Electronic device having a static artificial intelligence model for external conditions including age blocking for vaping and ignition starting using data analysis and method of operation thereof

Abstract

According to one embodiment, a method for generating results that reflect one or more physiological conditions of a user is disclosed. The method comprises generating a plurality of constrained data sets associated with a plurality of predetermined constraints linked to a plurality of predetermined physiological conditions; constructing a plurality of independent static models based on a plurality of predetermined physiological conditions—each independent static model being linked to a specific constraint—; installing a plurality of independent static models in a device comprising a processor to execute commands and sensors to collect sensor data linked to the plurality of independent static models; having a user execute one or more of the plurality of independent static models through a user interface based on sensor data detected from the user; and providing one or more results (inferences) to the user through a user interface associated with the execution of one or more of the plurality of independent static models, wherein one or more results reflect one or more physiological conditions of the user.

Description

Technology Field

[0001] The present application claims the benefit of U.S. Provisional Patent No. 63 / 138,519, filed by inventor Martin Zizi et al. on January 17, 2021, titled “Electronic device having a static artificial intelligence model for contextual situation including age blocking for vaping and ignition starting using data analysis and method of operating the same,” and also claims the benefit of U.S. Provisional Patent No. 63 / 072,099, filed by inventor Martin Zizi et al. on August 29, 2020, titled “Electronic device having a static artificial intelligence model for contextual situation using data analysis and method of operating the same,” both of which are incorporated herein by reference.

[0002] The present disclosure generally relates to a static artificial intelligence (AI) model for external situations using data analysis. Brief explanation of the drawing

[0003] Figure 1 is a diagram illustrating a classification chart of biometric recognition forms. Figure 2 is a block diagram of the overall flow processing of a situational static model for artificial intelligence. Figure 3 is a table of examples of various types of motion classification for human body parts. Figure 4 is a block diagram illustrating the operating environment (system) of electronic devices that combine a situational static model for artificial intelligence. FIG. 5 is a more detailed block diagram of an electronic device used in the system illustrated in FIG. 4. Figure 6 is a functional block diagram of a feature processing system. Figure 7 is a flowchart of the static model operation for providing artificial intelligence. Figure 8 is a functional block diagram of a static model processing system. Figure 9 is a diagram showing an exemplary sensing structure (4-dimensional sensing stretching material) for a situational static model to provide artificial intelligence. Figure 10 is a functional block diagram of a sensor for a situational static model to provide artificial intelligence. Figure 11 is an acceleration waveform of a detected acceleration signal from a body part along a single axis (X, Y, or Z) over time. FIG. 12 is a flowchart for collecting motion signal data by an input data handler of an electronic device. Figure 13 is a flowchart of the sleep mode operation of an electronic device with a situational static model to provide artificial intelligence with low power consumption. FIG. 14 is a flowchart of the security mode operation of an electronic device having a situational static model for providing security data analysis with a secure core of a multiprocessor. Figure 15 is a block diagram of an external situation feature extractor. Figure 16 is a flowchart of various types / formats of sensor data over time that can be used with a situational static model. FIG. 17 is a flowchart of the preprocessing operation for the external situation feature extractor of FIG. 15. Figure 18 is a diagram showing data samples for a single-axis accelerometer over a time series. FIG. 19 is a flowchart of a feature extraction operation for generating a set of feature vectors. Figure 20 is an exemplary table showing a set of feature vectors for several feature vectors that provide time series analysis over time. FIG. 21 is a table showing several feature vectors that can be used to obtain a set of feature vectors for multiple different physiological states. Figure 22 is a chart of plots showing the distribution of divergence features for recognizing non-human (e.g., bot, animal) signals that are distinct from human signals. Figure 23a is a chart of the first plot of the time series of signal data for entropy feature analysis. Figure 23b is a chart of the second plot of the time series of signal data for entropy feature analysis together with Figure 23a. Figure 24 is a chart of a pair of gyroscope X-axis data plots of the low mean band and high mean band of body motion data for determining blood glucose levels for a blood glucose context for an artificial intelligence state model. Figure 25 is a table of data sets that can be used to detect various physiological states of human users as a static model of artificial intelligence. Figure 26 is a table of data sets used to detect various physical characteristics of human users as a static model of artificial intelligence. FIG. 27 is a functional block diagram of the static model analyzer illustrated in FIG. 8. Figure 28 is a flowchart of the training mode operation for a static model analyzer to acquire a time series of data from a dataset. FIG. 29 is a flowchart of the operation (interference) mode of a static AI model associated with the final steps shown in FIG. 7. Figure 30 is a functional block diagram of a static AI model framework for software implementation of a static AI model. FIG. 31 is a diagram showing various device types in which a static AI model including software, FPGA (Field Programmable Gate Array), and ASIC (Application Specific Integrated Circuit) is used. FIG. 32 is a diagram illustrating a static model processing system of an electronic device that can be used to detect various states of external conditions, such as liveliness, age, or gender. FIG. 33 is a flowchart between a server and a client (e.g., a smartphone) for creating a new user account associated with the server using liveness physiological states determined by a static AI model. FIG. 34 is a flowchart between a server and a client (e.g., a smartphone) accessing personal health records from a server using liveness physiological states determined by a static AI model along with other authentication parameters. Figure 35a is a flowchart showing the use of a static artificial intelligence model for the pass / fail implementation of age-blocking (parental control function). FIG. 35b is a diagram illustrating the client-server implementation for each of the age blocking and processes. Figure 36 is a flowchart of an age-based application of artificial intelligence based on neurological information for controlling vehicle ignition or starting. Figure 37 is a flowchart illustrating additional AI to provide protection against side effects from nicotine abuse. FIG. 38a is a diagram illustrating an implementation form in which AI technology-based neuroscience can be embedded in any hardware (HW) / software (SW) System On Chip (SOC) device or phone to form a parental control function device. FIG. 38b is a diagram illustrating an evaporator with artificial intelligence and SOC to provide age blocking. Figure 39 is a diagram showing the 3-D vector space of three different features extracted from neural-tagging data. Specific details for implementing the invention

[0004] In the following detailed description of the embodiments of the present disclosure, many specific details and various examples are described to provide an overall understanding. However, it is clear and obvious to those skilled in the art that the embodiments may be practiced without such specific details, and that many changes or modifications to the embodiments may be made within the scope of the present disclosure. In certain examples, well-known methods, procedures, parts, functions, circuits, and well-known or conventional details have not been described in detail so as not to unnecessarily obscure aspects of the embodiments of the present disclosure.

[0005] The terms, words, and expressions used herein are merely for describing embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. Unless otherwise defined, all terms used herein, including technical and scientific terms, may have the same or similar meaning in context as would be generally understood by a person skilled in the art. In some cases, although terms are defined in the present disclosure, they should not be understood as excluding or limiting the scope of the present disclosure.

[0006] Embodiments according to the present disclosure may be implemented as a device, a method, a server-client device and / or method, a combination of a device and / or method, a chipset, a computer program, or any combination of those described above. Accordingly, embodiments may take the form of a complete hardware embodiment (including a chipset), a complete software embodiment (including firmware, any type of software, etc.), or an embodiment combining software and hardware. Software and hardware aspects may be referred to herein as a "module," "unit," "part," "block," "component," "part," "system," "subsystem," etc. Additionally, embodiments may take the form of a computer program product implemented on any tangible medium of expression (including a computer file) on which computer-available program code is implemented.

[0007] The terms “one embodiment,” “embodiment,” “one example,” or “example” may refer to specific features, structures, or characteristics described in connection with an embodiment or example of the present disclosure. Accordingly, not all of these terms used herein refer to the same embodiment or example. Additionally, specific features, structures, or characteristics may be combined in any suitable combination and / or subcombination in one or more embodiments or examples.

[0008] You will notice that the singular form may include the plural form unless the context clearly refers otherwise. For example, "sensor" can refer to one or multiple sensors.

[0009] In some cases, the terms “first,” “second,” etc., have been used in this specification to describe various components, but these components are not limited by these terms. These terms may be used to distinguish one component from another and may be independent of the order or importance of the components. For example, the first sensor may be referred to as the second sensor, and likewise, the second sensor may be referred to as the first sensor. The first sensor and the second sensor are both sensors, but they may not be the same sensor.

[0010] As used herein, the term “and / or” may include any and all possible combinations of one or more of the items listed in association. For example, “A or B,” “at least one of A and B,” “at least one of A or B,” “one or more of A or B,” “one or more of A and B,” “A and / or B,” “at least one of A and / or B,” or “one or more of A and / or B” may all indicate “comprising at least one A,” “comprising at least one B,” or “comprising at least one A and at least one B.”

[0011] As used herein, the terms “have,” “having,” “can have,” “include,” “include,” “can include,” “have,” “compose,” or “compose” indicate the presence of components, features, steps, actions, functions, numerical values, parts, members, or combinations thereof, but do not exclude the addition or presence of one or more other components, features, steps, actions, functions, numerical values, parts, members, or combinations thereof. For example, a method or apparatus having a list of components is not limited to having only these components but may include other components not explicitly listed.

[0012] It will be understood that if the first component is "connected" or "coupled" to the second component, or "coupled" to the second component, the first component may be directly "connected" or "coupled" to the second component, or directly "coupled" to the second component, or at least one of the other components may be placed between the first component and the second component. On the other hand, it will be understood that if the first component is "directly connected" or "directly coupled" to the second component, other components may not be placed between the first component and the second component.

[0013] In this disclosure, embodiments of various types of electronic devices and related operations associated with user identification, authentication, and data encryption are described. If an electronic device can acquire information about a user's external situation, there may be various useful types of applications that can be developed. Information regarding a user's external situation may be collected from various sources. These sources may include, but are not limited to, sensor data, user data on the Internet, data sets, etc. One possible application based on situational awareness may be the data analysis of signals from the human body by AI technology. The human body is one of the well-known complex systems composed of many parts capable of interacting with one another. It possesses inherently rich and almost infinite variations at the molecular and functional levels, but in its broadest sense, it is dense and rich in information. Almost all external human situations (e.g., physiological states) can be observed through the complex interactions between various organs of the human body. When this becomes a neuromuscular tone influenced by these external conditions (e.g., physiological states), some types of these states originating from the human body can be effectively deciphered by appropriately analyzing neuromuscular tone signals collected from various types of sensors on the user's body parts. If these results are utilized in electronic devices, many useful applications become possible, such as providing users with visual information about their physiological state, improving the functionality of current biometric applications, protecting personal information at a higher level of security, or answering simple binary queries like gender and age.

[0014] In some embodiments, the electronic device is a handheld type of portable device, a smartphone, a tablet computer, a mobile phone, a telephone, an e-book reader, a navigation device, a desktop computer, a laptop computer, a workstation computer, a server computer, a single-board computer, a camera, a camcorder, an electronic pen, wireless communication equipment, an access point (AP), a drone, a projector, an electronic board, a photocopier, a watch, glasses, a head-mounted device, a wireless headset / earphone, electronic clothing, various types of wearable devices, a television, a DVD player, an audio player, a digital multimedia player, an electronic photo frame, a set-top box, a TV box, a game console, a remote controller, a bank ATM, a payment system device (including a POS and a card reader), a refrigerator, an oven, a microwave oven, an air conditioner, a vacuum cleaner, a washing machine, a dishwasher, an air purifier, a home automation control device, a smart home device, various types of home appliances, a security control device, an electronic lock / unlock device (including a key or lock), an electronic signature receiving device, and various types of security These may include system devices, blood pressure measuring devices, blood glucose monitoring devices, heart rate monitoring devices, body temperature measuring devices, magnetic resonance imaging devices, computed tomography devices, magnetic resonance angiography devices, various types of portable medical measuring devices, various types of medical devices, water meters, electric meters, gas meters, radio wave meters, thermometers, various types of measuring devices, AI devices, AI speakers or AI robots, various types of IoT devices, etc.

[0015] The electronic device may be a combination of one or more of the devices described above or a part thereof. In some embodiments, the electronic device may be part of furniture, a building, a structure, or a machine (including a vehicle, automobile, airplane, or ship), or any type of embedded board, chipset, computer file, or some type of sensor. The electronic device of the present disclosure is not limited to the devices described above and may be a new type of electronic device as technology advances.

[0016] FIG. 1 shows a classification of biometric modalities adapted from "A review of biometric technology along with trends and prospects," published in "Pattern Recognition, 2014, 47(8):2673-2688" and authored by UNAR JA, SENG WC, and ABBASI A. Measurements and calculations related to human characteristics are also referred to as "biometrics." While there may be various advantages and applications utilizing these conventional methods when biometrics are used in physiological state applications, well-known biometrics do not appear to provide very robust security solutions in some aspects. The physiological biometric solution disclosed herein, which utilizes an AI state model for external conditions of the human body (physiological states) associated with neuromuscular tone detection, can provide an improved, effective, robust, and enhanced solution for physiological state applications including liveness, identification, ability, or encryption. The location of the neuromuscular tone detection technology associated with the remainder of biometrics is also illustrated in FIG. 1. The remainder of the field and In contrast, neuromuscular tone sensing technology is a live physiological signal that is by no means identical but is recognizable.

[0017] It is in a novel category, along with functional MRI scans of the brain, EEG (Electroencephalography), ECG (Electrocardiogram), EMG (Electromyography), and EKG (Electrocardiogram) from heart rate or external / internal electrodes.

[0018] Behavioral biometric methods are linked to a user's behavior or habits. Known anatomical biometric methods are linked to a user's physical features, such as fingerprints, iris scans, veins, facial scans, and DNA. Specific user motions are habitual or part of a user's motion repertoire. For example, a user signing a document is a contextual motion that develops into a behavioral habit. The motions typically analyzed for a signature are the macro-motions or large-scale motions the user makes with a writing instrument. Most of these behaviors are autonomous movements because they are motions driven by the user's consciousness or intention. For example, from the large motion of a signature, one can visually determine whether the writer is left-handed or right-handed.

[0019] While these large motions may be useful, there are micro-motions (very small motions) that a user makes when signing, performing other movements, or simply resting without making any motion. These micro-motions may include neuro-derived, neuro-based, or neuromuscular tones and are invisible. Therefore, they belong to involuntary movements rather than the user's consciousness or intention. These micro-motions of the user are attributed to each individual's unique neuromuscular anatomical structure and may also include very important signals referred to herein as neuro-derived micro-motions or neuromuscular tones. The signals of these micro-motions are linked to motor control processes from the individual's motor cortex to their hand. One or more sensors, signal processing algorithms, and / or filters can capture electrical signals ("motion signals" and "micro-motion signals") containing the user's neurally-induced micro-motions. Of particular interest are the micro-motion electronic signals representing the user's micro-motions within the motion signals.

