Ebike intelligent man-machine interaction method and system based on Bluetooth Mesh networking

Abstract

The invention provides an ebike intelligent man-machine interaction method and an ebike intelligent man-machine interaction system based on Bluetooth Mesh networking. The method belongs to the technical field of intelligent transportation and Internet of Things. The method comprises the following steps: acquiring each functional module of an ebike and Bluetooth communication node information of intelligent equipment carried by a user; performing Mesh network topology structure analysis on the acquired Bluetooth communication node information, and constructing a Bluetooth Mesh network topology structure of an ebike use scene; according to the constructed Bluetooth Mesh network topology structure, performing network configuration and parameter setting on each node to form a complete ebike Bluetooth Mesh communication network; through a Bluetooth Mesh networking technology, an e-bike function module and intelligent equipment carried by a user are connected to form an efficient and stable communication network. The network has an ad-hoc network capability, a topological structure can be automatically adjusted according to increase and decrease of nodes, and the stability and the real-time performance of communication are ensured, so that the overall response speed and the interaction efficiency of the system are remarkably improved.

Description

TECHNICAL FIELD

[0001] The application provides an ebike intelligent human-computer interaction method and system based on Bluetooth Mesh networking, and belongs to the technical field of intelligent transportation and Internet of Things. BACKGROUND

[0002] With the increasing attention to healthy travel and green travel, ebike (electric bicycle) as a convenient and environmentally friendly means of transportation has been widely used. However, the traditional ebike has many deficiencies in human-computer interaction, such as single interaction mode, limited information display, and inability to realize multi-device collaborative control. Bluetooth Mesh networking technology has the advantages of low power consumption, self-organizing network, and multi-node communication, and its application in the intelligent human-computer interaction of ebike can effectively improve the use experience and intelligent level of ebike. However, there is no mature ebike intelligent human-computer interaction method based on Bluetooth Mesh networking at present, so it is necessary to develop a new method to solve the above problems. SUMMARY

[0003] The application provides an ebike intelligent human-computer interaction method and system based on Bluetooth Mesh networking, which solves the problems mentioned in the background technology:

[0004] The ebike intelligent human-computer interaction method based on Bluetooth Mesh networking provided by the application comprises the following steps:

[0005] S1, acquiring Bluetooth communication node information of each functional module of the ebike and a smart device carried by a user; performing Mesh network topology analysis on the acquired Bluetooth communication node information, constructing a Bluetooth Mesh network topology structure of the ebike use scenario; and performing network configuration and parameter setting on each node according to the constructed Bluetooth Mesh network topology structure, to form a complete ebike Bluetooth Mesh communication network;

[0006] S2, in the running process of the ebike, collecting data related to the ebike through each functional module and the smart device, preprocessing the collected data, and classifying the data according to different types; and performing feature extraction on the classified data;

[0007] S3, constructing a user intention recognition model by using a machine learning algorithm based on the extracted feature data; determining an interaction mode according to the recognized user intention, in combination with the functions of the ebike and the current use scenario;

[0008] S4, after determining the interaction mode, performing collaborative interaction between the ebike and each smart device through the Bluetooth Mesh network; and performing fusion processing on information from different devices;

[0009] S5、According to the actual use feedback of the user and the interaction effect, the user intention recognition model and the interaction strategy are continuously optimized;The communication quality of the Bluetooth Mesh network is regularly evaluated, and the network parameters are adjusted according to the evaluation results.

[0010] The ebike intelligent man-machine interaction system based on Bluetooth Mesh networking provided by the application comprises a memory, a processor, and a computer program stored on the memory and capable of running on the memory, and the processor executes the program to realize the ebike intelligent man-machine interaction method based on Bluetooth Mesh networking as described in any of the above.

[0011] The application has the following advantages: through Bluetooth Mesh networking technology, the function modules of e-bike (such as motor controller, battery management system, instrument panel, etc.) are connected with the smart devices (such as smart phones, smart watches) carried by the user to form an efficient and stable communication network. The network has self-organizing network capability, which can automatically adjust the topology according to the increase and decrease of nodes, ensure the stability and real-time of communication, and significantly improve the response speed and interaction efficiency of the whole system.

[0012] Through the multi-source data acquisition mechanism, multi-dimensional data including riding state, battery state, user physiological indicators and environmental trajectory are obtained, and pre-processing and feature extraction are performed, effectively removing noise and outliers, and improving data quality.

[0013] The user intention recognition model is trained using historical data, so that the system can accurately predict the user's potential intention (such as acceleration, deceleration, mode switching, information viewing, etc.) according to the current riding state, user physiological data and environmental information, and dynamically select the most appropriate interaction mode. This intelligent interaction mode improves user experience and reduces operational burden.

[0014] After determining the interaction mode, the system realizes the collaborative interaction between e-bike and multiple smart devices through Bluetooth Mesh network. At the same time, the information from different devices is fused (such as GPS trajectory and riding speed fusion, heart rate and riding state fusion), which further improves the integrity and accuracy of information, and helps to provide more personalized and accurate services.

[0015] The system has a feedback-driven optimization mechanism, which can continuously optimize the user intention recognition model and interaction strategy according to the actual use and interaction effect of the user;At the same time, the communication quality of the Bluetooth Mesh network is regularly evaluated, and the network parameters are dynamically adjusted to cope with environmental changes or device aging, etc., so as to ensure the long-term stability, security and user experience consistency of the system.

[0016] Based on the analysis results of user behavior and health data, the system can provide personalized cycling recommendations, health guidance, energy consumption management, etc. for users, not only improving the intelligence level of e-bikes, but also enhancing the added value and market competitiveness of the product. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 For the method steps of the present application;

[0018] Figure 2 For the present application Figure 1 S1 step specific implementation diagram. DETAILED DESCRIPTION

[0019] The preferred embodiments of the present application are described below in conjunction with the accompanying drawings, it should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application.

[0020] One embodiment of the present application, as shown in Figure 1 The ebike intelligent human-computer interaction method based on Bluetooth Mesh networking, the method comprises:

[0021] S1, obtain the Bluetooth communication node information of each function module of the ebike and the smart device carried by the user; perform Mesh network topology analysis on the obtained Bluetooth communication node information, construct a Bluetooth Mesh network topology structure of the ebike use scene; according to the constructed Bluetooth Mesh network topology structure, perform network configuration and parameter setting on each node, and form a complete ebike Bluetooth Mesh communication network;

[0022] S2, in the running process of the ebike, through each function module and the smart device, collect data related to the ebike, pre-process the collected data, and classify the data according to different types; extract features from the classified data,

[0023] S3, based on the extracted feature data, a user intention recognition model is constructed by using a machine learning algorithm; according to the recognized user intention, the function of the ebike and the current use scene are combined to determine the interaction mode;

[0024] S4, after determining the interaction mode, the ebike and each smart device are cooperatively interacted through the Bluetooth Mesh network; and the information from different devices is fused and processed;

[0025] S5, according to the actual use feedback and interaction effect of the user, the user intention recognition model and the interaction strategy are continuously optimized; the communication quality of the Bluetooth Mesh network is evaluated regularly, and the network parameters are adjusted according to the evaluation results.

[0026] The working principle of the above technical solution is as follows: the system first collects the Bluetooth communication node information of each functional module (motor controller, battery management system, instrument panel, etc.) on the ebike and the user's smart device (smartphone, smartwatch, etc.). These information is the basis for building a Bluetooth Mesh network. The node information obtained is analyzed for Mesh network topology, taking into account factors such as the distance between nodes, communication signal strength, and node function importance. The purpose is to build a topology that can ensure stable and efficient communication between nodes, and the structure should have the ability to automatically adjust to accommodate the addition or subtraction of nodes. According to the built Bluetooth Mesh network topology, the network configuration and parameter settings of each node are performed, so that they communicate according to the Mesh network protocol, thereby forming a complete ebike Bluetooth Mesh communication network.

[0027] During the operation of the ebike, each functional module and smart device collects real-time data related to the ebike, including riding speed, motor speed, battery level, riding distance, user heart rate, and motion trajectory. These data reflect the running state of the ebike and the user's usage. The collected data is preprocessed to remove noise and outliers, ensuring the accuracy and reliability of the data. Then the data is classified according to different types for subsequent feature extraction and analysis. The classified data is extracted for features, such as average speed, maximum speed, and speed change trend from riding speed data, remaining battery percentage, and power consumption rate from battery power data, and average heart rate and heart rate fluctuation range from user heart rate data. Through feature extraction, the original data is transformed into a more valuable form, facilitating subsequent user intent recognition and interactive decision-making.

[0028] Based on the extracted feature data, a user intent recognition model is constructed using machine learning algorithms. This model, through learning from a large amount of historical data, can accurately identify user intent based on current riding conditions, user physiological data, and environmental information, such as whether the user wants to accelerate, decelerate, switch riding modes, or view specific information. According to the identified user intent, combined with the functions of the ebike and the current use scenario, the appropriate interaction mode is determined. Interaction modes can include voice interaction, instrument panel display interaction, and mobile app interaction, among others. For example, for different user intents, the most appropriate interaction mode is selected to meet user needs and improve user experience.

[0029] After determining the interaction mode, the ebike and each smart device are cooperatively interacted through the Bluetooth Mesh network. For example, when the user issues a control instruction through the smart phone, the instruction is transmitted to the corresponding functional module of the ebike through the Bluetooth Mesh network, realizing the control of the ebike; at the same time, the state information of the ebike can also be fed back to the smart phone in real time for the user to view. This cooperative interaction enables the user to control and obtain information of the ebike through different devices. The information from different devices is fused to improve the accuracy and integrity of the information. For example, the riding speed information collected by the ebike instrument panel is fused with the motion trajectory information obtained by the smart phone GPS positioning system to more accurately calculate the user's riding distance and speed distribution; the heart rate data collected by the user's smart watch is fused with the riding state data of the ebike to analyze the impact of riding on the user's body and provide more personalized health advice. Information fusion can comprehensively utilize the data advantages of different devices to provide users with more comprehensive and accurate information.

