Riding rest strategy generation method and device, equipment and storage medium

Abstract

The invention belongs to the technical field of data processing, and discloses a riding rest strategy generation method and device, equipment and a storage medium. According to the method, the current riding route of the rider is divided to obtain the divided multiple sections of riding routes, then the route type corresponding to each section of riding route is determined, the riding physical power data corresponding to each section of riding route is determined based on the route type, and then the rest strategy corresponding to the rider is generated according to the riding physical power data. According to the method, the current riding route of the rider is firstly divided to obtain multiple sections of different types of riding routes, and then the riding physical power data corresponding to each section of riding route is determined based on the route type, so that the riding physical power data consumed by the rider in the process of passing through different terrains can be respectively determined; and then a rest strategy corresponding to the rider is generated according to the riding physical power data, so that the rest strategy can be formulated for the rider in time, and the riding experience and safety are improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, device and storage medium for generating cycling rest strategies. Background Technology

[0002] In cycling, cyclists have an increasing need for route planning. They not only need reasonable route planning, but also need to consider issues such as rest and supplies. Currently, personalized cycling routes are usually recommended based on the cyclist's exercise status and safety needs, but the selection of rest stops and the provision of supply information during the ride are not taken into account. Especially during long-distance or complex terrain cycling, timely rest reminders are crucial to improving the cycling safety of cyclists. Summary of the Invention

[0003] The main purpose of this application is to provide a method, device, equipment and storage medium for generating cycling rest strategies, aiming to solve the technical problem of how to formulate rest strategies for cyclists in a timely manner as they traverse various terrains.

[0004] To achieve the above objectives, this application provides a method for generating cycling rest strategies, which includes the following steps: The cyclist's current cycling route is divided into multiple segments to obtain the resulting cycling routes; Determine the route type corresponding to each cycling segment, and determine the cycling physical fitness data corresponding to each cycling segment based on the route type; Rest strategies are generated based on cycling physical fitness data.

[0005] Optionally, determine the route type corresponding to each cycling segment, and determine the cycling physical fitness data corresponding to each cycling segment based on the route type, including: Determine the path length and route type for each segment of the cycling route. Route types include: uphill, flat, and downhill. When the route type is flat, the cycling physical exertion data is determined based on the path length; When the route type is uphill or downhill, the target gradient coefficient is determined according to the route type, and the cycling physical exertion data is determined according to the path length and the target gradient coefficient.

[0006] Optionally, if the route type is uphill or downhill, the target gradient coefficient is determined based on the route type, including: If the route type is uphill or downhill, determine the slope angle corresponding to each segment of the cycling route; The correction coefficient for each segment of the cycling route is determined based on the slope angle. The initial slope coefficients for each section of the route are corrected using the correction coefficients to obtain the target slope coefficients.

[0007] Optionally, the correction coefficients for each segment of the cycling route are determined based on the slope angle, including: When the route type is downhill, determine the interval corresponding to the slope angle; The correction coefficient is determined based on the interval and slope angle; When the route type is uphill, the correction coefficient is determined based on the slope angle.

[0008] Optionally, a rest strategy for cyclists can be generated based on their cycling physical fitness data, including: The predicted cycling distance for the next length interval is determined based on the cycling physical fitness data corresponding to each cycling segment. Calculate the current remaining rideable amount within the current length range based on the remaining rideable amount for each rider and the predicted rideable amount. Based on the current remaining total number of rideable bikes, determine the physical condition data of the riders and collect current weather data; Input physical condition data, current weather data, cycling physical strength data, and map information corresponding to the current cycling route into a preset prediction model to obtain the rest strategy corresponding to the cyclist.

[0009] Optionally, before inputting physical condition data, current weather data, cycling stamina data, and map information corresponding to the current cycling route into a preset prediction model to obtain the cyclist's corresponding rest strategy, the following steps are also included: Obtain historical physical condition data and historical cycling physical strength data for cyclists, as well as historical weather data and historical map information; The initial prediction model is trained using historical physical condition data, historical weather data, historical cycling physical strength data, and historical map information to obtain the preset prediction model.

[0010] Optionally, the initial prediction model includes: a convolutional neural network and a long short-term memory network; the initial prediction model is trained using historical physical condition data, historical weather data, historical cycling physical fitness data, and historical map information to obtain a preset prediction model, including: Historical physical condition data, historical weather data, historical cycling physical strength data, and historical map information are input into a convolutional neural network to obtain the target feature sequence; The target feature sequence is input into a long short-term memory network to obtain the historical rest strategies corresponding to cyclists; The initial prediction model is trained based on historical rest strategies and the actual rest strategies of cyclists to obtain the preset prediction model.