[0020] Therefore, when motion signals are appropriately analyzed for micro-motion signals representing the user's micro-motions, the resulting data can yield stable physiological identifiers of the user representing vitality, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc. When physiological states are decoded or processed as unwritten signatures, these physiological states of unique identifiers derived from the user's neuromuscular tone are the user's neurodynamic fingerprints. Neurodynamic fingerprints may be referred to herein as NFP (Neuro-Fingerprint) or NP (Neuro-Print).

[0021] A user's micro-motions are linked to the cortical or subcortical control of motor activity in the brain or the human nervous system. Like mechanical filters, an individual's specific musculoskeletal anatomy can influence the user's micro-motions and contribute to motion signals that include these micro-motions. These contributed signals are signals of muscle movement induced by neural signals, which can be referred to as neuromuscular tones. Motion signals captured from the user may reflect parts of proprioceptive control loops, including the brain and proprioceptors present in the user's body. By utilizing electronic devices with neurological algorithms and focusing on micro-motion signals rather than macro-motion signals, machines can better mimic human cognitive interfaces. This can improve human-machine interfaces. For example, consider a human cognitive interface between a husband and wife, or between people in a close relationship. When a husband touches his wife's arm, she can often recognize immediately from the sensation that her husband has touched her, because she is accustomed to his touch. If the touch is unique, humans can often recognize immediately from that unique sensation that it is touching him or her.

[0022] Neuromuscular tone signals are extracted in response to micro-motions associated with a specific type or form of tremor. A tremor is an unintentional, rhythmic muscle movement that causes vibration in one or more parts of the human body. Tremors may or may not be visible to the naked eye. Visible tremors are more common in middle-aged or elderly people. Visible tremors are considered to be a disorder in the part of the brain that controls one or more muscles throughout the body, or specifically, throughout areas such as the hands and / or fingers.

[0023] Most tremors occur in the hand. Therefore, micro-motion tremors can be detected when gripping a device with an accelerometer or through a finger touching a touchpad sensor.

[0024] Different types of tremors exist. The most common form or type of tremor occurs in healthy individuals. For much of the time, healthy individuals are unaware of this type of tremor because the motion is very small and occurs while performing other movements. The micro-motions of the object of interest associated with a specific type of tremor are so small that they cannot be seen with the naked eye.

[0025] Tremors can be activated under various conditions (rest, posture, movement) and can be classified as resting tremor, action tremor, postural tremor, or kinetic or intention tremor. Resting tremor is a tremor that occurs when the affected body part is inactive and supported against gravity. Action tremor is attributed to autonomous muscle activation and encompasses many types of tremor, including postural tremor, kinetic or intention tremor, and task-specific tremor. Postural tremor is linked to supporting a body part against gravity (such as extending an arm away from the body). Kinetic or intention tremor is linked to both goal-directed movement and non-goal-directed movement. For example, kinetic tremor is the motion of moving a finger to one's nose, which is sometimes used to detect drivers operating under the influence of alcohol. Another example of kinetic tremor is the motion of lifting a glass of water from a table. Task-specific progression occurs during very specific motions, such as when writing on paper with a pen or pencil.

[0026] Tremors are thought to originate from some pool of neurons within the nervous system, some brain structures, some sensory reflex mechanisms, and / or some neurodynamic coupling and resonance, which vibrate whether or not they are visible.

[0027] Although many tremors have been described physiologically or pathologically (without any disease), it is accepted that the magnitude of these tremors may not be very useful for their classification. However, the frequency of tremors and other types of invariant features associated with non-autonomous signals, including neuromuscular tones acquired from a user, may be subjects of interest. The frequency of tremors and other types of invariant features can be utilized in a useful manner to extract the signals of interest.

[0028] Many pathological conditions, such as Parkinson's disease (3-7 Hz), cerebellar disease (3-5 Hz), dystonia (4-7 Hz), and various neurological disorders (4-7 Hz), induce motions / signals of low frequencies, such as frequencies below 7 Hz. Since pathological conditions are not common to all users, these frequencies of motions / signals are not useful for extracting neuromuscular tone signals and are preferably filtered out. However, some of the embodiments disclosed herein are used to place particular emphasis on these pathological signals as a method for recording, monitoring, and observing said pathologies to determine health wellness or deterioration.

[0029] Other tremors, such as physiological, essential, orthostatic, and augmented physiological tremors, can occur under normal health conditions. These tremors are not health abnormalities in themselves; therefore, they appear throughout the population. Physiological tremors are of interest, along with others common to all users, because they generate micro-motions at frequencies ranging from 3 to 30 Hz or 4 to 30 Hz. They can be activated when muscles are used to support body parts against gravity. Thus, if someone holds an electronic device with their hand to support their hand and arm against gravity, physiological tremors that can be detected by an accelerometer may be generated. Similarly, if a finger touches the touchpad of an electronic device and supports it against gravity, physiological tremors that can be easily detected by the finger touchpad sensor may be generated.

[0030] Essential tremors of the movement type may occur and be detected when a user must enter a PIN or login ID to access a device or phone. The frequency range of the essential tremors may be between 4 and 12 Hz, but may be reduced to a frequency range of 8 to 12 Hz to avoid detection of tremors caused by unusual physiological conditions.

[0031] In the case of physiological tremors (or the aforementioned augmented physiological tremors with a large magnitude), the coherence between different sides of the body is low. That is, the physiological tremors on the left side of the body do not have very high coherence with the physiological tremors on the right side of the body. Therefore, tremors in the left hand or fingers are expected to differ from tremors in the user's right hand or right fingers. Accordingly, an AI state model system for external situations (e.g., physiological states) will require the user to consistently use the same side of the hand or finger for authentication, or alternatively, will require multiple authorized user calibration parameter sets, one for each hand or one for each finger, to be used to extract neuromuscular tone signals.

[0032] Neuromuscular junction signals contain much more information than user-specific invariants. They contain situation-specific information that can be measured across multiple users. Such information is analyzed and modeled from raw data obtained under situation-constrained conditions. Refer to Figure 2, which illustrates the overall processing flow of a situational static model.

[0033] In these situations—specific conditions—these motions with high frequencies of the object of interest may be considered as noise by others in the art. Therefore, signals with low frequencies (e.g., 12 or 30 Hz) but high harmonics (up to 1500 or 4000 Hz) may be appropriate because they contain the necessary information.

[0034] Such static models can be used as an improvement to the overall field of biometrics or can be used on their own for context awareness.

[0035] A raw signal captured by a finger touchpad sensor in an electronic device or an accelerometer in a portable electronic device may contain a number of unwanted signal frequencies. Therefore, a certain type of filtration having a response for filtering out signals outside the desired frequency range may be used to obtain a macro-motion signal from the raw electronic signal. Alternatively, to obtain a micro-motion signal from the raw electronic signal, means for separation / extraction of signals within the desired frequency range may be used. For example, a finite impulse response bandpass filter (e.g., a passband of 8 to 30 Hz) may be used to select a low signal frequency range of interest in the raw electronic signal detected by the touchpad or accelerometer. Alternatively, to achieve similar results, a low-pass filter (e.g., 30 Hz cutoff) and a high-pass filter (e.g., 8 Hz cutoff), or a high-pass filter (e.g., 8 Hz cutoff) and a low-pass filter (e.g., 30 Hz cutoff) can be combined in series.

[0036] FIG. 3 is a diagram illustrating one example of several types of motion classification according to some embodiments. This exemplary classification table provides a high understanding of which types of characteristics should be considered and measured to be extracted or filtered from the user's acquired motion signal to acquire feature data associated with neuromuscular tone signals.

[0037] FIG. 4 is a block diagram of an electronic device illustrating an exemplary operating environment (400) according to some embodiments.

[0038] The electronic devices (401) may include a processing unit (410), a sensor (420), an input / output interface (430), a display (440), a static model accelerator (450), a memory (460), a power system (470), a communication interface (280), etc. The electronic devices (401, 402, 403, 404, 405) may communicate with each other and may be connected via a network (406) or a communication interface (480).

[0039] It should be understood that this is merely an example of some embodiments described in the present disclosure. The electronic device (401, 402, 403, 404, 405) may include more or fewer parts than shown in FIG. 4, and unlike FIG. 4, two or more parts may be combined together, or specific parts of the parts may be mixed together. The various parts shown in FIG. 4 may be implemented in hardware, software, or a combination of hardware and software.

[0040] The processing unit (410) may include at least one central processing unit, and the central processing unit may include at least one processing core. The processing unit (410) may additionally include at least one of co-processors, communication processors, digital signal processing cores, graphics processing cores, low-power sensor control processors, and dedicated controllers. Additionally, various hierarchical internal volatile and non-volatile memories may be included to perform functions such as an initial booting procedure, communication operation with an external electronic device, operation of downloading an initial boot or loader-related program from an external electronic device, interrupt operation, and operation for improving the performance of the electronic device in a runtime operation of a program. The processing unit may load program instructions from memory, communication modules, or external sources, decode such instructions, execute operations or data processing, store results based on decoded instructions, or perform static model processing on external conditions including the user's physiological state, which may be liveness, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc. To those skilled in the art, the term processing unit may also be referred to as a processor, application processor (AP), central processing unit (CPU), Micro Controller Unit (MCU), or controller.

[0041] The sensor (420) can detect or measure the state or physical quantity of an electronic device and convert it into an electrical signal. The sensor (420) may include an optical sensor, an RGB sensor, an IR sensor, a UV sensor, a fingerprint sensor, a proximity sensor, a compass, an accelerometer sensor, a gyroscope sensor, a barometer, a grip sensor, a magnetic sensor, an iris sensor, a GSR (Galvanic Skin Response) sensor, an EEG (Electroencephalography) sensor, an ECG (Electrocardiogram) sensor, an EMG (Electromyography) sensor, an EKG (Electrocardiogram) sensor, external / internal electrodes, etc. The sensor (420) can collect signals (e.g., motion signals, neuromuscular tones, etc.) from a part of the user's body and transmit them to at least one part of the electronic device (401) including a processing unit (410) or a static model accelerator (450), and then perform static model processing on external conditions including physiological conditions of the users, such as vitality, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc.

[0042] The input / output interface (430) may include an input interface and an output interface. The input interface receives input in the form of signals and / or commands from a user or an external device of the electronic device (401) and transmits the input to the components of the electronic device. The output interface transmits output signals to the electronic device (401) through the components or to the user. For example, the input / output interface may include an input button, an LED, a vibration motor, various serial interfaces (e.g., USB (Universal Serial Bus), UART (Universal asynchronous receiver / transmitter), HDMI (High Definition Multimedia Interface), MHL (Mobile High-definition Link), IrDA (Infra-red Data Association), etc.).

[0043] The display (440) can display various content, such as images, text, or videos, to the user. The display (440) may be an LCD (liquid crystal display), an OLED (organic light emitting diode) display, a holographic output device, etc. The display (440) may include a display driver IC (DDI) or a display panel. The display driver IC may transmit an image driving signal corresponding to image information received from the processing unit (410) to the display panel, and the image may be displayed according to a predetermined frame rate. The display driver IC may include components such as a video memory capable of storing image information, an image processing unit, a display timing controller, a multiplexer, etc. The display (440) may include an input device such as a touch recognition panel, an electronic pen input panel, a fingerprint sensor, a pressure sensor, etc., or an output device such as a haptic feedback component. Depending on the specifications of the electronic device (401), the display (440) may optionally not be included, or may include at least one light-emitting diode in a very simple form factor.The display (440) can display a status indicator describing the location where the user contacts a part of the user's body and the start, processing, or completion state of gathering signals (e.g., motion signals, neuromuscular tones, etc.), and by doing so, the electronic device can perform static model processing of external conditions including physiological conditions of the users, which may be liveness, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc.

[0044] The memory (460) may include at least one of volatile memory (462) (e.g., DRAM (Dynamic RAM), SRAM (Static RAM), SDRAM (Synchronous Dynamic RAM), etc.) and non-volatile memory (464) (e.g., NOR flash memory, NAND flash memory, EPROM (Erasable and Programmable ROM), EEPROM (Electrically Erasable and Programmable ROM), HDD (Hard Disk Drive), SSD (Solid State Drive), SD (Secure Digital) card memory, Micro SD card memory, MMC (Multimedia Media Card), etc.). At least one of a boot loader, an operating system (491), a communication function (492) library, a device driver (493), a static model library (494), an application (495), or user data (496) may be stored in the non-volatile memory (464). When the electronic device is powered on, the volatile memory (462) starts operating. The processing unit (410) can load programs or data stored in non-volatile memory into volatile memory (462). By interfacing with the processing unit (410) during the operation of the electronic device, the volatile memory (462) can serve as the main memory in the electronic device.

[0045] The power system (470) can supply power to, control, and manage the electronic device (401). The power system may include a Power Management Integrated Circuit (PMIC), a battery (472), a charging IC, a fuel gauge, etc. The power system may receive AC or DC power as a power source. The power system (470) may provide wired and wireless charging functions to charge the battery (472) with the supplied power.

[0046] The wireless communication interface (480) may include, for example, cellular communication, Wi-Fi communication, Bluetooth, GPS, RFID, NFC, etc., and may additionally include an RF circuit unit for wireless communication. The RF circuit unit may include an RF transceiver, a PAM (Power Amp Module), a frequency filter, a LNA (Low Noise Amplifier), or an antenna, etc.

[0047] FIG. 5 is a detailed block diagram of an exemplary electronic device according to some embodiments. The electronic device (500) may include a processing unit (501), a camera (550), an input / output interface (553), a haptic feedback controller (554), a display (555), a near-field communication (556), an external memory slot (557), a sensor (570), a memory (590), a power system (558), a clock source (561), an audio circuit (562), a SIM card (563), a wireless communication processor (564), an RF circuit (565), and an NP accelerator (566).

[0048] It should be understood that the electronic device is merely one example of an embodiment of the present disclosure. The electronic device may optionally have more or fewer parts than illustrated, optionally combine two or more parts, or optionally have other arrangements or configurations of parts. The various parts illustrated in FIG. 5 may be implemented in hardware, software, or a combination of hardware and software.

