Multi-dimensional child growth guardian method and device, storage medium, computer program product and smart watch

Abstract

This application relates to the field of smartwatch technology, and more particularly to a multi-dimensional child protection method, device, storage medium, computer program product, and smartwatch. The method acquires multi-source physiological and behavioral monitoring data, location information, and scene clue information from the smartwatch, and generates a dataset to be analyzed based on these data. Based on the dataset, the current state of the wearer is determined, and the data acquisition strategy for the multi-source physiological and behavioral monitoring data is adaptively adjusted according to the current state. The dataset is then preprocessed to obtain a processed dataset. A fusion representation is constructed from the processed dataset to obtain fusion features, and the target event type and corresponding handling instructions are determined based on these features. Based on the handling instructions, the smartwatch outputs interactive prompts and sends alarm information associated with the target event type to the monitoring terminal.

Description

Technical Field

[0001] This application relates to the field of smartwatch technology, and in particular to a multi-dimensional child protection method, device, storage medium, computer program product, and smartwatch. Background Technology

[0002] In the field of children's smart wearable devices, children's smartwatches, as everyday personal items, are widely used for scenarios such as location tracking, voice calls, and basic physiological indicator monitoring. However, with the increasing complexity of application scenarios and parents' growing demand for "health-safety-scenario-based protection," existing children's smartwatches, while possessing some integrated functions, still fall short in the integrated implementation of data acquisition, analysis and decision-making, and alarm linkage. On the one hand, in terms of health and behavior monitoring, existing devices mostly focus on collecting single or limited physiological indicators such as heart rate and blood oxygen, lacking the coordinated integration of behavioral dimensions such as sleep structure and exercise intensity. They also lack dynamic collection and analysis mechanisms based on changes in the wearer's state, resulting in data collection often employing fixed strategies and failing to form a tight closed loop with subsequent analysis. On the other hand, in terms of safety protection, existing solutions typically rely on single positioning technology, which has insufficient reliability in complex scenarios such as indoor environments. Furthermore, they lack mechanisms to link environmental / scenario cues with physiological and behavioral information, leading to suboptimal safety protection for children. Therefore, improving the child safety protection capabilities of smartwatches has become an urgent technical problem to be solved. Summary of the Invention

[0003] The main purpose of this application is to provide a multi-dimensional child protection method, device, storage medium, computer program product, and smartwatch, aiming to solve the technical problem of how to improve the child safety protection capabilities of smartwatches.

[0004] To achieve the above objectives, this application provides a multi-dimensional child protection method, which is applied to a smartwatch and includes: The system acquires multi-source physiological and behavioral monitoring data, location information, and scene clue information obtained by the smartwatch, and generates a dataset to be analyzed based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information. Based on the dataset to be analyzed, the current state of the wearable object is determined, and the acquisition strategy of the multi-source physiological and behavioral monitoring data is adaptively adjusted according to the current state. The dataset to be analyzed is then preprocessed to obtain the processed dataset. The processed dataset is fused to construct a fused representation, which yields fused features. Based on the fused features, the target event type and the corresponding handling instructions are determined. Based on the handling command, the smartwatch is controlled to output interactive prompts and send alarm information associated with the target event type to the monitoring terminal. The alarm information includes a location information field related to the location information and an environmental clue field related to the scene clue information.

[0005] In one embodiment, after the step of controlling the smartwatch to output interactive prompts based on the handling command and sending alarm information associated with the target event type to the monitoring terminal, the method further includes: When the handling instruction indicates that external linkage is required, a linkage request is sent to the external linkage device; According to a preset data security policy, at least one of the following is performed: local encrypted storage and end-to-end encrypted transmission of the dataset to be analyzed and / or the alarm information. Upon receiving a data deletion request, the system performs deletion processing on the corresponding data and generates a deletion certificate.

[0006] In one embodiment, the steps of determining the current state of the wearable object based on the dataset to be analyzed, adaptively adjusting the acquisition strategy of the multi-source physiological and behavioral monitoring data according to the current state, and preprocessing the dataset to be analyzed to obtain a processed dataset include: The consistency verification and temporal alignment processing of the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information in the dataset to be analyzed are performed, and the state judgment input is determined based on the aligned data. Based on the state determination input, state recognition processing is performed to determine the current state of the wearable object, and acquisition control parameters are generated according to the current state. Based on the acquisition control parameters, the acquisition strategy of the multi-source physiological and behavioral monitoring data is adaptively adjusted. After the acquisition strategy completes adaptive adjustment, the dataset to be analyzed is preprocessed. The preprocessing includes at least one of abnormal data identification, missing data completion, and data normalization to obtain the processed dataset.

[0007] In one embodiment, the step of constructing a fused representation of the processed dataset to obtain fused features, and determining the target event type and the corresponding disposal instruction based on the fused features, includes: Based on the processed dataset, sub-features related to physiological state, behavioral pattern, spatial location and scene cues are extracted respectively, and the sub-features are organized into a set of features to be fused. The set of features to be fused is subjected to cross-modal association and fusion representation construction to generate fusion features for characterizing the processed dataset; The fusion feature is input into the preset event determination module to obtain the target event type corresponding to the fusion feature, and a corresponding handling instruction is generated based on the target event type.

[0008] In one embodiment, the step of acquiring multi-source physiological and behavioral monitoring data, location information, and scene clue information acquired by the smartwatch, and generating a dataset to be analyzed based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information, includes: The smartwatch's acquisition component collects multi-source physiological and behavioral monitoring data of the wearer, and the smartwatch's positioning component obtains location information corresponding to the multi-source physiological and behavioral monitoring data. During the collection of the multi-source physiological and behavioral monitoring data, the scene perception component of the smartwatch is invoked to obtain scene clue information, and the scene clue information is associated and identified with the multi-source physiological and behavioral monitoring data and the location information; The data is organized and processed based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information. The data organization and processing includes at least one of timestamp unification, data format standardization, and data field encapsulation to generate a dataset to be analyzed.

[0009] In one embodiment, the step of controlling the smartwatch to output interactive prompts based on the handling command and sending alarm information associated with the target event type to the monitoring terminal includes: The processing command is parsed to determine the alarm interaction configuration, which includes at least one of the following: interaction method, interaction content, and interaction duration conditions. Based on the alarm interaction configuration, the smartwatch is controlled to output interactive prompts, and an alarm message body is generated based on the target event type. The alarm message body includes an event identifier field and a status description field associated with the target event type. The alarm message body is encapsulated with the location information field related to the location information and the environmental clue field related to the scene clue information to obtain alarm information associated with the target event type. The alarm information is then sent to the monitoring terminal through a preset communication interface to control the smartwatch to output interactive prompts and send alarm information associated with the target event type to the monitoring terminal.

