Outdoor exercise information processing method and device, program product and storage medium

Abstract

The embodiment of the invention discloses an outdoor exercise information processing method and equipment, a program product and a storage medium, and the method comprises the steps: receiving a monitoring instruction sent by a user, responding to the monitoring instruction, and collecting to-be-processed data according to each pre-configured target data collection device and collection mode; wherein the to-be-processed data comprises user data and outdoor environment data, and the user data comprises user physiological data, user voice data and user image data; inputting the to-be-processed data into a predetermined multi-modal processing model, and performing feature splicing and feature processing on the to-be-processed data through the multi-modal processing model to obtain multi-modal output data; and generating motion guidance information based on the multi-modal output data, and displaying the motion guidance information to the user. According to the method, the exercise guidance information needed by the user at the current moment can be accurately and comprehensively determined through the multi-modal processing model, and the safety and experience feeling of the user during outdoor exercise are guaranteed.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and in particular to an outdoor sports information processing method, device, program product and storage medium. Background Art

[0002] With the popularity of outdoor sports, more and more people are participating in outdoor activities such as hiking, cross-country running and climbing snow-capped mountains. However, due to the lack of real-time professional guidance, athletes often find it difficult to make scientific decisions in time when faced with complex outdoor environments and emergencies, posing a major safety hazard.

[0003] Most existing sports guidance solutions rely on manual professional guides or static training guides, which are not accurate and comprehensive enough and cannot provide dynamic guidance to users in real time. Summary of the Invention

[0004] Embodiments of the present invention provide an outdoor sports information processing method, device, program product, and storage medium. When a user performs outdoor sports, the method can accurately and comprehensively determine the sports guidance information required by the user at the current moment, thereby ensuring the user's safety and experience in outdoor sports.

[0005] In a first aspect, an embodiment of the present invention provides a method for processing outdoor sports information, comprising:

[0006] Receive a monitoring instruction sent by a user, and in response to the monitoring instruction, collect data to be processed according to pre-configured target data collection devices and collection methods; wherein the data to be processed includes user data and outdoor environment data, and the user data includes user physiological data, user voice data, and user image data;

[0007] Inputting the data to be processed into a predetermined multimodal processing model, performing feature splicing and feature processing on the data to be processed by the multimodal processing model to obtain multimodal output data;

[0008] Generating exercise guidance information based on the multimodal output data, and presenting the exercise guidance information to the user.

[0009] In a second aspect, an embodiment of the present invention provides an outdoor sports information processing device, the device comprising:

[0010] A data acquisition module, configured to receive monitoring instructions sent by a user and, in response to the monitoring instructions, to acquire data to be processed according to pre-configured target data acquisition devices and acquisition methods; wherein the data to be processed includes user data and outdoor environment data, and the user data includes user physiological data, user voice data, and user image data;

[0011] A data processing module, configured to input the data to be processed into a predetermined multimodal processing model, perform feature concatenation and feature processing on the data to be processed through the multimodal processing model, and obtain multimodal output data;

[0012] A result display module is used to generate exercise guidance information based on the multimodal output data and display the exercise guidance information to the user.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, an outdoor sports information processing method as described in any one of the embodiments of the present invention is implemented.

[0014] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the outdoor sports information processing method as described in any one of the embodiments of the present invention.

[0015] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements the outdoor sports information processing method as described in any one of the embodiments of the present invention.

[0016] In an embodiment of the present invention, a monitoring instruction sent by a user is received, and in response to the monitoring instruction, data to be processed is collected according to pre-configured target data collection devices and collection methods; wherein the data to be processed includes user data and outdoor environment data, and the user data includes user physiological data, user voice data, and user image data; the data to be processed is input into a predetermined multimodal processing model, and feature splicing and feature processing are performed on the data to be processed by the multimodal processing model to obtain multimodal output data; based on the multimodal output data, exercise guidance information is generated, and the exercise guidance information is displayed to the user. That is, in the method of the embodiment of the present invention, when a user performs outdoor exercise, the multimodal processing model can accurately and comprehensively determine the exercise guidance information required by the user at the current moment, thereby ensuring the safety and experience of the user in outdoor exercise. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1A first flow chart of a method for processing outdoor sports information provided by an embodiment of the present invention;

[0019] Figure 2 A second flow chart of a method for processing outdoor sports information provided by an embodiment of the present invention;

[0020] Figure 3 A third flow chart of a method for processing outdoor sports information provided by an embodiment of the present invention;

[0021] Figure 4 A fourth flow chart of a method for processing outdoor sports information provided by an embodiment of the present invention;

[0022] Figure 5 A schematic structural diagram of an outdoor sports information processing device provided by an embodiment of the present invention;

[0023] Figure 6 A schematic structural diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0025] Figure 1 This is the first flow chart of a method for processing outdoor sports information provided by an embodiment of the present invention. When a user performs outdoor sports, the method of the embodiment of the present invention can accurately and comprehensively determine the sports guidance information that the user needs at the current moment, so that the user can adjust the sports strategy or sports status in time according to the running guidance information, thereby ensuring the safety and experience of the user in outdoor sports. The information collected in the method of the embodiment of the present invention is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse. This method can be executed by an outdoor sports information processing device provided by an embodiment of the present invention, and the device can be implemented in software and / or hardware. The following embodiments will be described by taking the device integrated in an electronic device as an example. The electronic device can be a server, a controller or a computer device, etc., with reference to Figure 1 , the method may specifically include the following steps:

[0026] Step 101: Receive a monitoring instruction sent by a user, and in response to the monitoring instruction, collect data to be processed according to pre-configured target data collection devices and collection methods.