[0030] According to the actual use feedback and interaction effect of the user, the user intention recognition model and the interaction strategy are continuously optimized. For example, if it is found that the user's satisfaction with a certain interaction mode is low, or the recognition accuracy of the recognition model is not high in some cases, the model can be retrained and adjusted by collecting more user data and interaction records to improve the performance of the model and the adaptability of the interaction. The communication quality of the Bluetooth Mesh network is regularly evaluated, and the network parameters are adjusted according to the evaluation results to ensure the stability and reliability of the network. For example, when it is found that the communication signal of a certain node is weak, the transmission power of the node can be adjusted or the network topology structure can be optimized to ensure the communication quality of the entire network. Continuous optimization can continuously improve the performance and user experience of the system, ensuring that the system maintains good running state in the long-term use process.

[0031] The effect of the above technical solution is that through the construction of an efficient and stable Bluetooth Mesh network, the e-bike can efficiently communicate with smart devices (such as smart phones, smart watches, etc.), support multiple interaction modes (voice, instrument panel, APP, etc.), thereby improving the interactive experience between the user and the e-bike.

[0032] Based on the adaptive characteristics of the Bluetooth Mesh network, the nodes can automatically adjust the network structure, reducing the need for manual debugging and maintenance. In addition, the Mesh network has strong scalability and can easily adapt to e-bike systems of different sizes.

[0033] Through machine learning algorithms to analyze and extract features of the collected data, the user's intention can be accurately identified, optimizing the e-bike's functions and control strategies, making it more user-friendly and suitable for different scenarios.

[0034] The Bluetooth Mesh network ensures real-time communication and data fusion between the e-bike and smart devices, allowing for more accurate integration and analysis of riding data (such as speed, heart rate, etc.) and external environmental information (such as GPS trajectory, etc.), providing more personalized services and health recommendations.

[0035] Through optimizing user feedback and interaction effects, the system can continuously improve the accuracy of intent recognition, enhancing the adaptability and personalization of the e-bike system, allowing different users to have customized riding experiences.

[0036] By regularly evaluating and optimizing network communication quality, especially for node signal optimization, the stability of the entire Mesh network is improved, ensuring reliable operation of the e-bike in complex environments.

[0037] One embodiment of the present application, as shown in Figure 2 includes:

[0038] S11, through the scanning program, the Bluetooth communication node information of the e-bike function module and the smart device is obtained, and the node information includes node name, MAC address and signal strength;

[0039] S12, a graph theory algorithm is used to construct a Bluetooth Mesh network topology structure for e-bike use scenarios;

[0040] S13, based on the dynamic adjustment algorithm of the network topology structure, when a new node joins the network, the new node is automatically identified and reasonably integrated into the existing topology structure according to its location and function; when an existing node leaves the network, the algorithm can detect the absence of the node in time and re-plan the network path;

[0041] S14, according to the constructed Bluetooth Mesh network topology structure, a unique network address is allocated to each node, and the communication parameters of the node are set;

[0042] S15, through the above configuration and setting, each node can communicate according to the Mesh network protocol to form a complete e-bike Bluetooth Mesh communication network.

[0043] The working principle of the above technical solution is: install Bluetooth communication modules on each functional module of the ebike (such as motor controller, battery management system, instrument panel, etc.), and ensure that these modules can work normally. At the same time, it is required that the user carries a smart device (such as a smartphone, smartwatch, etc.) with Bluetooth enabled. This is the basic hardware condition for establishing Bluetooth communication. Through the scanning program, the system can actively search and obtain the Bluetooth communication node information of the ebike functional modules and smart devices. These information includes node name (used to identify device type), MAC address (unique identifier for each Bluetooth device), and signal strength (an important indicator reflecting communication quality). By obtaining this information, the system can preliminarily understand the node situation in the network.

[0044] Considering the distance between nodes, the physical distance between nodes is measured or estimated, and combined with the propagation characteristics of Bluetooth signals (such as signal attenuation law), the influence of distance on communication quality is analyzed. Too far distance may cause serious signal attenuation, affecting the stability and reliability of communication. Real-time monitoring of node communication signal strength and recording signal strength changes in different time periods. This helps to evaluate the stability of communication and timely discover signal fluctuations or abnormal situations, providing basis for subsequent network optimization. According to the importance of node function, for example, the motor controller and battery management system are crucial to the operation of the ebike, and should be given higher priority. When constructing the topology structure, the communication needs and connection stability of these important nodes will be given priority. Use graph theory algorithms (such as minimum spanning tree algorithm, shortest path algorithm, etc.) to construct Bluetooth Mesh network topology structure for ebike use scenarios. The structure aims to ensure stable and efficient communication between nodes, and through reasonable planning of node connection relationship, optimize communication path and improve the overall performance of the network.

[0045] Based on the dynamic adjustment algorithm of network topology structure, when a new node joins the network, the system can automatically identify the new node and reasonably integrate it into the existing topology structure according to its location and function. For example, when the user carries a smartwatch into the coverage range of the ebike Bluetooth Mesh network, the network can automatically add it to the topology structure and establish communication connection with other nodes. When an existing node leaves the network, the algorithm can detect the absence of the node in time and re-plan the network path. This ensures the stability and reliability of the network, even if a node leaves, it will not cause the entire network to be paralyzed or communication interrupted.

[0046] According to the constructed Bluetooth Mesh network topology, a unique network address is assigned to each node. This ensures that the node can be accurately identified in the network, avoiding address conflicts and communication chaos. The communication parameters of the node are set, such as transmission power, communication frequency, data transmission rate, etc., to meet the communication needs of different nodes. For example, for nodes with a long distance, the transmission power can be appropriately increased to enhance signal strength; for nodes that require high-speed data transmission, a higher data transmission rate can be set. The security parameters of the node are configured, such as encryption algorithms, keys, etc., to ensure the security of communication data. By encrypting communication data, it prevents data from being stolen or tampered with, ensuring the safety of user information and ebike operation data.

[0047] Each node can communicate according to the Mesh network protocol to form a complete ebike Bluetooth Mesh communication network. This network has the characteristics of stability, efficiency, and security, and can meet the needs of ebike intelligent human-computer interaction, providing users with a convenient and comfortable riding experience.

[0048] The effect of the above technical solution is that through the Bluetooth Mesh network, efficient and stable communication can be carried out between the e-bike and the user's smart device, supporting multiple interaction modes (such as voice, instrument panel, APP, etc.). The interaction experience between the user and the e-bike is enhanced, making the riding process more personalized and convenient.

[0049] The adaptive characteristics of the Bluetooth Mesh network enable nodes to automatically adjust the network structure, reducing the need for manual debugging and maintenance. It has strong scalability and can adapt to e-bike systems of different sizes, reducing the difficulty of later expansion and maintenance.

[0050] Through machine learning algorithms to analyze and extract features from the collected data, accurate recognition of user intent can be achieved, thereby optimizing the functions and control strategies of the e-bike, making the system more in line with user needs and usage scenarios, and improving the overall level of intelligence.

[0051] Bluetooth Mesh network ensures real-time communication and data fusion between e-bike and smart devices, enabling accurate integration and analysis of riding data (such as speed, heart rate, etc.) and external environmental information (such as GPS trajectory, etc.), providing personalized riding recommendations and health services for users.

[0052] The system continuously optimizes user feedback and interaction effects, improving the accuracy of intent recognition and enhancing the adaptability and personalization of the e-bike system. Different users can enjoy customized riding experiences, meeting various personalized needs.

[0053] Regularly evaluating and optimizing communication quality, especially node signal optimization, improves the stability of the entire Mesh network, ensures the reliable operation of e-bikes in complex environments, and reduces system failures caused by signal problems.

[0054] In one embodiment of the present invention, the step S13 includes:

[0055] S131. Based on the deployed node monitoring module, continuously scan for devices within the Bluetooth signal range. When a new Bluetooth signal is detected, the new node access process is initiated. The MAC address of the new node is compared with the known node database to determine whether it is a newly added node. If it is a new node, its function information is further obtained.

[0056] S132: Based on the RSSI (Received Signal Strength Indication) value of the Bluetooth signal and the location information of known nodes, preliminarily determine the approximate location of the new node; based on the functional information of the new node, evaluate its role and importance in the ebike Bluetooth Mesh network;

[0057] S133. Based on the location and function evaluation results of the new nodes, the network topology is replanned using graph theory algorithms, and the load balancing of the nodes in the network is considered. The network path is adjusted to evenly distribute the communication traffic among the nodes.

[0058] S134. Send network configuration information to the new node, update the network topology, incorporate the new node into the network, and notify other nodes about the joining information of the new node; at the same time, update the network path;

[0059] S135. Real-time monitoring of the communication status of nodes in the network. When a node is detected to be unresponsive for a long time or the signal strength continues to decrease, a node departure detection process is initiated. The node is compared with the active node list in the node database to determine whether it has left the network. If confirmed to have left, a network reconstruction process is initiated to re-plan the network path.

[0060] S136. After a node joins or leaves the network, the network stability is evaluated in real time, and the network topology is further optimized based on the evaluation results.