[0011] Furthermore, to achieve the above objectives, this application also provides a cycling rest strategy generation device, which includes: The route segmentation module is used to divide the cyclist's current cycling route into multiple segments. The data determination module is used to determine the route type corresponding to each cycling segment and to determine the cycling physical fitness data corresponding to each cycling segment based on the route type. The strategy generation module is used to generate rest strategies for cyclists based on their cycling physical fitness data.

[0012] In addition, to achieve the above objectives, this application also proposes a cycling rest strategy generation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the cycling rest strategy generation method described above.

[0013] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the cycling rest strategy generation method described above.

[0014] This application divides the cyclist's current route into multiple segments, determines the route type for each segment, and then identifies the corresponding cyclist's physical exertion data based on the route type. Finally, it generates a rest strategy tailored to the cyclist based on this physical exertion data. This approach first divides the cyclist's current route into multiple segments of different types, then determines the physical exertion data for each segment based on the route type. This allows for the identification of the cyclist's physical exertion while traversing different terrains, and finally, the generation of a rest strategy based on this data. This enables timely implementation of rest strategies for cyclists, improving both the cycling experience and safety. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the first embodiment of the cycling rest strategy generation method of this application; Figure 2 This is a flowchart illustrating the second embodiment of the cycling rest strategy generation method of this application; Figure 3 This is a flowchart illustrating the third embodiment of the cycling rest strategy generation method of this application; Figure 4 This is a structural block diagram of the first embodiment of the cycling rest strategy generation device of this application; Figure 5 This is a schematic diagram of the structure of the cycling rest strategy generation device in the hardware operating environment involved in the embodiments of this application.

[0018] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0020] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0021] It should be noted that the executing entity of this application can be a mobile device with data processing, network communication and program execution functions, such as a mobile phone or tablet computer.

[0022] Based on this, embodiments of this application provide a method for generating cycling rest strategies, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the cycling rest strategy generation method of this application.

[0023] In this embodiment, the cycling rest strategy generation method includes the following steps: Step S10: Divide the cyclist's current cycling route to obtain multiple segments of the cycling route.

[0024] Understandably, the current cycling route can be the route from the starting point to the end point. The current cycling route can be divided into multiple segments. In one feasible embodiment, the starting point A and ending point C of the current cycling route can be obtained using GPS (Global Positioning System). The waypoints B of the current cycling route can also be determined based on starting point A and ending point C. Specifically, the elevation difference of each segment of the current cycling route can be determined to identify whether it is uphill, downhill, or flat. The starting and ending points of each segment are then waypoints B. For example, if a 1-kilometer stretch consists of 500 meters of uphill and 500 meters of flat road, then B1-B2 are the starting and ending points of the uphill section, and B2-B3 are the starting and ending points of the flat road section. Alternatively, the waypoints can be determined using the current cycling route displayed on a mobile device map.

[0025] It should be understood that after determining the starting point A, the waypoint B, and the destination C in the current cycling route, the divided cycling routes can be determined as follows: starting point A - waypoint B1, waypoint B1 - waypoint B2... waypoint Bn - destination C.

[0026] Step S20: Determine the route type corresponding to each cycling segment, and determine the cycling physical fitness data corresponding to each cycling segment based on the route type.

[0027] Understandably, the route type corresponding to each segment of the cycling route can be determined. Route types may include uphill, flat, and downhill types. In one feasible embodiment, the starting point A, waypoint B, and destination C can be imported into the navigation system, and the road conditions along the route can be described. The road condition description includes the following characteristics: road type (highway, city road, provincial road, etc.), number of lanes, speed limit, road surface condition (good, average, poor, etc.), and whether it is a steep slope (obtained from map information based on elevation difference). This information can be read from the navigation system; for example, if there is no steep slope within 100 meters, it is considered flat; otherwise, it is marked as uphill or downhill.

[0028] In practical implementation, cycling physical exertion data for each segment of the cycling route can be determined based on the route type. This data can include the cyclist's expended physical exertion and remaining physical exertion. When the route is downhill, the cyclist requires less physical exertion; when the route is uphill, the cyclist requires more physical exertion; and when the route is flat, the cyclist requires moderate physical exertion.