[0027] The data to be processed includes user data and outdoor environment data. User data includes user physiological data, user voice data, and user image data. User physiological data includes but is not limited to the user's body temperature, heart rate, blood oxygen saturation, movement trajectory, and status. Outdoor environment data includes but is not limited to temperature, humidity, light intensity, atmospheric pressure, air quality, ultraviolet intensity, wind speed, wind direction, rainfall, and soil temperature and humidity. Different types of outdoor sports require different data to be processed, so different types of outdoor sports require different data collection devices. The target data collection device is pre-configured based on the outdoor sports information uploaded by the user, and is used to collect user data and outdoor environment data, such as various sensors for collecting body temperature, heart rate, blood oxygen, and positioning data. The data collection devices of this solution are all pluggable and combinable sensors or communication modules. The collection method is predetermined and is used to instruct the target data collection device how to collect the data to be processed. The collection method includes the collection frequency and collection volume of each type of data to be processed.

[0028] Specifically, when a user begins outdoor exercise, they can send monitoring instructions to the controller through an interactive device, such as a mobile phone application, smartwatch, or voice assistant. After receiving the monitoring instructions, the controller controls each target data collection device to collect user data and outdoor environment data in real time according to a predetermined collection method.

[0029] Step 102: Input the data to be processed into a predetermined multimodal processing model, perform feature splicing and feature processing on the data to be processed through the multimodal processing model, and obtain multimodal output data.

[0030] Among them, the multimodal processing model is a predetermined model used to obtain motion guidance information based on the data to be processed. The multimodal model can be a deep learning model based on the attention mechanism. This model can directly take a unified or separate embedding of data of different modalities at the input end, and then learn the correlation and importance between different modal information through a multi-head attention mechanism. The multimodal model based on the attention mechanism helps to capture cross-modal features, such as potential associations between vision and semantics. The multimodal model can also be a hybrid model composed of multiple network topologies such as convolutional neural networks, recurrent neural networks and / or graph neural networks, so that it can flexibly adapt to different types of input data. In this solution, the controller can detect the network environment in real time. When the network environment is good, the various models in the cloud server (such as the multimodal processing model) can be used. When the network environment is poor, the local end-side models of the controller (including the multimodal processing model) can be used.

[0031] In an optional embodiment, before receiving the monitoring instruction sent by the user, the pre-established initial multimodal model can be trained based on the multimodal data collected during the historical period. For example, the general vision-language model, video understanding model or other cross-modal base model is trained through the multimodal data to obtain a multimodal processing model that can generate outdoor guidance information and adapt to outdoor sports scenes. Of course, the multimodal data collected during the historical period includes big data in the field of outdoor sports and outdoor sports data generated by each user in various outdoor sports activities.

[0032] In an optional embodiment, after the data to be processed is obtained, the data to be processed can be preprocessed. For example, the data collected by each sensor can be discretized or processed in time series; frame sampling or feature extraction can be performed on image data and video data; regularization cleaning and word segmentation can be performed on voice data and text data to obtain preprocessed data to be processed. Through the input layer of the multimodal processing model, stacking or position encoding and other technologies are used to splice the data to be processed of different modalities by dimension or by channel stacking to obtain a comprehensive feature vector. Furthermore, feature processing is performed on the comprehensive feature vector. For example, the comprehensive feature vector can be classified, identified and predicted by the core algorithm of the multimodal processing model (such as multilayer perceptron, convolutional neural network, attention mechanism or random forest, etc.) to obtain multimodal output data.

[0033] Step 103: Generate exercise guidance information based on the multimodal output data, and display the exercise guidance information to the user.

[0034] The exercise guidance information is a series of personalized suggestions and tips determined based on the output data of each target sub-model. It is used to help users make more scientific and safer decisions during outdoor activities. The exercise guidance information is a series of personalized suggestions and tips determined based on the output data of each target sub-model. It is used to help users make more scientific and safer decisions during outdoor activities.

[0035] After obtaining the multimodal output data, a comprehensive analysis of the physiological data, environmental data, voice data, and image data in the multimodal output data is performed to obtain exercise guidance information in various dimensions. For example, the multimodal data includes whether the user's heart rate data is normal. If the user's heart rate is too high, exercise guidance information is generated to recommend reducing exercise intensity. The multimodal data also includes whether the ambient temperature is too high. If the ambient temperature is too high, exercise guidance information is generated to recommend increasing rest time.

[0036] The technical solution of this embodiment receives monitoring instructions sent by the user, responds to the monitoring instructions, and collects data to be processed according to pre-configured target data collection devices and collection methods; wherein the data to be processed includes user data and outdoor environment data, and the user data includes user physiological data, user voice data, and user image data; inputs the data to be processed into a predetermined multimodal processing model, performs feature splicing and feature processing on the data to be processed through the multimodal processing model to obtain multimodal output data; generates exercise guidance information based on the multimodal output data, and displays the exercise guidance information to the user. The technical solution of this embodiment can accurately and comprehensively determine the exercise guidance information required by the user at the current moment through the multimodal processing model when the user is engaged in outdoor exercise, thereby ensuring the user's safety and experience in outdoor exercise.

[0037] Figure 2 This is a second flow chart of a method for processing outdoor sports information provided by an embodiment of the present invention. The method of this embodiment can be as follows Figure 2 As shown, the method may include the following steps:

[0038] Step 201: Receive a monitoring instruction sent by a user, and in response to the monitoring instruction, collect data to be processed according to pre-configured target data collection devices and collection methods.

[0039] The data to be processed includes user data and outdoor environment data, and the user data includes user physiological data, user voice data and user image data.

[0040] Step 202: Perform data fusion on the data to be processed according to a predetermined fusion model and a predetermined outdoor monitoring mode to obtain fused data of the data to be processed.