[0049] The processing unit (501) may include at least one central processing unit (502), and the central processing unit may include at least one processing core. The processing unit (501) may further include at least one of co-processors, communication processors, digital signal processing cores, graphics processing cores, low-power sensor control processors, and dedicated controllers. The processing unit (501) may be implemented as a System On Chip (SoC) including various components in the form of a semiconductor chip. In one embodiment, the processing unit (501) may be equipped with a Graphics Processing Unit (520), a Digital Signal Processing (DSP) (521), an interrupt controller (522), a camera interface (523), a clock controller (524), a display interface (525), a sensor core (526), ​​a position controller (527), a security accelerator (528), a multimedia interface (529), a memory controller (530), a peripheral device interface (531), a communication / connectivity (532), an internal memory (540), etc. Additionally, various hierarchical internal volatile and non-volatile memories may be included to perform functions such as an initial booting procedure, communication operation with an external electronic device, operation of downloading an initial boot or loader-related program from an external electronic device, interrupt operation, or operation for improving the performance of the electronic device in a runtime operation of a program.The processing unit may load program instructions from memory (590), communication / connectivity (532), or wireless communication processor (564), decode the instructions, execute operations or data processing, store results according to the decoded instructions, or perform static model processing on external conditions including physiological states of users, such as liveness, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc. To those skilled in the art, the term processing unit may also be referred to as a processor, application processor (AP), central processing unit (CPU), Micro Controller Unit (MCU), or controller.

[0050] The central processing unit (502) may include at least one processor core (504, 505, 506). The central processing unit (502) may include processor cores with relatively low power consumption, processor cores with high power consumption but high performance, and at least one cluster including multiple cores, such as, for example, a first cluster (503) and a second cluster (514). This structure is a technology used to improve the performance and power consumption gains of an electronic device by dynamically allocating cores in a multi-core environment, taking into account the amount of computation and current consumed. The processor cores may be equipped with circuits and technologies to enhance security. ARM processors, which are one of the well-known mobile processors, have implemented this type of security technology called TRUSTZONE for their processors. For example, the first core (504) may be a single physical processor core capable of operating in a normal mode (507) and a security mode (508). Depending on the mode, the processor's registers and interrupt processing mechanism may be operated individually so that access to resources requiring security (e.g., peripheral devices or memory areas) is accessible only in security mode. The monitor mode (513) enables mode switching between the normal mode (507) and the security mode (508). In the normal mode (507), the mode can be switched to the security mode (508) via a specific instruction or interrupt. Applications running in the normal mode (507) and the security mode (508) are separated from each other, so that they cannot affect applications running in their respective modes, thereby allowing applications requiring high reliability to run in the security mode (508). Consequently, the reliability of the system can be enhanced.Security can be increased by enabling the execution of some of the actions in performing static model processing of external situations including the physiological states of users in security mode (508).

[0051] The camera (550) may include a lens, an optical sensor, an image signal processor (ISP), etc. for acquiring images, and may acquire still images and moving images. The camera (550) may include a plurality of cameras (e.g., a first camera (551), a second camera (552)) to provide various functions associated with enhanced camera functions.

[0052] The input / output interface (553) may include an input interface and an output interface. The input interface receives input in the form of signals and / or commands from a user or an external device of the electronic device (500) and transmits the input to the components of the electronic device. The output interface transmits output signals to the user or through the components of the electronic device (500). For example, the input / output interface may include an input button, an LED, a vibration motor, various serial interfaces (e.g., USB (Universal Serial Bus), UART (Universal asynchronous receiver / transmitter), HDMI (High Definition Multimedia Interface), MHL (Mobile High-definition Link), IrDA (Infra-red Data Association), etc.) or other known interfaces.

[0053] The haptic feedback controller (554) may include a vibration motor, commonly referred to as an actuator, to provide the user with the ability to feel a specific sensation through touch.

[0054] A display (touch-sensing display) (555) can display various content, such as images, text, and videos, to a user. The display (555) may be an LCD, an OLED display, or a holographic output device. The display (555) may include a display driver IC (DDI) or a display panel. The display driver IC can transmit an image driving signal corresponding to image information received from the processing unit (501) to the display panel, and the image may be displayed according to a predetermined frame rate. The display driver IC may be implemented in the form of an IC and may include components such as a video memory capable of storing image information, an image processing unit, a display timing controller, a multiplexer, etc. The display (555) may include an input device such as a touch recognition panel, an electronic pen input panel, a fingerprint sensor, a pressure sensor, etc., or an output device such as a haptic feedback component. Depending on the specifications of the electronic device (500), the display (555) may optionally not be included, or may include at least one light-emitting diode in a very simple form factor. The display (555) can display a status indicator describing the location where the user contacts a part of the user's body and the start, processing, or completion status of gathering motion signals, and by doing so, the electronic device can perform static model processing of external conditions including the physiological conditions of the users, which may be liveness, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc.

[0055] Near-field wireless communication (556), such as NFC (Near Field Communication), RFID (Radio Frequency Identification), and MST (Magic Secure Transmission), can be implemented in a wireless communication system to communicate with other electronic devices nearby.

[0056] The external memory slot (557) may include an interface for mounting a memory card (e.g., SD card, micro SD card, etc.) to expand the storage space of the electronic device (500).

[0057] The power system (558) can function to supply, control, and manage power to the electronic device (500). The power system may include a Power Management Integrated Circuit (PMIC), a battery (559), a charging IC (560), a fuel gauge, etc. The power system may receive AC or DC power as power. The power system (558) may provide wired and wireless charging functions to charge the battery (559) with the supplied power.

[0058] The clock source (561) may include at least one of a system clock oscillator that acts as a reference for the operation of the electronic device (500) and a frequency oscillator for transmitting and receiving RF signals.

[0059] The audio circuit (562) may include an audio input unit (e.g., a microphone), an audio output unit (e.g., a receiver, a speaker), and / or a codec that performs conversion between an audio signal and an electrical signal to provide an interface between the user and the electronic device. An audio signal that can be obtained through the audio input unit may be converted into an analog electrical signal, then sampled and digitized, and transmitted to another component (e.g., a processing unit) within the electronic device (500) so that audio signal processing may be performed. Digital audio data transmitted from another component within the electronic device (500) may be converted into an analog electrical signal so that an audio signal may be generated through the audio output unit.

[0060] A SIM card (563) is an IC card that implements a Subscriber Identification Module for identifying a subscriber in cellular communication. In most cases, a SIM card is installed in a slot provided in an electronic device (510), and the card may be implemented in the form of an embedded SIM coupled to the electronic device depending on the type of electronic device. Each SIM card may have its own unique number, which may include a fixed number ICCI (Integrated Circuit Card Identifier) ​​and IMSI (International Mobile Subscriber Identity) information that varies per subscriber line.

[0061] The wireless communication processor (564) may include, for example, cellular communication, Wi-Fi communication, Bluetooth, GPS, etc. Through the wireless communication processor (564), static model processing of external conditions including the physiological states of users may be performed via a network in cooperation with at least one other electronic device (including a server) (including a server).

[0062] The RF circuit (565) may include a transceiver, a PAM (power amp module), a frequency filter, an LNA (Low Noise Amplifier), an antenna, etc. To perform transmission and reception via radio frequency in a wireless environment, it may exchange control information and user data with a wireless communication processor and a processing unit.

[0063] The static model accelerator (566) can be used to increase the performance of the entire system by increasing the speed of computational execution for processing signals obtained from parts of the user's body, or by performing computations or parts of computations required to perform static model processing for external conditions including physiological conditions of users, such as liveliness, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc.

[0064] One or more sensors (570) can detect or measure the state, physical quantity, etc. of an electronic device and convert it into an electrical signal. The sensor (570) may include a compass (571), an optical sensor (572), a fingerprint sensor (573), a proximity sensor (574), a gyroscope sensor (575), an RGB sensor (576), a barometer (578), a UV sensor (579), a grip sensor (580), a magnetic sensor (581), an accelerometer (582), an iris sensor (583), etc. The sensor (570) can collect motion signals from parts of the user's body and transmit them to at least one part of the electronic device (500) including a processing unit (501) and a physiological state accelerator (566), and perform static model processing on external conditions including the user's physiological state, which may be liveliness, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc.

[0065] The memory (590) may include at least one of volatile memory (591) (e.g., DRAM (Dynamic RAM), SRAM (Static RAM), or SDRAM (Synchronous Dynamic RAM), etc.) and non-volatile memory (592) (e.g., NOR flash memory, NAND flash memory, EPROM (Erasable and Programmable ROM), EEPROM (Electrically Erasable and Programmable ROM), HDD (Hard Disk Drive), SSD (Solid State Drive), SD (Secure Digital) card memory, Micro SD memory, MMC (Multimedia Media Card), etc.). At least one of boot loaders, an operating system (593), a communication function (594) library, a device driver (595), a static model library for external conditions (596), an application (597), or user data (598) may be stored in the non-volatile memory (592). When the electronic device is powered on, the volatile memory (591) starts operating. The processing unit (501) can load programs or data stored in non-volatile memory into volatile memory (591). By interfacing with the processing unit (501) during the operation of the electronic device, the volatile memory (591) can serve as the main memory in the electronic device.

[0066] The electronic device (500) can acquire a signal from a part of the user's body through a sensor (570) and can provide the acquired signal to at least one of a processing unit (501), a static model accelerator (566), and / or a memory (590), and through the interaction between these parts, can perform static model processing on external conditions including physiological states of users, such as vitality, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc. Static model processing on external conditions including physiological states of users can be performed independently by the electronic device (500) and can be performed in cooperation with at least one other electronic device (including a server) through a network.

[0067] feature processing system

[0068] FIG. 6 is a block diagram of an embodiment of a feature processing system (600). The feature processing system (600) can perform static model processing on external conditions including the physiological states of users. The feature processing system (600) may be implemented in the electronic device (500) of FIG. 5 or the electronic device (401) of FIG. 4, and additional hardware components or software modules may be used. The feature processing system (600) may be configured in combination with at least one example of the various embodiments described herein, each of the functions of FIG. 6. The feature processing system (600) may include an input data handler (602), a feature extractor (604), a feature analyzer (606), and a feature application framework (608). The feature processing system (600) may be implemented in hardware, in software, or as a combination of hardware and software.

[0069] In some embodiments, the input data handler (602) may include various types of sensors, including an accelerometer, a gyroscope, a geomagnetic sensor, an optical sensor, an electroencephalography (EEG), an electrocardiogram (ECG), an electromyography (EMG), a galvanic skin response (GSR), etc. Image information data may be obtained from a camera, and the data may be collected and processed in the form of a computer file. The feature extractor (604) receives specific data from the input data handler (602), performs preprocessing to remove unwanted signals or performs specific processes for processing efficiency, and performs extraction of numerical feature data representing the characteristics of the observed data. The feature analyzer (606) analyzes the feature data based on the characteristic feature data extracted by the feature extractor (604). When analyzing feature data, feature data obtained from a feature extractor may be used, data in the form of computer files already collected through other channels may be analyzed, and a combination of these data may be analyzed. The feature analyzer (606) may derive information associated with the analyzed feature data and may store the information derived in this way. By using the previously stored information associated with the feature data, analysis results for new input feature data may be derived. The feature application framework (608) may use the result information of the feature analyzer (606) to perform identification, authentication, liveness, encryption, or other specific functions using these.

[0070] Example of static model behavior

[0071] One of the external conditions may be the users' physiological state. Physiological measurements that can be derived from accelerometer and gyroscope data are as follows:

[0072] - Blood sugar levels

[0073] - Female hormone levels

[0074] - Stress hormone levels

[0075] - Presence of drugs such as alcohol, nicotine, caffeine, THC, CBD, and prescription drugs

[0076] - Sleep deprivation

[0077] - Presence of human neuromuscular tremor or motion

[0078] - Absence of human neuromuscular tremors or motion.

[0079] Scientific papers demonstrating how each of the aforementioned "physiological states" affects neuromuscular progression may be provided. These physiological states appearing in accelerometer and gyroscope data include specific frequency elements and repetitive, non-repetitive, chaotic, and / or sinusoidal patterns that can be quantified using transposition processing and feature extraction methods.

[0080] This static model of external conditions, including the user's physiological states, may reside in an electronic device (401) or electronic device (500), such as, for example, any embedded system, medical device, or web application. The model is static in that it does not require any interaction with external training data to function efficiently and improve its detection. The static model quantifies whether a physiological state exists, the probability that a specific physiological state exists, or the degree to which a physiological state exists. This static model respects the user's privacy by not including data excluded from the initial training set.

[0081] FIG. 7 is an example of a flowchart of a static model operation for an external situation (e.g., physiological states) of an electronic device (401) or an electronic device (500). The electronic device (401, 500) loads information of a static model operation mode including a set of constraints for an external situation (e.g., physiological states) of the user, configures a static model parameter set according to the static model operation mode, collects sensor signal data including neuromuscular tones from a part of the user's body at a predetermined sampling frequency over a predetermined sample period, suppresses signal components associated with the user's autonomous movement from the sensor data, generates data sets of mathematical formulas regarding the external situation (e.g., physiological states) based on the static model operation mode from the suppressed signal components of the sensor data associated with the autonomous movement, constructs a feature vector table including a plurality of feature vector sets based on the data sets of mathematical formulas, executes a static model using the feature vector table according to the static model operation mode, and generates report information regarding the external situation (e.g., physiological states) based on the execution result of the static model.

[0082] In some embodiments, the constraint set of external conditions (e.g., physiological conditions) may be blood glucose levels, female hormone levels, stress hormone levels, the presence of drugs (alcohol, nicotine, caffeine, THC, CBD, prescription drugs, etc.), sleep deprivation, human neuromuscular tremors, or motion. Information of a static model operation mode including the constraint set of the user's physiological conditions may be stored in memory (460, 590) or may be downloaded via communication from a server computer prior to the operation of FIG. 7. In some embodiments, the user may select at least one set of the constraint sets of external conditions (e.g., physiological conditions) for the static model operation, or the application program may automatically select the constraint sets of external conditions (e.g., physiological conditions) according to the purpose of the application program.

