Wearable electronic device, user pose recognition system and method for recogniting pose of user

Abstract

The invention provides a wearable electronic device, a user posture recognition system and a method for recognizing the posture of a user. The wearable electronic device includes a sensing module configured to detect a signal associated with a posture of a user; a recognition module electrically connected to the sensing module and configured to recognize the signal as a plurality of generic markers according to a classification model, each of the plurality of generic markers corresponding to one of the poses of the user; and a configuration module electrically connected to the identification module and configured to configure the plurality of general marks into a plurality of configuration marks and output the plurality of configuration marks.

Description

Technical Field

[0001] The present invention relates to a wearable electronic device, a user posture recognition system, and a method for recognizing a user's posture. More specifically, the present invention relates to a wearable electronic device, a system, and a method for user gesture recognition.

[0002] Prior Art

[0003] In a traditional posture recognition system for recognizing a user's gesture or posture to confirm the user's intention, a classification model is used to classify signals derived from the user's gesture or posture into various predefined recognition tags. To be applicable to more usage scenarios, the recognition system may need to support more recognizable gestures or postures in the classification model. For example, if the posture recognition system needs to comply with applications in a factory scenario, a teaching scenario, or a game scenario simultaneously, the number of postures / gestures that the classification model needs to recognize may be no less than a dozen. However, simply increasing the number of recognition tags that the classification model can recognize may lead to a poor user experience. For example, due to the excessive number of gestures or postures that the classification model can recognize, the probability of misjudgment by the classification model may instead increase in a specific usage scenario.

[0004] Specifically, all the gestures or postures that a user may use may include dozens, but in a specific usage scenario, the gestures or postures that the user actually uses may be only several. To comply with different usage scenarios, the existing solution is to establish respective classification models for each specific scenario. For example, if applied in a factory scenario, a teaching scenario, or a game scenario, three different classification models are established. However, installing multiple classification models in the recognition system may result in an overly long conversion time between different classification models, and thus fail to meet the real-time requirements of the user. Moreover, each classification model needs to be trained according to a specific scenario. When the number of combinations of predefined gestures or postures is excessive, it is bound to increase the difficulty of training a specific model for each scenario. After establishing the corresponding classification model for each specific scenario, each classification model established according to a specific scenario only contains recognition tags for fewer gestures or postures. In such a case, it may also make each classification model more likely to classify predefined gestures or postures that do not conform to the scenario as gestures or postures that are significantly different from the user's current gesture or posture, resulting in a decrease in the accuracy of gesture recognition. For example, if the classification model for the game scenario is only trained to recognize four gesture recognition tags, such as "scissors", "stone", "cloth", and "other", when the user makes a "snapping fingers" gesture that is not defined in the game scenario, the classification model may recognize it as the "stone" recognition tag, rather than necessarily recognizing the "snapping fingers" gesture as the "other" recognition tag. Therefore, an improved user posture recognition system is needed to improve the above technical problems. Summary of the Invention

[0005] Embodiments of the present disclosure provide a wearable electronic device. The wearable electronic device includes: a sensing module configured to detect a signal associated with a user's posture; an identification module electrically connected to the sensing module and configured to identify the signal as a plurality of general markers according to a classification model, each of the plurality of general markers corresponding to one of the postures of the user; and a configuration module electrically connected to the identification module and configured to configure the plurality of general markers as a plurality of configuration markers and output the plurality of configuration markers.

[0006] Embodiments of the present disclosure provide a user posture identification system. The user posture identification system includes: an identification module configured to identify a signal from a user as a plurality of general markers representing a plurality of gesture patterns of the user according to a classification model; and a configuration module configured to configure the plurality of general markers as a plurality of configuration markers based on a fuzzy judgment algorithm.

[0007] Embodiments of the present disclosure provide a method for identifying a user's posture. The method includes: detecting, by a sensing module, a signal associated with a user's posture; identifying, by an identification module, the signal as a plurality of general markers representing the user's posture, wherein each of the plurality of general markers corresponds to one of the postures of the user; and configuring, by a configuration module, the plurality of general markers as a plurality of configuration markers.

[0008] Embodiments of the present disclosure provide a user posture identification system, which at least includes an identification module and a configuration module. The identification module can identify a variety of general identification markers, and the configuration module further configures / maps the identified general identification markers as specific configuration identification markers according to corresponding rule logics in response to different usage scenarios. In this way, there is no need to establish corresponding classification models for each specific scenario, the time required for switching between different classification models can be saved, and the user experience of the user posture identification system can be improved. The identification module can accurately distinguish postures / gestures, and then use the configuration module to further configure / map the general identification markers identified by the identification module as fewer configuration identification markers required for a specific usage scenario, thereby improving both the identifiable postures / gestures and the identification accuracy. For example, if only four gesture identification markers such as "scissors", "stone", "cloth", and "others" are required for the required usage scenario, when the user makes a "snap" gesture, the classification model of the identification module can clearly identify it as a "snap" identification marker, rather than misidentifying it as a "stone" identification marker. Subsequently, the "snap" identification marker is configured as an "other" identification marker through the configuration module.

[0009] Brief Description of the Drawings

[0010] As will be best understood from the following embodiments when read in conjunction with the accompanying drawings, aspects of some embodiments of the present invention are best understood. It should be noted that the various structures may not be drawn to scale, and the dimensions of the various structures may be arbitrarily increased or decreased for clarity of discussion.