[0041] The fusion model integrates text, voice, visual, and sensor time-series data from various data acquisition devices and data sources into a unified representational space. The outdoor monitoring mode is a preconfigured set of monitoring tasks and strategies tailored to different outdoor activity scenarios and user needs. Different outdoor scenarios correspond to different outdoor monitoring modes. For example, a suitable outdoor monitoring mode is used for snowy mountain climbing, while a suitable outdoor monitoring mode is used for grassland hiking.

[0042] Specifically, after obtaining the data to be processed, it is screened and classified according to the outdoor monitoring mode, and the processed data is input into the fusion model according to its type. The fusion model can align the timestamps of the data to be processed from different modalities to ensure temporal synchronization of the data. It also performs spatial registration on the image data to eliminate differences caused by factors such as shooting angle and resolution. Furthermore, the fusion model can extract features from the data to be processed. For example, it can extract key features of physiological data such as heart rate, blood oxygen, and body temperature to obtain user physiological data signs; extract key features of environmental data such as temperature, air pressure, and positioning trajectory to obtain environmental data features; extract features such as voice intonation and speaking rate through speech analysis technology to obtain user voice data features; and extract image features such as edges, textures, and expressions through image processing technology to obtain user image features. After extracting features from various types of data (data from different modalities) of the image to be processed, the features of the different modalities are aligned into the same feature space, and the features in the same feature space are fused through methods such as feature splicing and weighted summation. For example, user physiological data features, environmental data features, user voice data features, and user image data features are spliced into a comprehensive feature vector to obtain fused data of the data to be processed.

[0043] Step 203: Process the fused data according to the predetermined target sub-models corresponding to the outdoor monitoring mode to obtain result data corresponding to the data to be processed.

[0044] Among them, each target sub-model includes one or more of the following: a sports strategy sub-model, an emotional support sub-model, a team collaboration sub-model, and a risk assessment sub-model. The target sub-model is used to analyze the fused data to generate specific sports guidance information for the user. Different outdoor monitoring modes correspond to different target sub-models. For example, the target sub-models corresponding to the hiking mode can be a sports strategy sub-model and an emotional support sub-model. The target sub-models corresponding to the snow mountain climbing mode can be a sports strategy sub-model, a risk assessment sub-model, and an emotional support sub-model. The target sub-models corresponding to the team cross-country running mode can be a sports strategy sub-model, a team collaboration sub-model, and an emotional support sub-model.

[0045] Specifically, before receiving monitoring instructions from the user, the controller has already determined the outdoor monitoring mode based on the user's requirements and other information, and then determines the corresponding target sub-model based on the determined outdoor monitoring mode. After obtaining the fused data processed by the fusion model, the fused data is input into the target sub-model, which processes the fused data. Based on the data output by each target sub-model, the result data corresponding to the processed data is obtained.

[0046] Exemplarily, fused data including the user's physiological data (such as heart rate and blood oxygen), outdoor environment data (such as temperature and altitude) and motion trajectory data are input into the motion strategy sub-model, and the motion strategy sub-model is used to analyze the user's current physiological state, such as whether the heart rate is within the normal range and whether the blood oxygen saturation is normal. Evaluate the current environmental conditions, such as whether the temperature is too high or the altitude is too high. Generate personalized exercise recommendations based on the physiological state and environmental conditions. For example, if the user's heart rate is too high, it is recommended to reduce the intensity of exercise; if the ambient temperature is too high, it is recommended to increase the rest time. Exemplarily, fused data including the user's voice data (for emotion analysis), expression data and physiological data are input into the emotional support sub-model, and the emotional support sub-model performs voice analysis and expression recognition to evaluate the user's emotional state, such as whether he is anxious or tired. Combined with the user's physiological data (such as heart rate and blood oxygen), determine whether the user needs emotional support. Generate emotional support recommendations based on the user's emotional state and physiological data. Exemplarily, fused data including physiological data, location data and communication data of team members are input into the team collaboration sub-model, and the current status of team members, such as the physiological status and location information of each member, is analyzed through the team collaboration sub-model. According to the overall situation of the team, the marching queue is adjusted or the supply points are allocated. For example, if a member is tired, it is recommended that the team as a whole slow down or adjust the queue. Exemplarily, fused data including outdoor environmental data (such as terrain and weather), user physiological data and motion trajectory data are input into the risk assessment sub-model, and the current environmental conditions are analyzed through the risk assessment sub-model to identify potential risk areas or situations. For example, the detection of air pressure changes in high-altitude areas may indicate the risk of avalanche. The data output by each sub-model is sorted to obtain the result data corresponding to the data to be processed output by each target sub-model.

[0047] Step 204: Generate exercise guidance information based on the result data, and display the exercise guidance information to the user.

[0048] Specifically, after obtaining each result data, each result data is sorted according to the urgency and importance of each result data. For example, the result data output by the risk assessment sub-model has the highest priority (highest urgency and importance). According to the priority of each result data, each result data is integrated into one or more comprehensive sports guidance information. Exemplarily, the sports guidance information obtained by integrating each result data is: "There is a risk of avalanche in the area ahead, please choose an alternative route and take protective measures. It is recommended that you reduce your speed to 5 kilometers per hour and take a break every 30 minutes. You look a little tired, it is recommended that you take a break and listen to relaxing music. "After determining the sports guidance information, the text-type sports guidance information can be converted into voice prompt information, and the voice prompt information can be played to the user. Alternatively, the sports guidance information is visualized to obtain visual guidance information, and the visual guidance information is displayed to the user through devices such as mobile phone applications, smart watches or smart glasses.

[0049] In an optional embodiment, after displaying exercise guidance information to the user, user feedback regarding the exercise guidance information can be collected and subsequent exercise guidance information can be dynamically adjusted based on the feedback. For example, a mobile phone application can be used to display a "whether to accept the suggestion" message to the user. If the user chooses not to accept the suggestion, the controller can record the suggestion and adjust subsequent exercise guidance information based on the user's feedback.

