distribution data of the user's feet; Breast sway data acquisition unit: By attaching position sensors to different positions on the user's breasts, it collects breast sway data when the user is running; Menstrual cycle data collection unit: Users manually upload their own menstrual cycle data; Running route environment data acquisition unit: Users manually upload image data of their running route environment; Weather data collection unit: Collects weather data at the user's running location; Geographic environment data acquisition unit: collects data on the user's location and altitude; The data processing module includes: Timestamp alignment unit: Time-aligns running posture data, breast swing data, and dynamic distribution data of foot pressure; Denoising processing unit: performs noise reduction processing on the collected data; Grayscale processing unit: Performs grayscale processing on image data, reducing the burden on the data analysis module and improving the analysis efficiency of the data analysis module; The data analysis module includes: 3D Convolutional Neural Network: Analyzes the user's running posture to determine whether the user's running posture is correct; Spatiotemporal graph neural network: Analyzes the static and dynamic pressure distribution of a user's foot; Long Short-Term Memory Network: Analyzing changes in a user's breasts while running; Convolutional Neural Network: Analyzes images of the running route environment to predict potential dangers while running in that environment; Recurrent Neural Network: Based on the analysis results of 3D convolutional neural networks, spatiotemporal graph neural networks, long short-term memory networks and convolutional neural networks, as well as the physiological data uploaded by users and the obtained weather and geographical environment data, a suitable running plan is customized for users, corrects bad postures used during running, and customizes running equipment selection plans for users. At the same time, according to the analysis and processing of possible dangerous situations, emergency measures are customized to ensure that users can exercise safely, comfortably and efficiently through running. The data transmission module includes: Feature extraction unit: Uses a convolutional neural network to extract joint positions from the image; Transmission unit: Transmits the extracted image data of user joint positions to the cloud server, so that the cloud service can optimize the neural network according to the image data uploaded by different users, and transmits the completed image to the data storage module for local storage; The control and management module includes: Classification unit: Classifies the received data; Management Unit: Adjusts the data storage period and deletes data that has exceeded the storage period to ensure that the storage unit has sufficient storage space. Storage unit: Stores the categorized data; The control and management module includes: Human-Computer Interaction Unit: Provides an interaction platform for users and the system, enabling users to operate the system and display data within the system; Authentication unit: Verifies the identity information of logged-in users to ensure the security of user information and the system; Centralized control unit: centrally manages the data acquisition module, data processing module, data analysis module, data transmission module, and data storage module; The running posture data acquisition unit acquires the user's running posture by using multiple cameras at different angles while the user is exercising on the treadmill. The foot pressure data acquisition unit uses an insole with a flexible pressure sensor array and a micro-airbag array.

[0020] A method for selecting equipment for female runners includes the following steps: S1. Collect user running posture, foot pressure, breast movement, menstrual period, running route environment, geographical environment data and weather data through the data acquisition module; S2. The time stamp alignment unit performs time alignment on the running posture data, breast swing data, and dynamic distribution data of foot pressure. The noise reduction unit performs noise reduction on the collected data. The grayscale processing unit performs grayscale processing on the image data, thereby reducing the burden on the data analysis module and improving the analysis efficiency of the data analysis module. S3. Using a 3D convolutional neural network based on the MobileNetV3 architecture and model distillation technology, the system predicts joint angle errors to determine whether the user's running posture is correct. It also analyzes the static and dynamic pressure distribution of the user's feet using a spatiotemporal graph neural network, analyzes the changes in the user's breasts during running using a long short-term memory network, and analyzes the environmental images of the running route using a convolutional neural network to predict the dangers that may occur when running in this environment. S4. Based on the analysis results of 3D convolutional neural networks, spatiotemporal graph neural networks, long short-term memory networks, and convolutional neural networks, as well as the physiological data uploaded by users and the acquired weather and geographical environment data, the system customizes a suitable running plan for users, corrects bad postures during running, and customizes running equipment selection plans for users. At the same time, based on the analysis and processing of potential dangerous situations, the system customizes first aid measures to ensure that users can exercise safely, comfortably, and efficiently through running. S5. The human-computer interaction unit displays customized running plans, running equipment selection plans and first aid measures to the user, enabling the user to reasonably arrange running time and equip appropriate running equipment and first aid items according to the running equipment selection plan and first aid measures. S6. The feature extraction unit uses a convolutional neural network to extract the joint positions in the image. The extracted user joint position image data is transmitted to the cloud server through the transmission unit. This allows the cloud service to optimize the neural network based on the image data uploaded by different users. The completed image is then transmitted to the data storage module for local storage.

[0021] The present invention discloses an intelligent system and method for selecting equipment for female runners. Its installation, connection, or setting methods are all common mechanical methods, and any method that can achieve its beneficial effect can be implemented. The flexible pressure sensor is located at the bottom of the micro-airbag. Technicians in the industry only need to install and operate it according to the accompanying instruction manual, without requiring any creative work from those skilled in the art.

[0022] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. An intelligent system for selecting equipment for female runners, characterized in that, include: Data acquisition module: Collects data on the user's running posture, foot pressure, breast movement, menstrual cycle, running route environment, geographical environment, and weather. Data processing module: preprocesses the collected data, aligns the data in time, performs noise reduction, and converts the images to grayscale to reduce the burden on the data analysis module. Data analysis module: Analyzes the processed data and customizes personalized running plans and running equipment selection schemes for users based on the analysis results; Data transmission module: Performs feature extraction processing on the data, transmits only the image data of the user's joint area to the cloud server, and transmits the complete data to the data storage module to protect the user's privacy; Data storage module: Classifies and stores the received data; Control and Management Module: Provides an interaction platform for users and the system, verifies user identities, and centrally manages the data acquisition module, data processing module, data analysis module, data transmission module, and data storage module.