[0029] Step S30: Generate a rest strategy for the cyclist based on the cycling physical fitness data.

[0030] It should be understood that after obtaining the cycling physical strength data of the cyclist, a rest strategy corresponding to the cyclist can be generated. In one feasible embodiment, the current user's physical strength and current physical fitness can be obtained by combining the cycling distance, cycling speed, and rest time during each ride. The number of rests suitable for this cycling plan, the number of rests, and the duration of each rest are given. Specifically, the user's physical strength has an initial default value / or the user can input it themselves. Then, the physical strength is converted into the total amount of cycling that can be done. By calculating how much cycling will be consumed for each segment of the road, the user is recommended to rest in the segments where the cycling volume is alarmed. Each rest can be determined by motion positioning to know that the user has not been cycling, or the user can set a rest time for themselves. The user's physical strength will recover during the rest, which is used for subsequent calculations. The rest strategy can be roughly obtained through the above method.

[0031] In a specific implementation, this embodiment can also combine a model to generate an accurate rest strategy. The model can be a convolutional neural network, which can be trained using the cyclist's historical cycling data. After training, the cyclist's current physical strength data is input into the model so that the model outputs a rest strategy. The rest strategy obtained from the model is then used to calibrate the roughly obtained rest strategy, thereby improving the accuracy of formulating a rest strategy for the cyclist.

[0032] This embodiment divides the cyclist's current route into multiple segments, determines the route type for each segment, and then determines the cyclist's physical exertion data based on the route type. Finally, it generates a rest strategy for the cyclist based on this physical exertion data. This embodiment first divides the cyclist's current route into multiple segments of different types, then determines the physical exertion data for each segment based on the route type. This allows for the determination of the cyclist's physical exertion data as they traverse different terrains, and finally generates a rest strategy based on this data. This enables timely implementation of rest strategies for cyclists, improving the cycling experience and safety.

[0033] refer to Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the cycling rest strategy generation method of this application.

[0034] Based on the first embodiment described above, in this embodiment, step S20 includes: Step S201: Determine the path length and route type corresponding to each cycling segment. Route types include: uphill, flat, and downhill.

[0035] Understandably, the path length and route type corresponding to each cycling route segment can be determined. In one feasible embodiment, if a cycling route segment has virtually no elevation difference, then the cycling route segment is considered to be a flat road type; if the starting elevation of a cycling route segment is higher than the ending elevation, then the cycling route segment is considered to be a downhill type; if the starting elevation of a cycling route segment is lower than the ending elevation, then the cycling route segment is considered to be an uphill type.

[0036] Step S202: If the route type is flat, determine the cycling physical strength data based on the path length.

[0037] It should be understood that, when the route type is flat, cycling physical exertion data can be directly determined based on the path length. In one feasible embodiment, , This refers to cycling physical fitness data under flat road conditions. The distance is the path length on a flat road. Cycling physical fitness data can be expressed as the total amount of time a cyclist can complete on a flat road.

[0038] Step S203: If the route type is uphill or downhill, determine the target gradient coefficient according to the route type, and determine the cycling physical strength data according to the path length and the target gradient coefficient.

[0039] Understandably, if the route type is uphill or downhill, it means that the corresponding cycling route has a gradient. In this case, the target gradient coefficient can be determined according to the route type. The target gradient coefficient can represent the impact of the gradient on physical strength. Then, the cycling physical strength data can be determined according to the path length and the target gradient coefficient. The cycling physical strength data can be obtained by multiplying the path length by the target gradient coefficient.

[0040] Furthermore, in order to accurately obtain the target gradient coefficient corresponding to each segment of the cycling route, in this embodiment, when the route type is uphill or downhill, the target gradient coefficient is determined according to the route type, including: when the route type is uphill or downhill, determining the gradient angle corresponding to each segment of the cycling route; determining the correction coefficient corresponding to each segment of the cycling route according to the gradient angle; and correcting the initial gradient coefficient corresponding to each segment of the route according to the correction coefficient to obtain the target gradient coefficient.

[0041] It should be understood that when the route type is uphill or downhill, the corresponding gradient angle for each segment of the cycling route can be determined. For any given segment of the cycling route, the vertical height difference of that segment is... , and The elevations of the starting and ending points of the cycling route are represented respectively, and then the horizontal distance of the cycling route is calculated. , This indicates the path length of the cycling route and the corresponding initial gradient coefficient. The gradient angle of this cycling route .