[0050] The technical solution of this embodiment receives a monitoring instruction sent by a user, responds to the monitoring instruction, and collects data to be processed according to pre-configured target data collection devices and collection methods. The data to be processed includes user data and outdoor environmental data, and the user data includes user physiological data, user voice data, and user image data. The data to be processed is fused according to a predetermined fusion model and a predetermined outdoor monitoring mode to obtain fused data of the data to be processed. The fused data is processed according to predetermined target sub-models corresponding to the outdoor monitoring mode to obtain result data corresponding to the data to be processed. Exercise guidance information is generated based on the result data and displayed to the user. The technical solution of this embodiment, by collecting user physiological data, voice data, image data, and outdoor environmental data, can fully understand the user's physical condition and environmental conditions. The fusion model is used to fuse features of multimodal data from different data collection devices, fully utilizing the advantages of multi-source data and providing richer information for subsequent data analysis. Through the target sub-models, exercise guidance information for outdoor sports can be dynamically adjusted in real time based on the fused data, promptly responding to changes in the user's physical condition and environment, and providing real-time exercise recommendations and risk warnings to the user. That is, the technical solution of this embodiment can accurately and comprehensively determine the exercise guidance information required by the user at the current moment when the user performs outdoor sports, thereby ensuring the user's safety and experience in outdoor sports.

[0051] Figure 3 This is a third flow chart of a method for processing outdoor sports information provided by an embodiment of the present invention. This embodiment is a refinement of the above embodiment. The specific method can be as follows: Figure 3 As shown, the method may include the following steps:

[0052] Step 301: Receive a monitoring instruction sent by a user, and in response to the monitoring instruction, collect data to be processed according to pre-configured target data collection devices and collection methods.

[0053] The data to be processed includes user data and outdoor environment data, and the user data includes user physiological data, user voice data and user image data.

[0054] Step 302: Classify the data to be processed based on the outdoor monitoring mode to obtain various types of data to be processed.

[0055] The outdoor monitoring mode is a preconfigured set of monitoring tasks and strategies based on various outdoor activity scenarios and user needs. Different outdoor monitoring modes correspond to different classification methods for the data to be processed. For example, in the Snow Mountain Climbing mode, heart rate and blood oxygen saturation are classified as user physiological data, while temperature and air pressure are classified as outdoor environmental data. After obtaining the data to be processed, it is classified according to the determined outdoor monitoring mode to obtain the data of different types.

[0056] For example, if the outdoor monitoring mode is a hiking mode, the data to be processed can be classified into: user physiological data: heart rate and motion trajectory; outdoor environmental data: temperature, humidity and light intensity; user voice data and user image data. If the outdoor monitoring mode is a snow mountain climbing mode, the data to be processed can be classified into: user physiological data: heart rate, blood oxygen saturation and body temperature. Outdoor environmental data: temperature, air pressure, wind speed and wind direction; user voice data and image data. If the outdoor monitoring mode is a team cross-country running mode, the data to be processed can be classified into: user physiological data: heart rate and motion trajectory; user voice data and user image data; outdoor environmental data: temperature, humidity and wind speed. If the outdoor monitoring mode is a desert exploration mode, the data to be processed can be classified into: user physiological data: heart rate and body temperature; outdoor environmental data: temperature, humidity, wind speed, wind direction and ultraviolet intensity; user voice data and image data.

[0057] Step 303: Input each type of data to be processed and its corresponding data type into the fusion model. Through the fusion model, extract features of each type of data to be processed based on each data type to obtain each to-be-processed feature corresponding to each type of data to be processed.

[0058] The fusion model is a pre-trained model based on a deep learning architecture for processing multimodal data. In this solution, the fusion model can be a large language model. The fusion model includes a feature extraction module, a feature alignment module, and a fusion module. Feature extraction is the process of converting raw data into more representative and interpretable features. After obtaining each type of data to be processed and its corresponding data type, it is input into the fusion model, where the feature extraction module extracts features from each type of data.

[0059] Exemplarily, the various types of data to be processed include: user physiological data: heart rate, blood oxygen saturation, body temperature, and movement trajectory, etc. User voice data: voice intonation and voice content, etc. User image data: facial expression images and terrain images, etc. Outdoor environmental data: temperature, humidity, light intensity, air pressure, air quality, ultraviolet intensity, wind speed, wind direction, rainfall, and soil temperature and humidity, etc. Feature extraction of user physiological data is performed through a feature extraction module: features such as average heart rate and heart rate variability are extracted; features such as average blood oxygen saturation and blood oxygen saturation change rate are extracted; features such as average body temperature and body temperature change rate are extracted; features such as movement speed, movement acceleration, and movement direction are extracted; and user physiological data features are obtained based on the above extracted features. Feature extraction of user voice data is performed through a feature extraction module: features such as pitch, sound intensity, and speaking speed are extracted; features such as keywords and semantic information in the voice are extracted through voice recognition technology, and user voice data features are obtained based on the above extracted features. Feature extraction of user image data is performed through a feature extraction module: facial expression features are extracted to obtain user image features. The feature extraction module extracts features from outdoor environmental data: Using image processing techniques, it extracts terrain features such as slope and obstacle locations; extracts features such as average temperature and temperature change rate; extracts features such as average humidity and humidity change rate; extracts features such as average light intensity and change rate; extracts features such as average air pressure and air pressure change rate; and extracts features such as average wind speed, wind speed change rate, and wind direction. Based on these extracted features, the outdoor environmental data features are derived.

[0060] Step 304: perform feature alignment and multimodal fusion on each feature to be processed through the fusion model to obtain fused data of the data to be processed.

