Intelligent swing car with user motion monitoring function and monitoring method

Abstract

The embodiment of the invention discloses an intelligent swing car with a user motion monitoring function and a monitoring method, and the intelligent swing car comprises a car frame, a rotating wheel rotationally arranged below the car frame, a motor, and a steering wheel connected with the front end of the car frame through a rotating shaft; wherein the frame is of a hollow structure and comprises an upper shell and a lower shell, and a containing cavity is formed after the upper shell and the lower shell are closed in a covering mode; according to the intelligent swing car, the operation mode matched with the current user is automatically matched through the intelligent judgment module, and the safety and the intelligent flexibility of the intelligent swing car operated by the user are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of twisting cars, and in particular to an intelligent twisting car with a user motion monitoring function and a monitoring method. Background Art

[0002] As a popular recreational sports tool for children and adults, the twisting car is deeply loved by the market because of its simple and easy operation and strong fun. However, the traditional twisting car has relatively simple functions and operation modes. It can only provide basic sliding functions and lacks safety monitoring of the user's exercise process. The safety needs to be improved. In addition, with the increasing attention paid to healthy exercise and the widespread application of technology in daily life, users' demand for intelligent sports equipment is also growing. At present, there is no intelligent twisting car on the market that can meet the functions of exercise monitoring and safety warning at the same time. Summary of the invention

[0003] In view of the defects in the prior art, the present invention provides an intelligent twisting car with a user motion monitoring function, which improves the safety and intelligence of the child user operating the twisting car. To achieve the above purpose, the present invention provides the following technical solutions: A smart twisting car with a user motion monitoring function comprises a frame, a rotating wheel rotatably arranged under the frame, a motor, and a steering wheel connected to the front end of the frame through a rotating shaft; wherein the frame is a hollow structure and comprises an upper shell and a lower shell, wherein the upper shell and the lower shell are covered to form a receiving cavity; the smart twisting car further comprises: Weighing sensor, used to collect the weight information of the current user; The central control module is used to receive the guardian user instruction A or the instruction B output by the intelligent judgment module, and execute the motion operation mode adapted to the current user based on the instruction A or the instruction B; wherein the guardian user instruction A is issued by the guardian mobile phone APP, and the guardian user instruction A has a higher priority than the instruction B output by the intelligent judgment module; The GPS positioning module is used to collect the current location information of the smart car in real time and send it to the central control module and the guardian user's mobile phone; A motion data collection module is used to collect the posture information of the current user operating the smart twisting car, and the posture information at least includes speed information, acceleration information, and angular velocity information; The intelligent judgment module is used to intelligently determine the adaptive operation mode according to the weight information of the current user and the posture information of the current user operating the intelligent twisting car, and generate a corresponding instruction B to send to the central control module.

[0004] Furthermore, the central control module, GPS positioning module, motion data acquisition module and intelligent judgment module are respectively arranged in the accommodating cavity; and the weighing sensor is arranged on the upper shell.

[0005] Further, the motion operation mode is divided into two levels of safety operation mode and normal operation mode; Among them, in the first level safety operation mode, the central control module controls the motor to achieve the first speed limit, the first exercise time limit and the first area restriction processing; the first area is the safety area set in advance by the guardian user, and the range of the safety area is a circular area with the guardian user's real-time mobile phone positioning position as the center and the first safety distance threshold as the radius; In the second level safety operation mode, the central control module controls the motor to achieve the second speed limit and the second movement duration limit processing.

[0006] Furthermore, when the smart twisting car exceeds the safety area, the central control module sends an alarm indication message to the guardian user's mobile phone and temporarily adjusts the speed limit value to half of the first speed limit to improve safety, and then adjusts it to the first speed limit after the smart twisting car is in the safety area.

[0007] Furthermore, the intelligent judgment module includes a deep learning model, a user data storage module and an instruction generation module.