[0042] In practice, the correction coefficient for each segment of the cycling route can be determined based on the slope angle. Since cycling downhill requires less effort than cycling uphill, the correction coefficient for downhill routes is greater than that for uphill routes. The initial slope coefficient for each segment is then corrected based on these correction coefficients to obtain the target slope coefficient. Cycling physical exertion data under uphill conditions , This represents the path length for uphill routes. Cycling physical exertion data for downhill routes. , This represents the path length on the downhill route.

[0043] Furthermore, in order to obtain the correction coefficients for uphill and downhill types, in this embodiment, the correction coefficients corresponding to each cycling route segment are determined based on the slope angle, including: when the route type is downhill, determining the interval corresponding to the slope angle; determining the correction coefficient based on the interval and the slope angle; and when the route type is uphill, determining the correction coefficient based on the slope angle.

[0044] Understandably, when the route type is downhill, the interval corresponding to the slope angle can be determined, and then the correction coefficient can be determined based on the interval and the slope angle. In a feasible embodiment, if the slope angle is in the interval 1:0°≤ If the angle is ≤10°, then the correction coefficient k = 1 - 0.01 Calculate the target slope coefficient The formula is:

[0045] In the formula, This is the initial slope coefficient.

[0046] If the slope angle is in the range 2:10° < If the angle is ≤45°, then the correction coefficient k = 0.9 - (0.9 / 35) × ( -10), calculate the target slope coefficient The formula is:

[0047] If the slope angle is in range 3: If the slope is greater than 45°, then the correction coefficient k = 0, and the target slope coefficient is... =0, that is >45° >1, because tan45°=1.

[0048] It should be understood that when the route type is uphill, the correction coefficient can be directly determined based on the slope angle, and the correction coefficient k = 1 + 0.1 Calculate the target slope coefficient The formula is:

[0049] This embodiment determines the path length and route type for each cycling segment. Route types include uphill, flat, and downhill. When the route type is flat, cycling physical exertion data is determined based on the path length. When the route type is uphill or downhill, a target gradient coefficient is determined based on the route type, and then cycling physical exertion data is determined based on both the path length and the target gradient coefficient. This embodiment, by determining cycling physical exertion data based on path length when the route type is flat, and by determining cycling physical exertion data based on the path length and the target gradient coefficient corresponding to the uphill or downhill route, takes into account the impact of gradient on physical exertion during cycling, thus obtaining accurate cycling physical exertion data.

[0050] refer to Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the cycling rest strategy generation method of this application.

[0051] Based on the above embodiments, in this embodiment, step S30 includes: Step S301: Determine the predicted cycling distance for the next length interval based on the cycling physical fitness data corresponding to each cycling route segment.

[0052] Understandably, in this embodiment, the length interval can be every kilometer. After obtaining the cycling physical exertion data corresponding to each segment of the cycling route, the predicted cycling distance for the next length interval, i.e., the next kilometer, is... The corresponding cycling stamina data is only available when there is an uphill, downhill, or flat road in the next kilometer.

[0053] Step S302: Calculate the current remaining rideable amount within the current length interval based on the remaining rideable amount corresponding to the rider and the predicted rideable amount.

[0054] It should be understood that the remaining total riding distance can be the distance that the cyclist can still ride at the current moment. If it is a flat road, the riding distance can be directly used as the riding amount. If it is uphill or downhill, the riding distance needs to be multiplied by a coefficient to obtain the riding amount. This coefficient can be set by the cyclist.

[0055] In the specific implementation, within the current length range, i.e., the current one kilometer, the current remaining total number of rideable bikes. , This represents the remaining cycling distance for the next kilometer. This represents the remaining number of rideable bikes for each cyclist. This is the predicted cycling distance for the next kilometer. Additionally, this embodiment allows setting an initial total physical exertion level. , This is the physical strength coefficient. This is the initial total number of rides that can be taken. First-time riders can set this value.

[0056] Step S303: Determine the physical condition data of the riders based on the current remaining total number of rideable bikes, and collect the current weather data.

[0057] Understandably, the system can determine a cyclist's physical condition based on the remaining available riding capacity. When a user is resting, their energy and riding volume can be increased, with the specific increase predicted by a large model. During non-rest periods, physical indicators such as heart rate, blood pressure, body temperature, and respiratory rate are monitored. Ideally, all indicators are collected via smart devices and automatically input into the monitoring center. Physical condition data can include the aforementioned heart rate, blood pressure, body temperature, and respiratory rate. Current weather data can also be collected.

