Non-contact interaction and health early warning system and method based on biological electric field change

Abstract

The invention discloses a non-contact interaction and health early warning system and method based on biological electric field change. The system collects low-frequency biological electric field change signals generated on the surface of human skin in a non-contact state through a biological electric field sensing module arranged on a frame and / or a back plate of a mobile terminal, and performs preprocessing and feature analysis on the signals; transient features for interactive recognition and statistical features for health status assessment are extracted, respectively. The system further carries out multi-mode fusion analysis on the statistical characteristics and physiological parameters such as heart rate, blood oxygen and / or body temperature, and therefore air interaction instruction output and predictive early warning of the abnormal health state are achieved. Meanwhile, the sensing module is triggered to work through an energy management mechanism when an effective electric field change is detected, so that the overall power consumption is reduced. According to the invention, while the man-machine interaction convenience is improved, the integration of health monitoring and early warning is realized.

Description

Technical Field

[0001] This invention relates to the field of mobile terminal sensing and health detection technology, and in particular to a contactless interaction and health early warning system and method based on changes in bioelectric field. Background Technology

[0002] With the continuous integration of mobile terminal functions, human-computer interaction and health monitoring capabilities have gradually become important technological directions for smart terminals. Existing human-computer interaction methods mainly include touch operation, voice interaction, and camera-based visual recognition interaction, but these methods generally depend on specific usage conditions or external environments. For example, the reliability of touch operation decreases significantly when hands are wet, gloves are worn, or during exercise; voice interaction is easily affected by environmental noise; and camera-based gesture recognition has high requirements for lighting conditions, posture angle, and privacy environment, making it difficult to use stably in complex or restricted scenarios.

[0003] In the field of health monitoring, existing mobile terminals mostly rely on single or limited physiological parameters such as heart rate, blood oxygen, and body temperature for status detection. Their technical approach typically focuses on passively collecting data on physiological changes that have already occurred, making it difficult to reflect potential early abnormalities in the human body, and lacking the ability to conduct trend analysis and early warning of health risks. In addition, different health functions often rely on independent sensors and processing logic, resulting in a fragmented system structure and high power consumption, making it difficult to balance monitoring effectiveness and energy consumption control in long-term continuous use scenarios.

[0004] The human bioelectric field, as an intrinsic physiological signal formed by the combined effects of neural activity, muscle activity, and the cardiovascular system, contains rich information about behavioral intentions and health status. However, current applications of bioelectric fields are mostly limited to medical-grade contact detection scenarios, and an integrated technical solution has not yet been developed that can stably sense changes in bioelectric fields in a non-contact manner on mobile terminals, while simultaneously serving contactless interaction and health risk warning.

[0005] Therefore, how to achieve stable human-computer interaction by utilizing changes in bioelectric fields without relying on physical contact, and at the same time combine multimodal physiological data to comprehensively assess and predict health status, remains a technical problem to be solved in the existing technology.

[0006] Therefore, existing technologies still need to be improved. Summary of the Invention

[0007] Current mobile terminals still heavily rely on touch, voice, or visual perception for human-computer interaction, exhibiting limited adaptability to different environments and user states. This makes it difficult to achieve stable and reliable operation in contactless, restricted, or complex scenarios. Furthermore, existing health monitoring solutions primarily focus on the passive collection of single physiological parameters, lacking the comprehensive analytical capabilities for potential abnormal states and failing to provide timely and proactive health risk warnings. In addition, interactive and health monitoring functions are typically implemented separately, resulting in complex system structures and high energy consumption, which is unfavorable for long-term, continuous deployment on mobile terminals.

[0008] Therefore, it is necessary to provide a new technical solution that, without relying on physical contact, achieves the synergy between human-computer interaction and health status assessment through a unified sensing mechanism, while ensuring controllable system energy consumption and improving the applicability of interaction and the effectiveness of health early warning.

