Passive repetition state intention-based enabling method and system

Abstract

The invention discloses an intention enabling method and system based on a passive repetitive state, and belongs to the technical field of Internet of Things communication and human-computer interaction. According to the method, a substance state transmission channel is established in an intelligent patch or intelligent equipment, substance state changes caused by passive repetition states of monitored objects (including human beings, animals or intelligent equipment) are detected, and time sequence signals are generated; and performing time domain feature analysis on the time sequence signal, mapping different feature intervals to corresponding intention instructions, and sending the intention instructions to the Internet of Things equipment through a near field communication module. The passive repetition state comprises physiological or movement signals such as heartbeat, breathing, pulse, gait, eyeball movement, body temperature rhythm and the like, and a periodic operation signal of the intelligent equipment. The method can realize real-time sensing and intention enabling of the physiological state, the emotional state and the fatigue state of the user, and is applied to the fields of health monitoring, safety early warning, man-machine cooperation, emotional interaction and the like. According to the invention, the false triggering rate is less than 0.01%, and non-inductive, continuous and accurate state monitoring and intention identification can be realized.

Description

Technical Field

[0001] This invention belongs to the field of IoT communication and human-computer interaction technology, specifically relating to a method and system for intention empowerment based on passive repetitive states. This invention establishes a material state transmission channel in a smart patch or smart device, detects changes in the material state caused by the passive repetitive states of the monitored object (including humans, animals, or smart devices), performs temporal feature analysis on the state changes, maps different feature intervals to different intention commands, and sends them to IoT devices via near-field communication, thereby achieving real-time perception and intention empowerment of the monitored object's physiological, emotional, and operational states. Background Technology

[0002] Existing intent recognition technologies are mainly divided into two categories: active intent recognition and passive intent recognition. In terms of active intent recognition, there are existing technical solutions that identify user intent through active interaction methods such as touchscreens, voice, and gestures. In terms of passive intent recognition, existing technologies are mostly concentrated in the field of brain-computer interfaces, identifying user intent through electroencephalogram (EEG) signals. For example, Chinese patent CN119157557B discloses a method and system for active and passive intent recognition based on EEG signals, which identifies the user's active and passive intent categories by extracting active and passive features from EEG signals. This technology is mainly applied in the field of brain-computer interfaces, requiring specialized equipment such as EEG caps, limiting its application scenarios and making it difficult to achieve daily, unobtrusive, and continuous monitoring.

[0003] On the other hand, while existing smartwatches and other devices have integrated PPG sensors for heart rate monitoring and accelerometers for motion monitoring, their functions are limited to measuring single parameters. They fail to fully utilize the rich information in the signals to comprehensively assess the user's state, and even more so, they fail to translate passively monitored states into executable intention commands. Furthermore, current technologies primarily focus on monitoring human users, lacking effective technical solutions for passive state monitoring of animals and smart devices.

[0004] This invention proposes for the first time that by detecting changes in the material state caused by the passive repetitive states of the monitored object (such as heartbeat, breathing, gait, equipment operation cycle, etc.), and through time-domain feature analysis, different feature intervals are mapped to intention commands, thereby realizing real-time perception and intention empowerment of the monitored object's state without requiring active operation from the monitored object. Summary of the Invention

[0005] I. Purpose of the Invention

[0006] This invention aims to solve the following technical problems:

[0007] This paper provides a method based on passive repetitive state intent empowerment to achieve continuous and imperceptible monitoring and intent recognition of the monitored object;

[0008] It covers a variety of monitored object types, including humans, animals, and smart devices;

[0009] It covers a variety of passive repetitive states, including heartbeat, respiration, pulse, gait, eye movements, body temperature rhythm, and equipment operating cycle;

[0010] By analyzing the time-domain characteristics of the time-series signal, the state of the monitored object is comprehensively determined and converted into intentional commands;

[0011] It enables pure software upgrades to existing smartwatches, as well as seamless monitoring of animals and devices.