[0008] Furthermore, the intelligent judgment module receives the weight information of the current user output by the weighing sensor and the posture information of the current user operating the intelligent twisting car output by the motion acquisition module; When the user weight information exceeds the first weight threshold, the instruction generation module of the intelligent judgment module directly generates a normal operation mode instruction; When the user weight information is lower than the first weight threshold, the intelligent judgment module identifies the current user through the deep learning model; when the deep learning model identifies the specific target user, the motion operation mode associated with the specific target user is matched, the current motion operation mode is determined based on the associated motion operation mode, and the corresponding instruction B is generated, and the instruction B is sent to the central control module; The motion operation mode associated with the specific target user is a motion operation mode previously used by the specific target user. When there are multiple motion operation modes previously used, the motion operation mode with the most number of uses or the motion operation mode used most recently is selected as the current motion operation mode. When the deep learning model fails to identify a specific target user, a default motion operation mode instruction is generated based on the current user weight information, wherein the first type of user matches the first level safety operation mode by default, and the second type of user matches the second level safety operation mode by default.

[0009] Furthermore, the intelligent judgment module selects a corresponding data sub-library based on the weight information of the current user to train the deep learning model; inputs the posture information of the current user operating the smart twisting car into the trained deep learning model for intelligent judgment to identify the specific target user; The deep learning model includes a user feature preprocessing module, a graph convolutional network (GCN) processing module, an LSTM network processing module, and a feature fusion and classification module; The user feature preprocessing module is used to construct a time series matrix of posture information, wherein each row of the time series matrix of posture information represents posture information within a time step, and each column represents a feature, which are velocity information, acceleration information and angular velocity information respectively; The graph convolutional network (GCN) processing module is used to treat the posture information in each time step as a node, build a graph structure, aggregate and update the node features through the graph convolutional network (GCN), and output the updated node feature matrix. H GCN ; LSTM network processing module, used to input the time series matrix of the posture information into the LSTM network, capture the time series features, and output: the hidden state of the LSTM H LSTM ; Feature fusion and classification module, used to receive the output feature matrix of GCN and LSTM H GCN and H LSTM , generate fusion features, and output user identification based on the softmax classifier.

[0010] Furthermore, the user data storage module is composed of two data sub-libraries, namely, a first data sub-library for storing historical motion data of the first category of users; and a second data sub-library for storing historical motion data of the second category of users; wherein the weights of the first category of users and the second category of users increase sequentially; and the above historical motion data includes user posture information of multiple users' historical operation of the smart twisting car.

[0011] Furthermore, the instruction generation module is further configured to generate a motion operation mode instruction matching a specific target user identifier when the user identifier output by the softmax classifier is a specific target user identifier.

[0012] Another object of the present invention is to provide a monitoring method for an intelligent twisting car with a user motion monitoring function, the method comprising, when a user operates the above-mentioned intelligent twisting car, sending an alarm information of the current user exceeding a safety range generated during the operation, as well as the current user location information and the current user's continuous operation time information of the twisting car to the guardian user's mobile phone.

[0013] In combination with all the above technical solutions, the present invention has the following advantages compared with the prior art: (1) A variety of safety operation modes are designed for different users. The first-level safety operation mode implements speed limits and area restrictions, which improves the safety performance of young children using tricycles. It sends alarm information when the child exceeds the safe area, making it easier for guardians to provide safety protection. The second-level safety operation mode is designed for older children and relaxes restrictions. It increases the convenience of operation while ensuring safety. The normal operation mode is designed for older children and adults and is not restricted in use.

[0014] (2) An intelligent judgment module based on deep learning is set up to identify the current user and accurately and quickly match the appropriate operation mode corresponding to him / her, thereby improving the intelligence of the twisting car.

[0015] (3) The deep learning model is based on GCN and LSTM, which combines the features of the two neural networks to achieve the accuracy and speed of identifying specific target users. On the one hand, GCN is good at processing graph structure data and can capture the association information between nodes; on the other hand, LSTM is good at processing sequence data and can capture long-term dependencies in time series. Combining the two can simultaneously utilize graph structure and time series information to improve the performance of deep learning models in identifying user identities.