[0009] The technical solution of the present invention is as follows: This invention provides a contactless interaction and health early warning system based on changes in bioelectric field, comprising: A bioelectric field sensing module is installed on the frame and / or back panel of a mobile terminal to collect low-frequency bioelectric field change signals generated on the surface of human skin in a non-contact state. The signal preprocessing module is used to amplify, denoise, and decompose the bioelectric field change signal in the frequency domain. The feature parsing module is used to extract transient features for interactive identification and statistical features for health status assessment from the processed bioelectric field change signal. A multimodal fusion analysis module is used to fuse and analyze the statistical features with at least one physiological parameter data; The decision output module is used to output contactless interactive commands and / or health warning information based on the fusion analysis results.

[0010] In one embodiment, the bioelectric field sensing module includes multiple micro electric field sensors distributed in an array to sense electric field disturbances caused by human movement or physiological state.

[0011] In one embodiment, the detection frequency range of the bioelectric field change signal is 0.1 Hz to 100 Hz.

[0012] In one embodiment, the feature parsing module identifies air gestures, muscle micro-contractions, or operational intentions based on the transient features, and generates corresponding contactless interaction commands.

[0013] In one embodiment, the feature parsing module identifies long-term trends in bioelectric field changes based on the statistical features, which are used to characterize potential abnormal states related to the cardiovascular or nervous systems.

[0014] In one embodiment, the multimodal fusion analysis module uses the statistical characteristics of bioelectric field changes as the dominant feature and combines heart rate, blood oxygen, and / or body temperature data to comprehensively assess health status.

[0015] In one embodiment, the feature parsing module and the multimodal fusion analysis module perform pattern recognition on the bioelectric field change signal based on a machine learning model.

[0016] In one embodiment, the system further includes an energy management module for triggering the bioelectric field sensing module to enter a working state when a change in the bioelectric field is detected to exceed a preset threshold.

[0017] In one embodiment, the health warning information includes abnormality alert information, risk level information, and / or emergency contact trigger instructions.

[0018] In another aspect, the present invention provides a contactless interaction and health early warning method based on changes in bioelectric field, comprising: The system collects bioelectric field change signals, performs feature analysis and multimodal fusion analysis on the signals, and outputs contactless interactive commands and / or health warning information.

[0019] In summary, this invention introduces changes in the bioelectric field as a unified sensing entry point, constructing an integrated technical solution in mobile terminals that combines contactless interaction with health early warning. Compared to existing interaction methods that rely on touch, voice, or visual perception, this invention requires no physical contact or specific environmental conditions. By sensing and analyzing changes in the human body's bioelectric field, it can recognize the user's operational intentions, thereby improving the stability and applicability of human-computer interaction in complex usage scenarios. Furthermore, this invention is not limited to utilizing transient changes in the bioelectric field; it further analyzes the statistical characteristics of the bioelectric field and combines this with physiological parameters such as heart rate, blood oxygen, and body temperature for multimodal fusion modeling. This enables a comprehensive assessment of health status and predictive early warning of potential anomalies, transforming health monitoring from passive response to proactive early warning.

[0020] Furthermore, this invention, through adaptive control of the sensing module's operating state, effectively reduces overall system energy consumption while ensuring interactive response and monitoring effectiveness, making it suitable for long-term, continuous operation in mobile terminals. Therefore, this invention enhances interactive convenience while achieving synergistic integration of health monitoring and early warning functions, demonstrating significant practical value and promising prospects for wider application.

[0021] Compared with the prior art, the present invention has at least the following unexpected beneficial effects.

[0022] First, this invention does not treat the bioelectric field as merely a source of a single interactive signal or a single physiological parameter. Instead, it performs hierarchical analysis of bioelectric field changes, extracting transient features for interactive identification and statistical features for health status assessment. This allows the same type of non-contact sensing signal to simultaneously serve two different technical purposes: human-computer interaction and health early warning. This technological concept breaks through the traditional design approach of separating interactive and health monitoring functions and separating sensors and processing logic in existing technologies. It achieves functional synergy without adding extra sensing hardware, and its overall system structure and technical effects are not simply a superposition of existing technologies.