[0012] II. Core Inventive Concept

[0013] The core inventive concept of this invention is to: modulate the passive repetitive state of the monitored object (including human heartbeat, breathing, gait, animal heart rate, activity rhythm, and the operating cycle and vibration frequency of smart devices) into executable intention commands through material state modulation and temporal feature analysis, and send them to IoT devices through near-field communication, thereby realizing indirect perception and intention empowerment of the monitored object's state.

[0014] It should be noted that the "monitored object" in this invention should be broadly understood as any entity capable of generating a passive repetitive state, including humans, animals, and any intelligent device or machine capable of generating periodic operating signals. The "passive repetitive state" refers to periodic physiological, motor, or operational signals unconsciously generated by the monitored object.

[0015] Examples of passively repetitive states in humans: heartbeat, pulse, breathing, gait, eye movements, and body temperature rhythm.

[0016] Examples of passive repetitive states in animals: heart rate, respiratory rate, activity rhythm, gait, and body temperature changes.

[0017] Examples of passively repetitive states of smart devices: operating cycle, vibration frequency, signal flashing.

[0018] The physical principle upon which this invention is based is that any physical substance (including photons, electrons, phonons, etc.) exists in a specific operating state. These states can be altered through the passive repetition of the monitored object's state, and such alterations can be detected by sensors and converted into time-series signals. For example, heartbeats and pulses cause minute vibrations and periodic changes in blood flow on the body surface, which can be detected by photoplethysmography; respiration causes periodic undulations in the chest and abdomen, which can be detected by pressure sensors; gait generates periodic impact forces, which can be detected by accelerometers; and the operating cycle of equipment causes periodic vibrations or signal changes in the equipment, which can be detected by accelerometers or photoelectric sensors.

[0019] Three- or four-layer analytical system

[0020] This invention employs a unified four-layer analysis system to ensure accurate identification:

[0021] First layer: Time-domain baseline learning. A time-domain baseline model of the signal is established and dynamically updated, filtering out unintentional disturbances. After the initial alignment, a 5-second learning period begins, during which the signal is sampled at a frequency of 200Hz, and the mean μ and standard deviation σ are calculated. The baseline threshold is set to μ-3σ. Under stable alignment, the baseline is updated at an ultra-low frequency of 0.01Hz, with a forgetting factor α=0.98.

[0022] The second layer: Transient mutation detection. Valid events must meet preset mutation amplitude and rate thresholds. For example, a heart rate signal change amplitude exceeding a preset threshold is considered a valid event.

[0023] The third layer: Frequency characteristic analysis. This involves performing frequency analysis on periodic signals to extract features such as the fundamental frequency, harmonics, and spectral distribution.

[0024] Fourth layer: Pattern recognition. The extracted features are matched with a preset pattern library to identify the corresponding state of the monitored object.

[0025] IV. Passive Repeated State and Intent Command Mapping

[0026] When the monitored subject is a human, an anxiety state command is sent when the heart rate rises above the threshold; an arrhythmia warning command is sent when the heart rate fluctuates abnormally; a respiratory system abnormality warning command is sent when the respiratory rate is abnormal; and a fall risk warning command is sent when the gait is abnormal.

[0027] When the monitored object is an animal, a health abnormality warning command is sent when the heart rate or activity level is abnormal.

[0028] When the monitored object is a smart device, a device fault warning command is sent when the operating cycle or vibration frequency is abnormal.

[0029] V. Application Scenarios

[0030] The technical solution of this invention can be applied to fields such as health monitoring, smart elderly care, pet monitoring, industrial equipment monitoring, smart home, and telemedicine.

[0031] Beneficial effects

[0032] This invention has beneficial effects such as multi-object coverage, passive intent empowerment, unified parsing framework, existing device empowerment, and complementarity with active intent. Attached Figure Description

[0033] Figure 1 : Schematic diagram of the intelligent patch structure of this invention;

[0034] Figure 2: Schematic diagram of the intention-empowerment principle based on heart rate in this invention;

[0035] Figure 3 This invention is based on a schematic diagram of the intention-empowering principle of breathing.