[0016] (4) In practical applications, the deep learning model uses data from different databases to train the corresponding model according to the different weights of users, further improving the pertinence, accuracy and speed of the deep learning model in identifying user identities.

[0017] (5) Users can customize the relevant parameters in each operating mode through the mobile phone APP to improve the flexibility of the smart twist car.

[0018] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other purposes, features and advantages of the present invention will become more apparent by describing the embodiments of the present invention in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0020] Figure 1 It is a schematic structural diagram of a smart twisting car provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0021] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0022] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0023] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0024] It should also be understood that, in the embodiments of the present invention, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0025] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0026] The structural diagram of the intelligent twisting car with user motion monitoring function is shown in Figure 1 .like Figure 1 As shown, the present invention provides a smart twisting car with a user motion monitoring function, comprising a frame 1, a rotating wheel 2 rotatably arranged under the frame, a motor 3, and a steering wheel 4 connected to the front end of the frame through a rotating shaft. The motor 3 includes a magnet and a Hall sensor installed on the rotating wheel. The frame is a hollow structure and includes an upper shell 5 and a lower shell 6, and the upper shell and the lower shell are covered to form a receiving cavity 7; the smart twisting car also includes: Weighing sensor, used to collect the weight information of the current user; Preferably, the weighing sensor is arranged on the upper shell; with such arrangement, when the user rides the tricycle, the user directly contacts the upper shell, which can improve the weighing accuracy.

[0027] The central control module is used to receive the guardian user instruction A or the instruction B output by the intelligent judgment module, and execute the motion operation mode adapted to the current user based on the instruction A or the instruction B; wherein the guardian user instruction A is issued by the guardian's mobile phone APP, and the priority of the guardian user instruction A is higher than the instruction B output by the intelligent judgment module.

[0028] Preferably, the motion operation mode is divided into a two-level safety operation mode and a normal operation mode.

[0029] In the first level safety operation mode, the central control module controls the motor to achieve the first speed limit, the first exercise duration limit and the first area restriction processing; the first area is the safety area set in advance by the guardian user, and the range of the safety area is a circular area with the guardian user's real-time mobile phone positioning position as the center and the first safety distance threshold R1 (R1 supports user customization, the default setting is 20M) as the radius; when the smart twisting car exceeds the safety area, the central control module sends an alarm indication message to the guardian user's mobile phone, and temporarily adjusts the speed limit value to half of the first speed limit to improve safety. After the smart twisting car is in the safety area, it is adjusted to the first speed limit. The guardian user receives the alarm indication message and can move closer to the direction of the smart twisting car for easy monitoring to improve safety. As an example, the first speed limit defaults to 5KM / h, which supports user customization; the first exercise duration defaults to half an hour, which supports user customization; R1 defaults to 20M, which supports user customization.

[0030] Among them, in the second level safety operation mode, the central control module controls the motor to achieve the second speed limit and the second exercise duration limit processing. As an example, the second speed limit defaults to 10KM / h, which supports user customization; the second exercise duration defaults to 1 hour, which supports user customization. The second speed limit is greater than the first speed limit, and the second exercise duration is greater than the first exercise duration.

[0031] It should be noted that when the first exercise duration or the second exercise duration limit is reached, the central control module sends an overtime warning indication message to the guardian user's mobile phone, and implements the brake processing at the same time, and the current user can no longer use the smart twist car for a period of time (for example, the default half an hour or the default one hour). In this case, the guardian user resends instruction A or replaces a new operating user to use the smart twist car to lift the above restrictions.

[0032] It should be noted that in normal operation mode, the usage functions of the smart twist car are not restricted.

[0033] The GPS positioning module is used to collect the current location information of the smart car in real time and send it to the central control module and the guardian user's mobile phone.

[0034] It should be noted that such a design can facilitate the central control module to determine whether the smart tricycle is in a safe area based on the current location information of the smart tricycle and the current location information of the guardian user's mobile phone in the first level safety operation mode.