[0058] It should be understood that when the remaining amount of rideable time is below the threshold, it indicates that the user's energy is low or insufficient for the next stage of riding. If the remaining amount of rideable time is insufficient for the next stage or close to the threshold, the user can be reminded to adjust their riding pace through voice announcements and text reminders. If the user is too excited or exerts too much effort, they can also be reminded to slow down. If there is a rest stop or service area ahead, the user can be reminded to go there to rest and replenish energy through voice announcements and text reminders.

[0059] Step S304: Input the physical condition data, current weather data, cycling physical strength data, and map information corresponding to the current cycling route into the preset prediction model to obtain the rest strategy corresponding to the cyclist.

[0060] Understandably, physical condition data, current weather data, cycling stamina data, and map information corresponding to the current cycling route can be input into a preset prediction model. The preset prediction model can be a pre-trained network model, which can be composed of a convolutional neural network (CNN) and a long short-term memory network (LSTM) to obtain the rest strategy corresponding to the cyclist. The rest strategy can include the number of rests, the number of rests, the duration of each rest, recommended rest points, and nearby locations where supplies can be purchased.

[0061] In its specific implementation, this embodiment can also calculate cycling evaluations, such as climbing intensity, average speed, and calorie consumption, and display them to the cyclist. Furthermore, it records the distance traveled (L) in meters; the cycling time (T) in seconds; the average cycling speed (V) in km / h; and GPS information.

[0062] Furthermore, in order to accurately obtain the initial prediction model, in this embodiment, before step S304, the method further includes: acquiring the historical physical condition data and historical cycling physical strength data corresponding to the cyclist, and acquiring historical weather data and historical map information; training the initial prediction model with the historical physical condition data, historical weather data, historical cycling physical strength data and historical map information to obtain the preset prediction model.

[0063] It should be understood that, in order to train the initial prediction model, sample data can be collected. This sample data may include historical physical condition data and cycling physical strength data of cyclists within a historical time period, as well as historical weather data and historical map information within the same period. Inputting this sample data into the initial prediction model allows for its training, resulting in a prediction model. In this embodiment, the initial prediction model comprises a Convolutional Neural Network (CNN) and a Long Short-Term Memory Network (LSTM), forming a CNN-LSTM model.

[0064] Furthermore, in order to effectively train the initial prediction model, in this embodiment, the initial prediction model is trained using historical physical condition data, historical weather data, historical cycling physical strength data, and historical map information to obtain a preset prediction model. This includes: inputting historical physical condition data, historical weather data, historical cycling physical strength data, and historical map information into a convolutional neural network to obtain a target feature sequence; inputting the target feature sequence into a long short-term memory network to obtain the historical rest strategy corresponding to the cyclist; and training the initial prediction model based on the historical rest strategy and the actual rest strategy corresponding to the cyclist to obtain the preset prediction model.

[0065] Understandably, by inputting historical physical condition data, historical weather data, historical cycling physical strength data, and historical map information into a convolutional neural network, the convolutional neural network can output a target feature sequence. Inputting the target feature sequence into a long short-term memory network can yield historical rest strategies based on sample data. Furthermore, standard actual rest strategies can be pre-set. Thus, the initial prediction model can be trained based on the historical rest strategies and the actual rest strategies to obtain a preset prediction model.

[0066] It should be understood that, based on the historical physical condition dataset, historical weather dataset, and historical cycling physical fitness dataset (including uphill, flat, and downhill datasets), as well as historical map information, a convolutional neural network is trained to obtain a first, second, third, fourth, fifth, and sixth classifier. These classifiers are then cascaded to form a classification network. A trained LSTM neural network is then connected after the classification network to obtain a CNN-LSTM combined neural network model. Based on this CNN-LSTM combined neural network model, a rest strategy is derived for the current dataset: the historical physical condition dataset, historical weather dataset, and historical cycling physical fitness dataset (including uphill, flat, and downhill datasets), and historical map information.