[0061] The working principle of the above technical solution is that the node monitoring module deployed in the ebike Bluetooth Mesh network continuously scans the devices within the Bluetooth signal range. Once a new Bluetooth signal is detected, the system immediately starts the new node access process. By comparing the MAC address of the new node with the known node database, the system can quickly determine whether the node is a newly added node. This step ensures that only the true new node will enter the subsequent access process, avoiding repeated processing. If it is determined to be a new node, the system will further obtain its function information, such as node type, supported communication protocol, etc. These information is crucial for subsequent network topology planning and node configuration.

[0062] Based on the RSSI value of the Bluetooth signal and the location information of the known nodes, the system can preliminarily determine the approximate location of the new node. This helps to reasonably arrange the connection relationship of the new node in the subsequent network topology planning. According to the function information of the new node, the system evaluates its role and importance in the ebike Bluetooth Mesh network. For example, if the new node is a sensor related to cycling safety, it should be given a higher priority to ensure the stability and reliability of its communication.

[0063] Based on the location and function evaluation results of the new node, the system uses graph theory algorithm to re-plan the network topology. This step aims to ensure that the new node can efficiently integrate into the existing network, while optimizing the communication performance of the overall network. When re-planning the network topology, the system will consider the load balancing of the nodes in the network to avoid performance degradation due to some nodes bearing too much communication tasks. By adjusting the network path, the communication traffic is evenly distributed among the nodes, improving the overall efficiency of the network.

[0064] The system sends network configuration information to the new node, including network address, communication parameters, security parameters, etc. These information is the basis for the new node to communicate according to the Mesh network protocol. Update the network topology, include the new node in the network, and notify other nodes about the joining information of the new node. At the same time, update the network path to ensure efficient transmission of data between the new node and existing nodes.

[0065] The system monitors the communication status of the nodes in the network in real time, and immediately starts the node departure detection process once it detects that a node has been unresponsive for a long time or the signal strength has continuously decreased. By comparing the active node list in the node database, the system confirms whether the node has left the network. This step ensures that only the truly departed node will trigger the network reconstruction process. If the node is confirmed to have left, the system starts the network reconstruction process to re-plan the network path. This helps to maintain the stability and reliability of the network, avoiding communication interruption or performance degradation due to node departure.

[0066] After a node joins or leaves the network, the system evaluates network stability in real time, including metrics like communication latency and packet loss rate. These metrics reflect the network's communication performance and reliability. Based on these evaluation results, the system further optimizes the network topology, adjusting node transmit power and communication frequency. This step aims to continuously improve network stability and performance to meet the requirements of intelligent human-computer interaction on ebikes.

[0067] The benefits of this technical solution are: by automatically detecting and flexibly handling the addition of new nodes, the system can dynamically adjust the network structure based on actual needs, ensuring that the network can expand as devices and nodes increase. This automated adjustment enables the e-bike Bluetooth Mesh network to efficiently adapt to different environments and user needs, improving the system's adaptability.

[0068] By automatically monitoring and adjusting the joining and leaving of nodes, the need for manual intervention is reduced, making network maintenance easier and more cost-effective. The system can manage the lifecycle of nodes on its own, improving the network's self-healing capabilities.

[0069] By monitoring the signal strength and response status of nodes in real time, the system can react promptly and re-plan network paths when a node leaves or signal quality degrades. This enhances network robustness and prevents overall network performance degradation caused by a single node problem.

[0070] The network topology is optimized through graph theory algorithms to ensure that communication tasks are evenly distributed among nodes, avoiding overload of certain nodes and improving communication efficiency and data transmission stability.

[0071] When each new node joins, the system sends it security configuration information, such as encryption algorithms and keys, to ensure the communication security of the newly joined node in the network. This improves the security of the entire network and protects data transmission from attacks.

[0072] Based on the functional information of new nodes (such as safety sensors and powertrain modules), the system assesses their importance within the network and assigns them different priorities. This intelligent management effectively optimizes e-bike performance and ensures the stable operation of key modules (such as safety monitoring).

[0073] The system can monitor and respond to dynamic changes in the network in real time, including node additions and departures, or signal changes. This allows the network to quickly adjust to different environments or user scenarios, ensuring efficient system operation.

[0074] In one embodiment of the present invention, the step S133 includes:

[0075] The existing nodes and the new node are represented as vertices in the graph structure in graph theory, and the connection relationship between the vertices is represented as an edge; the relative positions of the vertices in the graph are preliminarily determined according to the known node position information;

[0076] In combination with the function information of the new node, the communication demand between the new node and the existing nodes is analyzed, and based on a graph theory algorithm (such as Dijkstra algorithm), the optimal communication path between the new node and the existing nodes is calculated according to the communication demand and the position information between the nodes;

[0077] The quality of the planned communication path is evaluated, and the network topology structure is fine-tuned according to the path quality and stability evaluation results; the quality of the communication path is evaluated by the following formula:

[0078]

[0079] wherein, ωi represents a standardized basic index (length, hop count, delay, bandwidth, and packet loss rate, all of which are in [0, 1]); ω n ωi represents a basic index weight; H represents the hop count of the path; R k ωi represents the reliability of the kth link (in [0, 1]); S m ωi represents the stability coefficient of the mth node (in [0, 1]); and β represents the stability weight (in [0, 1]);

[0080] The adjusted network topology structure is displayed in a visual manner, and a detailed network topology update scheme is generated, including changes in the connection relationship of the nodes and adjustments of the communication parameters.

[0081] The working principle of the above technical solution is as follows: the graph structure in graph theory is used to model the Bluetooth Mesh network, and the existing nodes and the new node are represented as vertices in the graph. The connection relationship between the vertices (i.e., the communication link) is represented as an edge, which facilitates the use of mathematical methods to process network topology problems. For example, in a simple ebike Bluetooth Mesh network, the motor controller, the battery management system, the instrument panel, and the newly added smart device are all vertices in the graph, and the Bluetooth communication link between them is an edge. According to the known node position information, the relative positions of the vertices in the graph are preliminarily determined. Although this is not a strict physical position mapping, it helps to understand the influence of the spatial relationship between the nodes on communication. For example, nodes that are close to each other in the graph may be arranged in close proximity to facilitate subsequent consideration of communication distance and signal strength.

[0082] Based on the functional information of the new node, analyze its communication needs with existing nodes, including communication frequency, data size, etc. Different functional nodes have different communication needs. For example, sensors related to cycling safety may require high-frequency, small-data-volume communication to deliver safety information in real time; while nodes for data recording and analysis may require low-frequency, large-data-volume communication. Based on graph theory algorithms (such as Dijkstra algorithm), according to the communication needs and location information between nodes, the optimal communication path between the new node and the existing node is calculated. Dijkstra algorithm can find the shortest path from a starting point to all other vertices, which can be understood as finding the optimal communication link that meets the communication needs and takes into account factors such as location. In the process of path planning, sufficient consideration is given to the load balancing of nodes in the network to avoid performance degradation due to excessive communication tasks on some nodes. Just as in a traffic network, a road cannot carry too much traffic flow, otherwise it will cause congestion, and the same is true in a Bluetooth Mesh network, where communication tasks should be reasonably distributed.

[0083] The quality of the planned communication path is evaluated, including communication delay, packet loss rate, signal strength, etc. Communication delay refers to the time required for data to travel from the sender to the receiver, packet loss rate refers to the proportion of lost data packets in the total data packets during data transmission, and signal strength directly affects the stability and reliability of communication. Through the evaluation of these indicators, the performance of the communication path can be understood. Use simulation or actual testing methods to verify the stability of the path in different scenarios. For example, in different cycling environments (such as urban roads, mountain roads, etc.), test whether the communication path can maintain stable communication. Ensure that the new node can efficiently and stably integrate into the existing network, just like a new member joining a team and ensuring that it can smoothly integrate and play its due role.

[0084] Based on the results of path quality and stability evaluation, fine-tune the network topology, such as optimizing the connection between nodes, adjusting the transmission power of nodes, etc. If it is found that the signal strength of a communication path is weak, the transmission power of the relevant nodes can be adjusted; if it is found that some nodes are heavily loaded, the connection between nodes can be optimized to transfer part of the communication tasks to other nodes. Ensure that the adjusted network topology can meet the communication needs of the new node, while maintaining the overall stability and performance of the network. Just like adjusting a mechanical structure, both the newly added components should work normally and the stability and performance of the entire mechanical structure should not be affected.

[0085] The adjusted network topology is displayed in a visual manner, facilitating the user to intuitively understand the connection relationship and structure of the network. For example, the communication links between nodes, the positions and states of nodes, and other information are displayed in a graphical manner. A detailed network topology update plan is generated, including changes in node connection relationships, adjustments in communication parameters, etc. This provides clear guidance for subsequent network maintenance and management, like a detailed construction drawing, guiding engineers on how to modify and upgrade the network.

[0086] The effect of the above technical solution is that the system can select the most suitable path for data transmission by calculating the optimal communication path through graph theory algorithm and combining the function information and communication demand of nodes. Not only reduces the communication delay, but also improves the efficiency of data transmission, ensuring that the new node can be stably and efficiently integrated into the network.

[0087] During path planning, the system fully considers the load conditions of each node to avoid performance degradation of some nodes due to excessive communication tasks. This reduces network bottlenecks caused by node overload and improves the overall performance and stability of the network.

[0088] The planned communication path is verified through quality assessment (including delay, packet loss rate, signal strength, etc.) to ensure the stability of the path in different scenarios. This enhances the stability of the network and reduces data transmission errors or interruptions caused by unstable paths.

[0089] Based on the evaluation of path quality, the system can fine-tune the network topology, adjust the connection relationship between nodes and communication parameters such as transmission power, etc. This ensures that the adjusted network topology can better meet the communication needs of new nodes while maintaining the overall stability and performance of the network.