[0023] Secondly, this invention uses the statistical characteristics of changes in the bioelectric field as the core basis for health assessment, and combines this with multimodal fusion analysis of physiological parameters such as heart rate, blood oxygen, and body temperature to achieve trend assessment and predictive early warning of health status. Compared with existing technical solutions that mainly rely on passive detection based on a single physiological parameter, this invention can identify potential abnormal states before obvious changes in physiological indicators, thereby outputting early warning information in advance over time. This technical effect is not common in existing mobile terminal health monitoring solutions, nor can it be directly expected by technicians using conventional technical means.

[0024] Furthermore, this invention employs non-contact bioelectric field sensing as a unified sensing mechanism, enabling the system to maintain stable interactive response and continuous health monitoring capabilities even in complex usage scenarios such as wet hands, movement, or limb limitations. Compared to existing solutions that rely on touch or vision, this invention demonstrates a significant advantage in adaptability to usage scenarios. This advantage is not achieved through simply replacing the interaction method, but rather stems from the perception and utilization of the body's internal physiological signals.

[0025] Furthermore, this invention adaptively controls the operating state of the bioelectric field sensing module, triggering the relevant module to enter the working state only when a change in an effective electric field is detected. This significantly reduces system energy consumption while ensuring interactive sensitivity and monitoring accuracy. This effect is somewhat unexpected in technical solutions that simultaneously achieve contactless interaction and health warning functions, and is beneficial for the long-term, continuous operation of the system on mobile terminals.

[0026] In summary, this invention not only differs from existing technologies in its technical implementation path, but also achieves comprehensive technical effects that are difficult to predict in terms of functional synergy, forward-looking health warning, and energy consumption control. It has outstanding substantive features and significant progress. Attached Figure Description

[0027] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings: Figure 1 A system structure diagram of a contactless interaction and health early warning system based on changes in bioelectric field provided by the present invention; Figure 2 A flowchart illustrating the steps of a non-contact interaction and health early warning method based on changes in bioelectric field provided by this invention; Figure 3 The timing diagram of bioelectric field signal processing for a contactless interaction and health early warning system based on changes in bioelectric field provided by the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention is further described in detail below. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. The embodiments of the invention are described below in conjunction with the accompanying drawings.

[0029] One embodiment of the present invention provides a contactless interaction and health early warning system based on changes in bioelectric field. Please refer to [link to relevant documentation]. Figure 1 ,include: The bioelectric field sensing module 1 is deployed on the frame and / or back panel of the mobile terminal to collect low-frequency bioelectric field change signals generated on the surface of human skin in a non-contact state. Signal preprocessing module 2 is used to amplify, denoise, and decompose the bioelectric field change signal. Feature parsing module 3 is used to extract transient features for interactive identification and statistical features for health status assessment from the processed bioelectric field change signal. The multimodal fusion analysis module 4 is used to fuse and analyze the statistical features with at least one physiological parameter data; The decision output module 5 is used to output contactless interactive instructions and / or health warning information based on the fusion analysis results.

[0030] In one specific embodiment, the contactless interaction and health warning system based on bioelectric field changes provided by the present invention is integrated into a mobile terminal. The system uses bioelectric field changes as a unified sensing entry point to achieve the synergy of contactless interaction and health warning functions.

[0031] The system includes a bioelectric field sensing module 1, which is deployed on the frame and / or back panel of the mobile terminal. By placing multiple miniature electric field sensors close to the user's hand or naturally proximal area of ​​the body, the system can sense low-frequency bioelectric field changes generated by the human body when operating the terminal or in a natural state, without direct contact with human skin. These bioelectric field changes mainly originate from electric field disturbances caused by human neural activity, muscle activity, and cardiovascular system activity. They are characterized by requiring no physical contact and being less affected by ambient light and noise, thus providing a basic data source for subsequent interactive recognition and health status analysis.