[0083] Static model processing system for external conditions

[0084] FIG. 8 is a block diagram of an embodiment of a static model processing system (800). In some embodiments, the static model processing system (800) may be implemented in the electronic device (500) of FIG. 5 or the electronic device (401) of FIG. 4, and additional hardware components or software modules may be used. The feature processing system (600) of FIG. 6 may be implemented in the form of a static model processing system (800) that processes physiological states as in FIG. 8. The static model processing system (800) may be configured in combination with at least one example of the various embodiments described herein. The static model processing system (800) may include an input data handler (802), an external situation feature extractor (804), a static model analyzer (806), and a static model application framework (808). The static model processing system (800) may be implemented in hardware, in software, or as a combination of hardware and software. The static model processing system (800) may be in the form of software running on the electronic device (401) of FIG. 4 or the electronic device (500) of FIG. 5. Some parts of the static model processing system (800) may be implemented in the electronic device (401) or the electronic device (500) in the form of software associated with a dedicated hardware accelerator.

[0085] In some embodiments, the input data handler (802) may collect data from various types of sensors including an accelerometer, a gyroscope, a geomagnetic sensor, an optical sensor, an EEG (electroencephalography), an ECG (electrocardiogram), an EMG (electromyography), an EKG (electrocardiogram), external / internal electrodes, a GSR (galvanic skin response), an EMS (electromagnetic sensing), etc. Image information data may be obtained from a camera, and the data may be collected and processed in the form of a computer file. The external context feature extractor (804) receives specific data from the input data handler (802), performs preprocessing to remove unwanted signals or performs specific processes for processing efficiency, and performs extraction of numerical feature data representing the characteristics of the observed data. The static model analyzer (806) analyzes the feature data based on the characteristic feature data extracted by the external context feature extractor (804). When analyzing feature data, feature data obtained from an external situation feature extractor may be used, data in the form of computer files already collected through other channels may be analyzed, and a combination of these data may be analyzed. The static model analyzer (806) may derive information associated with the analyzed feature data and may store the information derived in this way. By using the previously stored information associated with the feature data, analysis results for new input feature data may be derived. The static model application framework (808) may perform static model processing on external situations, including the user's physiological state, which may be liveness, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc., by using the result information of the static model analyzer (806).

[0086] (1) Input data handler (802)

[0087] In some embodiments, the NP input data handler (802) can collect data from various types of sensors including an accelerometer, a gyroscope, a geomagnetic sensor, an optical sensor, an EEG (electroencephalography), an ECG (electrocardiogram), an EMG (electromyography), an EKG (electrocardiogram), external / internal electrodes, a GSR (galvanic skin response), an EMS (electro-magnetic sensing), etc. Image information data can be obtained from a camera, and the data can be collected and processed in the form of a computer file.

[0088] In some embodiments, the input data handler (802) may collect movement signal data from a body part of the user's body that can be obtained by a sensor of the electronic device (500). The sensor may include a sensor capable of detecting the user's movement or vibration. For example, the sensor may include a barometer (571), a gyroscope sensor (575), an accelerometer (582), a geomagnetic sensor, a camera (550), an optical sensor, a touch sensor of a touch-sensing display (555), electroencephalography (EG), electrocardiogram (ECG), electromyography (EMG), electrocardiogram (EKG), external / internal electrodes, galvanic skin response (GSR), electro-magnetic sensing (EMS), or a combination thereof.

[0089] Sensors can detect motion, vibration, and movements associated with neuromuscular inductive signals generated from parts of the user's body in contact with electronic devices. Movements or micro-movements associated with neuromuscular inductive signals can be detected by the sensor in the form of analog electrical signals. For example, in the case of a sensor utilizing MEMS technology, physical quantities altered by the force of movement generated in contact with a part of the user's body can be measured as electrical analog signals using methods such as capacitance, piezoelectricity, piezoresistivity, or thermal sensing.

[0090] FIG. 9 illustrates an example of a sensing structure in a sensor on an electronic device (401) or an electronic device (500). Acceleration or angular velocity measures the force substantially applied to an object and indirectly measures the acceleration or angular velocity from a force applied from the outside of the object. Therefore, micro-motion or macro-motion of a muscle induced by a neuro-inductive mechanism is transmitted as a force applied to the electronic device, and the measured force can be indirectly calculated in the form of acceleration or angular velocity. As an external force is applied from the outside of the electronic device to which the sensor is attached, the moving plate (MASS) of FIG. 9 moves, and because the distance of the electrodes in the sensing structure changes, a change in capacitance occurs. The changed capacitance is converted into an analog voltage, and the analog voltage signal is applied to the input of an A / D converter through an amplifier. Multiple sensing structures enable the measurement of multiple axes' values ​​of acceleration and angular velocity, and these values ​​can be used for more sophisticated applications. The measured electrical analog signal can be sampled at a predefined sampling frequency for a predefined period (e.g., 3, 5, 10, 20, 30 seconds, etc.) in an A / D converter.

[0091] FIG. 10 is a block diagram of a sensor on an electronic device (401) or an electronic device (500). The sensor (1010) may include an acceleration sensing structure (1012), a gyroscope sensing structure (1014), a temperature sensor (1016), an EMS (1017), an A / D converter (1018), signal conditioning (1020), a serial interface (1022), an interrupt controller (1024), a FIFO (1026), a register (1028), a memory (1030), a processor (1032), an external sensor interface (1034), and a system bus (1036).

[0092] The acceleration sensing structure (1012) may include multiple sensing structures to measure acceleration of multiple axes. The acceleration measured by the acceleration sensing structure may be an analog output in the form of an analog voltage, which can be converted into digital data through an A / D converter. The acceleration measured from the acceleration sensing structure (1012) may drift due to temperature changes due to the properties of the material in which the sensing structure is made. The drift of the sensing value can be compensated with the help of a temperature sensor (1016). The signal conditioning (1020) may include a signal processing filter required for signal processing to improve signal quality. The processor (1032) can control the configuration of the signal processing filter. The measured acceleration values ​​can be stored in registers (1023) through the signal conditioning (1020). The acceleration values ​​stored in the registers (1023) can be recorded in the range of ±2g, ±4g, ±8g, ±16g based on a predefined configuration.

[0093] The gyroscope sensing structure (1014) may include multiple sensing structures to measure rotations of multiple axes. The rotation measured by the gyroscope sensing structure (1014) may be an analog output in the form of an analog voltage, which can be converted into digital data through an A / D converter. The rotation measured from the gyroscope sensing structure (1014) may drift due to temperature changes caused by the properties of the material comprising the sensing structure. The drift of the sensing value can be compensated with the help of a temperature sensor (1016). The signal conditioning (1020) may include a signal processing filter required for signal processing to improve signal quality. The processor (1032) can control the configuration of the signal processing filter. The measured rotation values ​​can be stored in registers (1023) through the signal conditioning (1020). The rotation values ​​stored in the registers (1023) can be recorded in the range of ±125, ±250, ±600, ±1000, ±2000 degrees / sec based on a predefined configuration.

[0094] By implementing a FIFO (1026) structure in the sensor (1010), the host processor (1040) does not need to constantly monitor the sensor data, and accordingly, the current consumption of the electronic device is reduced. The host processor (1040) may be the processing unit (410) of the electronic device (401) and the processing unit (501) of the electronic device (500). Data detected by the sensor may be transmitted to the host processor (1040) via a serial interface (1022). The serial interface (1022) enables the host processor (1040) to set the control register of the sensor. The serial interface (1022) may include SPI, I2C, etc. The interrupt controller (1022) can configure an external interrupt pin connected to the host processor (1040), an interrupt latching and clearing method, and can send an interrupt trigger signal to the host processor (1040). The interrupt signal can be triggered when sensor data is ready, or when the data is ready in the FIFO to be read by the host processor (1040). Additionally, if an additional sensor is connected via an external sensor interface (1034) to reduce power consumption of the entire electronic device system, the interrupt can be triggered even when the host processor (1040) reads data from an external predecessor. To reduce power consumption of the electronic device, the host processor (1040) may enter sleep mode, and if no data is provided from the external sensor (1060) connected to the sensor (1010), the host processor (1040) may continue to maintain sleep mode.When sensor data is ready, the sensor (1010) can act as a sensor core or sensor hub by waking the host processor through the sensor's interrupt control and enabling the necessary data processing for the host processor (1040).

[0095] Referring to FIG. 11, the acceleration waveform (1100) of the hand acceleration signal with respect to a single axis (X, Y, or Z) is illustrated over time. A portion (1101) of the hand acceleration waveform (1100) is expanded into a waveform (1100T) as illustrated. While analog signal waveforms may be illustrated in the drawings, it should be noted that analog signal waveforms are sampled over time and can be represented as a sequence of digital numbers ("digital waveform") on discrete periodic timestamps. While an accelerometer detects acceleration over time, if a sensor detects displacement over time, it can be converted into acceleration by differentiating the displacement signal twice with respect to time.

[0096] The acceleration of the hand for each axis is sampled over a predetermined sampling time period (1105), such as a time length of, for example, 5, 10, 20, or 30 seconds. The sampling frequency is selected so that it is compatible with the subsequent filtering. For example, the sampling frequency may be 250 Hz (4 milliseconds between samples). Alternatively, the sampling frequency may be, for example, 430 Hz or 200 Hz. Sampling of the analog signal may be performed by a sampling analog-to-digital converter to generate samples (S1-SN) represented as digital numbers over timestamps (T1-TN) over a given predetermined sampling time period. Assuming a sampling time period of 20 seconds and a sampling frequency of 250 Hz, the dataset for acceleration will contain three times 6000 samples over time (3 axes), totaling 15k samples.

[0097] In some embodiments, since human intrinsic neuromuscular tone is mainly observed in the range of 3 Hz to 30 Hz, the sampling frequency of the NP input data handler (802) may be, for example, 60 Hz, 200 Hz, 250 Hz, 430 Hz, 500 Hz, which is more than twice the 30 Hz frequency. The collected data of the input data handler (802) may perform noise removal and signal quality improvement operations to improve signal quality. Analog values ​​sampled at a predefined sampling frequency may be converted into digital signals through a quantization process in an A / D converter (1018). In the quantization process, quantization may be performed according to a predefined bit rate. When performing quantization, linear quantization may be performed with a constant quantization width, and non-linear quantization, which expands and compresses the quantization width according to a predefined value within a specific range, may be used to obtain a high-quality signal-to-noise ratio for the application.

[0098] FIG. 12 illustrates an example of a flowchart for collecting moving signal data of an input data handler (802) on an electronic device (401) or an electronic device (500). The electronic device collects sensor signal data including neuromuscular tones from a body part of a user's body at a predetermined sampling frequency over a predetermined sample period, converts an analog voltage value measured from a sensing structure including a mass plate into a digital value, compensates for a digital value drifted by temperature with the help of a temperature sensor (1016), stores a number of digital values ​​in a FIFO (1026), and generates an interrupt signal to a host processor (1040) when the FIFO data is ready to be delivered.

[0099] FIG. 13 illustrates an example of a flowchart of the sleep mode operation of a static model processing system (800) on an electronic device (401) or an electronic device (500). In some embodiments, when the electronic device (401, 500) is implemented as a portable device, power consumption may become a critical issue. The electronic device (401, 500) may operate in sleep mode. When the electronic device operates in sleep mode, various methods may be applied to minimize power consumption, such as shutting down the power of some components in the electronic device (401, 500), switching to a low-power mode, or lowering the frequency of the operating clock. Power consumption efficiency may be increased when the processing unit (501) enters sleep mode. However, because a delay may occur in terms of the mutual response between the user and the electromagnetic device in sleep mode, a coprocessor such as a sensor core (526) may be included within the processing unit or within the electronic device. Even when the processing unit (501) enters sleep mode, the sensor core (526) can continuously observe signal detection from the sensor (570). When the sensor core (526) determines that processing of the processing unit (501) is required, the sensor core (526) can generate an interrupt signal to the processing unit (501), and the processing unit (501) exits sleep mode. At this point, power can be supplied again to some of the components that were in sleep mode, and the processing unit (501) changes the frequency of the operating clock to operate at a high-speed clock to exit low-power mode and be activated from sleep mode.

[0100] FIG. 14 is a diagram illustrating an example of a flowchart of a security mode operation of a static model processing system (800) on an electronic device (401) or an electronic device (500). Static model processing for external conditions may be considered as a security requirement operation. In this case, the operation of processing data collection from a sensor may be performed by switching the first core (404) within the processor unit (501) to a security mode (508). A signal transmitted via a bus or interrupt by the sensor or sensor cores may be transmitted to a monitor mode (513) to switch the first core (504) to a security mode (508). When the execution mode of the first core (504) is switched to a security mode, the execution environment for security is isolated from the general execution environment. The core entering the security mode (508) may access or control system resources of the electronic device that can only access the security operation system in the security execution environment.

[0101] In some embodiments, the input data handler (802) can identify a data collection mode from the user. For example, the data acquisition mode may include a data acquisition mode for learning and a data acquisition mode for inference. In the data acquisition mode for inference, signal acquisition for training may be performed simultaneously to improve the performance of a previously trained model. When collecting data, UI-related components may be displayed on the electronic device screen to collect data in a sitting posture, a standing posture, a walking posture, etc. Additionally, UI-related components are displayed so that the user can input by distinguishing an activity state, such as whether the user is running, riding a bicycle, or riding a vehicle. In another embodiment, the collected data may be analyzed to determine the user's posture or activity state in order to process the corresponding information.

[0102] In some embodiments, in performing static model processing on external conditions including a user’s physiological state, which may be liveness, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc., the electronic device (401, 500) may perform such function by assigning such function to a cluster of high-performance processor cores. For example, if the first cluster (503) is a cluster of high-performance cores, the first cluster (503) may be assigned.

[0103] External situation feature extractor (804)

[0104] FIG. 15 is a block diagram of an external situation feature extractor (1500). The external situation feature extractor (1500) may include a preprocessing handler (1510), a signal filtering handler (1512), and a feature extraction handler (1514).

[0105] In some embodiments, the external situation feature extractor (804) may be configured as the external situation feature extractor (1500) of FIG. 15. The external situation feature extractor (804, 1500) may obtain numerical data, such as first sensor data (1502) and second sensor data (1504), from the input data handler (802). When input data is received from an accelerometer or gyroscope sensor, numerical data may be collected as shown in FIG. 16. FIG. 16 is a diagram illustrating examples of various types of sensor data and formats that may be used in the present specification.