[0090] Through visual network topology display, users can clearly see the changes in node connection relationships and communication parameters, helping technical personnel quickly understand network conditions and perform debugging and optimization. This reduces the complexity of network maintenance and adjustment, improving operational efficiency.

[0091] Path planning is combined with the actual functions and communication needs of nodes, allowing new nodes to dynamically select the most suitable communication path according to actual scenarios and tasks. This enables the system to intelligently optimize in different application scenarios, providing more flexible network adaptability.

[0092] Through simulation or actual testing, the system can verify the stability of the path and optimize the network performance in different scenarios. This improves the adaptability of the system in a changing environment, ensuring stable network operation.

[0093] The above formula combines common network performance indicators such as length, hop count, delay, bandwidth, and packet loss rate (which usually affect network efficiency), while adding two important factors, link reliability and node stability, making the evaluation criteria more comprehensive; the introduction of weight factors and stability weights allows the formula to be flexibly adjusted according to different needs. For example, in some network environments, bandwidth may be more important than delay, or for some high-reliability applications, stability may be more critical than other factors. Through flexible weight allocation, the formula can adapt to diverse needs.

[0094] The inclusion of link reliability and node stability not only considers the instantaneous performance of the path but also fully considers the stability of long-term network operation. This is very important because many network applications require stable performance over a long period of time. The formula gives a quantitative path quality Q, making network optimization more practical. By scoring each path, it is clear which paths are optimal, and further optimization can be based on these results. In this way, path selection and fine-tuning are no longer experience-driven but scientific decisions based on data and analysis. The optimized topology is visualized, enhancing the understandability and operability of the solution. At the same time, generating detailed update plans helps the team track changes during actual deployment, ensuring that network structure and performance improvement are synchronized.

[0095] In one embodiment of the present application, the S135 comprises:

[0096] Real-time monitoring of the communication status of nodes in the network, when detecting that the signal strength of a certain node is continuously decreasing or has been unresponsive for a long time, marking it as a potential abnormal node; further analyze the historical communication data of the abnormal node to confirm whether there is an abnormal situation;

[0097] For nodes confirmed to have abnormalities, start the node departure detection process; compare the active node list in the node database to query the latest state information of the node and confirm whether it has actually left the network;

[0098] If it is confirmed through comparison that the node has left the network, remove it from the active node list and record the relevant information; at the same time, update the network topology structure and mark the node as having left the state;

[0099] According to the changes in the network topology structure after the node leaves, start the network reconstruction process; use graph theory algorithms to re-plan the network path;

[0100] Verify the reconstructed network; according to the verification results, further optimize the network topology structure, notify other nodes in the network of the information about the node departure and network reconstruction, and update the relevant records of the network management system.

[0101] The working principle of the above technical solution is: through the monitoring mechanism deployed in the network, the communication state of each node is continuously monitored in real time. This includes real-time tracking of node signal strength and continuous observation of node response. Signal strength is an important indicator of the quality of communication between nodes, and the response of the node reflects whether the node is in normal working condition. When the signal strength of a node is continuously decreasing or has been unresponsive for a long time, it indicates that the node may have abnormal conditions, and it is marked as a potential abnormal node. For the marked potential abnormal node, further analyze its historical communication data. Historical communication data contains the communication records of the node in the past period of time, through in-depth analysis of these data, it can be confirmed whether there are communication interruption, data loss and other abnormal conditions. For example, if it is found that the node frequently appears communication interruption in a period of time, or a large number of data packets are lost in the data transmission process, it can be more determined that the node has abnormalities.

[0102] For the node confirmed to have abnormalities, the system starts the node departure detection process. The purpose of this process is to accurately determine whether the node has actually left the network. By comparing the active node list in the node database, the latest state information of the node is queried. The active node list records the node information in the current network in the normal working state, by comparing with the list, it can be confirmed whether the node has actually left the network. If the node is not in the active node list, or the state of the node recorded in the list does not match the actual situation, it can be confirmed that the node has left the network.

[0103] If it is confirmed through comparison that the node has left the network, it is removed from the active node list, and the leaving time, reason and other related information are recorded. These information has important significance for subsequent network management and troubleshooting, for example, by analyzing the leaving reason of the node, the possible problems in the network can be found, and corresponding measures can be taken to improve. At the same time, update the network topology structure, mark the node as left state. The network topology structure reflects the connection relationship between each node in the network, by marking the left node, the network topology structure can more accurately reflect the actual situation of the current network.

[0104] According to the changes in the network topology after the node leaves, the network reconstruction process is started. After the node leaves, the original network topology may no longer meet the communication needs of the network, so it is necessary to re-plan the network path to ensure efficient communication connection between the remaining nodes. Graph theory algorithms are used to re-plan the network path. Graph theory algorithms can calculate the optimal network path based on the position of nodes in the network, communication needs, and other factors. For example, Dijkstra's algorithm can find the shortest path from a starting point to all other vertices. By applying these algorithms, the communication path between the remaining nodes can be made more efficient and stable. The reconstructed network is tested and verified, and the network topology is further optimized based on the verification results. Verification tests can include communication delay tests, packet loss rate tests, and other tests to understand the performance of the reconstructed network. If the communication performance between certain nodes is not ideal, the node's transmission power, communication frequency, and other parameters can be adjusted to optimize the network's communication quality and stability.

[0105] The information about the node leaving and network reconstruction is notified to other nodes in the network to ensure that they can update their routing tables and network topology information in a timely manner. In the network, each node needs to select a communication path based on the network topology, so timely updating of the routing table and network topology information is crucial to ensure the normal operation of the network. The relevant records of the network management system are updated, including node leaving information, network reconstruction information, and other information. These records can provide a reference for subsequent network management and maintenance. For example, by analyzing the historical records of node leaving, potential weaknesses in the network can be found and appropriate measures can be taken to strengthen them.

[0106] The effect of the above technical solution is that by monitoring the communication status of the nodes in real time, potential abnormal nodes with decreased signal strength or long periods of non-response can be detected in a timely manner, reducing the risk of network interruption and enhancing the reliability of the network.

[0107] After detecting the abnormal node, the node leaving detection process is started, and the historical data of the abnormal node is automatically analyzed to quickly confirm whether it has actually left the network, reducing the need for human intervention and shortening the fault recovery time.

[0108] Network reconstruction is performed using graph theory algorithms, which can automatically adjust the network path to ensure efficient communication connection between the remaining nodes, enhancing the adaptability of the network after the node leaves.

[0109] The network topology after the node leaves can be adjusted through optimization algorithms to ensure that the system continues to operate efficiently and stably after the node leaves.

[0110] By automatically updating node status, topology and routing table, network management is simplified, manual operation is reduced, and operation and maintenance efficiency is improved.

[0111] Through real-time monitoring, historical data analysis, path reconstruction and other automated processes, the network's self-diagnosis and repair capabilities are enhanced, making the network's operation more intelligent.

[0112] By ensuring that abnormal nodes are detected and removed in a timely manner, the network can quickly adapt to node changes, reducing the decline in network performance caused by node departure, and ensuring the stability of data transmission.

[0113] By updating the network topology and path planning in a timely manner, the communication between the remaining nodes is ensured to be unaffected by node departure, thereby reducing the risk of communication delay and path interruption.

[0114] This scheme supports dynamic joining and leaving of nodes, and through optimization of network topology and path planning, it can support larger-scale network expansion and meet future demands.

[0115] By updating the network topology, recording the time and reason for leaving, and other information, the system's tracking ability for abnormal node states is enhanced, and the security of network management is improved.

[0116] One embodiment of the present application, the S2, comprises:

[0117] S21, during the operation of the ebike, data related to the ebike is collected through various functional modules and intelligent devices;

[0118] S22, the collected data is cleaned, and the cleaned data is smoothed using a filtering algorithm, and the smoothed data is classified according to different types;

[0119] S23, and the classified data is feature extracted;

[0120] S24, through feature extraction, the original data is converted into feature data with representativeness and analyzability.

[0121] The working principle of the above technical solution is: during the operation of the ebike, data related to the ebike is collected through functional modules distributed at different parts of the ebike and intelligent devices carried by the user.

[0122] including:

[0123] Motor Controller and Motor Data: A speed sensor installed in the ebike's motor controller enables real-time and accurate collection of riding speed data. For example, when a rider accelerates or decelerates, the speed sensor quickly detects and records the change in speed. Furthermore, a speed sensor installed on the motor provides information on motor speed, which is closely related to riding speed. By analyzing motor speed, we can understand the vehicle's power output.

[0124] Battery Management System Data: The battery management system collects battery charge data, including remaining charge percentage, voltage, and current. The remaining charge percentage provides a visual indication of the remaining battery charge, while voltage and current data can be used to assess the battery's operating status and health. For example, a sudden drop in voltage or an abnormal increase in current could indicate a battery failure.

[0125] Dashboard data: The dashboard records riding mileage data. Riding mileage is one of the important indicators to measure ebike usage. It can reflect the rider's travel distance and the frequency of vehicle use.

[0126] Smart device data: Smartwatches use built-in heart rate sensors to collect heart rate data, which can reflect a cyclist's physical condition and exercise intensity. For example, when a cyclist rides at a high intensity, their heart rate increases; when the intensity decreases, their heart rate decreases accordingly. Mobile phones use GPS to capture the user's movement trajectory. This trajectory records the cyclist's route and location, providing geospatial data for subsequent analysis.