[0010] Furthermore, to achieve the above objectives, this application also proposes a multi-dimensional child growth protection device, which is applied to a smartwatch, and the multi-dimensional child growth protection device includes: The data acquisition module is used to acquire multi-source physiological and behavioral monitoring data, location information, and scene clue information acquired by the smartwatch, and to generate a dataset to be analyzed based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information. The strategy adjustment module is used to determine the current state of the wearable object based on the dataset to be analyzed, adaptively adjust the acquisition strategy of the multi-source physiological and behavioral monitoring data according to the current state, and preprocess the dataset to be analyzed to obtain the processed dataset. The fusion instruction module is used to construct a fusion representation of the processed dataset, obtain fusion features, and determine the target event type and the corresponding disposal instruction based on the fusion features; The alarm interaction module is used to control the smartwatch to output interactive prompts based on the handling command, and to send alarm information associated with the target event type to the monitoring terminal. The alarm information includes a location information field related to the location information and an environmental clue field related to the scene clue information.

[0011] In addition, to achieve the above objectives, this application also proposes a smartwatch, which includes: a memory, a processor, and a multi-dimensional child growth protection program stored on the memory and executable on the processor, wherein the multi-dimensional child growth protection program is configured to implement the steps of the multi-dimensional child growth protection method as described in any of the above embodiments.

[0012] In addition, to achieve the above objectives, this application also proposes a storage medium storing a multi-dimensional child growth protection program, which, when executed by a processor, implements the steps of the multi-dimensional child growth protection method described above.

[0013] In addition, to achieve the above objectives, this application also proposes a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the multi-dimensional child growth protection method described above.

[0014] This application acquires multi-source physiological and behavioral monitoring data, location information, and scene clue information from a smartwatch, and generates a dataset to be analyzed based on these data. The current state of the wearable object is determined based on this dataset, and the data acquisition strategy for the multi-source physiological and behavioral monitoring data is adaptively adjusted according to the current state. The dataset is then preprocessed to obtain a processed dataset. A fusion representation is constructed on the processed dataset to obtain fusion features, and the target event type and corresponding handling instructions are determined based on these fusion features. The smartwatch is then controlled to output interactive prompts based on the handling instructions, and alarm information associated with the target event type is sent to the monitoring terminal. The alarm information includes location information fields related to the location information and environmental clue fields related to the scene clue information. This application acquires multi-source physiological and behavioral monitoring data, location information, and scene clues from a smartwatch simultaneously to generate a dataset to be analyzed. Based on this dataset, the current state of the wearable object is determined to drive the adaptive adjustment of the acquisition strategy. The dataset is then preprocessed to obtain a processed dataset. A fusion representation is constructed from the processed dataset to form fusion features, and the target event type and its corresponding handling instructions are determined accordingly. Finally, based on the handling instructions, the watch interaction prompts are triggered, and an alarm message containing location information and environmental clue fields is sent to the monitoring terminal. This establishes the identification and alarm output of safety-related events on a unified link of multi-source data, adaptive state processing, and fusion judgment, thereby improving the smartwatch's ability to identify and handle children's safety risks. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating the first embodiment of the multi-dimensional child growth protection method of this application; Figure 2 This is a schematic diagram of a sub-process in the second embodiment of the multi-dimensional child growth protection method of this application; Figure 3 This is a schematic diagram of a sub-process in the third embodiment of the multi-dimensional child growth protection method of this application; Figure 4 This is a schematic diagram of the modular structure of the multi-dimensional child growth protection device according to an embodiment of this application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the multi-dimensional child growth protection method in the embodiments of this application.

[0016] 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

[0017] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0018] 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.

[0019] In the field of children's smart wearable devices, children's smartwatches, as everyday personal items, are widely used for scenarios such as location tracking, voice calls, and basic physiological indicator monitoring. However, with the increasing complexity of application scenarios and parents' growing demand for "health-safety-scenario-based protection," existing children's smartwatches, while possessing some integrated functions, still fall short in the integrated implementation of data acquisition, analysis and decision-making, and alarm linkage. On the one hand, in terms of health and behavior monitoring, existing devices mostly focus on collecting single or limited physiological indicators such as heart rate and blood oxygen, lacking the coordinated integration of behavioral dimensions such as sleep structure and exercise intensity. They also lack dynamic collection and analysis mechanisms based on changes in the wearer's state, resulting in data collection often employing fixed strategies and failing to form a tight closed loop with subsequent analysis. On the other hand, in terms of safety protection, existing solutions typically rely on single positioning technology, which has insufficient reliability in complex scenarios such as indoor environments. Furthermore, they lack mechanisms to link environmental / scenario cues with physiological and behavioral information, leading to suboptimal safety protection for children. Therefore, improving the child safety protection capabilities of smartwatches has become an urgent technical problem to be solved.

[0020] The main solution of this application is as follows: First, acquire multi-source physiological and behavioral monitoring data, location information, and scene clue information obtained from a smartwatch. Then, generate a dataset to be analyzed based on this data. Next, determine the current state of the wearable object based on the dataset, adaptively adjust the data acquisition strategy for the multi-source physiological and behavioral monitoring data according to the current state, and preprocess the dataset to be analyzed to obtain a processed dataset. Then, construct a fusion representation of the processed dataset to obtain fusion features, and determine the target event type and the corresponding handling instructions based on the fusion features. Finally, control the smartwatch to output interactive prompts based on the handling instructions and send alarm information associated with the target event type to the monitoring terminal. The alarm information includes location information fields related to the location information and environmental clue fields related to the scene clue information.

[0021] This application acquires multi-source physiological and behavioral monitoring data, location information, and scene clues from a smartwatch simultaneously to generate a dataset to be analyzed. Based on this dataset, the current state of the wearable object is determined to drive the adaptive adjustment of the acquisition strategy. The dataset is then preprocessed to obtain a processed dataset. A fusion representation is constructed from the processed dataset to form fusion features, and the target event type and its corresponding handling instructions are determined accordingly. Finally, based on the handling instructions, the watch interaction prompts are triggered, and an alarm message containing location information and environmental clue fields is sent to the monitoring terminal. This establishes the identification and alarm output of safety-related events on a unified link of multi-source data, adaptive state processing, and fusion judgment, thereby improving the smartwatch's ability to identify and handle children's safety risks.

[0022] It should be noted that the executing entity of the method in this embodiment can be a computing service device with data processing, network communication, and program execution functions, or it can be the aforementioned smartwatch with the same or similar functions. This embodiment and the following embodiments will be described using a smartwatch as an example.

[0023] Based on this, a first embodiment of the multi-dimensional child growth protection method of this application is proposed. Please refer to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the multi-dimensional child growth protection method of this application.