[0106] Multidimensional sensor data can be referred to as raw data. Signal processing, such as preprocessing and filtering, is performed on the raw data to enable optimal performance in the next stage.

[0107] FIG. 17 is a diagram illustrating an example of a flowchart of the preprocessing operation of an external situation feature extractor (804, 1500) on an electronic device (401) or an electronic device (500).

[0108] In some embodiments, methods for performing preprocessing may be determined based on the use of collected signals. For example, collected signals may be used for authentication, posture estimation, and activity information estimation. The preprocessing method may be processed differently based on its use and may partially overlap. The preprocessing handler (1010) may check for the following input data:

[0109] - Sensor errors (surge, saturation, or flat signals);

[0110] - User error (shaking or squeezing the phone);

[0111] - Static data (not including the dynamic range of "human" signals).

[0112] The preprocessing handler (1010) can process the input data by determining the quality of the input data or determining that it is an error (outside the expected range of the data).

[0113] Input state machine operations can be performed depending on the quality of the input data.

[0114] If the quality of the input data is determined to be very low, the operation to collect the input data may be performed again, or a user interface may be created that requires the user to perform additional actions to collect more input data. In the preprocessing process, the signal acquired from the motion sensor during the approximately 1 to 2 seconds at the start of signal acquisition may contain a significant amount of the user's macro motion signal and may be heavily affected by shaking of the electronic device. As a result, the signal may be ignored at the start of signal acquisition and / or at a specific interval immediately before the acquisition is completed.

[0115] In some embodiments, the preprocessing handler (1510) may perform a resampling procedure or interpolation on the input data. The resampling function may be uniform or non-uniform data for the new fixed-rate data. Input data derived from sensors that are sampled with a high level of hardware abstraction and can be highly deformed depends on the sampling configuration for hardware components or sensor components manufactured by a particular company. Consequently, input data from sensors written in a raw data format may be sampled non-uniformly. The input data may be corrected to a new uniform rate by the resampling procedure of the preprocessing handler (1510) before further analysis. The resampling procedure may correct small deviations in non-uniform samples through linear or cubic interpolation and provide a constant time between samples. For example, the resampling procedure can use a cubic "spline" to correct deviations in the sampling rate.

[0116] One example of software code is as follows:

[0117] [Ax, T] ​​= resample( Axyz(:, 1), time, 'spline');

[0118] [Ay, T] = resample(Axyz(:, 2), time, 'spline');

[0119] [Az, T] = resample( Axyz(:, 3), time, 'spline');.

[0120] In some embodiments, the signal filtering handler (1512) can perform the following filtering processing on the input data.

[0121] - Various band-pass filters;

[0122] - Reduction of gravitational and behavioral effects at very low frequencies;

[0123] - Focus on broadband information in the harmonics of the signal.

[0124] A signal filtering handler (1512) may perform filtering to remove unwanted signals for micro-motion data extraction from the collected signal. Unwanted signals may include, for example, noise, macro-motion signals, distortions caused by gravity, etc. Since power noise may be generated in the collected signal while the electronic device is charging, the signal may be filtered by taking into account characteristics attributable to power noise. The frequencies of neuromuscular micro-motions derived from neurons or attributable to the intrinsic neuromuscular anatomy of human-based neurons may be observed mainly in the range of 3 Hz to 30 Hz. Signals in the range of 3 Hz to 30 Hz or 4 Hz to 30 Hz from the collected input motion data may be extracted using a signal processing algorithm. The cutoff frequency of the band-pass filter of the signal processing algorithm may be changed based on the characteristics of the unwanted signals to be removed. For example, in one embodiment, a signal within the range of 4 Hz to 30 Hz may be extracted, and in another embodiment, a signal within the range of 8 Hz to 30 Hz may be extracted. In yet another embodiment, signals within the range of 4 Hz to 12 Hz or 8 Hz to 12 Hz may be extracted.

[0125] The signal filtering handler (1512) analyzes the input data and classifies / identifies the input data into small signals and large signals, which are separated from the small signal magnitudes of micro-motions. The signal filtering handler (1512) can also suppress / filter macro motions (large movements of the user's body, large movements of the arms, or walking, running, jogging, hand movements, etc.) from the collected input data. An exemplary analysis may be in the form described in "Time Series Classification Using Gaussian Mixture Models of Reconstructed Phase Spaces" by Richard J. Povinelli et al. in IEEE Transactions on Knowledge and Data Engineering, Vol. 16, No. 6, June 2004. Alternatively, the separation of large signals attributable to autonomous motion may be described in Sensors 2011, vol. by Kalyana C. Veluvolu et al. This can be done using the BMFLC-Kalman filter described in "Estimation of Physiological Tremor from Accelerometers for Real-Time Applications" on pages 4020-4036 of 11.

[0126] In some embodiments, the feature extraction handler (1514) can extract unique features from the extracted neuromuscular micromotion data according to the static model operation mode. FIG. 18 shows an example of a time series of single-axis accelerometer data samples showing a crossing of the central axis based on the extracted neuromuscular micromotion data, generated and processed by the preprocessing handler (1510) and the signal filtering handler (1512). These crossings represent physiological states and can be measured using mathematical functions such as Barlow features. Barlow features are typically used in EEG electroencephalography analysis. Barlow features are one example of hundreds of potential features that can measure the presence of physiological states. By taking the absolute value of the average of the discrete differences along the axes of the time-series gyroscope or accelerometer data, the overall trend of the measured neuromuscular progression to cross the center line of the origin can be quantified. This measurement can be used to train a state machine learning model, either alone or in combination with any number of other features and preprocessing techniques.

[0127] In some embodiments, the scale of the signal data or extracted feature data may vary depending on the type and structure of the electronic device, the variation of the sensor component, the sampling frequency of the signal, the type of contact between the user and the electronic device, etc. For example, the signal data or the first feature data may be measured with a scaling of 1 to 10, and the second feature data may be measured with a scale of 1 to 1000. In this case, standardization may be performed on the signal data or feature data. In other words, the signal data or feature data may be made to follow a normal distribution by centering the data so that the standard deviation is 1 and the mean is 0. A simple mathematical formula for standardization is as follows.

[0128]

[0129] Here, is the sample mean of specific feature data, and is the standard deviation.

[0130] In some embodiments, normalization may be performed instead of standardization as needed to process the components of a static model feature analyzer, and both normalization and standardization may be used. Additionally, normalization or standardization may be performed on sensor data, on feature data, or on all or part of the sensor data or feature data. The normalization or standardization process may be skipped based on the characteristics of the sensor data or feature data.

[0131] In some embodiments, it is necessary to reduce the number of data points significantly to improve the overall performance of the system. An initial step may include subtracting each data value from the mean of the measured data so that the empirical mean becomes 0 and each variance of the data becomes 1. After this initial step, based on the correlation between the data, the direction of maximum variance in high-dimensional data may be discovered, and the number of data points may be reduced by projecting them into new subspaces with dimensions equal to or smaller than the original. A simple procedure may be used to standardize n-dimensional data, generate a covariance matrix, decompose it into eigenvectors and eigenvalues, and generate a projection matrix by selecting the eigenvector corresponding to the largest eigenvalue. After generating the projection matrix, a transformation through the projection matrix into signal data or feature data may be performed to reduce the dimensionality of the n-dimensional data. The aforementioned process can transform the extracted dataset associated with neuromuscular tone into a dataset having linearly uncorrelated characteristics.

[0132] FIG. 19 is a flowchart of an exemplary feature extraction operation of an external situation feature extractor (804) in an electronic device (500) or an electronic device (401).

[0133] In some embodiments, output data from some processing or the following values ​​may be obtained from the preprocessed data and used as feature vectors. In one embodiment, the following values ​​may be obtained from the preprocessed data, and the values ​​may be used directly, partially modified, or a combination thereof to be used as feature vectors.

[0134] * Mathematical maximums, minimums, medians, and difference values

[0135] * Statistical mean, variance, standard variance, energy, entropy

[0136] * Correlation, zero-crossing rate

[0137] DC component, spectral peak, spectral centroid, spectral bands, spectral energy, spectral entropy in frequency domain analysis

[0138] * Wavelet coefficients of the wavelet transformation

[0139] Multiple types of features for extracting physiologically relevant information

[0140] * Hurst, entropy, Lyapunov divergence with sampling reduction for efficiency, Hjorth, Barlow, EEMD

[0141] * The aforementioned features commonly used in ECG and EEG analysis

[0142] Combinational impact of filters with features

[0143] In some embodiments, micro-motion data may be collected from various people and analyzed in a laboratory. By collecting and analyzing data from various sources such as age, gender, region, and body size, features with low correlation between features may be selected.

[0144] FIG. 20 illustrates an example of a feature vector set according to some embodiments. Features may be selected in the laboratory based on various types of motion classification characteristics illustrated in FIG. 3. The feature vector may be configured differently depending on the use of the collected signal. For example, the set of features used for authentication and the set of features for pose estimation or activity information estimation may partially overlap but may also be configured differently.

[0145] FIG. 21 illustrates an example of a feature vector set for physiological states according to some embodiments. These features may be selected in a laboratory based on the analysis of various types of experimental results in a laboratory. The feature vector set may be configured differently depending on the physiological states. The weights of the features or the set of features used for each physiological state may partially overlap or be configured differently.

[0146] The feature vectors described above in FIG. 21 represent relevant features having checkmarks for corresponding physiological states according to some embodiments. For liveness determination, a highly informative feature may be Barlow activity. This feature is intended to provide the machine learning algorithm with information regarding the sum of time-series accelerometer or gyroscope zero-crossings read by the static model analyzer (806). Compared to many mechanically generated signals or non-human-generated signals that affect the value of a feature such as Barlow activity, there are zero-crossings that are less consistent with neuromuscular signals or zero-crossings of larger magnitude. These quantitative feature values ​​can provide information to help the machine learning classifier make a liveness determination.

[0147] A distinct example of a feature containing information to aid in classification decisions regarding blood glucose levels may be mean band power. The mean band power feature contains information about the power contained within specific frequency bands of the time series signal. This feature may be higher or lower in specific frequency bands based on the influence of the user's blood glucose level. The values ​​of this feature may be used by a machine learning algorithm in a static model analyzer (806) to determine the extent to which a physiological state of hypoglycemia exists or the presence of hypoglycemia.

[0148] Combining several features can be useful when determining the presence of stress hormones or the extent to which stress hormones are present by a machine learning algorithm within a static model analyzer (806). Many features are used to train the machine learning algorithm to help distinguish the presence of stress hormones in neuromuscular signals from physiological conditions where stress hormones may be elevated, such as low blood sugar or sleep deprivation. Information contained in the average band power feature, LD matrix, entropy-based features, Barlow activity, and mobility can train the machine learning algorithm to more accurately recognize the presence of stress hormones and provide a unique determination from other physiological conditions where stress hormones may be present, such as low blood sugar.

[0149] FIG. 22 illustrates a divergence feature distribution capable of distinguishing humans from non-humans as one of the examples in the present disclosure. This figure shows the distribution of a single feature calculated over nine humans and the same feature from non-human (static) recordings calculated from accelerometer data. The accelerometer data was filtered to frequencies between 10 Hz and 15 Hz within the spectrum of human physiological neuromuscular tones. The distribution shows how the values ​​of the features vary over approximately 100 recordings per person and demonstrates that non-human signals can be easily distinguished from human signals. The types of physiological states vary depending on the selection or combination of features. Features or combinations thereof that clearly describe physiological states can be determined after appropriate experiments in a laboratory, and the results of such experiments can be stored directly or indirectly on the device as a set of constraints for the static model operation mode. The set of constraints can be downloaded or updated on the device via a network.

[0150] In some embodiments, entropy feature analysis may be applied to perform static model processing on users' physiological states, including vitality, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc. Entropy is a candidate feature class used to predict or measure one or more of the aforementioned physiological states. It is a non-linear feature used to quantify the information content or predictability of a sample of time-series sensor data. Kolmogorov, Approximate Shannon, and Sample Entropy are all different methods used to quantify the complexity of time-series samples, such as accelerometer or gyroscope data. One implementation of the entropy feature used to quantify physiological states involves dividing a time-series data sample into "N" segments of equal length. The calculation performed for each segment compares the similarity or distance of each segment against all others based on an experimentally derived distance metric threshold. Each segment receives a score regarding how many of the total number of segments it is similar to, and the average of the logarithm of each proportion is calculated. The same calculations are performed for segments of increasing length. These entropy values ​​quantify how repetitive the signal is. Physiological signals, such as neuromuscular tremors and movements, contain non-linear, non-repetitive, and complex patterns that express themselves over time. Mechanically generated time-series signals or signals from non-physiological systems can have lower entropy values ​​than those influenced by human physiology. Sleep deprivation is known to affect neuromuscular tremors to an extent that can be quantified using entropy analysis.

[0151] FIG. 23 is a diagram illustrating time series signals of entropy feature analysis. The time series signal on the upper left has lower entropy than the time series signal on the upper right of FIG. 23. By utilizing such features as described, physiological states can be quantified and displayed in an N-dimensional feature subspace used to train a static machine learning model. This static machine learning model can be used to determine the probability or extent that any of the states exist within a sample of time series sensor data and / or the presence or absence of any of the aforementioned physiological states.

[0152] In some embodiments, frequency analysis may be applied to perform static model processing on users' physiological states, including vitality, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc. Frequency analysis is a feature class used to measure or predict one or more of the aforementioned physiological states. One example of a feature belonging to this class is the average band power feature. The average band power feature can be used to determine the presence of physiological states, such as low blood glucose. For example, if low blood glucose is present, the magnitude of the signal presence in accelerometer or gyroscope time series data may increase. This increase in magnitude is likely to exist in a specific frequency band associated with human physiology and can be measured in conjunction with the average band power feature.

[0153] Figure 24 illustrates a raw signal of low average band power on the x-axis of a gyroscope. The figures described above show how an orange signal, which is a signal that can indicate a physiological state of low blood glucose, differs from a signal without low blood glucose. The average band power in specific frequency bands will be higher in a physiological state of low blood glucose.