[0036] Figure 4 : Schematic diagram of the intention-enabling principle based on gait in this invention

[0037] Figure 5 This invention is based on a schematic diagram of the intent-enabled principle of the device operating cycle;

[0038] Figure 6 : Flowchart of the time-domain analysis system of this invention;

[0039] Figure 7 : Application scenario diagram of health monitoring in this invention;

[0040] Figure 8 : Application scenario diagram of the device monitoring of this invention.

Claims

1. A method for enabling intentions based on passive repetitive states, characterized in that, include: Channel establishment steps: At least one material state transmission channel is established inside a smart patch set on or inside the surface of the monitored object, or between the patch and the monitored object. The material state transmission channel carries the operating state of the physical material. Detection steps: Detect the changes in the material state caused by the passive repetitive state of the monitored object, and generate corresponding time-series signals; the passive repetitive state includes periodic physiological, motion, or operational signals unconsciously generated by the monitored object; Analysis steps: Perform time-domain feature analysis on the time-series signals, and map different feature intervals to corresponding intention commands; Communication steps: The intent command is sent to at least one IoT device via a near-field communication module to control the IoT device to perform an operation corresponding to the intent command.

2. The method according to claim 1, characterized in that, The monitored object includes at least one of humans, animals, and smart devices; the passive repetitive state includes at least one of heartbeat, respiration, pulse, gait, eye movement, body temperature rhythm, equipment operating cycle, and vibration frequency.

3. The method according to claim 1, characterized in that, It also includes time-domain baseline learning: establishing and dynamically updating a time-domain baseline model of the material state to filter out state fluctuations caused by unintentional disturbances; and transient mutation detection: determining that a valid event has occurred in response to the difference between the real-time sampled value of the state and the baseline model exceeding a preset mutation threshold and the time-domain rate of change exceeding a preset rate threshold.

4. The method according to claim 1, characterized in that, The analysis step includes analyzing the characteristics of the time-series signal, which involves counting the number of transitions of the material state signal per unit time, timing the duration of the material state signal remaining below the threshold or continuously outputting, and analyzing the frequency or amplitude changes of the material state signal.

5. The method according to claim 1, characterized in that, The operational state of the physical substance includes at least one of the motion state of photons, the motion state of electrons, and the vibration state of phonons; the motion state of photons is detected by photoplethysmography, and the vibration state of phonons is detected by a piezoelectric sensor.

6. The method according to claim 1, characterized in that, The intent command includes at least one of the following: an anxiety state command sent when the heart rate rises above a threshold; an arrhythmia warning command sent when the heart rate fluctuates abnormally; a respiratory system abnormality warning command sent when the respiratory rate is abnormal; a fall risk warning command sent when the gait is abnormal; and an equipment failure warning command sent when the equipment is malfunctioning.

7. The method according to claim 1, characterized in that, The near-field communication module includes at least one of the following: Bluetooth module, Bluetooth Low Energy module, Ultra Wideband module, Near Field Communication module, Wi-Fi module, Thread module, Zigbee module, ANT+ module, Radio Frequency Identification module, or Star Flash module.

8. An Internet of Things (IoT) communication system for performing the method according to any one of claims 1-7, characterized in that, The device includes at least one smart patch, at least one near-field communication module, a processor, and at least one Internet of Things (IoT) device. The smart patch is disposed on the surface or inside of the monitored object and is used to establish a material state transmission channel and output a timing signal characterizing a passive repetitive state. The near-field communication module is used to receive the timing signal. The processor is electrically connected to the near-field communication module and is configured to execute the method described in any one of claims 1-7 to generate an intent command. The IoT device is used to receive and execute the intent command generated by the processor.

9. The Internet of Things communication system according to claim 8, characterized in that, The smart patch includes a flexible substrate, a material state transceiver unit, a modulation medium, an encapsulation layer, and an adhesion layer; the material state transceiver unit is disposed on the flexible substrate and is used to excite and detect the operating state of the physical material, including at least one of a photoplethysmography sensor, a piezoelectric sensor, an accelerometer, a pressure sensor, and a temperature sensor. The modulation medium is disposed on the material state transmission path to convert passive repetitive states into state changes; the encapsulation layer covers each component; the adhesion layer is disposed below the flexible substrate to adhere to the surface of the monitored object.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method described in any one of claims 1-7.

Images