[0032] The system further includes a signal preprocessing module 2, which is connected to the bioelectric field sensing module 1 and is used to preprocess the acquired bioelectric field change signals. Specifically, the signal preprocessing module 2 can amplify the original signal to improve the signal-to-noise ratio of the weak bioelectric field signal; at the same time, it can suppress the influence of environmental electromagnetic interference and random noise through filtering, denoising and other methods, and perform frequency domain decomposition processing on the signal so that the subsequent feature analysis process can be carried out on a stable and controllable signal basis.

[0033] The system also includes a feature analysis module 3, which analyzes the preprocessed bioelectric field change signal. This module 3 distinguishes the bioelectric field change signal into different time scales for analysis. On one hand, it extracts transient features characterizing the user's operational intentions, reflecting short-term electric field changes such as gesture changes and muscle micro-contractions. On the other hand, it extracts statistical features characterizing health status, reflecting the trend and stability of the bioelectric field within a certain time range. Through this differentiation, the same type of bioelectric field signal can serve two different technical purposes: contactless interactive recognition and health status assessment.

[0034] The system further includes a multimodal fusion analysis module 4, which is connected to the feature parsing module 3. This module is used to perform fusion analysis on the statistical features and at least one physiological parameter data. The physiological parameter data may include heart rate, blood oxygen, and / or body temperature data, which can be acquired by existing sensors in the mobile terminal. The multimodal fusion analysis module 4 uses the statistical characteristics of bioelectric field changes as the primary analytical basis and combines this with the physiological parameter data to comprehensively assess the user's health status, thereby improving the accuracy and stability of health status assessment.

[0035] The system also includes a decision output module 5, which is connected to the feature parsing module 3 and the multimodal fusion analysis module 4, respectively, and is used to generate corresponding output information based on the analysis results. When the user's operation intention is identified based on transient features, the decision output module 5 outputs a corresponding contactless interaction command to realize air-based operation of the mobile terminal; when abnormal trends or potential risks are identified based on statistical features and fusion analysis results, the decision output module 5 outputs health warning information to prompt the user to pay attention to their health status or take appropriate measures.

[0036] With the above-described structure, the system described in this embodiment can achieve the collaborative work of contactless interaction and health warning without relying on physical contact, and improve the interactive adaptability and health monitoring capabilities of mobile terminals in complex usage scenarios without adding additional complex hardware structures.

[0037] In a further embodiment, the bioelectric field sensing module 1 includes multiple micro electric field sensors, which are distributed in an array to sense electric field disturbances caused by human movement or physiological state.

[0038] Multiple miniature electric field sensors are distributed in an array on the frame and / or back panel of the mobile terminal. This array-based distribution allows the bioelectric field sensing module 1 to synchronously collect electric field disturbances generated by the human body at different spatial locations, thereby improving the spatial sensing capability of bioelectric field changes and the overall signal stability.

[0039] Specifically, the miniature electric field sensor can be placed in areas that the user's fingers, palm, or body naturally approach during daily use, such as the side frame, upper part of the back panel, or the middle area of ​​the mobile terminal. By deploying the sensor at multiple points, compared to a single sensor structure, signal instability caused by changes in hand posture or partial obstruction can be effectively reduced, enabling the system to reliably acquire bioelectric field change signals under different grip methods and usage postures.

[0040] In this embodiment, each miniature electric field sensor is used to sense electric field disturbances caused by human movement or physiological state. These disturbances do not require direct electrical connection with human skin; rather, they are sensed non-contactly. The collected electric field change signals can reflect the electric field changes caused by human neural activity, muscle activity, or cardiovascular system activity, thereby providing a multi-channel raw data foundation for subsequent signal preprocessing and feature analysis.