[0067] Specifically, this embodiment first constructs a convolutional neural network (CNN) to process feature extraction from cyclist information and environmental data, obtaining a target feature sequence. The network architecture includes the following parts: Input layer: Multiple input nodes are set to receive historical physical condition datasets, historical weather datasets, uphill datasets, flat road datasets, downhill datasets from historical cycling physical strength datasets, and historical map information; Convolutional layer: Multiple convolutional layers perform convolution operations on the input data to extract local features, and multiple convolutional kernels are used to achieve multi-angle feature extraction; Activation layer: A ReLU (Rectified Linear Unit) activation function is added after the convolutional layers to solve the gradient vanishing problem and speed up training; Pooling layer: Max pooling is used to reduce computation and prevent overfitting; Fully connected layer: A fully connected layer is added at the end of the network to map the features extracted by the convolutional layers to the label space, integrate the features of different feature maps, and complete the classification or regression task.

[0068] Furthermore, this embodiment trains each classifier by establishing multiple corresponding datasets to train the CNN. The specific steps are as follows: First classifier: The CNN is trained using samples placed into a historical physical condition dataset, focusing on learning the relationship between physical condition and physical strength; Second classifier: The CNN is trained using samples placed into a historical weather dataset, focusing on learning the relationship between weather and physical strength; Third classifier: The CNN is trained using samples placed into an uphill dataset, focusing on learning the relationship between uphill data and physical strength; Fourth classifier: The CNN is trained using samples placed into a flat road dataset, focusing on learning the relationship between flat road data and physical strength; Fifth classifier: The CNN is trained using samples placed into a downhill dataset, focusing on learning the relationship between downhill data and physical strength; Sixth classifier: The CNN is trained using samples placed into historical map information, focusing on learning the relationship between map information and physical strength.

[0069] This embodiment cascades multiple trained classifiers to form a comprehensive classification network, specifically as follows: The output features of each classifier are concatenated to form a more comprehensive feature representation. This involves connections between the various classifiers to integrate the influence of different types of inputs. Using fusion strategies such as weighted averaging and concatenation, the features of multiple classifiers are combined to form a powerful feature representation. This can be specifically implemented through a feature fusion layer. Furthermore, this embodiment connects a Long Short-Term Memory (LSTM) network after the cascaded classification network. The feature sequences obtained from the classification network are input into the LSTM, which learns the correlation at different time points through its internal gating mechanism, enabling prediction of future riding states. The merged dataset is used to train the entire CNN-LSTM combined model, updating all weights in the joint network to ensure that the model effectively integrates the learning results of the convolutional layers and the LSTM layer. Based on the trained CNN-LSTM combined network, predictions are performed on new input data to obtain the rest strategy corresponding to the cyclist.

[0070] This embodiment determines the predicted cycling distance for the next length interval based on the cycling stamina data corresponding to each cycling segment. Then, it calculates the current remaining cycling distance for the current length interval based on the cyclist's remaining cycling distance and the predicted cycling distance. Next, it uses the cyclist's physical condition data corresponding to the current remaining cycling distance, collects current weather data, and inputs the physical condition data, current weather data, cycling stamina data, and map information corresponding to the current cycling route into a preset prediction model to obtain the cyclist's corresponding rest strategy. This embodiment inputs physical condition data, current weather data, cycling stamina data, and map information corresponding to the current cycling route into a preset prediction model, which can accurately predict the cyclist's rest strategy through deep learning, improving the cycling experience and safety.

[0071] Reference Figure 4 , Figure 4 This is a structural block diagram of the first embodiment of the cycling rest strategy generation device of this application.

[0072] like Figure 4 As shown, the cycling rest strategy generation device proposed in this application includes: The route division module 10 is used to divide the current cycling route of the cyclist and obtain multiple segments of the divided cycling route; The data determination module 20 is used to determine the route type corresponding to each segment of the cycling route, and to determine the cycling physical fitness data corresponding to each segment of the cycling route based on the route type. The strategy generation module 30 is used to generate rest strategies for cyclists based on their cycling physical fitness data.

[0073] This embodiment divides the cyclist's current route into multiple segments, determines the route type for each segment, and then determines the cyclist's physical exertion data based on the route type. Finally, it generates a rest strategy for the cyclist based on this physical exertion data. This embodiment first divides the cyclist's current route into multiple segments of different types, then determines the physical exertion data for each segment based on the route type. This allows for the determination of the cyclist's physical exertion data as they traverse different terrains, and finally generates a rest strategy based on this data. This enables timely implementation of rest strategies for cyclists, improving the cycling experience and safety.