[0127] The collected raw data may contain noise, outliers, and other issues, necessitating cleaning. A filtering algorithm is used to smooth the cleaned data. This removes high-frequency noise and stabilizes the data. For example, for cycling speed data, filtering can eliminate speed fluctuations caused by sensor measurement errors or road bumps, making the speed data more accurate and reliable. The smoothed data is categorized according to different types for subsequent targeted analysis and processing. Cycling speed, motor speed, and other data are classified as motion data; these data primarily reflect the ebike's motion state and performance. Battery charge level and remaining range are classified as energy data; energy data is crucial for evaluating ebike endurance and battery management. User heart rate, movement trajectory, and other data are classified as health and location data; these data can be used to analyze the cyclist's physical condition and travel habits.

[0128] Perform feature extraction, including:

[0129] Motion data feature extraction: For cycling speed data, calculate the average speed, maximum speed, and minimum speed within a certain time window. These features can reflect the overall cycling speed level and speed fluctuation range of the rider within a period of time. At the same time, analyze the speed change trend, such as acceleration and deceleration. Acceleration and deceleration can reflect the acceleration and deceleration behavior of the rider, which is important for evaluating the driving style of the rider and the dynamic performance of the vehicle.

[0130] Energy data feature extraction: Extract the remaining battery percentage, power consumption rate (the amount of power reduction per unit time), and estimated remaining range from the battery power data. The remaining battery percentage can directly reflect the remaining battery power, the power consumption rate can be used to evaluate the use efficiency of the battery and the energy consumption of the vehicle. The estimated remaining range is based on the current power and driving state to predict the distance the vehicle can still travel, providing a reference for the rider.

[0131] User health and location data feature extraction: Calculate the average heart rate, heart rate fluctuation range (difference between maximum and minimum heart rate), and correlation between heart rate and cycling intensity from user heart rate data. The average heart rate can reflect the overall heart rate level of the rider during cycling, the heart rate fluctuation range can reflect the change amplitude of the heart rate, and the correlation between heart rate and cycling intensity can be used to analyze the impact of cycling intensity on heart rate.

[0132] Through the above feature extraction process, the original data is transformed into representative and analyzable feature data. These feature data can more accurately reflect the running state of the ebike, the physical condition of the user, and the travel habits, etc., providing a basis for subsequent user intent recognition and interaction. For example, by analyzing the cycling speed and acceleration features, it can be determined whether the rider is accelerating, decelerating, or maintaining a constant speed, thereby inferring the rider's intent; by analyzing the correlation between user heart rate and cycling intensity, personalized exercise recommendations can be provided to the rider, improving the safety and comfort of cycling.

[0133] The effect of the above technical solution is that multiple sensors and intelligent devices are used to collect multi-dimensional data related to electric bicycles, which can comprehensively reflect various information during cycling, improving the accuracy and breadth of data collection.

[0134] Through cleaning and filtering processing of the collected data, noise is effectively removed, ensuring the quality and accuracy of the data, and reducing the subsequent analysis errors caused by inaccurate or incomplete data.

[0135] Through smoothing processing and feature extraction of the cleaned data, the original data is transformed into representative and analyzable feature data, providing a more accurate basis for user intent recognition and behavior prediction.

[0136] By extracting features such as average heart rate and heart rate fluctuation range from user heart rate data, the user's physical condition can be more accurately monitored and correlated with cycling intensity, improving the real-time and accuracy of health monitoring.

[0137] By extracting features such as battery power, consumption rate, and remaining range, the use of the battery can be monitored in real time, helping users understand the battery status and optimize cycling strategies, enhancing the intelligence of energy management.

[0138] By analyzing features such as motion trajectory and cycling speed, the user's cycling habits and preferences can be identified, providing more personalized cycling recommendations and feedback, and improving the user's cycling experience.

[0139] By extracting and classifying various data features, the subsequent user intent recognition process is simplified, allowing more efficient analysis and prediction of user behavior, reducing the complexity of intent recognition.

[0140] By collecting and processing multi-dimensional data in real time, the system can quickly respond to user needs and environmental changes, improving the real-time and flexibility of the overall system.

[0141] Through data cleaning, filtering, feature extraction and other preprocessing steps, the original data can be converted into more compact and effective feature data, improving the efficiency of data processing and the operability of subsequent analysis.

[0142] Converting feature data into more representative indicators makes cycling data easier to analyze and present, facilitating user data viewing and decision-making, and enhancing user interaction experience and decision support capabilities.

[0143] An embodiment of the present application, the S3, comprises:

[0144] S31, collect historical cycling data and user interaction records; label the collected data to determine the user intent corresponding to each data sample;

[0145] S32, select a machine learning algorithm, and use the labeled data to train the model; during training, continuously adjust the model parameters, use the test data set to evaluate the trained model, and optimize the model according to the evaluation results;

[0146] S33, analyze the functions of the ebike, and determine the appropriate interaction mode for each function; combine the user's historical usage habits and preferences to recommend interaction modes;

[0147] S34, according to the identified user intent, combined with the above interaction mode selection basis, determine the appropriate interaction mode.

[0148] The working principle of the above technical solution is as follows: a large amount of historical riding data and user interaction records are collected, covering riding states (such as speed, motor speed, etc.), user physiological data (such as heart rate, etc.), environmental information (such as weather, road conditions, etc.), and user intentions (such as accelerating, decelerating, switching riding modes, etc.). These data comprehensively reflect various factors in the riding process, providing a rich information base for subsequent user intention recognition. For example, in sunny and good road conditions, users may prefer to accelerate riding; while in rainy and complex road conditions, users may slow down or switch to a safer riding mode. The collected data is labeled to determine the user's intention corresponding to each data sample. Data labeling is a key step in machine learning model training. Through labeling, the model can learn the correspondence between different data features and user intentions. For example, a set of data with gradually increasing riding speed, rising motor speed, and rising user heart rate is labeled as "acceleration intention".

[0149] Select appropriate machine learning algorithms and use labeled data to train the model. Common machine learning algorithms such as decision trees, support vector machines, neural networks, etc. can be used for user intention recognition. During training, the model learns the feature patterns in the data and classifies new data based on these patterns, i.e. identifies user intentions. For example, neural networks can gradually improve the accuracy of user intention recognition through the learning and adjustment of multiple layers of neurons. Continuously adjust the parameters of the model and use the test data set to evaluate the trained model. Parameter adjustment is to optimize the performance of the model so that it can perform well on different data sets. The test data set is independent of the training data set and is used to evaluate the generalization ability of the model. Based on the evaluation results, the model is optimized, for example, if the model's accuracy on the test data set is low, the model's parameters may need to be adjusted, the amount of training data increased, or the algorithm replaced, etc. to ensure that the model can accurately identify user intentions based on current riding conditions, user physiological data, and environmental information, etc.

[0150] Analyze the functions of the ebike, such as acceleration, deceleration, switching riding modes, viewing riding data, etc. Determine the appropriate interaction mode for each function. Different functions have different requirements for interaction modes, for example, acceleration and deceleration functions require quick and accurate operation, suitable for using handlebar buttons or voice commands, etc. While the function of viewing riding data can be interacted through the instrument panel display or mobile APP, etc. Consider the current use scenario, for example, when the user is riding and the speed is fast, in order not to affect the safety of riding, the voice interaction or simple instrument panel display interaction should be preferred. Voice interaction can let users get information or operate without distraction, and simple instrument panel display can quickly convey key information. When the user is in a parked state, you can choose a more rich mobile APP interaction mode, such as viewing detailed riding data, setting riding parameters, etc. Combine the user's historical use habits and preferences to recommend interaction modes. For example, if the user is used to using mobile APP for operation, under the premise of safety and convenience, the mobile APP interaction mode is preferred. By analyzing the user's historical use records, you can understand the user's preferences and provide a more personalized interaction experience.

[0151] According to the identified user intent, combined with the above interaction mode selection basis, determine the appropriate interaction mode. For example, when the user's intent is to view the riding speed, display the speed information in real time in the form of numbers on the instrument panel, and at the same time, you can prompt the user's current speed through voice. This interaction mode can let users quickly get speed information and won't affect the safety of riding. When the user's intent is to switch the riding mode, prompt the user to confirm the operation through voice, such as "Are you sure you want to switch to sports mode?", And display the mode switching status and related information on the mobile APP, such as the power change after mode switching, the change of the range, etc. This interaction mode can ensure that the user understands the relevant information before switching the mode, avoiding inconvenience or safety hazards caused by misoperation.

[0152] The effect of the above technical solution is that by collecting a large amount of historical riding data and user interaction records, and labeling the data, the user's intent can be accurately identified. The machine learning model is continuously optimized during the training process, improving the accuracy of user intent recognition, ensuring that the system can accurately determine user needs according to different riding states, user physiological data and environmental information.

[0153] When designing the interaction mode, the safety in different riding states is fully considered. For example, when the user is riding at a high speed, the system prefers voice interaction or simple instrument panel display, avoiding the interference of complex operations on the safety of riding, and reducing the risk of user misoperation.

[0154] According to the user's historical usage habits and preferences, the system can intelligently recommend the most suitable interaction mode. For example, if the user is used to using the mobile phone APP operation, the system will preferentially recommend the mobile phone APP interaction mode, while meeting the safety and convenience requirements, improving the personalization and intelligence of the interaction mode.

[0155] By combining different usage scenarios and interaction requirements, the system can provide the best interaction mode at the appropriate time. For example, when the user is in a parking state, it is recommended to use a rich mobile phone APP interaction, while in the process of riding, a concise and fast interaction mode is preferred, improving the convenience and interaction experience of the user.

[0156] By combining real-time riding state, user physiological data and environmental information, the system can identify user intent and respond in real time during the riding process. For example, when the user wants to view the riding speed, the system displays the speed in real time on the instrument panel and provides voice feedback, allowing the user to obtain the required information without distraction.

[0157] By clearly analyzing the interaction mode of different functions, the system can select the most suitable interaction mode according to the specific function. For example, when the user's intention is to switch the riding mode, the system not only prompts the user to confirm through voice, but also synchronously displays the mode switching information on the mobile phone APP, enhancing the operability and transparency of the function operation.