[0061] Feature alignment is the process of converting features of different modalities into the same feature space, ensuring that the features of different modalities are consistent in dimension and semantics. Feature alignment methods include: linear mapping or multi-layer perceptron: mapping features of different modalities to the same dimension through a linear layer or multi-layer perceptron; pixel reorganization: reducing the dimension of image features while retaining key information. Multimodal fusion is the process of integrating the aligned features to generate a comprehensive feature vector. Multimodal fusion methods include: feature splicing: directly splicing feature vectors of different modalities together; weighted summation: performing weighted summation of features of different modalities, and dynamically adjusting the weights of the features of each modality according to the importance of the modality. Cross-attention mechanism: Through the cross-attention mechanism, the features of one modality can dynamically pay attention to the features of another modality, thereby performing feature fusion.

[0062] Specifically, after obtaining each feature to be processed, the features to be processed are aligned to the same feature space through a feature alignment method, and the aligned features are integrated into a comprehensive feature vector through a feature fusion method. For example, the features to be processed include: user physiological data features: [average heart rate, heart rate variability, average blood oxygen saturation, blood oxygen saturation change rate]; user voice data features: [pitch, voice intensity, speaking rate]; user image data features: [expression features, terrain features]; outdoor environment data features: [average temperature, temperature change rate, average humidity, humidity change rate]. Through feature alignment and feature fusion, the fused data can be obtained: [average heart rate, heart rate variability, average blood oxygen saturation, blood oxygen saturation change rate, pitch, voice intensity, speaking rate, expression features, terrain features, average temperature, temperature change rate, average humidity, humidity change rate].

[0063] Step 305: Input the fused data into each target sub-model to obtain each initial result data output by each target sub-model; determine the required result data of each target sub-model from each initial result data, and distribute the required result data of each target sub-model to each target sub-model through a pre-set intermediate layer.

[0064] Among them, each target sub-model includes one or more of the following: movement strategy sub-model, emotional support sub-model, team collaboration sub-model and risk assessment sub-model. The initial result data is the data output by each target sub-model after directly processing the fusion data. The middle layer is a pre-set key component for realizing efficient data interaction between sub-models. The required result data is the specific data requirements of each sub-model determined from the initial result data of each sub-model according to the business logic of each sub-model. The sub-models in this solution not only share data, but also share decision results to achieve dynamic decision-making. For example, the output of the risk assessment sub-model can be directly used as the input of the movement strategy sub-model.

[0065] Specifically, after obtaining the fused data, the fused data is input into each target sub-model to obtain the initial result data output by each target sub-model. Exemplarily, the fused data is input into the exercise strategy sub-model, which generates exercise recommendations based on the user's physiological state and environmental conditions. The fused data is input into the emotional support sub-model, which generates emotional support recommendations based on the user's emotional state. The fused data is input into the risk assessment sub-model, which generates risk warnings and response recommendations based on environmental conditions and the user's physiological state. After obtaining the initial result data, the initial result data is transmitted to the middle layer, which uses a standardized data format to store and transmit data, ensuring that different target sub-models can seamlessly exchange data. Based on the business logic of each target sub-model and the importance and urgency of each result data, the required result data of each target sub-model is determined. The required result data of each target sub-model is distributed to the corresponding target sub-model through the middle layer, enabling information sharing between the target sub-models.

[0066] Step 306: For each target sub-model, the fusion data and the required result data of the current target sub-model are input into the current target sub-model to obtain the result data output by the current target sub-model.

[0067] After obtaining the demand result data of each target sub-model, the fused data and the demand result data of each target sub-model are determined as the input data of each target sub-model. Data processing is performed again through each target sub-model, so that each target sub-model can perform more in-depth analysis and processing of the data according to its specific needs. Exemplarily, the outdoor monitoring mode is the "snow mountain climbing mode", and the target sub-models include: a movement strategy sub-model, a risk assessment sub-model and an emotional support sub-model. The initial result data of the risk assessment sub-model include: there is an avalanche risk in the area ahead. The initial result data of the movement strategy sub-model include: maintain the current movement state and continue to move forward. The demand result data of the movement strategy sub-model include the initial result data of the risk assessment sub-model. According to the fused data and the initial result data of the risk assessment sub-model, the movement strategy sub-model obtains the final result data: it is recommended to increase the speed to 5 kilometers per hour, take a break every 30 minutes, and choose an alternative route.

[0068] Step 307: Generate exercise guidance information based on the result data, and display the exercise guidance information to the user.

[0069] The technical solution of this embodiment receives a monitoring instruction sent by a user, responds to the monitoring instruction, and collects data to be processed according to pre-configured target data collection devices and collection methods; wherein the data to be processed includes user data and outdoor environment data, and the user data includes user physiological data, user voice data, and user image data; data classification is performed on the data to be processed based on the outdoor monitoring mode to obtain various types of data to be processed; each type of data to be processed and its corresponding data type are input into a fusion model, and through the fusion model, feature extraction is performed on each type of data to be processed based on each data type to obtain various features to be processed corresponding to each type of data to be processed; feature alignment and multimodal fusion are performed on each feature to be processed through the fusion model to obtain fused data of the data to be processed. Input the fused data into each target sub-model to obtain each initial result data output by each target sub-model; determine the required result data of each target sub-model from each initial result data, and distribute the required result data of each target sub-model to each target sub-model through a pre-set intermediate layer; wherein each target sub-model includes one or more of the exercise strategy sub-model, emotional support sub-model, team collaboration sub-model and risk assessment sub-model; for each target sub-model, input the fused data and the required result data of the current target sub-model into the current target sub-model to obtain the result data output by the current target sub-model. Generate exercise guidance information based on each result data, and display the exercise guidance information to the user. The technical solution of this embodiment, through the fusion model, extracts features of various types of data to be processed, and can extract more representative and interpretable features from the original data. Through feature alignment and multimodal fusion, it can integrate data from different modalities into a unified representation space, giving full play to the advantages of multi-source data and improving the accuracy and comprehensiveness of monitoring. Through the middle layer, centralized data management and unified sharing are achieved, and the required result data of each sub-model can be distributed in real time to ensure that each sub-model can obtain the required information in a timely manner, thereby generating more comprehensive and accurate sports guidance information through each sub-model, providing users with more comprehensive, accurate and personalized monitoring and guidance services, and improving the safety and efficiency of users' outdoor sports.