[0024] In this embodiment, the method is applied to a smartwatch, and the multi-dimensional child protection method includes the following steps: S1: Obtain multi-source physiological and behavioral monitoring data, location information, and scene clue information acquired by the smartwatch, and generate a dataset to be analyzed based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information; It should be noted that a smartwatch is a wearable terminal worn on the wrist, possessing multimodal sensing, positioning, communication, and interaction capabilities. Multi-source physiological and behavioral monitoring data is a collection of monitoring data acquired by the smartwatch's multimodal sensing capabilities, used to characterize the wearer's physiological state and behavioral activities. Location information is spatial location-related information acquired by the smartwatch's positioning capabilities. Scene cue information is cue information used to characterize the wearer's environment / activity scene. The dataset to be analyzed is a data set formed by organizing and associating the aforementioned multi-source physiological and behavioral monitoring data, location information, and scene cue information.

[0025] Specifically, during operation, the smartwatch utilizes its multimodal sensing module to continuously or periodically monitor the wearer, acquiring multi-source physiological and behavioral monitoring data. Simultaneously, it uses its global positioning module to obtain location information corresponding to the current monitoring period, establishing a correlation between location information and multi-source physiological and behavioral monitoring data within the same acquisition window or time dimension. As a possible implementation, the multimodal sensing module can cover data dimensions such as heart rate, blood oxygen, body temperature, exercise intensity, and sleep structure, while the global positioning module can employ multiple positioning methods in tandem to adapt to complex outdoor and indoor scenarios.

[0026] Furthermore, based on the acquisition of multi-source physiological and behavioral monitoring data and location information, the smartwatch further acquires scene clue information through a scene recognition unit. The scene clue information can be obtained from scene images captured by the camera through image recognition, or obtained through voice keyword extraction technology, and is used to indicate environmental / activity scene clues related to the wearer. Subsequently, the smartwatch performs data organization processing on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information, so that the three are related in data structure, including aligning time identifiers, unifying data fields, adding source identifiers or related indexes, etc., thereby generating a dataset to be analyzed based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information.

[0027] Because this step simultaneously acquires multi-source physiological and behavioral monitoring data, location information, and scene clues on the smartwatch side, and forms a unified dataset to be analyzed by organizing and associating these three types of information, subsequent processing does not need to repeatedly match or make separate judgments between isolated data sources. Instead, it can synchronously utilize the three key inputs of physiological / behavioral status, spatial location, and scene clues within the same dataset framework. This provides a consistent and associative data carrier for subsequent status determination, fusion modeling, and event judgment from the data foundation level, thereby improving the data support capabilities of the analysis and alarm chain for child growth protection scenarios.

[0028] S2: Determine the current state of the wearable object based on the dataset to be analyzed, adaptively adjust the acquisition strategy of the multi-source physiological and behavioral monitoring data according to the current state, and preprocess the dataset to be analyzed to obtain the processed dataset; It should be noted that the acquisition strategy is a set of control rules for the smartwatch to acquire multi-source physiological and behavioral monitoring data. Adaptive adjustment refers to dynamically updating the acquisition strategy based on the current state to match the acquisition control with the current state. Preprocessing is the data processing procedure performed on the dataset to be analyzed. The processed dataset is the data set obtained after adaptive adjustment of the acquisition strategy and preprocessing of the dataset to be analyzed.

[0029] Specifically, based on the dataset to be analyzed, the smartwatch extracts state representations from the multi-source physiological and behavioral monitoring data, and combines this with scene clues in the dataset to comprehensively determine the current activity stage or scene of the wearer, thereby determining the current state of the wearer. After determining the current state, the smartwatch generates acquisition control parameters based on the current state, and adaptively adjusts the acquisition strategy of the multi-source physiological and behavioral monitoring data based on the acquisition control parameters, so that the subsequent acquisition process corresponds to the current state in terms of acquisition rhythm, acquisition sequence, or acquisition channel combination.

[0030] Furthermore, after the acquisition strategy completes adaptive adjustment, the smartwatch performs preprocessing on the dataset to be analyzed to organize it into a data format that can be used for subsequent fusion representation construction. The preprocessing may include performing time correlation processing on the dataset to be analyzed to establish alignment relationships between data from different sources, identifying and processing abnormal or noisy data, completing or labeling missing or incomplete data, and standardizing and encapsulating data fields and data formats, so that the dataset to be analyzed meets the requirements of subsequent processing in terms of temporal consistency, field consistency, and usability, thereby obtaining the processed dataset.

[0031] Since this step first determines the current state of the wearable object based on the dataset to be analyzed, and then adaptively adjusts the acquisition strategy for multi-source physiological and behavioral monitoring data based on the current state, the acquisition control can be dynamically updated as the wearable object's state changes, thus ensuring that the data entering the subsequent processing chain maintains a correspondence with the current state. At the same time, by preprocessing the dataset to be analyzed and outputting the processed dataset, data from different sources form a unified data foundation in terms of time correlation, field organization, and data availability, thereby providing more stable and directly usable data input conditions for subsequent fusion representation construction and event determination based on the processed dataset.

[0032] S3: Construct a fusion representation for the processed dataset to obtain fusion features, and determine the target event type and the corresponding disposal instruction based on the fusion features; It should be noted that fusion representation construction is the process of associating and modeling information from different sources in the processed dataset to construct a unified representation. Fusion features are the feature results obtained from fusion representation construction. The target event type is the event category determined based on the fusion features. Disposal instructions are the control information corresponding to the target event type.

[0033] Specifically, based on the processed dataset, the smartwatch performs feature processing on at least the multi-source physiological and behavioral monitoring data, location information data, and scene cue data contained therein, to obtain sub-features that respectively represent physiological state, behavioral pattern, spatial location, and scene cue. Subsequently, based on the correlation between the sub-features (e.g., the correspondence under the same time window, the same location segment, or the same scene cue segment), a fusion representation construction process is performed to map the sub-features into a unified fusion representation, and outputs the fusion feature used to represent the processed dataset.

[0034] Furthermore, after obtaining the fusion feature, the smartwatch inputs the fusion feature into the event determination module to output the target event type corresponding to the fusion feature; furthermore, the smartwatch generates a handling instruction corresponding to the target event type based on the target event type and the preset handling rules / mapping relationship, and the handling instruction is used to instruct subsequent control over the smartwatch's interactive prompt format, alarm information organization fields, and alarm sending strategy.

[0035] Since this step takes the processed dataset as input and constructs fusion features through fusion representation, relevant information from multi-source physiological and behavioral monitoring, location, and scene cues is uniformly represented in the same feature space. Therefore, subsequent event determination can directly determine the target event type based on the fusion features, and further generate corresponding handling instructions based on the target event type. This achieves a structured connection from multi-source data to executable handling in the "data fusion representation - event type determination - handling instruction output" link, providing a clear control basis for subsequent interactive prompts and alarm information output.

[0036] S4: Based on the handling command, control the smartwatch to output interactive prompts and send alarm information associated with the target event type to the monitoring terminal, wherein the alarm information includes a location information field related to the location information and an environmental clue field related to the scene clue information.