[0074] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this application. In practical applications, those skilled in the art can select some or all of it to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0075] In addition, for technical details not described in detail in this embodiment, please refer to the cycling rest strategy generation method provided in any embodiment of this application, which will not be repeated here.

[0076] Based on the first embodiment of the cycling rest strategy generation device described in this application, a second embodiment of the cycling rest strategy generation device of this application is proposed.

[0077] In this embodiment, the data determination module 20 is also used to determine the path length and route type corresponding to each segment of the cycling route. The route type includes: uphill type, flat road type, and downhill type. When the route type is flat road type, the cycling physical strength data is determined based on the path length. When the route type is uphill or downhill type, the target gradient coefficient is determined based on the route type, and the cycling physical strength data is determined based on the path length and the target gradient coefficient.

[0078] Furthermore, the data determination module 20 is also used to determine the slope angle corresponding to each segment of the cycling route when the route type is uphill or downhill; determine the correction coefficient corresponding to each segment of the cycling route based on the slope angle; and correct the initial slope coefficient corresponding to each segment of the route based on the correction coefficient to obtain the target slope coefficient.

[0079] Furthermore, the data determination module 20 is also used to determine the interval corresponding to the slope angle when the route type is downhill; determine the correction coefficient based on the interval and the slope angle; and determine the correction coefficient based on the slope angle when the route type is uphill.

[0080] Furthermore, the strategy generation module 30 is also used to determine the predicted cycling volume in the next length interval based on the cycling physical strength data corresponding to each cycling route segment; calculate the current remaining cycling volume in the current length interval based on the remaining cycling volume corresponding to the cyclist and the predicted cycling volume; determine the physical condition data corresponding to the cyclist based on the current remaining cycling volume, and collect the current weather data; input the physical condition data, current weather data, cycling physical strength data, and map information corresponding to the current cycling route into the preset prediction model to obtain the rest strategy corresponding to the cyclist.

[0081] Furthermore, the strategy generation module 30 is also used to acquire historical physical condition data and historical cycling physical strength data corresponding to the cyclist, as well as historical weather data and historical map information; the initial prediction model is trained by the historical physical condition data, historical weather data, historical cycling physical strength data and historical map information to obtain a preset prediction model, which includes a convolutional neural network and a long short-term memory network.

[0082] Furthermore, the strategy generation module 30 is also used to input historical physical condition data, historical weather data, historical cycling physical strength data, and historical map information into a convolutional neural network to obtain a target feature sequence; input the target feature sequence into a long short-term memory network to obtain the historical rest strategy corresponding to the cyclist; and train the initial prediction model based on the historical rest strategy and the actual rest strategy corresponding to the cyclist to obtain a preset prediction model.

[0083] Other embodiments or specific implementations of the cycling rest strategy generation device of this application can be found in the above-described method embodiments, and will not be repeated here.

[0084] This application provides a cycling rest strategy generation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the cycling rest strategy generation method in the above embodiment 1.

[0085] The following is for reference. Figure 5 The diagram illustrates a structural schematic of a cycling rest strategy generation device suitable for implementing embodiments of this application. The cycling rest strategy generation device in this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The cycling rest strategy generation device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0086] like Figure 5As shown, the cycling rest strategy generation device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the cycling rest strategy generation device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the cycling rest strategy generation device to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows cycling rest strategy generation devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0087] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0088] The cycling rest strategy generation device provided in this application, employing the cycling rest strategy generation method in the above embodiments, can solve the technical problem of how to formulate rest strategies for cyclists in a timely manner while they traverse various terrains. Compared with the prior art, the beneficial effects of the cycling rest strategy generation device provided in this application are the same as those of the cycling rest strategy generation method provided in the above embodiments, and other technical features in this cycling rest strategy generation device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0089] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0090] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0091] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the cycling rest strategy generation method in the above embodiments.

[0092] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0093] The aforementioned computer-readable storage medium may be included in the cycling rest strategy generation device; or it may exist independently and not assembled into the cycling rest strategy generation device.

[0094] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the cycling rest strategy generation device, cause the cycling rest strategy generation device to: divide the cyclist's current cycling route into multiple segments; determine the route type corresponding to each segment of the cycling route, and determine the cycling physical fitness data corresponding to each segment of the cycling route based on the route type; and generate a rest strategy corresponding to the cyclist based on the cycling physical fitness data.