[0041] Furthermore, the array structure enables the system to suppress the impact of environmental noise or occasional interference on individual sensors through signal comparison and fusion between different sensors, further improving the robustness and reliability of bioelectric field sensing. The aforementioned array-type bioelectric field sensing module 1 configuration allows the present invention to achieve stable acquisition of weak bioelectric field changes without increasing the complexity of the hardware structure.

[0042] In a further embodiment, the detection frequency range of the bioelectric field change signal is 0.1 Hz to 100 Hz.

[0043] This frequency range is designed to cover the main electric field variations related to human physiological activities, in order to meet the needs of both contactless interactive identification and health status assessment applications.

[0044] Specifically, lower-frequency bioelectric field changes can reflect the slow electric field changes caused by the human cardiovascular system and some neural activities, which is beneficial for extracting statistical features for health status assessment. Higher-frequency bioelectric field changes, on the other hand, can reflect short-term electric field disturbances such as changes in hand gestures and micromuscle contractions, which is beneficial for extracting transient features for contactless interactive recognition. By limiting the detection frequency range to the above intervals, the system can simultaneously meet the signal requirements of both interactive and health warning functions within the same perception framework.

[0045] In this embodiment, the signal preprocessing module 2 can perform corresponding filtering and frequency domain decomposition processing on the signals within the specified frequency range to suppress high-frequency interference or low-frequency drift unrelated to human physiological activities, thereby ensuring that the bioelectric field signal entering the feature analysis module 3 has high effectiveness and resolvability. By limiting the frequency range, the bioelectric field sensing module 1 has clear design boundaries in engineering implementation, while avoiding invalid acquisition of signals in irrelevant frequency bands, thus helping to reduce system power consumption and improve overall processing efficiency.

[0046] In a further embodiment, the feature parsing module 3 identifies air gestures, muscle micro-contractions, or operational intentions based on the transient features, and generates corresponding contactless interaction commands.

[0047] The feature analysis module 3 performs short-time window analysis on the preprocessed bioelectric field change signal, focusing on the amplitude changes, rate of change, and waveform characteristics of the signal within a short time scale. When a human performs air gestures or produces micro-muscle contractions, it triggers significant disturbances in the bioelectric field within a short period of time. These disturbances are sudden and repeatable in time, and differ significantly from the electric field changes in a naturally still state. By extracting and analyzing these transient change characteristics, different types of operational intentions can be effectively distinguished.

[0048] In this embodiment, the transient features can be used to characterize changes in gesture direction, movement rhythm, or muscle contraction-triggered behaviors. For example, when a finger slides, clicks, or pauses in the air, it forms a change pattern with specific temporal characteristics in the bioelectric field signal; while the bioelectric field changes caused by micro-muscle contractions are characterized by short duration but relatively concentrated amplitude. The feature parsing module 3 identifies the above features and maps them to corresponding interactive events, thereby generating corresponding contactless interactive commands.

[0049] By using a recognition method based on the transient characteristics of bioelectric fields, this implementation method can achieve human-computer interaction without relying on touch screens, cameras, or voice input, enabling mobile terminals to maintain stable operation response capabilities in scenarios such as wet hands, movement, or limited lighting conditions.

[0050] In a further embodiment, the feature parsing module 3 identifies long-term trends in bioelectric field changes based on the statistical features, which are used to characterize potential abnormal states related to the cardiovascular or nervous systems.

[0051] Unlike transient features used for interactive recognition, the statistical features focus on analyzing the overall distribution characteristics of bioelectric field change signals over a longer time range. The feature parsing module 3 can perform statistical analysis on the mean, fluctuation amplitude, stability, or trend of bioelectric field change signals within a preset time window, thereby obtaining statistical feature information reflecting the physiological state of the human body.

[0052] In this embodiment, changes in the state of the human cardiovascular or nervous system often do not immediately manifest as obvious transient abnormalities, but rather gradually reflect long-term shifts or changes in the fluctuation patterns of the bioelectric field. Through continuous monitoring and comparative analysis of the above statistical characteristics, the feature analysis module 3 can identify characteristic patterns in the trend of bioelectric field changes that differ from the normal state, thereby characterizing potential abnormal states.