[0158] By automatically identifying user intent and recommending appropriate interaction modes, users do not need to perform complex manual operations, reducing the complexity of operation, simplifying the interaction process between users and the system, and improving the overall user experience.

[0159] The system continuously optimizes intent recognition and interaction mode recommendation through machine learning algorithms, making the interaction between users and electric bicycles more intelligent, enhancing the adaptability and intelligent characteristics of the system, and improving the overall interaction experience.

[0160] Through precise intent recognition and personalized interaction recommendation, users can make riding decisions more efficiently, such as selecting riding mode switching, viewing riding data, etc., reducing decision-making time and improving overall riding efficiency.

[0161] Through continuous training and optimization of machine learning algorithms, the system can make corresponding adjustments according to changing user needs and riding environments, thereby improving the maintainability of the system and the expandability of future new functions.

[0162] One embodiment of the present application, the S4, includes:

[0163] S41, after determining the interaction mode, when the user issues a control instruction through the smart phone, the smart phone sends the instruction to the corresponding function module of the ebike through the Bluetooth Mesh network;

[0164] S42, after the function module of the ebike receives the instruction, it executes the corresponding operation and feeds back the operation result to the smart phone for the user to view;

[0165] S43, the riding speed information collected by the ebike instrument panel is fused with the motion trajectory information obtained by the smart phone GPS positioning system, and a more accurate riding distance and speed distribution is calculated through a data fusion algorithm;

[0166] S44, the heart rate data collected by the user's smart watch is fused with the riding state data of the ebike, and the influence of riding on the user's body is analyzed; personalized health advice is provided for the user.

[0167] The working principle of the above technical solution is: after determining the interaction mode, when the user issues a control instruction (such as acceleration, deceleration, switching riding mode, etc.) through the smart phone, the smart phone sends the instruction to the corresponding function module of the ebike through the Bluetooth Mesh network. Bluetooth Mesh network has the advantages of low power consumption, wide coverage, multi-node connection, etc., which can ensure stable and efficient transmission of instructions between the smart phone and the ebike. For example, when the user wants to accelerate during riding, he only needs to click the acceleration button on the phone APP, and the smart phone will quickly send the acceleration instruction to the motor controller of the ebike through the Bluetooth Mesh network. After the function module of the ebike receives the instruction, it immediately executes the corresponding operation. Taking the acceleration instruction as an example, after the motor controller receives the instruction, it will adjust the power supply parameters of the motor to increase the motor speed, thereby realizing the acceleration of the vehicle. At the same time, the function module will feed back the operation result to the smart phone for the user to view. For example, after the motor controller accelerates, it will feed back the speed information after acceleration to the phone APP through the Bluetooth Mesh network, and the user can real-time understand the running speed of the vehicle on the phone APP. This instruction execution and feedback mechanism realizes the real-time interaction between the user and the ebike, allowing the user to conveniently control the vehicle and obtain vehicle state information.

[0168] The speed information collected by the ebike instrument panel is real-time and accurate, reflecting the vehicle's speed at a certain moment. The trajectory information obtained by the smartphone GPS positioning system contains the location and route information of the ride, but may have some positioning errors. By fusing these two types of data, a more accurate ride distance and speed distribution can be calculated through the data fusion algorithm. The data fusion algorithm can determine the approximate location and route of the ride based on GPS positioning information, and combine the speed information from the instrument panel to more accurately calculate the speed and ride distance of each section. For example, on a straight road segment, GPS positioning information can determine the start and end points of the section, and the speed information from the instrument panel can record the speed changes of the vehicle on that section. Through the data fusion algorithm, the actual ride distance and average speed of that section can be calculated. This data fusion method compensates for the shortcomings of a single data source, improving the accuracy and reliability of the ride data.

[0169] The heart rate data collected by the user's smartwatch can reflect the user's physical condition, while the ebike's ride status data (such as ride speed, motor power, etc.) reflects the intensity and difficulty of the ride. There is a certain correlation between these two types of data, for example, the greater the ride intensity, the higher the user's heart rate may be. By fusing heart rate data with ride status data, the impact of riding on the user's body can be analyzed. By analyzing heart rate and ride speed, motor power, etc., it can be determined whether the user's ride intensity is appropriate. If the heart rate is too high and the ride speed and motor power are also large, it indicates that the user's ride intensity may be too large, and the system can provide more personalized health recommendations to the user, such as "based on your current heart rate and ride intensity, we recommend that you reduce your speed appropriately to maintain healthy riding." This data fusion and analysis method can help users better understand their physical condition and ride intensity, and arrange their ride plan reasonably to ensure ride safety.

[0170] The effect of the above technical solution is that through the Bluetooth Mesh network, the smartphone can quickly transmit the user's control instructions to the functional modules of the electric bicycle, reducing the delay of instruction transmission, improving the response speed and accuracy of the system, and ensuring timely feedback of user operations.

[0171] Through clear division of labor among functional modules and instruction feedback mechanism, the electric bicycle can efficiently execute user instructions and feedback operation results to the phone APP. This interactive method simplifies the operation process, reduces the occurrence of user operation errors, and improves the reliability and user experience of the system.

[0172] By integrating the speed information from the ebike dashboard with the trajectory information obtained from the smartphone's GPS positioning system, a data fusion algorithm is used to calculate a more accurate distribution of riding distance and speed. This technology enhances the accuracy and real-time nature of riding data, providing more precise riding information and route analysis.

[0173] By integrating heart rate data collected by the user's smartwatch with the e-bike's riding status data, the system can analyze the user's physical response during riding and provide more personalized health advice. For example, if the system determines that the user's riding intensity is too high, it will promptly prompt the user to reduce speed, helping the user maintain an appropriate riding intensity and reduce health risks.

[0174] When the user issues a control command, the smartphone provides real-time feedback based on the riding status and the result of the operation, such as speed information after acceleration, enhancing the user's interactive experience with the system. The system's feedback not only reflects the result of a single operation but also incorporates the user's real-time status, making the feedback more intelligent and dynamic.

[0175] By integrating cycling data from multiple sources, the system can provide users with more accurate cycling information and reasonable health recommendations. Based on this data, users can make more effective cycling decisions and avoid excessive cycling or other behaviors that may cause health problems.

[0176] The system seamlessly collaborates with multiple devices via a Bluetooth Mesh network, reducing reliance on external hardware. Users can access cycling data and health information without relying on numerous independent devices, making the system more accessible and accessible.

[0177] By integrating cycling data (such as speed and distance) with health data (such as heart rate) and external positioning data (such as GPS), the system seamlessly integrates multiple functions, providing users with a more comprehensive and enriched cycling experience. This multi-functional integration enhances the system's comprehensiveness and practicality, and improves the overall user experience.

[0178] By simplifying the transmission process of control commands and optimizing the command feedback mechanism, users can more conveniently control their e-bikes via their mobile phones while also checking their riding status in real time. This optimization improves system operability and interactive fluidity, reducing any lag or delay during operation.

[0179] Through deep integration with devices such as smartphones and smart watches, users can obtain various data and health status feedback about cycling in real time, enhancing their sense of control and participation in the cycling process and improving the overall user experience.

[0180] In one embodiment of the present invention, the step S43 includes:

[0181] Preprocess the riding speed information collected by the ebike dashboard and the motion trajectory information obtained by the smartphone GPS positioning system;

[0182] Extract key features from the preprocessed cycling speed information, extract features related to cycling speed from the motion trajectory information, and try to match them with the cycling speed features to identify the speed characteristics of different road sections;

[0183] Based on the feature matching results, a data fusion model is constructed. Through the constructed data fusion model, the riding distance and speed distribution are calculated based on the riding speed information and motion trajectory information;

[0184] The cycling process is divided into multiple segments based on the segment division in the motion trajectory information. For each segment, the cycling distance and average speed of the segment are calculated using the data fusion model. The average speed is obtained using the following formula:

[0185]

[0186] in, represents the average speed of the i-th road section (m / s); v d (t) represents the instantaneous speed function collected by the instrument panel; v g (t) represents the instantaneous velocity function calculated by GPS; T i =[t i2 -t i1 ] represents the time interval of road section i; w i represents the fusion weight;

[0187] The riding distance and speed distribution calculated by the data fusion algorithm are compared and verified with the actual situation. Based on the verification results, the data fusion model is optimized and adjusted.

[0188] The working principle of the above technical solution is as follows: The speed information collected by the ebike instrument panel may be disturbed by noise, such as sensor measurement error, instantaneous speed fluctuation caused by road bumps, etc. By removing noise, filtering and smoothing, etc., these interference factors can be effectively eliminated, making the speed data more stable and accurate. For example, using a moving average filtering algorithm, the speed data within a certain time window is averaged to smooth out the instantaneous speed fluctuations and obtain data closer to the true speed. The motion trajectory information obtained by the smartphone GPS positioning system may have problems such as inconsistent coordinate systems and inconsistent timestamps. In order to ensure the consistency of the speed information in time and space, the motion trajectory information needs to be preprocessed. Coordinate conversion can unify the position information in different coordinate systems to the same coordinate system, which is convenient for subsequent data analysis and fusion. Time stamp alignment is to match the speed information and trajectory information in time sequence to ensure that the corresponding speed and position information can be obtained at the same time point.