[0037] It should be noted that the handling instruction is control information generated by the preceding steps based on the target event type. Interactive prompts are human-computer interaction information output by the smartwatch to the wearer. The monitoring terminal is the monitoring-side terminal device that establishes a communication connection with the smartwatch. Alarm information is the information carrier sent to the monitoring terminal. The location information field is a field in the alarm information used to characterize the wearer's spatial location. The environmental cue field is a field in the alarm information used to characterize scene clues.

[0038] Specifically, the smartwatch receives and parses the processing command to determine an interaction prompt configuration that matches the target event type. The interaction prompt configuration is used to limit the interaction channel, interaction content, and interaction triggering conditions. Subsequently, the smartwatch executes the interaction prompt output locally based on the interaction prompt configuration to provide the wearer with prompt information corresponding to the target event type. The interaction prompt output can be implemented through at least one of the following methods: display interface prompts, voice prompts, and vibration prompts.

[0039] Furthermore, while or after executing the interactive prompt output, the smartwatch constructs an alarm message body based on the target event type, generates a location information field related to the location information based on the location information, and generates an environmental clue field related to the scene clue information based on the scene clue information; the location information field and the environmental clue field are written into the alarm message body to form the alarm information, and the alarm information is sent to the monitoring terminal through the communication interface, so that the monitoring terminal receives the alarm information associated with the target event type.

[0040] Since this step uses the handling command as the control entry point, the smartwatch can execute the corresponding interactive prompt output according to the target event type, and further send alarm information associated with the target event type to the monitoring terminal. At the same time, the alarm information carries at least a location information field generated by the location information and an environmental clue field generated by the scene clue information. Therefore, when the monitoring terminal receives the alarm, it can simultaneously obtain the structured content of "event category association information - location association information - environmental clue association information", thereby providing clearer information support for the monitoring side to identify and handle alarm events.

[0041] This embodiment acquires multi-source physiological and behavioral monitoring data, location information, and scene clue information from a smartwatch, and generates a dataset to be analyzed based on these data. The current state of the wearable object is determined based on this dataset, and the data acquisition strategy for the multi-source physiological and behavioral monitoring data is adaptively adjusted according to the current state. The dataset is then preprocessed to obtain a processed dataset. A fusion representation is constructed from the processed dataset to obtain fusion features, and the target event type and corresponding handling instructions are determined based on these features. The smartwatch outputs interactive prompts based on the handling instructions and sends alarm information associated with the target event type to the monitoring terminal. The alarm information includes location information fields related to the location information and environmental clue fields related to the scene clue information. This embodiment acquires multi-source physiological and behavioral monitoring data, location information, and scene clues from the smartwatch simultaneously to generate a dataset to be analyzed. Based on the dataset, the current state of the wearable object is determined to drive the adaptive adjustment of the acquisition strategy. The dataset is preprocessed to obtain a processed dataset. Then, a fusion representation is constructed on the processed dataset to form fusion features, and the target event type and its corresponding handling instructions are determined accordingly. Finally, based on the handling instructions, the watch interaction prompts are triggered and an alarm message containing location information and environmental clue fields is sent to the monitoring terminal. This establishes the identification and alarm output of safety-related events on a unified link of multi-source data, adaptive state processing, and fusion judgment, thereby improving the smartwatch's ability to identify and handle children's safety risks.

[0042] Based on the first embodiment described above, a second embodiment of the multi-dimensional child growth protection method of this application is proposed. Please refer to... Figure 2 , Figure 2 This is a schematic diagram of a sub-process in the second embodiment of the multi-dimensional child growth protection method of this application.

[0043] like Figure 2 As shown, in this embodiment, after step S4, the following steps are also included: S4a: When the disposal instruction indicates that external linkage is required, a linkage request is sent to the external linkage device; S4b: Perform at least one of local encrypted storage and end-to-end encrypted transmission on the dataset to be analyzed and / or the alarm information in accordance with a preset data security policy; S4c: Upon receiving a data deletion request, perform deletion processing on the corresponding data and generate a deletion certificate.

[0044] It should be noted that external linkage refers to the interaction between the smartwatch and external devices / systems through IoT communication capabilities. A linkage request is a request message sent to the external linked device. A preset data security policy is a set of policy rules that constrain the storage and transmission security of the dataset to be analyzed and / or alarm information. Local encrypted storage is a storage mechanism that stores core data locally on the watch and saves it in an encrypted manner. A data deletion request is a deletion command or request message initiated by the monitoring side for specific data.

[0045] Specifically, after receiving the action command, the smartwatch parses the command to determine whether to trigger external linkage. When the action command indicates that external linkage is required, the smartwatch uses its IoT communication capabilities to identify the target external linkage device and generates a linkage request message matching the external linkage device. The linkage request message may include a linkage trigger identifier, an event association identifier, and request fields related to the linkage action. Subsequently, the smartwatch sends the linkage request to the external linkage device through a communication interface to achieve network linkage with external systems such as home, campus, or community security systems.

[0046] Furthermore, regarding data security processing, the smartwatch, according to a preset data security strategy, performs at least one of local encrypted storage and end-to-end encrypted transmission on the dataset to be analyzed and / or the alarm information: on the one hand, for data that needs to be stored on the watch side, the local encrypted storage mechanism is invoked to write the corresponding data into local storage in encrypted form; on the other hand, for data that needs to be sent outwards, an end-to-end encrypted transmission mechanism is enabled in the transmission link to protect the transmitted content. Further, when the smartwatch receives a data deletion request, it determines the target data range corresponding to the data deletion request and performs deletion processing on the target data; after completing the deletion processing, a deletion credential associated with the data deletion request is generated, and the deletion credential is stored or output for verification by the monitoring side.

[0047] This step sends a linkage request to external devices when the handling instruction indicates that external linkage is required, enabling the smartwatch to form cross-device collaboration with external systems. At the same time, it performs at least one of local encrypted storage and end-to-end encrypted transmission of the dataset to be analyzed and / or alarm information according to the preset data security policy, ensuring that the data is securely protected both during local storage and external transmission. Furthermore, upon receiving a data deletion request, it performs deletion processing on the corresponding data and generates deletion credentials, ensuring that the data deletion action has traceable credential output. Therefore, in the processing chain of "linkage request - secure storage / transmission - deletion and credentials", it not only achieves controllable triggering of external linkage capabilities, but also ensures that the entire data lifecycle processing has security constraints and a verifiable deletion closed loop.