[0053] It should be noted that this implementation method does not make judgments based on changes in the bioelectric field at a single point in time. Instead, it comprehensively analyzes statistical characteristics over a certain time range to reduce the impact of occasional interferences or short-term anomalies on the results, thereby improving the stability and reliability of health status assessment. Through this approach, the system can identify potential risk trends before significant changes in physiological parameters occur, providing a basis for subsequent health warnings.

[0054] In a further embodiment, the multimodal fusion analysis module 4 uses the statistical characteristics of bioelectric field changes as the dominant feature, and combines heart rate, blood oxygen and / or body temperature data to comprehensively assess health status.

[0055] The multimodal fusion analysis module 4 does not simply superimpose various physiological parameters, but rather establishes a fusion analysis mechanism centered on the statistical characteristics of bioelectric field changes, based on the differences in the roles of different parameters in health status assessment. As a comprehensive physiological signal reflecting human neural activity, muscle activity, and cardiovascular activity, bioelectric field changes can characterize the overall trend of changes in human physiological state; therefore, it is set as the dominant feature in the fusion analysis process.

[0056] In this embodiment, physiological parameters such as heart rate, blood oxygen, and body temperature are used as auxiliary features to correct or supplement the health status assessment results obtained based on the statistical features of the bioelectric field. When the statistical features of bioelectric field changes show an abnormal trend, the multimodal fusion analysis module 4 further combines the physiological parameter data for cross-validation to improve the accuracy and reliability of the health status assessment; while when the physiological parameters are within the normal fluctuation range but the bioelectric field changes show a continuous deviation, the system can still retain the ability to identify potential abnormal states.

[0057] By employing the master-slave fusion structure described above, this implementation avoids the misjudgment problems caused by over-reliance on a single physiological parameter in existing technologies, while also avoiding the increased computational complexity and energy consumption resulting from multi-parameter equal-weight fusion. This fusion method makes health status assessment more stable and is more conducive to applications in long-term, continuous monitoring scenarios.

[0058] In a further embodiment, the feature parsing module 3 and the multimodal fusion analysis module 4 perform pattern recognition on the bioelectric field change signal based on a machine learning model.

[0059] The machine learning model is used to classify and identify the transient and statistical features contained in the bioelectric field change signals, in order to distinguish different interaction intentions and different health state patterns. By introducing the machine learning model, the system can adaptively learn the bioelectric field change characteristics of different users under different usage states without relying on fixed thresholds or manual rules, thereby improving the recognition accuracy and system adaptability.

[0060] In this embodiment, the machine learning model can be trained based on historically collected bioelectric field data and corresponding interaction behavior or health status samples, enabling the model to gradually establish a mapping relationship between bioelectric field characteristics and user behavior and health status. The feature parsing module 3 can use the model to identify transient features to determine air gestures or operation intentions; the multimodal fusion analysis module 4 can use the model to analyze the fused feature data to output health status assessment results or early warning judgments.

[0061] It should be noted that the machine learning model described in this embodiment is not limited to a specific algorithm. Its purpose is to improve the ability to identify patterns of bioelectric field changes through a data-driven approach, thereby providing more adaptive analysis results for different users, different usage habits and different physiological characteristics while ensuring system flexibility.

[0062] In a further embodiment, the system also includes an energy management module 6, which is used to trigger the bioelectric field sensing module 1 to enter the working state when a change in the bioelectric field is detected to exceed a preset threshold.

[0063] The energy management module 6 is connected to the bioelectric field sensing module 1 and the signal preprocessing module 2, and is used to control the overall power consumption of the system. When the mobile terminal is in standby mode or the user is not operating it, the bioelectric field sensing module 1 can be in a low-power monitoring state or a sleep state, only performing coarse-grained detection of possible changes in the bioelectric field in the environment. When the detected change in the bioelectric field amplitude or characteristics exceeds a preset threshold, the energy management module 6 triggers the bioelectric field sensing module 1 to enter the working state, thereby initiating a complete signal acquisition and processing flow.