[0035] A motion data collection module is used to collect the posture information of the current user operating the smart twisting car, and the posture information at least includes speed information, acceleration information, and angular velocity information; Preferably, the motion data acquisition module is composed of a Hall sensor, an acceleration sensor, and an angular velocity sensor, which are responsible for real-time acquisition of speed information, acceleration information, and angular velocity information of the smart twisting car, respectively.

[0036] The intelligent judgment module is used to intelligently determine the adaptive operation mode according to the weight information of the current user and the posture information of the current user operating the intelligent twisting car, and generate a corresponding instruction B to send to the central control module.

[0037] Among them, the intelligent judgment module includes a deep learning model, a user data storage module and an instruction generation module.

[0038] The specific implementation process is as follows: the intelligent judgment module receives the weight information of the current user output by the weighing sensor and the posture information of the current user operating the intelligent twisting car output by the motion acquisition module; When the user weight information exceeds a first weight threshold (for example, the default is 20KG, which supports user customization. At this time, it can be considered that the current user is an older child or an adult and can operate the twisting car normally), the instruction generation module of the intelligent judgment module directly generates a normal operation mode instruction; When the user weight information is lower than the first weight threshold, the intelligent judgment module identifies the current user through the deep learning model; when the deep learning model identifies the specific target user, the motion operation mode associated with the specific target user is matched, the current motion operation mode is determined based on the associated motion operation mode, and the corresponding instruction B is generated, and the instruction B is sent to the central control module; The motion operation mode associated with the specific target user is a motion operation mode previously used by the specific target user. When there are multiple motion operation modes previously used, the motion operation mode with the most number of uses or the motion operation mode used most recently is selected as the current motion operation mode. When the deep learning model fails to identify a specific target user, a default motion operation mode instruction is generated based on the current user weight information, wherein the first type of user matches the first level safety operation mode by default, and the second type of user matches the second level safety operation mode by default.

[0039] Preferably, when the user weight information is lower than the first weight threshold, the intelligent judgment module selects a corresponding data sub-library based on the current user weight information to train the deep learning model; It should be noted that when the current user belongs to the first category of users, the corresponding data sub-database is the first data sub-database; when the current user belongs to the second category of users, the corresponding data sub-database is the second data sub-database. Such a design can greatly improve the matching speed and matching accuracy of the intelligent judgment module, while reducing the amount of calculation.

[0040] The posture information of the current user operating the smart twisting car is input into the trained deep learning model for intelligent judgment and identification of specific target users.

[0041] As an example, the deep learning model includes a user feature preprocessing module, a graph convolution network GCN processing module, an LSTM network processing module and a feature fusion and classification module; Among them, the user feature preprocessing module is used to construct a time series matrix of posture information, each row of the time series matrix of posture information represents posture information within a time step (for example, 1 second), and each column represents a feature, which are velocity information, acceleration information and angular velocity information respectively; preferably, the feature information of each posture information is normalized before constructing the time series matrix of the above-mentioned posture information.

[0042] The graph convolutional network (GCN) processing module is used to treat the posture information in each time step as a node, build a graph structure, aggregate and update the node features through the graph convolutional network (GCN), and output the updated node feature matrix. H GCN .

[0043] As an example, the GCN propagation rule is: ,in: It is l The node feature matrix of the layer, is the adjacency matrix plus the identity matrix, D is the degree matrix, is the ReLU function, is the weight matrix.

[0044] LSTM network processing module, used to input the time series matrix of the posture information into the LSTM network, capture the time series features, and output: the hidden state of the LSTM H LSTM .

[0045] As an example, the LSTM network includes a forget gate, an input gate, and an output gate. The relevant processing update formulas of the three parts are as follows: in, is the time series matrix of the posture information, It's the Gate of Forgetfulness. is the input gate, is the output gate, Represents the candidate state created by the tanh layer to be added to the unit at the current moment, Indicates the current state of the unit. Indicates the state of the unit at the previous moment, represents the output of the current unit, and represents the output of the unit at the previous moment, sigmoid and tanh is the activation function, is the weight vector, is the bias vector.