[0048] Based on the first embodiment described above, in this embodiment, step S2 includes: S21: Perform consistency verification and temporal alignment processing on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information in the dataset to be analyzed, and determine the state judgment input based on the aligned data; S22: Perform state recognition processing based on the state determination input to determine the current state of the wearable object, generate acquisition control parameters based on the current state, and adaptively adjust the acquisition strategy of the multi-source physiological and behavioral monitoring data based on the acquisition control parameters; S23: After the acquisition strategy completes the adaptive adjustment, the dataset to be analyzed is preprocessed. The preprocessing includes at least one of abnormal data identification, missing data completion, and data normalization to obtain the processed dataset.

[0049] It should be noted that consistency verification is the process of validating the validity and matching relationships of data from different sources in the dataset to be analyzed. Temporal alignment is the process of aligning data from different sources along the time dimension. State determination input is an input data structure or set of input features extracted / organized from the aligned data for use in state identification processing. Acquisition control parameters are a set of parameters generated from the current state and used to control the acquisition strategy. Data normalization is the process of uniformly scaling and representing data of different dimensions or ranges in the dataset to be analyzed.

[0050] Specifically, after acquiring the dataset to be analyzed, the smartwatch first performs consistency checks on the multi-source physiological and behavioral monitoring data, location information, and scene cue information to check the consistency of data fields, data types, association identifiers, and timestamp descriptions among the data sources, and marks or filters out data records that do not meet the consistency conditions. Subsequently, based on a unified time benchmark, time-series alignment processing is performed on each data source to establish a correspondence between data from different sources within the same time slice or the same acquisition window, thereby obtaining aligned data. After obtaining the aligned data, the smartwatch extracts input elements from the aligned data to characterize physiological fluctuations, behavioral changes, location changes, and scene cue changes, and combines them according to a preset structure to determine the state judgment input that can be directly used for state recognition.

[0051] Furthermore, the smartwatch performs state recognition processing based on the state determination input to output the current state of the wearable object and generates acquisition control parameters based on the current state. On this basis, the smartwatch adaptively adjusts the acquisition strategy for multi-source physiological and behavioral monitoring data based on the acquisition control parameters, ensuring that subsequent data acquisition corresponds to the current state in terms of acquisition rhythm, acquisition sequence, or acquisition channel combination. After the acquisition strategy completes adaptive adjustment, the smartwatch performs preprocessing on the dataset to be analyzed. This preprocessing includes at least one of abnormal data identification, missing data completion, and data normalization, to organize the dataset into a data format suitable for subsequent fusion representation construction and event determination, thereby obtaining the processed dataset.

[0052] This step first performs consistency verification and temporal alignment on the multi-source physiological and behavioral monitoring data, location information, and scene clue information in the dataset to be analyzed, and determines the state judgment input accordingly. This ensures that subsequent state recognition is based on aligned and correlated data. Then, state recognition is completed based on the state judgment input to determine the current state, and acquisition control parameters are generated according to the current state to adaptively adjust the acquisition strategy, so that the acquisition control corresponds to the current state. After the acquisition strategy is adaptively adjusted, at least one preprocessing step, including abnormal data identification, missing data completion, and data normalization, is performed on the dataset to be analyzed to obtain the processed dataset.

[0053] This embodiment acquires multi-source physiological and behavioral monitoring data, location information, and scene clue information from a smartwatch, and generates a dataset to be analyzed based on these data. The current state of the wearable object is determined based on this dataset, and the data acquisition strategy for the multi-source physiological and behavioral monitoring data is adaptively adjusted according to the current state. The dataset is then preprocessed to obtain a processed dataset. A fusion representation is constructed from the processed dataset to obtain fusion features, and the target event type and corresponding handling instructions are determined based on these features. The smartwatch outputs interactive prompts based on the handling instructions and sends alarm information associated with the target event type to the monitoring terminal. The alarm information includes location information fields related to the location information and environmental clue fields related to the scene clue information. This embodiment acquires multi-source physiological and behavioral monitoring data, location information, and scene clues from the smartwatch simultaneously to generate a dataset to be analyzed. Based on the dataset, the current state of the wearable object is determined to drive the adaptive adjustment of the acquisition strategy. The dataset is preprocessed to obtain a processed dataset. Then, a fusion representation is constructed on the processed dataset to form fusion features, and the target event type and its corresponding handling instructions are determined accordingly. Finally, based on the handling instructions, the watch interaction prompts are triggered and an alarm message containing location information and environmental clue fields is sent to the monitoring terminal. This establishes the identification and alarm output of safety-related events on a unified link of multi-source data, adaptive state processing, and fusion judgment, thereby improving the smartwatch's ability to identify and handle children's safety risks.

[0054] Based on the second embodiment described above, a third embodiment of the multi-dimensional child growth protection method of this application is proposed. Please refer to... Figure 3 , Figure 3 This is a schematic diagram of a sub-process in the third embodiment of the multi-dimensional child growth protection method of this application.

[0055] In this embodiment, step S3 includes: S31: Based on the processed dataset, extract sub-features related to physiological state, behavioral pattern, spatial location and scene cues respectively, and organize the sub-features into a set of features to be fused. S32: Perform cross-modal association and fusion representation construction processing on the set of features to be fused to generate fusion features for characterizing the processed dataset; S33: Input the fusion feature into the preset event determination module to obtain the target event type corresponding to the fusion feature, and generate the corresponding handling instruction based on the target event type.

[0056] It should be noted that physiological state refers to state information used to characterize the physiological monitoring dimension of the wearable object. Behavioral pattern refers to pattern information used to characterize the behavioral activity dimension of the wearable object. Cross-modal association is the process of establishing associations between sub-features from different modalities / sources. The preset event determination module is a functional module used to determine the event type of the fused features.

[0057] Specifically, based on the processed dataset, the smartwatch performs feature extraction processing in four dimensions: physiological, behavioral, location, and scene. In the physiological state dimension, sub-features reflecting physiological fluctuations and changes in physiological levels are extracted from physiological monitoring data. In the behavioral pattern dimension, sub-features reflecting activity stages, movement rhythms, and activity intensity changes are extracted from behavioral monitoring data. In the spatial location dimension, sub-features reflecting location changes and location segment distributions are extracted from location information data. In the scene cue dimension, sub-features representing environmental categories, activity scene prompts, or voice keyword cues are extracted from scene cue information. Subsequently, the smartwatch encapsulates the sub-features of each dimension according to a unified field structure and indexing rules, and establishes associated indexes for each sub-feature based on time identifiers, location identifiers, or scene identifiers, thereby organizing the sub-features into a set of features to be fused.

[0058] Furthermore, after obtaining the set of features to be fused, the smartwatch performs cross-modal association and fusion representation construction processing on the set of features to be fused, so as to establish a consistent correspondence between sub-features of different dimensions, and map the multi-dimensional sub-features into a unified fusion representation to generate fusion features for characterizing the processed dataset; further, the smartwatch inputs the fusion features into a preset event determination module, which outputs the target event type corresponding to the fusion features; after determining the target event type, the smartwatch generates a corresponding handling instruction based on the target event type and preset handling rules, so as to control the interactive prompt output and alarm information sending process in subsequent steps.