[0070] Figure 4 This is a fourth flow chart of a method for processing outdoor sports information provided by an embodiment of the present invention. This embodiment is a refinement of the above embodiment. The specific method can be as follows: Figure 4 As shown, the method may include the following steps:

[0071] Step 401: Receive outdoor scene information and demand information sent by the user.

[0072] Among them, outdoor scene information is used to describe the outdoor activity scene that the user is about to engage in, including but not limited to activity type: such as hiking, snow mountain climbing, desert exploration and team cross-country running, etc.; activity location: such as mountainous areas, grasslands and deserts, etc.; activity time: expected activity start time and end time; environmental conditions: such as expected weather conditions and temperature range, etc. Demand information is used to describe the specific needs that the user needs to monitor during outdoor activities, including but not limited to exercise type: such as running, climbing and cycling, etc.; exercise intensity: such as low intensity, medium intensity and high intensity; participant information: such as the number of team members and the health status of members, etc., and other needs: such as real-time heart rate monitoring, risk warning, team collaboration support and emotional support, etc. Specifically, before the user engages in outdoor activities, the user can send the outdoor scene information and demand information to the controller. The controller can determine the data acquisition device configuration, outdoor monitoring mode selection and data acquisition method required for the subsequent outdoor activities based on the outdoor scene information and demand information.

[0073] Step 402: Perform keyword analysis on the outdoor scene information and demand information to obtain scene keywords and demand keywords. Determine target data collection devices and outdoor monitoring modes based on the scene keywords and demand keywords.

[0074] Among them, keyword analysis is used to extract key information (scene keywords and demand keywords) from outdoor scene information and demand information. Each target data acquisition device is a pluggable and combinable sensor or communication module. The outdoor monitoring mode is a series of monitoring tasks and strategies configured according to different outdoor activity scenes and user needs. Specifically, after obtaining the outdoor scene information and demand information sent by the user, the outdoor scene information and demand information can be subjected to keyword analysis and extraction, scene keywords and demand keywords, through a predefined keyword list. Exemplarily, scene keywords can be keywords that describe outdoor activity scenes, including "hiking", "snow mountain", "desert" or "grassland". Demand keywords can be keywords that describe specific user needs, including "heart rate monitoring", "risk warning", "teamwork" and "emotional support".

[0075] Different scenario keywords and demand keywords correspond to different data collection devices and outdoor monitoring modes. According to the scenario keywords and demand keywords, the target data collection device and outdoor monitoring mode required for the outdoor activities that the user is going to carry out can be determined. Exemplarily, if the scenario keywords include "snow mountain climbing", the target data collection device may include a physiological data collection device: a pluggable heart rate belt, a blood oximeter, and a body temperature sensor; an environmental data collection device: a pluggable temperature sensor, a barometer, and a positioning device. If the demand keywords include "teamwork", the target data collection device may also include a short-range radio or satellite communication module (for data sharing between team members). Exemplarily, if the scenario keywords include "hiking", the outdoor monitoring mode is a hiking mode.

[0076] In this solution, optionally, determining target data collection devices and outdoor monitoring modes based on scenario keywords and requirement keywords includes: determining candidate recommended devices and candidate target devices based on the scenario keywords, requirement keywords, and a pre-determined scenario device database; sending the candidate recommended devices and candidate target devices to a user to obtain selected devices; and determining target data collection devices based on the selected devices and candidate target devices.

[0077] Among them, the candidate recommendation device is a portable data acquisition device recommended to the user by the controller based on the scene keywords and demand keywords. The candidate target device is a data acquisition device that must be carried and determined by the controller based on the scene keywords and demand keywords. The scene device database is predetermined by the controller and is used to record the candidate recommendation devices and candidate target devices corresponding to each outdoor scene and demand. After obtaining the scene keywords and demand keywords, the scene device database is searched for each candidate recommendation device and each candidate target device corresponding to the scene keywords and demand keywords. Each candidate recommendation device and each candidate target device is sent to the user, and the user can select the data acquisition device he needs from each candidate recommendation device according to actual needs, and send the selected data acquisition device to the controller, so that the controller obtains each selection device determined by the user based on each candidate recommendation device. Further, each target data acquisition device is determined based on each selection device and each candidate target device selected by the user.

[0078] By using scenario and requirement keywords, we can accurately identify candidate recommended devices and target devices. Users can then select their desired data acquisition device from the recommended candidates based on their actual needs. This flexible configuration approach not only improves device configuration adaptability but also reduces unnecessary equipment carrying and reduces the burden on users.

[0079] Step 403: Determine the data collection frequency based on the outdoor scene information, exercise type, and exercise intensity; and determine the collection method of the data to be processed based on the data collection frequency and the participant information.

[0080] Among them, the collection method is used to instruct the target data collection device how to collect the data to be processed. The collection method includes data collection frequency, data collection volume, and data items that need to be collected. Specifically, different outdoor scene information, exercise types, and exercise intensities correspond to different data collection frequencies. For example, under high-intensity exercise, physiological data may need to be used more frequently, so the corresponding data collection frequency is higher. Based on the information of the participants, it can be determined whether the user's outdoor exercise is a single-player mode or a team mode. If the number of participants exceeds one, the controller also needs to collect relevant data of other participants besides the user himself. If there is only one participant, the controller only needs to collect relevant data of the user himself.