[0154] FIG. 25 is a diagram illustrating examples of data sets according to physiological states, and FIG. 26 is a diagram illustrating examples of data sets according to physiological characteristics of the object of interest, respectively. Data sets according to physiological states or physiological characteristics may be determined in a laboratory, and these sets may be updated on electronic devices (401, 500) via a network. Before or when static model processing is started, the electronic devices (401, 500) may configure a static model processing system (800) with at least one of the aforementioned data sets according to the application.

[0155] (3) Static model analyzer (806)

[0156] FIG. 27 is a block diagram of a static model analyzer (806, 2700) according to one embodiment. The static model analyzer (806, 2700) may include a classifier engine (2740), a training interface (2710), a static model running interface (2720), and a tuning interface (2730). The classifier engine (2740) may include a training engine (2741), a static model running engine (2742), a tuning engine (2743), and a classifier kernel (2744).

[0157] FIG. 28 is a diagram illustrating an example of a flowchart of the training mode operation of a static model analyzer (805, 2700) on an electronic device (401) or an electronic device (500).

[0158] The static model analyzer (806, 2700) may operate in a training mode in a laboratory to construct static model parameters according to physiological states. The electronic device (401, 500) may enter this training mode in a laboratory to construct some parameters for future use of the static model for physiological states. In some embodiments, constructing some static model parameters may be performed on some laboratory electronic devices rather than on user devices. In most cases, the electronic devices (401, 500) for users do not necessarily need to enter a training mode, except to update or modify parameters for static models. FIG. 26 or FIG. 27 may be used to construct some static model parameters.

[0159] When operating in training mode, feature data (2750) of an authenticated user extracted from external situation feature extractors (804) can be collected. The collected feature data can be transmitted to the training engine (2741) of the classifier engine (2740) via the training interface (2701) for processing. In this case, the user feature data (2750) can be processed by various data processing algorithms or machine learning algorithms through cooperative operations of the training engine (2741) and the classifier kernel (2744) to determine the parameters of the static model.

[0160] To increase the accuracy or performance of a static model, the extracted feature data may be divided and processed into user feature data (2750), validation feature data (2752), and test feature data (2754). User feature data (2750) may be used for training to determine the parameters of the static model. Validation feature data (2752) may be used to improve the performance or accuracy of the model during training mode before evaluating the static model to select the optimal model. For example, validation feature data (2752) may be used to adjust the learning rate or perform validation while evaluating the model's performance during training mode. Test feature data (2754) may be used to evaluate the final model instead of being used to select the model. Noise feature data (2758) may be a type of feature data generated through a noise collection process. For example, noise feature data (2758) can be extracted from signals collected in an environment where a significant number of components different from micro-motions associated with neuromuscular tones exist, such as large movements or the presence of large vibrations around the electronic device. Landscape feature data (2758) can be feature data collected from feature extraction performed in a laboratory and from various people. Some sets of the extracted landscape feature data may be stored in the storage of the electronic device and used to improve the performance of the model.

[0161] FIG. 29 is a diagram illustrating an example of a flowchart of the static model learning mode operation of a static model analyzer (806, 2700) on an electronic device (401) or an electronic device (500).

[0162] The static model analyzer (806, 2700) may operate in static model learning mode. The electronic device (401, 500) may have been operated in training mode before the electronic device (401, 500) operates in static model learning mode so that parameters for models for feature data sets of physiological states of users are already configured. If information about the static model has already been generated, the static model learning engine (2742) of the classifier (2740) may operate with the classifier kernel (2744) through the static model interface (2720) on the new feature data (2750) of the user. The classifier kernel (2744) based on the previously generated static model may perform operations on the newly extracted feature data to generate numerical degrees of physiological states for the previously authenticated user.

[0163] (4) Static Model Application Framework (808)

[0164] FIG. 30 is a block diagram of a static model application framework (808) according to one embodiment. In some embodiments, the static model application framework (808) may provide for enabling multiple applications using the output of a static model analyzer (806). The static model application framework (808) may include an output state machine for performing static model processing on external conditions including the physiological states of users. The static model application framework (808) may provide an application programming interface (API) regarding the physiological states of users including liveliness, blood glucose levels, stress hormone levels, presence of drugs, identifiers, etc.

[0165] In some embodiments, the static model application framework (808) may use extracted feature data of the user associated with external situations including the user's physiological states. The user's feature data may be obtained by an external situation feature extractor (804), and they may be stored in a secure storage unit of an electronic device. To achieve a high level of security for personal biometric information, the static model application framework (808) may temporarily use the physiological states associated with the user's feature data and discard them after use.

[0166] FIG. 31 illustrates an example of a device type for a situational static model. Static models can be implemented in hardware, software, or a combination of hardware and software. Static models may take the form of a software library running on a microcontroller. Some components of the static models may be implemented within an SoC in the form of an accelerator. Static models may be implemented as a standalone chipset (or ASIC) as shown in FIG. 31, but the implementation forms of static models are not limited to this example.

[0167] Application example of a static model processing system for Liveness

[0168] Fraudulent access to websites and devices is a growing problem in the cyber world. Hackers, cybercriminals, and even nation-states are constantly poking around the network in search of vulnerabilities to exploit financial, political, and other gains. These criminals hack into cloud storage, utilize cyber robots, and access private / secret accounts to use counterfeit logon credentials. The advent of always-on AI adds an additional threat; what can stop an all-knowing AI bot that has accessed someone's entire digital and authenticating trail to digitally mimic an identical person? One way to address robots and forgery attempts attempting to jeopardize secure spaces is to augment logon credential and authentication technologies. One way authentication efforts can be strengthened is to combine secondary authentication inputs (multi-factor authentication) with authentication requests, or to add "liveness" credentials to verify that the authentication request is being made by a living requester rather than by a robot or forged inanimate data. The goal of today's "liveness" determination technologies, such as CAPTCHA, is to determine whether a human is engaging in an online transaction versus a spambot. CAPTCHAs are commonly used in the online world and frequently appear on desktop computing when requesting access to websites.What is proposed is a method to supplement a random authentication method among many authentication methods with an indicator of "liveness" that verifies that users employing a random method are physiologically active and living / breathing individuals. The methods described below provide evidence that a living person, not a bot or AI, is providing authentication information. The identity of individuals may be a function of the authentication method. This is important because, unlike authentication technologies with an accuracy of over 90% (preferably close to 100%), the goal of a method to demonstrate liveness is essentially binary, meaning "alive" or "not alive."

[0169] There are many situations where this is valuable. This novel method can utilize data that can be passively collected from ubiquitous embedded sensors present in portable mobile devices while users complete a certain form of authentication or provide another form of authentication without requiring additional actions from some parts of the user.

[0170] When access to a website on a mobile device is requested, sensor data from that device will be collected in the background. Contact and interaction with the device may serve as evidence in accelerometer, gyroscope, and other sensor data streams. One component of the sensor data relates to neuromuscular tones generated by the body's proprioceptive system, in which the brain continuously communicates with surrounding nerves to gauge the body's position within the environment. Other physiological biometric parameters may also be used to provide liveness indicators, but these parameters would require additional hardware to collect these signals. Extracting neuromuscular data is an invisible process easily collected from accelerometer data gathered by the phone whenever a user makes a call. This data can be processed on the device or remotely to determine the presence of a human. Neural networks or other methods of machine learning may be used to determine whether the signal presence is uniquely human. If the result is positive, the user will proceed with the submission of that form or access the site without any additional information. If the result is invalid, a standard CAPTCHA or OTP may be used as a Level 2 authentication request, or the user may be asked to hold the device again.

[0171] An alternative implementation utilizes a combination of the aforementioned method and external verification, in which the user receives a prompt via text or phone call and is instructed to hold their device while sensor data is collected from their device.

[0172] merit:

[0173] ■ A completely new method has no existing deception methods.

[0174] ■ Does not require additional user effort

[0175] ■ Uniquely designed for an improved user experience on mobile websites

[0176] ■ Predicting the trajectory of machine learning where biometric recognition may be the only feasible method to determine the presence of humans in digital transactions not vulnerable to hackers

[0177] disadvantage:

[0178] ■ Unexplored Area

[0179] ■ In a desktop setup, an accelerometer may be added to the mouse or touchpad interface to provide micro-motion data.

[0180] ■ Device hardware changes

[0181] ■ Additional APIs for customers may be required

[0182] FIG. 32 illustrates an example of a static model processing system for liveness physiological states on an electronic device (401) or an electronic device (500) according to some embodiments. In the electronic device, in the detection step (3211), an input data handler (802) may detect signals from outside the electronic device, for example, movement signal data from a part of the user's body. In the electronic device, in the preprocessing step (3212), an external situation feature extractor (804) may perform preprocessing of the signals collected from the input data handler (802), for example, suppression of signal components associated with the user's autonomous movement, noise, sensor errors, gravity, electronic power noise and other noise-related signals, and generation of a data set associated with neuromuscular tone. In the electronic device, in the feature extraction step (3213), an external situation feature extractor (804) can perform feature extraction from pre-processed signals, and can extract feature vector sets by generating data sets of mathematical expressions regarding the user's external situation, such as liveliness status, for example. In the electronic device, in the learning step (3214), a static model analyzer (806) can perform a training operation using the feature vector sets by calculating the parameters of static models and evaluating each static model. In the electronic device, in the prediction step (3215), a static model analyzer (806) can perform a static model learning operation by constructing a set of model parameters for each predetermined static model and generating a numerical degree of the matching level for a previously authenticated user. In the electronic device, in the determination step (3216), a static model application framework (808) can determine user access to the electronic device in response to the numerical degree of physiological states.

[0183] FIG. 33 is a diagram illustrating an example of a flowchart of a static model operation for liveness on an electronic device (401) or an electronic device (500). The electronic device (401, 500) can configure a static model operation mode as a constraint on the user's liveliness, load information of the static model operation mode including a constraint set of the user's external situation (physiological state), configure a static model parameter set according to the static model operation mode, collect sensor signal data including neuromuscular tone from a body part of the user's body at a predetermined sampling frequency over a predetermined sample period, suppress signal components associated with the user's autonomous movement from the sensor data, generate a data set of mathematical formulas regarding the user's external situation (e.g., physiological state) from the sensor data suppressed signal components associated with the autonomous movement based on the static model operation mode, construct a feature vector table including a plurality of sets of feature vectors based on the data sets of mathematical formulas, execute a static model using the feature vector table according to the static model operation mode, and generate report information regarding the external situation of liveliness (e.g., physiological state) based on the execution result of the static model.

[0184] FIG. 34a illustrates an example of creating a new account action using liveness physiological states. If a user wishes to create a new account on a mobile website or mobile application, the user's electronic device may send a request message to access a website that provides an interface for creating a new account, and the server-side electronic device may send web documents that provide a user interface for creating a new account based on the request from the user's electronic device. Based on the user's input through the web documents, the user's electronic device and the server-side electronic device may exchange information to proceed with the creation of the account procedure. When the user enters the website where they wish to create an account, the sensors present on the device immediately begin collecting background information (initiated by the website) by processing a static model of liveness physiological states. When the user fills in the required information to create an account, the sensors passively collect information with or without the user's knowledge. Once the user completes all fields and submits the information to create an account, a liveness determination will be made from the passively collected data. This liveness determination will determine whether human physiological signals are present in the passively collected data. In this case, passively collected data comes from the accelerometer, gyroscope, and magnetometer within the user's mobile device. From this sensor data, ballistocardiographs (heartbeats) and neuromuscular tones in the lymph can be detected. If the signal is determined to include these physiological signals, the user will be determined to be alive and human and will be permitted to create an account on the website or application.

[0185] FIG. 34b illustrates an example of accessing personal health records using liveness physiological states. If a user wishes to access a database containing their personal health records, the user's electronic device may send a request message to access a website that provides an interface to the database containing the personal health records, and the server-side electronic device may send a web document providing a user interface to access the personal health records based on the request from the user's electronic device. Based on the user's input through the web document, the user's electronic device and the server-side electronic device may exchange information to proceed with the login procedure. Upon entry with their established login credentials, a liveness determination will be performed to ensure that a human is performing their actions by processing a static model of the liveness physiological state. After submitting their login credentials and before accessing their health records, the user may be asked to use a heart rate sensor on the device for which they wish to access the health records. Information collected from this sensor will be calculated, and if it is determined that the signal collected from the heart rate sensor contains a human physiological signal, the liveness determination will allow the user to access their health records.

[0186] When a user attempts to access a website or device, random authentication technologies that are not visible to the user—particularly image-based methods—can benefit from automatically executed liveness verification. For example, when a user wants their online banking web portal and proceeds to open the application and provide a username and password or place their finger on a fingerprint sensor, the phone simultaneously captures neuro-mechanical micro-motion data continuously collected by an accelerometer within the phone and provides liveness verification along with the authentication input.

[0187] Static model processing of liveness physiological states can be combined with another abstract authentication parameter, namely passwords, PIN numbers, OTPs, etc., or with another behavior-based "liveness" parameter, namely CAPTCHA challenges, motion repertoires, voice commands, swipe patterns. The authentication sample for the static model may be one of a number of image-based physical features or other authentication technologies, including fingerprints, handprints, iris recognition, facial recognition, facial veins, etc.

[0188] Static model processing can automatically satisfy liveness evaluation by combining signals representing an arbitrary number of physiological functions (the information is received from the user during an authentication request via a conventional method by simultaneously sampling physiological data while acquiring authentication samples using other authentication methods (i.e., password / PIN entry, voice command, facial recognition, handprint analysis, iris recognition, motion repertoire, etc.)), evaluating physiological data to determine whether the physiological data matches known physiological functions, or by orienting the determination that there exists a physiological process to satisfy the liveness evaluation being combined with the authentication samples being collected.

[0189] Age blocking for minors driving and vaping prevention

[0190] Neural tapping interfaces and platforms allow for the capture of signals originating from the nervous system and relayed by neuromuscular junctions. Although these signals are inherently electronic, they can be easily captured by their micro-mechanical effects on muscle cells using devices equipped with MEMS (micro-electromechanical systems). Such devices may include smartphones, tablets, and any SOC (system on chip) system. Signals originating from the nervous system are present throughout the human body and can be acquired almost anywhere using a device equipped with a suitable sensor, as long as contact exists between the human body and the device. Such devices may include vaping systems, provided they are equipped with SOCs and MEMS.

[0191] Given that AI code is completely cloudless, companies can build products that can be trained using very inexpensive electronic chips (e.g., microcontrollers) or embed fully trained AI code capable of responding to or reasoning with some well-defined questions.