[0189] Extract key features from the preprocessed speed information, such as speed peaks and speed change rates. Speed peaks can reflect the maximum speed during the ride, and speed change rates can reflect the speed increase and decrease speed. These features can describe the overall trend and characteristics of the ride speed. Extract features related to ride speed from the motion trajectory information, such as road segment length and turning angle. Road segment length can be obtained by calculating the distance between adjacent points on the trajectory and accumulating it, and turning angle can be determined by analyzing the direction change of the points on the trajectory. Matching these trajectory features with ride speed features can identify the speed characteristics of different road segments. For example, on a long straight road segment, the ride speed may be relatively high and change little; while on a turning road segment, the ride speed may decrease and the speed change rate may increase.

[0190] Based on the feature matching results, a data fusion model is constructed. This model considers both ride speed information and motion trajectory information and fuses them through certain algorithms and rules. For example, a weighted average method can be used to assign different weights according to the importance of speed features and trajectory features to calculate more accurate ride distance and speed distribution. According to the road segment division in the motion trajectory information, the ride process is divided into multiple road segments. For each road segment, the ride distance and average speed of the road segment are calculated using the data fusion model. At the same time, considering the change of ride speed in the road segment, more detailed speed distribution information is obtained by further analyzing the distribution and trend of speed data. For example, the proportion of different speed intervals in the road segment can be calculated to understand the distribution of ride speed in the road segment.

[0191] Compare the cycling distance and speed distribution calculated by the data fusion algorithm with the actual situation. The accuracy of the data fusion results can be evaluated by measuring in the field or referring to other reliable data sources, such as professional cycling record equipment or official road information. Based on the verification results, optimize and adjust the data fusion model. If there is a large deviation between the calculated results and the actual situation, the model's parameters, algorithms, or feature extraction methods may need to be adjusted to improve the model's accuracy and reliability. For example, if the road segment length calculation is inaccurate, the trajectory feature extraction algorithm can be optimized to improve the accuracy of road segment length calculation.

[0192] The effect of the above technical solution is that by preprocessing the cycling speed information collected by the ebike instrument panel and the motion trajectory information obtained by the smartphone GPS positioning system (such as denoising, filtering, coordinate conversion, etc.), the time and spatial consistency between different data sources is ensured, thereby greatly improving the accuracy and reliability of the final calculation results.

[0193] By extracting key features from the preprocessed cycling speed information and motion trajectory information and performing feature matching, the system can identify the speed characteristics of different road segments. The establishment of the data fusion model enables the system to calculate more accurate cycling distance and speed distribution based on these precise features, improving the intelligence and accuracy of data fusion.

[0194] Based on road segment division, the data fusion model can provide detailed cycling data analysis for each road segment, including the cycling distance, average speed, and speed variation of the road segment. This detailed analysis improves the accuracy of cycling route analysis, allowing users to obtain more accurate cycling information and speed distribution.

[0195] By comparing the cycling data with the actual situation (such as field measurement or reference to other reliable data sources), deviations and errors in the data can be discovered and corrected in a timely manner, further improving the accuracy of the data fusion model and reducing the negative impact of inaccurate data.

[0196] The real-time cycling distance and speed distribution calculated by the data fusion model enable the system to dynamically feedback the cycling state and route characteristics, providing more real-time and personalized cycling recommendations to users, enhancing the interactivity and real-time nature of the cycling experience. By verifying and optimizing the data fusion model, the model has stronger adaptive ability and can be adjusted and optimized according to different cycling environments and actual situations. This continuous optimization capability improves the long-term effectiveness and applicability of the model.

[0197] By precisely calculating the riding distance and speed distribution of each road segment, the system can provide users with clearer route and speed planning, helping them make more scientific and reasonable cycling decisions, thereby reducing the risks and uncertainties that may be encountered during cycling.

[0198] This data fusion model can be dynamically adjusted according to different road segment characteristics and cycling conditions, has strong scalability and adaptability, and can be applied to different types of cycling scenarios or environments, enhancing the system's versatility.

[0199] Through the fusion and verification of multiple data sources, the system can ensure the credibility and reliability of the cycling data, improve users' trust and reliance on data analysis results, and further enhance users' experience.

[0200] Fusing and analyzing multi-dimensional data such as cycling speed information, road segment information, and turning angles improves the system's comprehensive and in-depth analysis capabilities for the cycling process, providing users with more comprehensive and detailed cycling information, and enhancing the system's overall performance and analysis capabilities.

[0201] The above formula combines two data sources: speed information collected by the instrument panel and speed calculated by the GPS positioning system. This way, the strengths of both can be complemented. Instrument panels usually provide high instantaneous accuracy but may be affected by environmental or device errors, while GPS provides stable location information but may have errors in urban high-rise, tunnel, and other environments. By combining the two, a more accurate average speed estimate can be obtained.

[0202] The fusion weight plays a key role in the formula, allowing dynamic adjustment of the weight of the two data sources according to the characteristics of the road segment. For some road segments, the instrument panel speed may be more reliable (such as flat roads), while in complex environments (such as urban dense areas), the speed data from GPS may be more valuable. Through adaptive fusion weights, the optimal use of data sources for each road segment can be achieved.

[0203] Through integration, this formula can capture the speed changes within a time interval, not just instantaneous speed. This helps to reduce the volatility of instantaneous data and provides a more stable and reasonable average speed estimate. The design of this formula makes the final average speed not just a theoretical value, but a data fusion result that takes into account actual cycling conditions. By comparing and verifying with actual conditions, the model can be continuously optimized, improving the accuracy of calculations and the reliability of practical applications.

[0204] During the calculation process, the fusion model is continuously optimized through comparison and verification with actual conditions. This not only improves the model's predictive ability, but also makes it more adaptable in different environments, especially in complex road conditions, thereby providing cyclists with more accurate cycling data.

[0205] In one embodiment of the present application, S5 comprises:

[0206] S51, periodically collect user feedback to understand user satisfaction with interaction methods and interaction effects;

[0207] S52, continuously optimize the user intent recognition model according to user feedback and actual interaction effects;

[0208] S53, periodically evaluate the communication quality of the Bluetooth Mesh network, and adjust the network parameters according to the evaluation results;

[0209] S54, at the same time, establish a network fault early warning mechanism, when the network appears abnormal situation, timely send out the alarm, and take corresponding measures to repair.

[0210] The working principle of the above technical solution is: periodically collect user feedback through questionnaire survey, user evaluation, online customer service and other ways. These feedback channels can comprehensively obtain user satisfaction information on interaction methods and interaction effects. Questionnaire survey can design targeted questions to understand user preferences and needs for interaction methods in different scenarios; user evaluation can intuitively reflect user's views on the overall interaction experience; online customer service can timely obtain specific problems and suggestions encountered by users in the use process. For example, set the question "How satisfied are you with the current voice interaction method?" in the questionnaire survey, understand the user's evaluation of the interaction method through the user's choice. According to user feedback and actual interaction effects, continuously optimize the user intent recognition model. When it is found that the user's satisfaction with a certain interaction method is low, or the recognition model has low recognition accuracy in certain situations, more relevant user data and interaction records are collected. These data contain user behavior and intent information in different scenarios, and the model is retrained and adjusted, which can improve the adaptability and recognition accuracy of the model to various situations. For example, if the user feedback is that the intent recognition is not accurate in a specific road condition (such as bumpy road), more riding data, user operation records and corresponding actual intent in that road condition are collected, and the model is trained specifically to make the model better recognize the user's intent in that road condition.

[0211] The communication quality of the Bluetooth Mesh network is evaluated periodically, and key indicators such as the communication signal strength of the nodes, data transmission delay, and packet loss rate are monitored. The communication signal strength reflects the strength of the signal between nodes, and low signal strength can lead to unstable data transmission; the data transmission delay is the time required for data to travel from the sending node to the receiving node, and high delay can affect the real-time performance of the system; the packet loss rate indicates the proportion of data packets lost during transmission, and high packet loss rate can result in incomplete data. By monitoring these indicators, the communication status of the Bluetooth Mesh network can be comprehensively understood. For example, professional network monitoring tools are used to periodically detect the communication signal strength of each node and record the data transmission delay and packet loss rate. Based on the evaluation results, network parameters are adjusted to ensure the stability and reliability of the network. When a node's communication signal is found to be weak, the signal strength can be enhanced by adjusting the node's transmission power; or by optimizing the network topology and re-planning the communication path to reduce signal interference and transmission delay. For example, the communication path that originally passes through multiple nodes can be changed to direct communication, or the position of the node can be adjusted to make communication with other nodes smoother. Through these adjustments, the communication quality of the Bluetooth Mesh network can be improved, ensuring stable and efficient data transmission.

[0212] A network fault warning mechanism is established to monitor various indicators of the Bluetooth Mesh network in real time and issue warnings when abnormal conditions occur. For example, when the communication signal strength of a node suddenly drops below a preset threshold, or the data transmission delay and packet loss rate exceed the normal range, the system will automatically trigger an alarm to notify relevant personnel for handling. At the same time, appropriate measures are taken to repair the fault. Depending on the specific circumstances of the fault, measures such as restarting the node, replacing hardware devices, and adjusting network configurations can be taken. For example, if the node software is faulty, the node can be restarted; if the hardware device is damaged, a new device needs to be replaced; if there is a network configuration problem, relevant parameters can be adjusted.

[0213] The effect of the above technical solution is that by regularly collecting user feedback and adjusting the user intent recognition model based on feedback, the system can optimize the interaction mode in real time, improve the accuracy and adaptability of user experience, and ensure that the system can be flexibly adjusted according to different user needs.

[0214] By analyzing user feedback and continuously optimizing the recognition model, the system can effectively improve user interaction satisfaction, especially in cases where the recognition accuracy is low or the interaction mode is not ideal, the system can quickly respond and make targeted improvements, enhancing user satisfaction and trust in use.