[0081] The technical solution of this embodiment receives outdoor scene information and demand information sent by the user. Keyword analysis is performed on the outdoor scene information and demand information to obtain scene keywords and demand keywords. Based on the scene keywords and demand keywords, each target data collection device and outdoor monitoring mode are determined. The data collection frequency is determined based on the outdoor scene information, exercise type, and exercise intensity; and the collection method for the data to be processed is determined based on the data collection frequency and participant information. The technical solution of this embodiment uses pluggable and combinable sensors and communication modules, allowing users to flexibly select heart rate, blood oxygen, air pressure, temperature and humidity, cameras, microphones, and / or satellite communication modules to adapt to different outdoor exercise scenarios. This modular hardware device approach can reduce unnecessary weight and energy consumption and can be configured according to actual needs or environmental extremes, thereby ensuring the lightweight and reliable equipment. By performing keyword analysis on the outdoor scene information and demand information, the outdoor monitoring mode can be accurately determined, thereby providing the user with a personalized monitoring solution. The collection method for the data to be processed is accurately determined based on the outdoor scene information, exercise type, and exercise intensity, improving the flexibility and adaptability of subsequent outdoor monitoring services.

[0082] Figure 5 This is a schematic diagram of the structure of an outdoor sports information processing device provided by an embodiment of the present invention, which is suitable for executing the outdoor sports information processing method provided by an embodiment of the present invention. Figure 5 As shown, the device may specifically include:

[0083] The data acquisition module 501 is configured to receive monitoring instructions sent by the user and, in response to the monitoring instructions, to acquire data to be processed according to pre-configured target data acquisition devices and acquisition methods; wherein the data to be processed includes user data and outdoor environment data, and the user data includes user physiological data, user voice data, and user image data;

[0084] The data processing module 503 is used to input the data to be processed into a predetermined multimodal processing model, perform feature splicing and feature processing on the data to be processed through the multimodal processing model, and obtain multimodal output data;

[0085] The result display module 504 is configured to generate exercise guidance information based on the multimodal output data and display the exercise guidance information to the user.

[0086] Optionally, the data processing module 503 is specifically configured to: classify the data to be processed based on the outdoor monitoring mode to obtain various types of data to be processed;

[0087] Inputting the various types of data to be processed and their corresponding data types into the fusion model, and performing feature extraction on the various types of data to be processed based on the various data types through the fusion model to obtain various features to be processed corresponding to the various types of data to be processed;

[0088] The fusion model is used to perform feature alignment and multimodal fusion on the features to be processed to obtain fused data of the data to be processed.

[0089] Optionally, each target sub-model includes one or more of a movement strategy sub-model, an emotional support sub-model, a team collaboration sub-model, and a risk assessment sub-model; the data processing module 503 is further configured to: input the fusion data into each target sub-model to obtain each initial result data output by each target sub-model;

[0090] Determining the required result data of each target sub-model from each initial result data, and distributing the required result data of each target sub-model to each target sub-model through a pre-set intermediate layer;

[0091] For each target sub-model, the fusion data and the required result data of the current target sub-model are input into the current target sub-model to obtain the result data output by the current target sub-model.

[0092] Optionally, the data processing module 503 is further configured to: receive outdoor scene information and demand information sent by the user;

[0093] Performing keyword analysis on the outdoor scene information and the demand information to obtain scene keywords and demand keywords;

[0094] The target data collection devices and outdoor monitoring modes are determined based on the scene keywords and the demand keywords.

[0095] Optionally, the data processing module 503 is further configured to: determine candidate recommended devices and candidate target devices based on the scenario keywords, the requirement keywords, and a predetermined scenario device database;

[0096] sending the candidate recommended devices and the candidate target devices to the user to obtain the selected devices determined by the user based on the candidate recommended devices;

[0097] The target data acquisition devices are determined according to the selection devices and the candidate target devices; the target data acquisition devices are pluggable and combinable sensors or communication modules.

[0098] Optionally, the data processing module 503 is further configured to: determine a data collection frequency based on the outdoor scene information, the exercise type, and the exercise intensity;

[0099] The collection method of the data to be processed is determined according to the data collection frequency and the participant information.

[0100] Optionally, the data processing module 503 is further configured to: obtain historical outdoor data of the user, the historical outdoor data including data collected when the user performs various outdoor sports during a historical period;

[0101] Performing data classification and data preprocessing on the historical outdoor data to obtain predetermined training data for each initial sub-model;

[0102] For each initial sub-model, if the current initial sub-model does not meet the preset conditions, the current initial sub-model is trained and optimized according to the training data of the current initial sub-model to obtain a current target sub-model that meets the preset conditions.

[0103] The outdoor sports information processing device provided in the embodiment of the present invention can execute the outdoor sports information processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For any content not described in detail in this embodiment, please refer to the description of any method embodiment of the present invention.

[0104] An embodiment of the present invention also provides a computer program product.

[0105] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer program products, which can include one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, referring to Figure 6 , Figure 6 The electronic device 12 shown is only an example and should not limit the functions and scope of use of the embodiments of the present application. Figure 6 As shown, electronic device 12 is implemented as a general-purpose computing device. Components of electronic device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 that connects various system components (including system memory 28 and processing unit 16).

[0107] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0108] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0109] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be configured to read and write non-removable, non-volatile magnetic media ( Figure 6 Not shown, often called a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the various embodiments of the present application.