[0192] Some questions that may be obvious due to their reported effects on neuromuscular function are age and some neuromuscular junction influencers, such as nicotine, for example. Heart rate variability (HRV), which reflects autonomic nervous system balance, is known to display a cut-off at approximately age 18 in humans. Neurotransmission at the neuromuscular junction is known to depend on nicotine receptors.

[0193] A proof of concept (POC) was previously established for age-blocking (or parental control) applications. The AI ​​code for age-blocking utilized smartphones for data capture and inference. The data extraction techniques of signal processing and its implementation (AI code) are not based on classical "statistical big data AI." Such a POC can achieve an effectiveness (accuracy) of between 87% and 94%, depending on the code version and implementation. Considering the limitations on age-related information content at the level of neuromuscular junctions, the 94% effectiveness (accuracy) of the age-blocking (or parental control) AI code based on the human nervous system is likely the absolute limit of the technology.

[0194] These age-blocking applications can form the basis of a new class of vaping devices that significantly reduce underage vaping and all its potentially harmful health effects, while also significantly diminishing its legal and branding importance. However, it is desirable to acquire more effective and accurate technology that approaches "99%" effectiveness / accuracy. To this end, the fusion of different data types can be utilized for greater accuracy. Private non-personal identification (PII) tagging can be used to check the age of buyers at point-of-sale (POS) locations, such as checkout registers, credit card machines, wireless contactless payment terminals with near-field communication, or other point-of-sale terminals.

[0195] FIG. 35a is a flowchart utilizing a static artificial intelligence model for the pass / fail implementation of age blocking (parental control function). If the buyer / user is a minor, they are blocked (fail) from buying or selling. If the buyer / user reaches adulthood (over the age of a minor), the buyer is not blocked (pass) from buying or selling.

[0196] Questions regarding the presence of physiological markers can be easily handled by constrained datasets collected from a population of volunteers. These constraints may include hormonal status, gender, muscle rigidity, age, etc. These constraints constitute the conditions. With such data, AI models can be trained, and inference engines can be built to address these conditions. Programming data and frameworks can be used to deploy pre-trained AI on chipsets, such as microcontrollers or System on Chip (SOCs).

[0197] In this implementation, the inference result can be used to control the ignition switch on a vaping device at an arbitrary SW or HW decision point associated with an arbitrary parental control system based on age restrictions. This is a pass / fail model.

[0198] A pre-trained AI (context-dependent physiological database, where context = age in this specification) is embedded within an SOC in a vaping device. The SOC is an inexpensive chipset with suitable sensors that allow processing to extract relevant information (feature functions) and inference for data capture. The result of the inference step can be used for a pass / fail implementation or a pass / check implementation.

[0199] In terms of pass / fail, the inference result is used to control the ignition switch of the device. The accuracy of the AI ​​can be booted at a slightly high level (about 94-95%), which is better than any other existing parental control feature, but it leaves room for some false positives and false negatives.

[0200] It desirablely reached a nearly perfect solution, that is, it was able to achieve 99% accuracy. As there is no mathematics or AI code capable of reaching that accuracy on its own, additional AT codes were used to allow secondary reasoning (referred to as TAG) to be fused together and implemented within the system in a manner with the highest possible trust and a very low probability of violation. This implements a pass / check system instead of a pass / fail system.

[0201] FIG. 35b is a diagram illustrating the client-server implementation of age blocking and processes in each case. The process utilizes a two-step check performed at the POS of any device under the supervision of an authorized salesperson. It will be noted that some forms of control are implemented according to legal status preventing the sale of vaping to minors. The cutoff age may vary between 18, 21, or 26 depending on the case, as a fused data implementation, and this is also true for the adaptive inference of the model for each different age limit.

[0202] This implies that the vaping device is shipped in a locked state (via its firmware) and must be unlocked or activated when the aforementioned sale is completed using age-blocking artificial intelligence based on neural signals.

[0203] In POS systems, neural system-based age blocking solutions combine tags—which are customizable but cannot be processed via user recognition while preserving user privacy—with manual age verification (carting). No arbitrary PII is ever collected by the device. Links within the database between the consumer's ID and the tag may or may not exist. Such links are not essential to the solution.

[0204] This utilizes two applications of technology along with some actions in POS. This allows for compliance with the final legal (regulatory) requirements specific to each country.

[0205] In POS, there are two stages:

[0206] - Carting / ID check. Based on those requirements (18, 21, 26), the buyer's ID is verified and stored in the seller database.

[0207] - Tagging. Specific devices are completely inactive and need to be activated after sale.

[0208] - Tagging is performed at the POS under the supervision of a seller in a 3-step process.

[0209] o Step 1 - The buyer holds the device with one hand for 30-60 seconds

[0210] o Step 2 - After this step, SOC extracts the TAG (within less than 1 second) (TAG = a vector of 3 numbers (numbers vector))

[0211] o Step 3 - When TAG is complete - Device functions are enabled

[0212] A TAG is a downgraded inference that extracts some appropriately selected features, such as three features. Such a TAG is a combination of three numeric vectors and some other parameters. These parameters reflect future users but do not allow for the identification of the said user on their own. This is due to the standard deviation linked to these features and the nature of these features themselves (i.e., their physiological and user-specific information content).

[0213] However, this TAG can be fully utilized as a check and decision point mechanism to enhance the global accuracy of age blocking technology. The TAG makes the device significantly private without violating GDPR.

[0214] By combining the use of age blocking with TAGs, controlling at the POS, and adding friction in the event of abuse, cloudless, friction-free AI-implemented age-based control for arbitrary vaping devices (or arbitrary devices or parental control systems) with a very high degree of accuracy can be achieved, thereby mitigating legal regulatory and branding risks.

[0215] Fig. 36 is a diagram illustrating another application of an age-based application of neural information-based artificial intelligence. The workflow of the child protection ignition control function for a vehicle is illustrated in Fig. 2. In this manner, children below the age limit will not be able to start the vehicle to operate it.

[0216] This solution can be implemented with or without two mini LEDs capable of reporting the results of two different inferences (red / green). This solution involves a method in which the merchant interacts with the device's firmware, which is, ideally, implemented through a connection between the device and some other device provided to the POS terminal.

[0217] After ID check and carding, the device switch is "on".

[0218] The user holds the device with their hand

[0219] NON-PII neural data acquisition

[0220] The AGE block and TAGGING codes are activated and results are given (2LED)

[0221] Four situations are obtained depending on the individual pass / fail of each engine.

[0222] The four cases can occur as follows:

[0223] A. Age(+) pass - Tag pass(+) ⇒ Device SOC allows ignition to proceed.

[0224] This may be a case where the age exceeds the legal limit, and the TAG falls within the appropriate parameters. Therefore, the user is an adult and falls within the scope where he / she should be.

[0225] B. Age (-) Failure - Tag Pass (+) ⇒ The device SOC allows ignition to proceed but counts.

[0226] - If this situation repeats [MAX 3X], the device SOC is locked.

[0227] - Go to POS for a check - The seller verifies the legal age, and if confirmed repeatedly (4 times), the age stringency is lowered. This will handle the voice case mentioned above. This is the case where the age block fails even though the user is an adult. Specific adaptations for the user are added to the device firmware by the seller (via connection).

[0228] C. Age(-) Unavailable - Tag Unavailable(-) ⇒ Device SOC is locked for x minutes (e.g., x=3 minutes).

[0229] - After x minutes, if the result is repeated, the device SOC is permanently locked.

[0230] - It can be reactivated at the POS with its legal owner according to the database.

[0231] This will handle abusive usage, such as when the device was purchased by an adult and given to a minor for use. Obviously, the person is too young, but the device tag is too far removed from this person.

[0232] D. Age (+) Pass - Tag Failure (-) ⇒ The device SOC proceeds with ignition and counts.

[0233] - If the situation repeats 3X times on its own, the device SOC is locked. This will handle the above positive cases.

[0234] - This may also be the case where another adult user (non-buyer) is using the device. It only allows this 3X (this may, of course, be modified according to some commercial needs).

[0235] - After the maximum number of attempts, you must go to the POS to unlock it.

[0236] principle:

[0237] - Device personalization through tagging

[0238] - Check at POS and

[0239] - "Punitive" friction is used.

[0240] When combined with 90% effective age blocking, tagging can be 90% effective (it does not allow identification, and the maximum overlap shown in Fig. 5 is 7-8%), and when the two processes are fused and used together, the cumulative error rate is less than 1%, so it may be desirable to unlock the vehicle's ignition.

[0241] Figure 37 is a flowchart showing additional AI to provide protection against side effects from nicotine abuse.

[0242] With the function of the SOC inside the vaping device, the effects of certain drugs / products / medicines on the neuromuscular junction can be monitored for side effects.

[0243] As nicotine is a clear option for a monitorable drug, vaping technology can be positioned and branded as a method to aid in smoking cessation. Such an impact will require a context-specific dataset (2,000 users with various nicotine dosages) that must be collected to train these additional static AI models aimed at inferring nicotine at certain nicotine usage thresholds. This is a safety feature of vaping technology that allows ignition only at safe levels (or some defined nicotine levels). This is a software-driven switch.

[0244] The device may be equipped with a third static AI model pre-trained with a nicotine-muscle normal dose-response curve. Inference may be triggered at regular time intervals during use of the vaping device and may be used as an additional condition for ignition (this may be product-optional).

[0245] Referring to FIG. 38a, neuroscience-based AI technology can be embedded in a phone or HW / SW SOC device to form a child protection device.

[0246] FIG. 38b is a diagram illustrating an evaporator with artificial intelligence and a System on Chip (SOC) to provide age blocking.

[0247] Figure 39 illustrates a 3D bubble plot representing fused data, one of which is a tag, to improve accuracy and reduce tagging errors. Three numbers are combined as vectors within a single bubble plot for a user. Each plotted bubble represents a different person, and their three numbers (from three different AI functions) are extracted 30 to 60 times and fused together. The repeated tests are averaged together and displayed as points in 3D space in Figure 39. The diameter of the circle (bubble) represents a portion of the statistical variance of the user's tests.

[0248] The data required to calculate these iterations is retrieved from the POS terminal over a period of 30 to 60 seconds, during which the buyer is asked to hold the device in one hand. The extraction and averaging calculation time is approximately 20 msec, and the vector is stored on the device (or exported via a connection to the user DB).

[0249] Figure 39 illustrates a 3-D vector space constructed on three different key features extracted from neural-tagging data. Each point (bubble) represents the average of 30 to 60 sweeps of data from the same individual. This average is represented at the center of a sphere, the radius of which is the standard deviation (SD). Data from 560 different users (the graph is incomplete, and some users are outside the axis scale range) is collected via mobile phones. The cumulative overlap area of ​​bubbles between any two individuals is less than 11%.

[0250] conclusion

[0251] The components of the embodiments are code segments of instructions that can be executed by one or more processors to perform and execute tasks and provide functions, essentially when implementing software. Programs or code segments may be stored on a processor-readable medium or storage device coupled to communicate with at least one or more processors. A processor-readable medium may include any medium or storage device capable of storing information. Examples of processor-readable media include, but are not limited to, electronic circuits, semiconductor memory devices, ROM (Read Only Memory), flash memory, EEPROM (Erasable Programmable Read Only Memory), floppy disks, CD-ROMs, optical disks, hard disks, and solid-state devices. Programs or code segments may be downloaded or transmitted between storage devices, for example, through a computer network such as the Internet or an intranet.

[0252] Although this specification contains many details, they should not be construed as a limitation to the scope of this disclosure or what may be claimed, but rather as a description of features for specific embodiments of this disclosure. In the context of individual embodiments, specific features described in this specification may be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may be implemented in multiple embodiments, individually or in sub-combinations. Furthermore, although features are described above as operating in a specific combination and may be initially claimed as such, in some cases, one or more features from the claimed combination may be excluded from the combination, and the claimed combination may be for a sub-combination or a variation of a sub-combination.

[0253] Accordingly, although specific exemplary embodiments have been specifically described and illustrated in the accompanying drawings, they should not be interpreted as being limited by such embodiments, but rather as being subject to the following claims.