[0095] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages—such as Python, Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0097] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0098] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described cycling rest strategy generation method. This solves the technical problem of how to promptly formulate rest strategies for cyclists traversing various terrains. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the cycling rest strategy generation method provided in the above embodiments, and will not be elaborated upon here.

[0099] The above are only some embodiments of this application and do not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A method for generating cycling rest strategies, characterized in that, The method for generating cycling rest strategies includes the following steps: The cyclist's current cycling route is divided into multiple segments to obtain the resulting cycling routes; Determine the route type corresponding to each cycling segment, and determine the cycling physical fitness data corresponding to each cycling segment based on the route type; A rest strategy is generated for the cyclist based on the cycling physical fitness data.

2. The cycling rest strategy generation method as described in claim 1, characterized in that, The process of determining the route type corresponding to each cycling segment and determining the cycling physical fitness data corresponding to each cycling segment based on the route type includes: Determine the path length and route type corresponding to each segment of the cycling route. The route types include: uphill, flat, and downhill. When the route type is the flat road type, the cycling physical exertion data is determined based on the path length; When the route type is either uphill or downhill, the target gradient coefficient is determined based on the route type, and the cycling physical exertion data is determined based on the path length and the target gradient coefficient.

3. The cycling rest strategy generation method as described in claim 2, characterized in that, When the route type is either uphill or downhill, determining the target slope coefficient based on the route type includes: When the route type is either uphill or downhill, determine the slope angle corresponding to each segment of the cycling route; The correction coefficients for each segment of the cycling route are determined based on the slope angle. The initial slope coefficients corresponding to each section of the route are corrected according to the correction coefficients to obtain the target slope coefficients.

4. The cycling rest strategy generation method as described in claim 3, characterized in that, The process of determining the correction coefficients corresponding to each segment of the cycling route based on the slope angle includes: When the route type is the downhill type, determine the interval corresponding to the slope angle; The correction coefficient is determined based on the interval and the slope angle; When the route type is the uphill type, the correction coefficient is determined based on the slope angle.

5. The cycling rest strategy generation method as described in any one of claims 1 to 4, characterized in that, The step of generating a rest strategy for the cyclist based on the cycling physical fitness data includes: The predicted cycling distance for the next length interval is determined based on the cycling physical fitness data corresponding to each cycling segment. Calculate the current remaining rideable total within the current length interval based on the remaining rideable total for the rider and the predicted rideable amount; Based on the current remaining total number of rideable bikes, determine the physical condition data of the riders and collect current weather data; The physical condition data, the current weather data, the cycling physical strength data, and the map information corresponding to the current cycling route are input into a preset prediction model to obtain the rest strategy corresponding to the cyclist.

6. The cycling rest strategy generation method as described in claim 5, characterized in that, Before inputting the physical condition data, the current weather data, the cycling stamina data, and the map information corresponding to the current cycling route into a preset prediction model to obtain the rest strategy corresponding to the cyclist, the method further includes: Obtain historical physical condition data and historical cycling physical strength data corresponding to the cyclists, as well as historical weather data and historical map information; The initial prediction model is trained using the historical physical condition data, the historical weather data, the historical cycling physical strength data, and the historical map information to obtain the preset prediction model.

7. The cycling rest strategy generation method as described in claim 6, characterized in that, The initial prediction model includes a convolutional neural network and a long short-term memory network; the process of training the initial prediction model using the historical physical condition data, the historical weather data, the historical cycling physical strength data, and the historical map information to obtain the preset prediction model includes: The historical physical condition data, historical weather data, historical cycling physical strength data, and historical map information are input into the convolutional neural network to obtain the target feature sequence; The target feature sequence is input into the long short-term memory network to obtain the historical rest strategy corresponding to the cyclist; The initial prediction model is trained based on the historical rest strategies and the actual rest strategies of the cyclists to obtain the preset prediction model.

8. A cycling rest strategy generation device, characterized in that, The cycling rest strategy generation device includes: The route segmentation module is used to divide the cyclist's current cycling route into multiple segments. The data determination module is used to determine the route type corresponding to each cycling route segment, and to determine the cycling physical fitness data corresponding to each cycling route segment based on the route type. The strategy generation module is used to generate a rest strategy corresponding to the cyclist based on the cycling physical fitness data.

9. A cycling rest strategy generation device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the cycling rest strategy generation method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the cycling rest strategy generation method as described in any one of claims 1 to 7.

Images