[0110] A program / utility 40 having a set (at least one) of program modules 46 may be stored, for example, in memory 28. Such program modules 46 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 46 generally implement the functions and / or methods of the embodiments described herein.

[0111] The electronic device 12 may also communicate with one or more external devices 14 (e.g., a keyboard, a pointing device, a display 24, etc.), one or more devices that enable a user to interact with the electronic device 12, and / or any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the electronic device 12 via the bus 18. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0112] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, such as implementing an outdoor sports information processing method provided by an embodiment of the present invention: receiving a monitoring instruction sent by a user, responding to the monitoring instruction, collecting data to be processed according to pre-configured target data collection devices and collection methods; wherein the data to be processed includes user data and outdoor environment data, and the user data includes user physiological data, user voice data and user image data; inputting the data to be processed into a predetermined multimodal processing model, and performing feature splicing and feature processing on the data to be processed through the multimodal processing model to obtain multimodal output data; generating exercise guidance information based on the multimodal output data, and displaying the exercise guidance information to the user.

[0113] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, it implements an outdoor sports information processing method as provided in all embodiments of the present invention: receiving a monitoring instruction sent by a user, responding to the monitoring instruction, collecting data to be processed according to pre-configured target data collection devices and collection methods; wherein the data to be processed includes user data and outdoor environment data, and the user data includes user physiological data, user voice data, and user image data; inputting the data to be processed into a predetermined multimodal processing model, performing feature splicing and feature processing on the data to be processed through the multimodal processing model to obtain multimodal output data; generating exercise guidance information based on the multimodal output data, and displaying the exercise guidance information to the user. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electronic device, device, or component that is electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction-executing electronic device, apparatus, or device.

[0114] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction-executing electronic device, apparatus, or device.

[0115] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0116] Computer program code for performing the operations of the present invention can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a stand-alone 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 a remote computer, the remote computer can be connected to the user's computer through 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., through the Internet using an Internet service provider).

[0117] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will appreciate that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments, and substitutions are possible for those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the scope of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for processing outdoor sports information, characterized in that: The method comprises: Receive a monitoring instruction sent by a user, and in response to the monitoring instruction, collect data to be processed according to pre-configured target data collection devices and collection methods; wherein the data to be processed includes user data and outdoor environment data, and the user data includes user physiological data, user voice data, and user image data; Inputting the data to be processed into a predetermined multimodal processing model, performing feature splicing and feature processing on the data to be processed by the multimodal processing model to obtain multimodal output data; Generating exercise guidance information based on the multimodal output data, and presenting the exercise guidance information to the user.

2. The method according to claim 1, characterized in that After collecting the data to be processed according to the pre-configured target data collection devices and collection methods, the method further includes: Performing data fusion on the data to be processed according to a predetermined fusion model and a predetermined outdoor monitoring mode to obtain fused data of the data to be processed; Processing the fused data according to predetermined target sub-models corresponding to the outdoor monitoring mode to obtain result data corresponding to the data to be processed; Generate exercise guidance information according to each result data, and present the exercise guidance information to the user.

3. The method according to claim 2, characterized in that Performing data fusion on the data to be processed according to a predetermined fusion model and a predetermined outdoor monitoring mode to obtain fused data of the data to be processed includes: Classifying the data to be processed based on the outdoor monitoring mode to obtain various types of data to be processed; Inputting the various types of data to be processed and their corresponding data types into the fusion model, and performing feature extraction on the various types of data to be processed based on the various data types through the fusion model to obtain various features to be processed corresponding to the various types of data to be processed; The fusion model is used to perform feature alignment and multimodal fusion on the features to be processed to obtain fused data of the data to be processed.

4. The method according to claim 2, characterized in that in, Each target sub-model includes one or more of a movement strategy sub-model, an emotional support sub-model, a team collaboration sub-model, and a risk assessment sub-model; the fusion data is processed according to each predetermined target sub-model corresponding to the outdoor monitoring mode to obtain result data output by each target sub-model, including: Inputting the fused data into each target sub-model to obtain each initial result data output by each target sub-model; Determining the required result data of each target sub-model from each initial result data, and distributing the required result data of each target sub-model to each target sub-model through a pre-set intermediate layer; For each target sub-model, the fusion data and the required result data of the current target sub-model are input into the current target sub-model to obtain the result data output by the current target sub-model.

5. The method according to claim 1, wherein Before receiving the monitoring instruction sent by the user, the method further includes: receiving outdoor scene information and demand information sent by the user; Performing keyword analysis on the outdoor scene information and the demand information to obtain scene keywords and demand keywords; The target data collection devices and outdoor monitoring modes are determined based on the scene keywords and the demand keywords.

6. The method according to claim 5, characterized in that Determining each target data collection device based on the scenario keyword and the requirement keyword includes: Determine candidate recommended devices and candidate target devices based on the scenario keywords, the requirement keywords, and a predetermined scenario device database, Sending the candidate recommended devices and the candidate target devices to the user to obtain selected devices, wherein the selected device is the device selected by the user from the candidate recommended devices; The target data acquisition devices are determined according to the selection devices and the candidate target devices; the target data acquisition devices are pluggable and combinable sensors or communication modules.

7. The method according to claim 5, characterized in that The collection method includes data collection frequency and user data collection indicators, and the demand information includes exercise type, exercise intensity, and participant information. After receiving the outdoor scene information and demand information sent by the user, the method further includes: determining a data collection frequency based on the outdoor scene information, the exercise type, and the exercise intensity; The collection method of the data to be processed is determined according to the data collection frequency and the participant information.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements an outdoor sports information processing method according to any one of claims 1 to 7.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the outdoor sports information processing method as described in any one of claims 1-7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the outdoor sports information processing method as described in any one of claims 1 to 7 is implemented.

Images