2. The intelligent system for selecting equipment for female runners as described in claim 1, characterized in that, The data acquisition module includes: Running posture data acquisition unit: collects the user's running posture data; Foot pressure data acquisition unit: collects static and dynamic pressure distribution data of the user's feet; Breast sway data acquisition unit: By attaching position sensors to different positions on the user's breasts, it collects breast sway data when the user is running; Menstrual cycle data collection unit: Users manually upload their own menstrual cycle data; Running route environment data acquisition unit: Users manually upload image data of their running route environment; Weather data collection unit: Collects weather data at the user's running location; Geographic environment data acquisition unit: Collects data on the user's location and altitude.

3. The intelligent system for selecting equipment for female runners as described in claim 1, characterized in that, The data processing module includes: Timestamp alignment unit: Time-aligns running posture data, breast swing data, and dynamic distribution data of foot pressure; Denoising processing unit: performs noise reduction processing on the collected data; Grayscale processing unit: Performs grayscale processing on image data, reducing the burden on the data analysis module and improving the analysis efficiency of the data analysis module.

4. The intelligent system for selecting equipment for female runners as described in claim 1, characterized in that, The data analysis module includes: 3D Convolutional Neural Network: Analyzes the user's running posture to determine whether the user's running posture is correct; Spatiotemporal graph neural network: Analyzes the static and dynamic pressure distribution of a user's foot; Long Short-Term Memory Network: Analyzing changes in a user's breasts while running; Convolutional Neural Network: Analyzes images of the running route environment to predict potential dangers while running in that environment; Recurrent Neural Networks: Based on the analysis results of 3D convolutional neural networks, spatiotemporal graph neural networks, long short-term memory networks, and convolutional neural networks, as well as the physiological data uploaded by users and the acquired weather and geographical environment data, suitable running programs are customized for users, bad postures during running are corrected, and running equipment selection programs are customized for users. At the same time, based on the analysis and processing of potential dangerous situations, emergency measures are customized to ensure that users can exercise safely, comfortably, and efficiently through running.

5. The intelligent system for selecting equipment for female runners as described in claim 1, characterized in that, The data transmission module includes: Feature extraction unit: Uses a convolutional neural network to extract joint positions from the image; Transmission Unit: Transmits the extracted image data of the user's joint positions to the cloud server, so that the cloud service can optimize the neural network based on the image data uploaded by different users, and transmits the completed image to the data storage module for local storage.

6. The intelligent system for selecting equipment for female runners as described in claim 1, characterized in that, The control and management module includes: Classification unit: Classifies the received data; Management Unit: Adjusts the data storage period and deletes data that has exceeded the storage period to ensure that the storage unit has sufficient storage space. Storage unit: Stores the categorized data.

7. The intelligent system for selecting equipment for female runners as described in claim 1, characterized in that, The control and management module includes: Human-Computer Interaction Unit: Provides an interaction platform for users and the system, enabling users to operate the system and display data within the system; Authentication unit: Verifies the identity information of logged-in users to ensure the security of user information and the system; Centralized control unit: centrally manages the data acquisition module, data processing module, data analysis module, data transmission module, and data storage module.

8. The intelligent system for selecting equipment for female runners as described in claim 2, characterized in that, The running posture data acquisition unit uses multiple cameras at different angles to capture the user's running posture while the user is exercising on the treadmill.

9. The intelligent system for selecting equipment for female runners as described in claim 2, characterized in that, The foot pressure data acquisition unit uses an insole with a flexible pressure sensor array and a micro-airbag array.

10. A method for selecting equipment for female runners, characterized in that, Includes the following steps: S1. Collect user running posture, foot pressure, breast movement, menstrual period, running route environment, geographical environment data and weather data through the data acquisition module; S2. The time stamp alignment unit performs time alignment on the running posture data, breast swing data, and dynamic distribution data of foot pressure. The noise reduction unit performs noise reduction on the collected data. The grayscale processing unit performs grayscale processing on the image data, thereby reducing the burden on the data analysis module and improving the analysis efficiency of the data analysis module. S3. Using a 3D convolutional neural network based on the MobileNetV3 architecture and model distillation technology, the system predicts joint angle errors to determine whether the user's running posture is correct. It also analyzes the static and dynamic pressure distribution of the user's feet using a spatiotemporal graph neural network, analyzes the changes in the user's breasts during running using a long short-term memory network, and analyzes the environmental images of the running route using a convolutional neural network to predict the dangers that may occur when running in this environment. S4. Based on the analysis results of 3D convolutional neural networks, spatiotemporal graph neural networks, long short-term memory networks, and convolutional neural networks, as well as the physiological data uploaded by users and the acquired weather and geographical environment data, the system customizes a suitable running plan for users, corrects bad postures during running, and customizes running equipment selection plans for users. At the same time, based on the analysis and processing of potential dangerous situations, the system customizes first aid measures to ensure that users can exercise safely, comfortably, and efficiently through running. S5. The human-computer interaction unit displays customized running plans, running equipment selection plans and first aid measures to the user, enabling the user to reasonably arrange running time and equip appropriate running equipment and first aid items according to the running equipment selection plan and first aid measures. S6. The feature extraction unit uses a convolutional neural network to extract the joint positions in the image. The extracted user joint position image data is transmitted to the cloud server through the transmission unit. This allows the cloud service to optimize the neural network based on the image data uploaded by different users. The completed image is then transmitted to the data storage module for local storage.

Images