Claims

Claim 1 Acquiring at least one movement information of a user including neuromuscular tone at a predetermined sampling frequency over a predetermined sample period; suppressing signal components associated with the user's voluntary movement from the acquired at least one movement information of the user; generating a plurality of constrained data sets associated with a plurality of predetermined constraints linked to a plurality of predetermined physiological conditions from the at least one movement information of the user in which the signal components associated with the voluntary movement are suppressed; constructing a plurality of independent static models based on a plurality of predetermined physiological conditions - each independent static model is linked to a specific constraint -; installing the plurality of independent static models within a device comprising a processor to execute sensors and commands to collect sensor data linked to the plurality of independent static models; and having a user execute one or more of the plurality of independent static models through a user interface based on sensor data detected from the user; and providing one or more results (inferences) to the user through a user interface associated with the execution of one or more of the plurality of independent static models, wherein one or more results are for the user A method that reflects one or more physiological situations. Claim 2 A method according to claim 1, further comprising terminating the execution of one or more of a plurality of independent static models until the next execution session with the user. Claim 3 A method comprising: acquiring at least one movement information of a user including a neuro-muscular tone at a predetermined sampling frequency over a predetermined sample period; suppressing signal components associated with the user's voluntary movement from the acquired at least one movement information of the user; generating a constraint data set associated with predetermined constraints linked to a predetermined physiological situation from the at least one movement information of the user in which the signal components associated with the voluntary movement are suppressed; constructing independent static models based on the predetermined physiological situations, each independent static model being linked to a specific constraint; installing the independent static models within a device comprising a processor to execute commands and sensors to collect sensor data linked to the independent static models; having the user execute one or more of the independent static models through a user interface based on sensor data detected from the user; and providing one or more results (inferences) to the user through a user interface associated with the execution of one or more of the independent models, wherein the one or more results reflect one or more of the user's physiological situations. Claim 4 A method according to claim 3, further comprising terminating the execution of one or more of a plurality of independent static models until the next execution session with the user. Claim 5 In claim 3, the predetermined physiological situation / state is the user's age, and the constraint data set is associated with the user's age range. Claim 6 In claim 3, the predetermined physiological characteristic state is the user's age, and the constraint data set is associated with the user's age cutoff / boundary situation. Claim 7 In claim 3, the constraint data set is associated with the user's gender. Claim 8 In claim 3, the constraint data set is associated with the user's attention state (wake / sleep / fatigue). Claim 9 In claim 3, the pharmaceutical data set is a method associated with the ovulation status of a female user. Claim 10 In claim 3, the pharmaceutical data set is a method associated with the pregnancy status of a female user. Claim 11 In claim 3, the constraint data set is associated with the user (see FIG. 25) in a method. Claim 12 In claim 3, the constraint data set is associated with whether the user is right-handed or left-handed. Claim 13 In claim 3, a method in which a constraint data set is associated with a user's liveliness character to distinguish it from a bot or machine. Claim 14 A method comprising: acquiring at least one movement information of a user including a neuro-muscular tone at a predetermined sampling frequency over a predetermined sample period; suppressing signal components associated with the user's voluntary movement from the acquired at least one movement information of the user; determining (forming) a plurality of constraint data sets associated with a plurality of predetermined constraints linked to a plurality of predetermined physiological situations from the at least one movement information of the user in which the signal components associated with the voluntary movement are suppressed; forming a plurality of independent static models based on the plurality of constraint data sets and a plurality of predetermined physiological situations, wherein each independent static model is linked to a specific constraint; and installing the plurality of independent static models within a device comprising a processor for executing a sensor and instructions to collect sensor data linked to the plurality of independent static models. Claim 15 A method according to claim 14, further comprising, prior to the above installation, generating multiple data sets of mathematical formulas from sensor data based on multiple predetermined physiological situations; performing training operations using multiple data sets for each model of multiple independent static models; and determining the model parameter sets of each model of multiple independent static models (predetermined prediction models). Claim 16 A method according to claim 15 further comprising verifying the operating mode of the processor and, based on the verification, setting the operating mode of the processor to a secure execution environment. Claim 17 A method according to claim 15, further comprising dividing a plurality of data sets into a user feature vector set, a verification feature vector set, and a test feature vector set based on mathematical formulas of a plurality of data sets; evaluating each model of a plurality of independent static models using the verification feature vector set to verify each model of a plurality of independent static models; and testing each model of a plurality of independent static models using the test feature vector set to determine the accuracy of each model of a plurality of independent static models. Claim 18 In claim 15, the mathematical expression is a method in which the feature is formed using at least one of Barlow Activity, Barlow Mobility, and Barlow Complexity features. Claim 19 In claim 15, a method further comprising receiving a landscape (other users—global users) feature vector set and a noise feature vector set before performing training, wherein the training is performed using the landscape feature vector set and the noise feature vector set. Claim 20 A method comprising: acquiring at least one movement information of a user including a neuro-muscular tone at a predetermined sampling frequency over a predetermined sample period; suppressing signal components associated with the user's voluntary movement from the acquired at least one movement information of the user; generating a plurality of constraint data sets associated with a plurality of predetermined constraints linked to a plurality of predetermined physiological situations from the at least one movement information of the user in which the signal components associated with the voluntary movement are suppressed; receiving a plurality of independent static models including model structures and model parameters based on a plurality of predetermined physiological situations, wherein each independent static model is linked to a specific constraint; executing one or more of the plurality of independent static models through a user interface based on sensor data detected from the user, using a sensor and a processor coupled to a processor to collect sensor data from the user; and providing one or more results (inferences) to the user through a user interface associated with the execution of one or more of the plurality of independent static models, wherein the one or more results reflect one or more physiological states of the user. Claim 21 In claim 20, a method further comprising generating multiple data sets of mathematical formulas from sensor data based on multiple predetermined physiological situations. Claim 22 A method according to claim 21, further comprising collecting sensor data including neuromuscular tone from a body part of a user's body at a predetermined sampling frequency over a predetermined sample period; and suppressing signal components associated with one or more autonomous movements of the user from the sensor data. Claim 23 In claim 21, the mathematical expression is a feature formed using at least one of Barlow Activity, Barlow Mobility, and Barlow Complexity features. Claim 24 A method according to claim 21, further comprising updating (tuning) the model parameters of a plurality of independent static models. Claim 25 In claim 24, a method further comprising determining whether, prior to updating, model parameters are required for one or more of a plurality of independent static models. Claim 26 In claim 24, the update comprises receiving a landscape feature vector set and a noise feature vector set, wherein the update is performed using the landscape feature vector set and the noise feature vector set. Claim 27 A method for determining a user’s liveness, comprising: acquiring at least one movement information of a user including a neuro-muscular tone at a predetermined sampling frequency over a predetermined sample period; determining, from the acquired at least one movement information of the user, a constraint data set associated with a predetermined liveness constraint linked to a physiological situation of liveness; forming an independent static model based on the physiological situation of the predetermined liveness, wherein the independent static model is linked to a predetermined liveness constraint; installing the independent static model within a device comprising a processor to execute commands and a sensor to collect sensor data linked to the independent static model; and having the user execute the independent static model through a user interface based on sensor data detected from the user; and providing a result (inference) to the user through a user interface associated with the execution of the independent static model, wherein the result reflects the physiological situation of the user’s liveness. Claim 28 In claim 27, a method further comprising terminating the execution of an independent static model until the next execution session with the user. Claim 29 A method comprising: acquiring at least one movement information of a user including a neuro-muscular tone at a predetermined sampling frequency over a predetermined sample period; suppressing signal components associated with the user's voluntary movement from the acquired at least one movement information of the user; determining (forming) a plurality of constraint data sets associated with a plurality of predetermined liveness constraints linked to physiological conditions of liveness from the at least one movement information of the user in which the signal components associated with the voluntary movement are suppressed; forming independent static models based on the constraint data sets and the predetermined physiological conditions of liveness, wherein the independent static models are linked to the predetermined liveness constraints; and installing a plurality of independent static models within a device comprising a processor for executing instructions to collect sensor data linked to the plurality of independent static models and a sensor. Claim 30 A method according to claim 29, further comprising, prior to the above installation, generating a plurality of data sets of mathematical formulas from sensor data based on a predetermined physiological situation; performing training operations using the plurality of data sets for each of the independent static models; and determining a set of model parameters of the independent static models (predetermined prediction models). Claim 31 A method according to claim 30, further comprising collecting sensor data including neuromuscular tone from a body part of a user's body at a predetermined sampling frequency over a predetermined sample period; and suppressing signal components associated with one or more autonomous movements of the user from the sensor data. Claim 32 A method according to claim 30, further comprising dividing a plurality of data sets into a user feature vector set, a verification feature vector set, and a test feature vector set based on mathematical formulas of a plurality of data sets; evaluating an independent static model using the verification feature vector set to verify an independent static model; and testing an independent static model using the test feature vector set to determine the accuracy of the independent static model. Claim 33 In claim 30, the mathematical expression is a method in which the feature is formed using at least one of Barlow Activity, Barlow Mobility, and Barlow Complexity features. Claim 34 In claim 30, a method further comprising receiving a landscape (other users—global users) feature vector set and a noise feature vector set before performing training, wherein the training is performed using the landscape feature vector set and the noise feature vector set. Claim 35 A method comprising: acquiring at least one movement information of a user including neuro-muscular tone at a predetermined sampling frequency over a predetermined sample period; suppressing signal components associated with the user's voluntary movement from the acquired at least one movement information of the user; generating a constraint data set associated with a predetermined liveness constraint linked to a predetermined physiological state of liveness from the at least one movement information of the user in which the signal components associated with the voluntary movement are suppressed; receiving an independent static model including a model structure and model parameters based on the predetermined physiological state of liveness, wherein the independent static model is linked to a predetermined liveness constraint; executing the independent static model through a user interface based on sensor data detected from the user, using a sensor and a processor coupled to a processor to collect sensor data from the user; and providing results (inferences) to the user through a user interface associated with the execution of the independent static model, wherein the results reflect the physiological state of the user's liveness. Claim 36 In claim 35, a method further comprising generating multiple data sets of mathematical formulas from sensor data based on multiple predetermined physiological situations. Claim 37 A method according to claim 36, further comprising verifying the operating mode of the processor and, based on the verification, setting the operating mode of the processor to a secure execution environment. Claim 38 In claim 36, the mathematical expression is a method in which the feature is formed using at least one of Barlow Activity, Barlow Mobility, and Barlow Complexity features. Claim 39 In claim 36, a method further comprising updating (tuning) the model parameters of an independent static model. Claim 40 In claim 39, a method further comprising determining whether updating model parameters is necessary for an independent static model before updating. Claim 41 In claim 39, the update comprises receiving a landscape (other users—power users) feature vector set and a noise feature vector set, wherein the update is performed using the landscape feature vector set and the noise feature vector set. Claim 42 In claim 41, a method further comprising determining whether updating model parameters is required for an independent static model before updating. Claim 43 A method for creating a user account comprising: sending a request message to access a website; receiving a web document that provides a user interface for creating a new account associated with the website; sending authentication information (login ID / password) to the website through the user interface; executing an independent static model including a model structure and model parameters based on the authentication information and the physiological situation of a predetermined liveness associated with at least one movement information of the user, including neuromuscular tone from a body part of the user, at a predetermined sampling frequency over a predetermined sample period, to determine the liveness of the user, wherein the independent static model is linked to a predetermined liveness constraint; sending the result of determining the liveness of the user to the website; and receiving the result of creating a new account associated with the website based on the liveness determination. Claim 44 A method for creating a user account comprises receiving a request message to access a website provided by a server system; sending a web document having a user interface for creating a new account associated with the website; receiving authentication information (login ID / password) through the user interface for the website; receiving results of a user's liveness determination for the website based on the authentication information and a physiological situation of predetermined liveness associated with at least one movement information of the user, including neuromuscular tone from a body part of the user at a predetermined sampling frequency over a predetermined sample period; and sending the result of creating a new account associated with the website based on the liveness determination, wherein the liveness determination is performed by an independent static model including a model structure and model parameters, and the independent static model is linked to a predetermined liveness constraint. Claim 45 A method for accessing personal records comprising: sending a request message to access a website; receiving a web document that provides a user interface for generating personal records associated with the website; sending authentication information (login ID / password) to the website through the user interface; executing an independent static model including a model structure and model parameters based on the authentication information and the physiological situation of predetermined liveness associated with at least one movement information of the user, including neuromuscular tone from a body part of the user, at a predetermined sampling frequency over a predetermined sample period, in order to determine the liveness of the user, wherein the independent static model is linked to a predetermined liveness constraint; sending the result of determining the liveness of the user to the website; and receiving access to personal records associated with the website based on the liveness determination. Claim 46 A method for accessing personal records comprises receiving a request message to access a website provided by a server system; sending a web document having a user interface for accessing personal records associated with the website; receiving authentication information (login ID / password) through the user interface for the website; receiving results of a user's liveness determination for the website based on the authentication information and a physiological situation of predetermined liveness associated with at least one movement information of the user, including neuromuscular tone from a body part of the user at a predetermined sampling frequency over a predetermined sample period; and approving access to personal records associated with the website based on the liveness determination, wherein the liveness determination is performed by an independent static model including a model structure and model parameters, and the independent static model is linked to a predetermined liveness constraint. Claim 47 In Paragraph 46, the personal record is a personal health record. Claim 48 An electronic device for accessing personal records comprises: a processor; a display coupled to the processor; one or more motion sensors coupled to the processor capable of detecting physiological conditions; a power circuit coupled to the processor; a wireless transceiver coupled to the processor; a memory coupled to the processor; and a non-transient computer program product comprising instructions stored in the memory, wherein the instructions send a request message to access a website; receive a web document having a user interface for accessing personal records associated with the website; send authentication information (login ID / password) through the user interface to the website; execute an independent static model comprising a model structure and model parameters based on the authentication information and the physiological conditions of a predetermined liveness associated with at least one movement information of the user, including neuromuscular tone from a body part of the user at a predetermined sampling frequency over a predetermined sample period, in order to determine the liveness of the user; and send the result of determining the liveness of the user to the website. An electronic device configured such that the processor performs the function of receiving access to personal records associated with a website based on a liveness decision. Claim 49 In claim 48, the authentication information is an electronic device including a login identity (ID) and a password. Claim 50 A server for approving or denying access to personal records, comprising: a processor; a power circuit coupled to the processor; a memory coupled to the processor; and a non-transient computer program product including instructions stored in the memory, wherein the instructions receive a request message to access a website provided by the server system; send a web document having a user interface for accessing personal records associated with the website; receive authentication information (login ID / password) through the user interface to the website; receive results of a user's liveness determination for the website based on the received authentication information and a physiological situation of predetermined liveness associated with at least one movement information of the user, including neuromuscular tone from a body part of the user at a predetermined sampling frequency over a predetermined sample period; and the processor is configured to perform the function of approving access to personal records associated with the website based on the liveness determination, wherein the liveness determination is performed by an independent static model including a model structure and model parameters, and the independent static model is linked to a predetermined liveness constraint. Claim 51 A method comprising: generating a constraint data set associated with predetermined constraints linked to a predetermined machine situation / state; constructing independent static models based on the predetermined machine situation / state, each independent static model being linked to a specific constraint; installing a plurality of independent static models within a device comprising a processor for executing instructions and sensors to collect at least one movement information of a user, including neuromuscular tones linked to the plurality of independent static models, from a body part of the user's body at a predetermined sampling frequency over a predetermined sample period; and having the user execute one or more of the plurality of independent static models through a user interface based on sensor data detected from the user; and providing one or more results (inferences) to the user through a user interface associated with the execution of one or more of the plurality of independent static models, wherein the one or more results reflect one or more physiological situations of the user. Claim 52 A method comprising: providing a static model including a set of constraints on the user's external situation; configuring a set of static model parameters according to a static model operation mode; acquiring at least one movement information of a user including neuromuscular tone from a body part of the user's body at a predetermined sampling frequency over a predetermined sample period; suppressing signal components associated with the user's voluntary movement from the acquired at least one movement information of the user; generating a data set of mathematical expressions associated with the user regarding the user's external situation based on the static model operation mode from the at least one movement information of the user in which the signal components associated with the voluntary movement are suppressed; configuring a feature vector table including a plurality of sets of feature vectors based on the data set of mathematical expressions associated with the user; executing the static model using the feature vector table according to the static model operation mode; and generating report information regarding the external situation based on the execution result of the static model. Claim 53 In Clause 52, the static model is provided as a digital file.

Images