[0215] For different road conditions and specific problems of user feedback (such as bumpy road), the accuracy and robustness of the user intent recognition model are improved by collecting more relevant data for retraining, ensuring that the system can maintain high recognition effect in variable environment. Continuous optimization and adjustment of the recognition model improve the dynamic adaptability of the system, which can adapt to changes in different use scenarios and environments, enhance the flexibility and operability of the system, and provide customized interactive experience for different users.

[0216] Periodically evaluate network communication quality and adjust network parameters based on evaluation results to ensure the communication stability of Bluetooth Mesh network, reduce signal interference and transmission delay, and improve the overall communication quality of the system, ensuring the continuous and efficient operation of the system.

[0217] By establishing a network fault warning mechanism, the system can issue an alarm and take repair measures in time when an exception occurs, enhancing the self-repairing ability of the system, reducing the impact of network failure, and ensuring the continuity and stability of the service.

[0218] Timely alarm and repair reduce the response time after failure, improve the timeliness and effectiveness of fault handling, and reduce service interruption and user experience problems caused by network anomalies.

[0219] By continuously monitoring the node communication signal strength, data transmission delay, packet loss rate, etc., and adjusting the network parameters, the data loss and delay in network communication can be effectively reduced, ensuring the smooth operation of the system and the accuracy of data transmission.

[0220] By optimizing the network topology structure and communication path, signal interference is reduced, network communication efficiency is improved, and the communication ability of the entire Bluetooth Mesh network is enhanced, improving the overall performance of the network.

[0221] Periodically evaluate and optimize the performance of the user intent recognition model and Bluetooth Mesh network to enhance the reliability of the system, ensure that the system always maintains high performance and maintainability during actual use, and provide stable and high-quality services.

[0222] One embodiment of the present application is an ebike intelligent human-computer interaction system based on Bluetooth Mesh networking, which includes a memory, a processor, and a computer program stored on the memory and executable on the memory. The processor executes the program to implement the ebike intelligent human-computer interaction method based on Bluetooth Mesh networking as described in any of the above embodiments.

[0223] It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application cover modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.

Claims

1. The ebike intelligent human-computer interaction method based on Bluetooth Mesh networking is characterized by: The method comprises: S1. Obtain the Bluetooth communication node information of each functional module of the ebike and the smart device carried by the user; perform Mesh network topology analysis on the obtained Bluetooth communication node information and construct the Bluetooth Mesh network topology structure of the ebike usage scenario; based on the constructed Bluetooth Mesh network topology structure, perform network configuration and parameter setting on each node to form a complete ebike Bluetooth Mesh communication network; S2. During the operation of the ebike, data related to the ebike is collected through various functional modules and intelligent devices, the collected data is pre-processed, and the data is classified according to different types; feature extraction is performed on the classified data; S3. Based on the extracted feature data, a user intent recognition model is constructed using a machine learning algorithm. Based on the identified user intent, the interaction mode is determined in combination with the ebike's functions and the current usage scenario. S4. After determining the interaction mode, the ebike and various smart devices are collaboratively interacted through the Bluetooth Mesh network; and the information from different devices is integrated and processed; S5. Continuously optimize the user intent recognition model and interaction strategy based on actual user feedback and interaction effects; regularly evaluate the communication quality of the Bluetooth Mesh network and adjust the network parameters based on the evaluation results.

2. The ebike intelligent human-computer interaction method based on Bluetooth Mesh networking according to claim 1, characterized in that: Said S1 comprises: S11, through the scanning program, obtain the Bluetooth communication node information of the ebike functional module and the smart device, the node information includes the node name, MAC address and signal strength; S12. Use graph theory algorithms to construct a Bluetooth Mesh network topology for ebike usage scenarios; S13, a dynamic adjustment algorithm based on the network topology structure, automatically identifies new nodes when they join the network and rationally integrates them into the existing topology structure based on their location and function; when existing nodes leave the network, the missing nodes are detected and the network path is replanned; S14. Assign a unique network address to each node according to the constructed Bluetooth Mesh network topology and set the communication parameters of the node; S15. Through the above configuration and settings, each node can communicate according to the Mesh network protocol to form a complete ebike Bluetooth Mesh communication network.

3. The ebike intelligent human-computer interaction method based on Bluetooth Mesh networking according to claim 2, characterized in that: Said S13 comprises: S131. Based on the deployed node monitoring module, continuously scan for devices within the Bluetooth signal range. When a new Bluetooth signal is detected, the new node access process is initiated. The MAC address of the new node is compared with the known node database to determine whether it is a newly added node. If it is a new node, its function information is further obtained. S132. Based on the RSSI value of the Bluetooth signal and the location information of known nodes, preliminarily determine the location of the new node; and evaluate the functional information of the new node; S133. Based on the position and function evaluation results of the new nodes, the network topology is replanned using graph theory algorithms; S134. Send network configuration information to the new node, update the network topology, incorporate the new node into the network, and notify other nodes about the joining information of the new node; at the same time, update the network path; S135. Real-time monitoring of the communication status of nodes in the network. When a node is detected to be unresponsive for a long time or the signal strength continues to decrease, a node departure detection process is initiated. The node is compared with the active node list in the node database to determine whether it has left the network. If confirmed to have left, a network reconstruction process is initiated to re-plan the network path. S136. After a node joins or leaves the network, the network stability is evaluated in real time, and the network topology is further optimized based on the evaluation results.

4. The ebike intelligent human-computer interaction method based on Bluetooth Mesh networking according to claim 3, characterized in that: The S133 includes: Using the graph structure in graph theory, existing nodes and new nodes are represented as vertices in the graph, and the connection relationship between vertices is represented as edges; based on the known node position information, the relative position of each vertex in the graph is preliminarily determined; Combined with the functional information of the new node, the communication requirements between it and the existing nodes are analyzed. Based on the graph theory algorithm, the optimal communication path between the new node and the existing nodes is calculated according to the communication requirements and location information between the nodes. Evaluate the quality of the planned communication paths and fine-tune the network topology based on the path quality and stability evaluation results; The adjusted network topology is displayed in a visual manner, and a detailed network topology update plan is generated.

5. The ebike intelligent human-computer interaction method based on Bluetooth Mesh networking according to claim 3 is characterized in that: The S135 includes: Real-time monitoring of the communication status of nodes in the network. When a node's signal strength is detected to be continuously decreasing or it is unresponsive for a long time, it is marked as a potential abnormal node. The historical communication data of the abnormal node is further analyzed to confirm whether there is any abnormality. For nodes that are confirmed to be abnormal, the node departure detection process is started. By comparing the active node list in the node database, the latest status information of the node is queried to confirm whether it has actually left the network. If the comparison confirms that the node has left the network, it will be removed from the active node list and the relevant information will be recorded. At the same time, the network topology will be updated and the node will be marked as having left. Based on the changes in network topology after the node leaves, the network reconstruction process is initiated; the network path is replanned using graph theory algorithms; Perform verification tests on the reconstructed network; further optimize the network topology based on the verification results, notify other nodes in the network of node departure and network reconstruction information, and update relevant records in the network management system.

6. The ebike intelligent human-computer interaction method based on Bluetooth Mesh networking according to claim 1, characterized in that: Said S2 comprises: S21, during the operation of the ebike, collecting data related to the ebike through various functional modules and intelligent devices; S22, cleaning the collected data, smoothing the cleaned data using a filtering algorithm, and classifying the smoothed data according to different types; S23, and extracting features from the classified data; S24. Through feature extraction, the original data is converted into representative and analyzable feature data.

7. The ebike intelligent human-computer interaction method based on Bluetooth Mesh networking according to claim 1, characterized in that: Said S3 comprises: S31. Collect historical riding data and user interaction records; annotate the collected data and determine the user intent corresponding to each data sample; S32. Select a machine learning algorithm and use the labeled data to train the model. During the training process, continuously adjust the model parameters, use the test data set to evaluate the trained model, and optimize the model based on the evaluation results. S33. Analyze the functions of the ebike and identify the appropriate interaction mode for each function; combine the user's historical usage habits and preferences to recommend interaction modes; S34. Determine a suitable interaction mode based on the identified user intent and the above interaction mode selection criteria.

8. The ebike intelligent human-computer interaction method based on Bluetooth Mesh networking according to claim 1, characterized in that: Said S4 comprises: S41. After the interaction mode is determined, when the user issues a control instruction through the smartphone, the smartphone sends the instruction to the corresponding functional module of the ebike through the Bluetooth Mesh network; S42, after receiving the instruction, the functional module of the ebike performs the corresponding operation and feeds back the operation result to the smart phone for the user to view; S43, fusing the riding speed information collected by the ebike dashboard with the motion trajectory information obtained by the smartphone GPS positioning system, and calculating the accurate riding distance and speed distribution through a data fusion algorithm; S44. Integrate the heart rate data collected by the user's smart watch with the ebike's riding status data to analyze the impact of riding on the user's body; and provide users with more personalized health advice.

9. The ebike intelligent human-computer interaction method based on Bluetooth Mesh networking according to claim 1, characterized in that: Said S5 comprises: S51. Regularly collect user feedback to understand user satisfaction with interaction methods and effects. S52. Continuously optimize the user intent recognition model based on user feedback and actual interaction effects; S53. Regularly evaluate the communication quality of the Bluetooth Mesh network and adjust network parameters based on the evaluation results. S54. At the same time, a network fault early warning mechanism should be established. When abnormal conditions occur in the network, an alarm will be issued in a timely manner and appropriate measures will be taken to repair the situation.

10. The ebike intelligent human-computer interaction system based on Bluetooth Mesh networking is characterized by: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the memory, wherein the processor executes the program to implement the ebike intelligent human-computer interaction method based on Bluetooth Mesh networking as described in any one of claims 1 to 9.

Images