[0059] This step first extracts sub-features related to physiological state, behavioral patterns, spatial location, and scene cues from the processed dataset and organizes them into a set of features to be fused, making information from different dimensions form a structured and associative input. Then, cross-modal association and fusion representation construction are performed on the set of features to be fused to generate fused features, so that multi-dimensional sub-features are comprehensively expressed in a unified representation. The fused features are then input into a preset event judgment module to obtain the target event type and generate disposal instructions accordingly. This achieves a structured connection from multi-source data to event category and then to disposal control, providing clear and directly executable control basis for subsequent interactive prompts and alarm information generation.

[0060] Based on the second embodiment described above, in this embodiment, step S1 includes: S11: Control the smartwatch's acquisition component to collect multi-source physiological and behavioral monitoring data of the wearer, and obtain the location information corresponding to the multi-source physiological and behavioral monitoring data through the smartwatch's positioning component; S12: During the process of collecting the multi-source physiological and behavioral monitoring data, the scene perception component of the smartwatch is called to obtain scene clue information, and the scene clue information is associated and identified with the multi-source physiological and behavioral monitoring data and the location information; S13: Based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information, perform data organization and processing, which includes at least one of timestamp unification, data format standardization, and data field encapsulation to generate a dataset to be analyzed.

[0061] It should be noted that the acquisition component is a functional component used to collect multi-source physiological and behavioral monitoring data of the wearable object. Location information refers to spatial location-related information corresponding to the multi-source physiological and behavioral monitoring data. The scene perception component is a functional component used to acquire scene cue information. Data organization and processing is the process of structuring and organizing the multi-source data.

[0062] Specifically, during operation, the smartwatch controls the data acquisition component to monitor the wearer's physiological and behavioral data, thereby acquiring multi-source physiological and behavioral monitoring data. Simultaneously, the smartwatch calls the positioning component to obtain location information corresponding to the multi-source physiological and behavioral monitoring data, enabling the location information to establish a correspondence with the multi-source physiological and behavioral monitoring data within the same acquisition period or time slice. As a possible implementation, the data acquisition component can output data from different monitoring channels based on the multimodal sensing module, and the positioning component can output location information using different positioning methods or a combination of positioning methods in outdoor and indoor scenarios.

[0063] Furthermore, during the collection of multi-source physiological and behavioral monitoring data, the smartwatch invokes a scene perception component to obtain scene clue information. This scene clue information can be composed of the recognition results of environmental images or the results of voice keyword extraction. Subsequently, the smartwatch associates and identifies the scene clue information with the multi-source physiological and behavioral monitoring data and the location information, enabling the three types of information to be correlated using the same time identifier, location identifier, or segment identifier. Further, the smartwatch performs data organization and processing based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information. This data organization and processing includes at least one of the following: unifying timestamps on data from different sources to establish consistency in the time dimension; standardizing data formats to establish consistency in fields and types; and encapsulating data fields to form a unified data structure, thereby generating a dataset to be analyzed.

[0064] Because this step acquires multi-source physiological and behavioral monitoring data through the acquisition component on the smartwatch side, obtains location information corresponding to the monitoring data through the positioning component, and further acquires scene clue information during the acquisition process and establishes an association identifier with the monitoring data and location information, and then generates a dataset to be analyzed through at least one data organization and processing method including timestamp unification, data format standardization and data field encapsulation, monitoring data, location information and scene clue information from different sources can form a clear correspondence and unified field expression within the same data structure, providing a structured and associative data foundation for subsequent state determination, fusion modeling and event recognition based on the dataset to be analyzed.

[0065] Based on the second embodiment described above, in this embodiment, step S4 includes: S41: Parse the handling instruction to determine the alarm interaction configuration, wherein the alarm interaction configuration includes at least one of the following: interaction method, interaction content, and interaction duration conditions; S42: Based on the alarm interaction configuration, control the smartwatch to output interactive prompts, and generate an alarm message body based on the target event type. The alarm message body includes an event identifier field and a status description field associated with the target event type. S43: Encapsulate the alarm message body with the location information field related to the location information and the environmental clue field related to the scene clue information to obtain alarm information associated with the target event type, and send the alarm information to the monitoring terminal through a preset communication interface to control the smartwatch to output interactive prompts and send alarm information associated with the target event type to the monitoring terminal.

[0066] It should be noted that the alarm interaction configuration is the interaction control configuration obtained by parsing the handling instructions. The interaction duration condition is used to limit the maintenance / termination of the interaction prompt. The alarm message body is the data structure used to carry the core alarm content. The preset communication interface is a pre-defined interface for data communication between the smartwatch and the monitoring terminal. The monitoring terminal is the terminal device on the monitoring side that receives alarm information.

[0067] Specifically, after receiving a handling command, the smartwatch parses the command to determine an alarm interaction configuration that matches the target event type. This alarm interaction configuration at least defines one or more of the following: interaction method, interaction content, and interaction duration conditions. Subsequently, based on the alarm interaction configuration, the smartwatch controls its local interaction unit to output an interaction prompt. This prompt can be implemented through at least one of the following interaction methods: a display interface, voice, or vibration, so that the wearer receives prompt information corresponding to the target event type on the watch side.

[0068] Furthermore, simultaneously with or after outputting interactive prompts, the smartwatch generates an alarm message body based on the target event type. The alarm message body includes at least an event identifier field and a status description field associated with the target event type. Further, the smartwatch generates a location information field based on location information and an environmental clue field based on scene clue information. The alarm message body is then encapsulated with the location information field and the environmental clue field to obtain alarm information associated with the target event type. Subsequently, the alarm information is sent to the monitoring terminal via a preset communication interface, thereby completing the interactive prompt output on the watch side and receiving the alarm information associated with the target event type on the monitoring side.

[0069] This step determines the alarm interaction configuration, including the interaction method, interaction content, and interaction duration conditions, by parsing the handling instructions, and controls the smartwatch to output interaction prompts accordingly. At the same time, it generates an alarm message body containing an event identifier field and a status description field based on the target event type. Then, it encapsulates the alarm message body with the location information field and environmental clue field to form alarm information and sends it to the monitoring terminal through a preset communication interface. This ensures that the alarm output has clear configuration basis and field-based content organization on both the watch side and the monitoring side.