[0046] Feature fusion and classification module, used to receive the output feature matrix of GCN and LSTM H GCN and H LSTM , generate fusion features, and output user identification based on the softmax classifier.

[0047] Preferably, the user data storage module is composed of two data sub-libraries, namely, a first data sub-library for storing the historical motion data of the first category of users; and a second data sub-library for storing the historical motion data of the second category of users; wherein the weights of the first category of users and the second category of users increase in sequence; and the above historical motion data includes the user posture information of multiple users who have historically operated the smart twisting car. As an example, the weight ranges of the first category of users and the second category of users can be specifically set and adjusted as needed during specific implementation. For example, the factory default setting is that the weight of the first category of users is less than 15KG, corresponding to children under 3 years old, and the weight of the second category of users is greater than or equal to 15KG and less than 20KG, corresponding to children aged 3-6 years old. When the user weight is greater than 20KG, it can be considered to correspond to a child over 6 years old or an adult.

[0048] Preferably, the instruction generation module is further configured to generate a motion operation mode instruction matching a specific target user identifier when the user identifier output by the softmax classifier is a specific target user identifier.

[0049] It should be noted that, as a preferred embodiment, the central control module, GPS positioning module, motion data acquisition module and intelligent judgment module are respectively arranged in the accommodating cavity.

[0050] Accordingly, the present invention also provides a monitoring method for a smart twisting car with a user motion monitoring function, the method comprising, when a user operates the smart twisting car, sending the warning information of the current user exceeding the safety range generated during the operation, the current user location information, and the current user's continuous operation time information of the twisting car to the mobile phone of the guardian user. The continuous operation time information of the current user can be sent in real time, can be sent periodically, or can be sent when the limited time is reached, which is not limited here.

[0051] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0052] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the method embodiment, since it basically corresponds to the product embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the product embodiment.

[0053] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0054] The method and apparatus of the present disclosure may be implemented in many ways. For example, the method and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0055] It should also be noted that in the apparatus, equipment and method of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present disclosure. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present disclosure. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown here, but to the widest scope consistent with the principles and novel features disclosed herein.

[0056] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof. For example, scooters, baby cars, children's balance cars, yo-yo cars, sliding cars, scooters, etc. and their variations are all within the scope of protection of the smart twisting car of the present invention.

Claims

1. An intelligent twisting car with a user motion monitoring function, comprising a frame, a rotating wheel rotatably arranged under the frame, a motor, and a steering wheel connected to the front end of the frame through a rotating shaft; The frame is a hollow structure and includes an upper shell and a lower shell, and the upper shell and the lower shell are covered to form a receiving cavity; the characteristic is that: The smart twist car also includes: Weighing sensor, used to collect the weight information of the current user; The central control module is used to receive the guardian user instruction A or the instruction B output by the intelligent judgment module, and execute the motion operation mode adapted to the current user based on the instruction A or the instruction B; wherein the guardian user instruction A is issued by the guardian mobile phone APP, and the guardian user instruction A has a higher priority than the instruction B output by the intelligent judgment module; The GPS positioning module is used to collect the current location information of the smart car in real time and send it to the central control module and the guardian user's mobile phone; A motion data collection module is used to collect the posture information of the current user operating the smart twisting car, and the posture information at least includes speed information, acceleration information, and angular velocity information; The intelligent judgment module is used to intelligently determine the adaptive operation mode according to the weight information of the current user and the posture information of the current user operating the intelligent twisting car, and generate a corresponding instruction B to send to the central control module.

2. The smart twisting car with user motion monitoring function as claimed in claim 1, characterized in that: The central control module, GPS positioning module, motion data acquisition module and intelligent judgment module are respectively arranged in the accommodating cavity; the weighing sensor is arranged on the upper shell.

3. The smart twisting car with user motion monitoring function as claimed in claim 1, characterized in that: The motion operation mode is divided into two levels of safety operation mode and normal operation mode; Among them, in the first level safety operation mode, the central control module controls the motor to achieve the first speed limit, the first exercise time limit and the first area restriction processing; the first area is the safety area set in advance by the guardian user, and the range of the safety area is a circular area with the guardian user's real-time mobile phone positioning position as the center and the first safety distance threshold as the radius; In the second level safety operation mode, the central control module controls the motor to achieve the second speed limit and the second movement duration limit processing.