[0064] In this embodiment, the preset threshold can be set according to the actual application scenario to distinguish between environmental noise or invalid disturbances and effective bioelectric field changes caused by changes in human behavior or physiological state. Through this method, the system can avoid continuous high-power acquisition and processing when there is no effective signal input, thereby significantly reducing overall energy consumption.

[0065] By introducing the energy management module 6, this embodiment effectively improves the system's battery life in mobile terminals while ensuring timely response to contactless interaction and continuous health monitoring, making it more suitable for long-term, continuous operation scenarios.

[0066] In a further embodiment, the health warning information includes abnormality alert information, risk level information, and / or emergency contact triggering instructions.

[0067] When the multimodal fusion analysis module 4 identifies a potential abnormal state based on the statistical characteristics of bioelectric field changes and the fusion analysis results of physiological parameters, the decision output module 5 can generate an abnormality alert to inform the user that their current health status may be showing an abnormal trend. This alert can be output through the mobile terminal's display interface, sound, or vibration to remind the user to pay attention to their own health status.

[0068] In this embodiment, the health warning information may further include risk level information, used to classify the identified abnormal states. Different risk levels may correspond to different prompting methods or handling strategies, enabling users to intuitively understand the current level of health risk and take appropriate countermeasures based on the prompts.

[0069] Furthermore, when the risk level is identified to meet preset conditions, the decision output module 5 can also trigger an emergency contact instruction, such as sending a notification message to a preset contact or executing an emergency call. Through the above-mentioned multi-level health warning output mechanism, this implementation not only provides basic abnormality alerts but also enables more proactive risk responses when necessary, thereby improving the system's practicality in health monitoring and early warning scenarios.

[0070] In one specific embodiment, the present invention also provides a contactless interaction and health early warning method based on changes in bioelectric field. This method is applied to the aforementioned contactless interaction and health early warning system based on changes in bioelectric field. Please refer to [link to relevant documentation]. Figure 2 Specifically, it includes the following steps: First, S1, collect signals of changes in the bioelectric field.

[0071] By using a bioelectric field sensing module 1 located on the frame and / or back panel of a mobile terminal, the module collects low-frequency bioelectric field change signals generated by the human body when operating the terminal or in a natural state without direct contact with human skin, providing a raw data basis for subsequent analysis.

[0072] Subsequently, S2, the collected bioelectric field change signals are preprocessed.

[0073] The original bioelectric field change signal is amplified, denoised, and decomposed in the frequency domain to suppress the effects of environmental electromagnetic interference and random noise, and to improve the stability and resolvability of the signal, so that the processed signal meets the requirements of subsequent feature analysis.

[0074] Next, in step S3, feature analysis is performed on the preprocessed bioelectric field change signal.

[0075] Transient features for contactless interaction recognition and statistical features for health status assessment are extracted from the bioelectric field change signals. The transient features are used to characterize gestures, muscle micro-contractions or operational intentions, while the statistical features are used to characterize the long-term trend of bioelectric field changes.

[0076] Subsequently, S4, multimodal fusion analysis is performed on the statistical features.

[0077] The statistical characteristics of the bioelectric field changes are fused with at least one physiological parameter data for analysis, with the statistical characteristics of bioelectric field changes as the dominant feature, and combined with heart rate, blood oxygen and / or body temperature data, to comprehensively assess the user's health status.

[0078] Finally, S5 outputs interactive instructions and / or health warning information based on the analysis results.

[0079] When the user's intention is identified based on transient features, the corresponding contactless interaction command is output; when abnormal trends or potential risks are identified based on statistical features and fusion analysis results, health warning information is output to remind the user to pay attention to their own health status or trigger corresponding coping measures.