[0070] This embodiment acquires multi-source physiological and behavioral monitoring data, location information, and scene clue information from a smartwatch, and generates a dataset to be analyzed based on these data. The current state of the wearable object is determined based on this dataset, and the data acquisition strategy for the multi-source physiological and behavioral monitoring data is adaptively adjusted according to the current state. The dataset is then preprocessed to obtain a processed dataset. A fusion representation is constructed from the processed dataset to obtain fusion features, and the target event type and corresponding handling instructions are determined based on these features. The smartwatch outputs interactive prompts based on the handling instructions and sends alarm information associated with the target event type to the monitoring terminal. The alarm information includes location information fields related to the location information and environmental clue fields related to the scene clue information. This embodiment acquires multi-source physiological and behavioral monitoring data, location information, and scene clues from the smartwatch simultaneously to generate a dataset to be analyzed. Based on the dataset, the current state of the wearable object is determined to drive the adaptive adjustment of the acquisition strategy. The dataset is preprocessed to obtain a processed dataset. Then, a fusion representation is constructed on the processed dataset to form fusion features, and the target event type and its corresponding handling instructions are determined accordingly. Finally, based on the handling instructions, the watch interaction prompts are triggered and an alarm message containing location information and environmental clue fields is sent to the monitoring terminal. This establishes the identification and alarm output of safety-related events on a unified link of multi-source data, adaptive state processing, and fusion judgment, thereby improving the smartwatch's ability to identify and handle children's safety risks.

[0071] In one embodiment, when generating a handling instruction, in addition to indicating the interaction method and alarm sending, the handling instruction also carries alarm receipt policy parameters and upgrade linkage policy parameters. The alarm receipt policy parameters define the confirmation receipt type and validity conditions of the monitoring terminal, while the upgrade linkage policy parameters define the linkage upgrade object and linkage request field template when the validity conditions are not met. After sending alarm information to the monitoring terminal, the smartwatch enters a receipt listening state: it receives the receipt message returned by the monitoring terminal through a preset communication interface and performs validity verification on the receipt message (e.g., consistency verification based on session identifier, event identifier field, and receipt type field) to determine whether the validity conditions are met. When met, the smartwatch marks the alarm event as a confirmed event and ends the upgrade process; when not met, the smartwatch sends a linkage request to an external linkage device according to the upgrade linkage policy parameters. The linkage request includes at least an event identifier field, a linkage action identifier field, and a handling request field associated with the target event type.

[0072] Furthermore, this embodiment introduces an alarm evidence package during the alarm generation stage. When generating the alarm message body, the smartwatch simultaneously generates evidence package metadata associated with the alarm message body. The evidence package metadata includes at least: a fusion feature summary field (used to characterize the fusion feature fragment or statistical summary that triggered the alarm), a data fragment index field (used to locate the processed dataset fragment corresponding to the alarm), and an integrity verification field (used to perform integrity verification on the evidence package content). The smartwatch associates and encapsulates the evidence package metadata with the alarm message body, location information field, and environmental clue field: wherein, when the alarm information is sent to the monitoring terminal, it may carry at least some fields of the evidence package metadata; at the same time, the complete content of the evidence package is subjected to at least one of local encrypted storage and / or end-to-end encrypted transmission according to a preset data security policy, so that the monitoring terminal can retrieve the evidence package content for verification when needed. If the monitoring terminal subsequently initiates a data deletion request, the smartwatch performs deletion processing on the evidence package data and its index data associated with the alarm event and generates a corresponding deletion credential.

[0073] In this embodiment, the smartwatch, while maintaining the (multi-source data collection and construction - state adaptation - fusion judgment - alarm output) process, further realizes the alarm confirmation receipt process and the upgrade linkage triggered by receipt failure, and provides structured management and secure handling of evidence packages strongly associated with alarm events, thereby enabling the alarm handling process to have a verifiable, upgradeable and traceable data support mechanism.

[0074] This application also provides a multi-dimensional child growth protection device; please refer to... Figure 4 , Figure 4This is a schematic diagram of the module structure of the multi-dimensional child growth protection device according to an embodiment of this application. The device is applied to a smartwatch, and the multi-dimensional child growth protection device includes: The data acquisition module 401 is used to acquire multi-source physiological and behavioral monitoring data, location information and scene clue information acquired by the smartwatch, and generate a dataset to be analyzed based on the multi-source physiological and behavioral monitoring data, the location information and the scene clue information; The strategy adjustment module 402 is used to determine the current state of the wearable object based on the dataset to be analyzed, adaptively adjust the acquisition strategy of the multi-source physiological and behavioral monitoring data according to the current state, and preprocess the dataset to be analyzed to obtain the processed dataset. The fusion instruction module 403 is used to construct a fusion representation of the processed dataset, obtain fusion features, and determine the target event type and the corresponding disposal instruction based on the fusion features; The alarm interaction module 404 is used to control the smartwatch to output interactive prompts based on the handling command, and to send alarm information associated with the target event type to the monitoring terminal. The alarm information includes a location information field related to the location information and an environmental clue field related to the scene clue information.

[0075] The multi-dimensional child protection device provided in this application, employing the multi-dimensional child protection method described in the above embodiments, can solve the technical problem of how to improve the child safety protection capabilities of smartwatches. Compared with the prior art, the beneficial effects of the multi-dimensional child protection device provided in this application are the same as those of the multi-dimensional child protection method described in the above embodiments, and other technical features in the multi-dimensional child protection device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0076] This application provides a smartwatch, 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, which are executed by the at least one processor to enable the at least one processor to perform the multi-dimensional child growth protection method described above.

[0077] The following is for reference. Figure 5 , Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the multi-dimensional child growth protection method in the embodiments of this application, which shows a schematic diagram of the structure of a smartwatch suitable for implementing the embodiments of this application. Figure 5 The smartwatch shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0078] like Figure 5 As shown, a smartwatch may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, 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 smartwatch. 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 smartwatch to communicate wirelessly or wiredly with other devices to exchange data. While the figures show smartwatches with various systems, it should be understood that implementing or having all of the systems shown is not required. More or fewer systems may be implemented alternatively.

[0079] In particular, 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, the 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. When the computer program is executed by the processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0080] The smartwatch provided in this application employs the multi-dimensional child protection method described in the above embodiments, which solves the technical problem of how to improve the child safety protection capabilities of smartwatches. Compared with the prior art, the beneficial effects of the smartwatch provided in this application are the same as those of the multi-dimensional child protection method described in the above embodiments, and other technical features of the smartwatch are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0081] 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.

[0082] The above description is merely a specific embodiment 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.

[0083] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the multi-dimensional child growth protection method described in the above embodiments.

[0084] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the smartwatch, the smartwatch causes the following actions: It acquires multi-source physiological and behavioral monitoring data, location information, and scene clue information, and generates a dataset to be analyzed based on these data; it determines the current state of the wearable object based on the dataset to be analyzed, adaptively adjusts the data acquisition strategy for the multi-source physiological and behavioral monitoring data according to the current state, and preprocesses the dataset to be analyzed to obtain a processed dataset; it constructs a fusion representation of the processed dataset to obtain fusion features, and determines the target event type and the corresponding handling instructions based on the fusion features; it controls the smartwatch to output interactive prompts based on the handling instructions, and sends alarm information associated with the target event type to the monitoring terminal, wherein the alarm information includes location information fields related to location information and environmental clue fields related to scene clue information. Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as 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).