4. The smart twisting car with user motion monitoring function as claimed in claim 3, characterized in that: When the smart car goes beyond the safety zone, the central control module sends an alarm to the guardian user's mobile phone and temporarily adjusts the speed limit to half of the first speed limit to improve safety. The speed limit will be adjusted to the first speed limit after the smart car is in the safety zone.

5. The smart twisting car with user motion monitoring function as claimed in claim 1, characterized in that: The intelligent judgment module includes a deep learning model, a user data storage module and an instruction generation module.

6. The smart twisting car with user motion monitoring function as claimed in claim 5, characterized in that: The intelligent judgment module receives the weight information of the current user output by the weighing sensor and the posture information of the current user operating the intelligent twisting car output by the motion acquisition module; When the user weight information exceeds the first weight threshold, the instruction generation module of the intelligent judgment module directly generates a normal operation mode instruction; When the user weight information is lower than the first weight threshold, the intelligent judgment module identifies the current user through the deep learning model; when the deep learning model identifies the specific target user, the motion operation mode associated with the specific target user is matched, the current motion operation mode is determined based on the associated motion operation mode, and the corresponding instruction B is generated, and the instruction B is sent to the central control module; The motion operation mode associated with the specific target user is a motion operation mode previously used by the specific target user. When there are multiple motion operation modes previously used, the motion operation mode with the most number of uses or the motion operation mode used most recently is selected as the current motion operation mode. When the deep learning model fails to identify a specific target user, a default motion operation mode instruction is generated based on the current user weight information, wherein the first type of user matches the first level safety operation mode by default, and the second type of user matches the second level safety operation mode by default.

7. The smart twisting car with user motion monitoring function as claimed in claim 6, characterized in that: The intelligent judgment module selects the corresponding data sub-library based on the weight information of the current user to train the deep learning model; the posture information of the current user operating the smart twisting car is input into the trained deep learning model for intelligent judgment to identify the specific target user; The deep learning model includes a user feature preprocessing module, a graph convolutional network (GCN) processing module, an LSTM network processing module, and a feature fusion and classification module; The user feature preprocessing module is used to construct a time series matrix of posture information, wherein each row of the time series matrix of posture information represents posture information within a time step, and each column represents a feature, which are velocity information, acceleration information and angular velocity information respectively; The graph convolutional network (GCN) processing module is used to treat the posture information in each time step as a node, build a graph structure, aggregate and update the node features through the graph convolutional network (GCN), and output the updated node feature matrix. H GCN ; LSTM network processing module, used to input the time series matrix of the posture information into the LSTM network, capture the time series features, and output: the hidden state of the LSTM H LSTM ; Feature fusion and classification module, used to receive the output feature matrix of GCN and LSTM H GCN and H LSTM , generate fusion features, and output user identification based on the softmax classifier.

8. The smart twisting car with user motion monitoring function as claimed in claim 5, characterized in that: The user data storage module is composed of two data sub-libraries, namely, a first data sub-library for storing historical motion data of first-category users; and a second data sub-library for storing historical motion data of second-category users. The weights of the first-category users and the second-category users increase in sequence. The historical motion data includes user posture information of multiple users operating the smart twisting car in history.

9. The smart twisting car with user motion monitoring function as claimed in claim 7, characterized in that: The instruction generation module is further used to generate a motion operation mode instruction matching a specific target user identifier when the user identifier output by the softmax classifier is a specific target user identifier.

10. A monitoring method for a smart twisting car with a user motion monitoring function, characterized in that: When a user operates the smart twisting car as described in any one of claims 1 to 9, the warning information that the current user exceeds the safety range generated during the operation, the current user location information, and the continuous time information of the current user operating the twisting car are sent to the guardian user's mobile phone.

Images