[0080] Through the above methods and steps, the technical effect of simultaneously achieving contactless interaction and health early warning based on changes in bioelectric field is achieved without relying on physical contact.

[0081] In summary, this invention constructs an integrated technical solution that combines contactless interaction and health early warning by introducing bioelectric field changes as a unified sensing signal source into mobile terminals. Through the acquisition, preprocessing, and feature analysis of bioelectric field change signals, transient features characterizing user operation intentions are distinguished from statistical features reflecting trends in health status. Furthermore, multimodal fusion analysis is performed using physiological parameters such as heart rate, blood oxygen, and body temperature, enabling the same sensing and processing architecture to simultaneously serve both human-computer interaction and health status assessment application scenarios.

[0082] In the above implementation, through an array-type bioelectric field sensing structure, a feature parsing mechanism based on time scale differentiation, and a master-slave multimodal fusion analysis method, stable recognition of user operation intentions and predictive early warning of abnormal health trends are achieved without relying on physical contact or complex external conditions. Simultaneously, an energy management mechanism adaptively controls the operating state of the sensing module, effectively reducing overall energy consumption while ensuring system responsiveness, making this solution suitable for long-term, continuous operation in mobile terminals.

[0083] Therefore, the technical solution described in this invention has good engineering feasibility in terms of structural design and functional synergy, and can effectively improve the human-computer interaction applicability and health monitoring capabilities of mobile terminals in complex usage scenarios.

[0084] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A contactless interactive and health early warning system based on changes in bioelectric field, characterized in that, include: A bioelectric field sensing module is installed on the frame and / or back panel of a mobile terminal to collect low-frequency bioelectric field change signals generated on the surface of human skin in a non-contact state. The signal preprocessing module is used to amplify, denoise, and decompose the bioelectric field change signal in the frequency domain. The feature parsing module is used to extract transient features for interactive identification and statistical features for health status assessment from the processed bioelectric field change signal. A multimodal fusion analysis module is used to fuse and analyze the statistical features with at least one physiological parameter data; The decision output module is used to output contactless interactive commands and / or health warning information based on the fusion analysis results.

2. The contactless interaction and health early warning system according to claim 1, characterized in that, The bioelectric field sensing module includes multiple micro electric field sensors, which are distributed in an array to sense electric field disturbances caused by human movement or physiological state.

3. The contactless interaction and health early warning system according to claim 1 or 2, characterized in that, The detection frequency range of the bioelectric field change signal is 0.1 Hz to 100 Hz.

4. The contactless interaction and health early warning system according to claim 1, characterized in that, The feature parsing module identifies air gestures, muscle micro-contractions, or operational intentions based on the transient features, and generates corresponding contactless interaction commands.

5. The contactless interaction and health early warning system according to claim 1, characterized in that, The feature parsing module identifies long-term trends in bioelectric field changes based on the statistical features, which are used to characterize potential abnormal states related to the cardiovascular or nervous systems.

6. The contactless interaction and health early warning system according to claim 1, characterized in that, The multimodal fusion analysis module 4 uses the statistical characteristics of bioelectric field changes as the primary feature, and combines heart rate, blood oxygen and / or body temperature data to comprehensively assess health status.

7. The contactless interaction and health early warning system according to claim 1, characterized in that, The feature parsing module and the multimodal fusion analysis module perform pattern recognition on the bioelectric field change signal based on a machine learning model.

8. The contactless interaction and health early warning system according to claim 1, characterized in that, The system also includes an energy management module, which is used to trigger the bioelectric field sensing module to enter the working state when a change in the bioelectric field is detected to exceed a preset threshold.

9. The contactless interaction and health early warning system according to claim 1, characterized in that, The health warning information includes abnormality alerts, risk level information, and / or emergency contact trigger instructions.

10. A non-contact interaction and health early warning method based on changes in bioelectric field, characterized in that, include: The system collects bioelectric field change signals, performs feature analysis and multimodal fusion analysis on the signals, and outputs contactless interactive commands and / or health warning information.

Images