[0085] 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.

[0086] 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.

[0087] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the above-described multi-dimensional child protection method, thereby solving the technical problem of how to improve the child safety protection capabilities of smartwatches. 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 multi-dimensional child protection method provided in the above embodiments, and will not be repeated here.

[0088] This application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the multi-dimensional child growth protection method described above.

[0089] The computer program product provided in this application can solve the technical problem of how to improve the child safety protection capabilities of smartwatches. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the multi-dimensional child growth protection method provided in the above embodiments, and will not be repeated here.

[0090] All user-related data involved in this application (such as multi-source physiological and behavioral monitoring data) were obtained with the user's permission or consent; that is, when this application is used in specific products or technologies, user permission is required to obtain and process the relevant data, and the processing of the relevant data must comply with the relevant laws, regulations and regulatory standards of the relevant countries and regions.

[0091] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. A multi-dimensional method for protecting children's growth, characterized in that, The method is applied to a smartwatch, and the method includes: The system acquires multi-source physiological and behavioral monitoring data, location information, and scene clue information obtained by the smartwatch, and generates a dataset to be analyzed based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information. Based on the dataset to be analyzed, the current state of the wearable object is determined, and the acquisition strategy of the multi-source physiological and behavioral monitoring data is adaptively adjusted according to the current state. The dataset to be analyzed is then preprocessed to obtain the processed dataset. The processed dataset is fused to construct a fused representation, which yields fused features. Based on the fused features, the target event type and the corresponding handling instructions are determined. Based on the handling command, the smartwatch is controlled to output interactive prompts and send alarm information associated with the target event type to the monitoring terminal. The alarm information includes a location information field related to the location information and an environmental clue field related to the scene clue information.

2. The method as described in claim 1, characterized in that, After the step of controlling the smartwatch to output interactive prompts based on the handling command and sending alarm information associated with the target event type to the monitoring terminal, the method further includes: When the handling instruction indicates that external linkage is required, a linkage request is sent to the external linkage device; According to a preset data security policy, at least one of the following is performed: local encrypted storage and end-to-end encrypted transmission of the dataset to be analyzed and / or the alarm information. Upon receiving a data deletion request, the system performs deletion processing on the corresponding data and generates a deletion certificate.

3. The method as described in claim 1, characterized in that, The steps of determining the current state of the wearable object based on the dataset to be analyzed, adaptively adjusting the acquisition strategy of the multi-source physiological and behavioral monitoring data according to the current state, and preprocessing the dataset to be analyzed to obtain the processed dataset include: The consistency verification and temporal alignment processing of the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information in the dataset to be analyzed are performed, and the state judgment input is determined based on the aligned data. Based on the state determination input, state recognition processing is performed to determine the current state of the wearable object, and acquisition control parameters are generated according to the current state. Based on the acquisition control parameters, the acquisition strategy of the multi-source physiological and behavioral monitoring data is adaptively adjusted. After the acquisition strategy completes adaptive adjustment, the dataset to be analyzed is preprocessed. The preprocessing includes at least one of abnormal data identification, missing data completion, and data normalization to obtain the processed dataset.

4. The method as described in claim 1, characterized in that, The step of constructing a fused representation of the processed dataset to obtain fused features, and determining the target event type and the corresponding disposal instruction based on the fused features, includes: Based on the processed dataset, sub-features related to physiological state, behavioral pattern, spatial location and scene cues are extracted respectively, and the sub-features are organized into a set of features to be fused. The set of features to be fused is subjected to cross-modal association and fusion representation construction to generate fusion features for characterizing the processed dataset; The fusion feature is input into the preset event determination module to obtain the target event type corresponding to the fusion feature, and a corresponding handling instruction is generated based on the target event type.

5. The method as described in claim 1, characterized in that, The step of acquiring multi-source physiological and behavioral monitoring data, location information, and scene clue information obtained by the smartwatch, and generating a dataset to be analyzed based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information, includes: The smartwatch's acquisition component collects multi-source physiological and behavioral monitoring data of the wearer, and the smartwatch's positioning component obtains location information corresponding to the multi-source physiological and behavioral monitoring data. During the collection of the multi-source physiological and behavioral monitoring data, the scene perception component of the smartwatch is invoked to obtain scene clue information, and the scene clue information is associated and identified with the multi-source physiological and behavioral monitoring data and the location information; The data is organized and processed based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information. The data organization and processing includes at least one of timestamp unification, data format standardization, and data field encapsulation to generate a dataset to be analyzed.

6. The method as described in claim 1, characterized in that, The step of controlling the smartwatch to output interactive prompts based on the handling command and sending alarm information associated with the target event type to the monitoring terminal includes: The processing command is parsed to determine the alarm interaction configuration, which includes at least one of the following: interaction method, interaction content, and interaction duration conditions. Based on the alarm interaction configuration, the smartwatch is controlled to output interactive prompts, and an alarm message body is generated based on the target event type. The alarm message body includes an event identifier field and a status description field associated with the target event type. The alarm message body is encapsulated with the location information field related to the location information and the environmental clue field related to the scene clue information to obtain alarm information associated with the target event type. The alarm information is then sent to the monitoring terminal through a preset communication interface to control the smartwatch to output interactive prompts and send alarm information associated with the target event type to the monitoring terminal.

7. A multi-dimensional child growth protection device, characterized in that, The device is used in a smartwatch, and the device includes: The data acquisition module is used to acquire multi-source physiological and behavioral monitoring data, location information, and scene clue information acquired by the smartwatch, and to generate a dataset to be analyzed based on the multi-source physiological and behavioral monitoring data, the location information, and the scene clue information. The strategy adjustment module is used to determine the current state of the wearable object based on the dataset to be analyzed, adaptively adjust the acquisition strategy of the multi-source physiological and behavioral monitoring data according to the current state, and preprocess the dataset to be analyzed to obtain the processed dataset. The fusion instruction module is used to construct a fusion representation of the processed dataset, obtain fusion features, and determine the target event type and the corresponding disposal instruction based on the fusion features; The alarm interaction module is used to control the smartwatch to output interactive prompts based on the handling command, and to send alarm information associated with the target event type to the monitoring terminal. The alarm information includes a location information field related to the location information and an environmental clue field related to the scene clue information.

8. A smartwatch, characterized in that, The smartwatch includes: a memory, a processor, and a multi-dimensional child growth protection program stored on the memory and executable on the processor, the multi-dimensional child growth protection program being configured to implement the steps of the multi-dimensional child growth protection method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a multi-dimensional child growth protection program, which, when executed by a processor, implements the steps of the multi-dimensional child growth protection method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the multidimensional child growth protection method as described in any one of claims 1 to 6.

Images