[0011] Figure 1 A schematic diagram showing a usage scenario according to some embodiments of the present invention.

[0012] Figure 2 A system architecture diagram showing a user posture recognition system according to some embodiments of the present invention.

[0013] Figure 3 A flowchart showing a user posture recognition system according to some embodiments of the present invention.

[0014] Figure 4 A configuration schematic diagram showing a configuration module according to some embodiments of the present invention.

[0015] Figure 5A 、 5B And 5C show a schematic diagram of a general marker configured as a configuration marker according to some embodiments of the present invention.

[0016] Figure 6A A flowchart showing a method for recognizing a user's posture according to some embodiments of the present invention.

[0017] Figure 6B A flowchart showing a method for recognizing a user's posture according to some embodiments of the present invention.

[0018] Figure 7 A schematic diagram showing a wearable electronic device according to some embodiments of the present invention.

[0019] Figure 8 A schematic diagram showing an arithmetic device according to some embodiments of the present invention.

[0020] Figures 9A - 9B 、10A-10B, 11A-11B, 12A-12B, 13A-13B, 14A-14B, 15A-15B, 16A-16B and 17A-17B show schematic diagrams of gesture patterns according to some embodiments of the present invention.

[0021] Common reference numerals are used throughout the drawings and the embodiments to indicate the same or similar components. The embodiments of the present invention will be readily understood from the following detailed description in conjunction with the accompanying drawings.

[0022] Embodiments

[0023] In the following description, numerous specific details are set forth to provide a thorough understanding of the embodiments. However, those skilled in the art will recognize that the techniques described herein may be practiced without one or more of the specific details or may be practiced using other methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring certain aspects. For example, in the description, a first operation that is performed before or after a second operation may include embodiments in which the first operation and the second operation are performed together, and may also include embodiments in which additional operations may be performed between the first operation and the second operation. For example, in the following description, the formation of a first feature above, on, or in a second feature may include embodiments in which the first feature and the second feature are formed in direct contact, and may also include embodiments in which additional features may be formed between the first feature and the second feature such that the first feature and the second feature are not in direct contact. Additionally, the present disclosure may repeat reference numerals and / or letters in various instances. This repetition is for the purpose of simplicity and clarity, and does not in itself indicate a relationship between the various embodiments and / or configurations discussed.

[0024] For purposes of ease of description, relative time terms such as "before", "prior to", "after", "subsequent to", and the like may be used herein to describe the relationship of one operation or feature to another operation or feature as illustrated in the figures. Relative time terms are intended to encompass different sequences of the operations depicted in the figures. Additionally, for ease of description, spatial relative terms such as "beneath", "below", "lower", "above", "upper", and the like may be used herein to describe the relationship of one component or feature to another component or feature as illustrated in the figures. Spatial relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. The device may be oriented in other ways (rotated 90 degrees or in other orientations), and the spatial relative descriptors used herein may be interpreted accordingly. For ease of description, relative terms for connection such as "connect", "connected", "connection", "couple", "coupled", "communicate", and the like may be used herein to describe an operation of connecting, coupling, or linking between two components or features. Relative terms for connection are intended to encompass different connections, couplings, or linkages of the devices or components. The devices or components may be directly or indirectly connected, coupled, or linked to each other, for example, via another set of components. The devices or components may be connected, coupled, or linked to each other in wired and / or wireless manners.

[0025] As used herein, unless the context clearly indicates otherwise, the singular terms "a" and "the" may include plural referents. For example, a reference to a device may include a plurality of devices unless the context clearly indicates otherwise. The terms "comprising" and "including" may indicate the presence of the described features, integers, steps, operations, components, and / or groups of components, but do not preclude the presence of one or more combinations of features, integers, steps, operations, components, and / or groups of components. The term "and / or" may include any and all combinations of one or more of the listed items.

[0026] In addition, quantities, ratios, and other numerical values are sometimes presented herein in a range format. It should be understood that such range formats are used for convenience and brevity and should be interpreted flexibly as including not only the explicitly specified numerical values that are range limits, but also all individual numerical values or sub-ranges subsumed within that range as if each numerical value and sub-range were explicitly specified.

[0027] The nature and use of the embodiments are discussed in detail below. However, it should be understood that the present disclosure provides many applicable inventive concepts that can be embodied in a variety of specific situations. The specific embodiments discussed merely illustrate specific ways of embodying and using the present disclosure and do not limit its scope.

[0028] Figure 1 A schematic diagram showing a usage scenario 1 according to some embodiments of the present invention. Refer to Figure 1 , usage scenario 1 includes a user 11 wearing a wearable electronic device 12, a display 13, and a computing device 14.

[0029] In some embodiments, the wearable electronic device 12 can detect the posture of the user 11. In some embodiments, the posture of the user can include static postures and dynamic movements. For example, static postures can include sitting postures, standing postures, hand postures (static gestures), etc., while dynamic postures can include head movements (such as turning the head, nodding, leaning back, etc.), hand movements (dynamic gestures), foot movements (such as stepping, striding, walking, jumping, etc.), etc. The "gesture" referred to herein can be a static gesture or a dynamic gesture.

[0030] In some embodiments, the wearable electronic device 12 can detect the gestures, sitting postures, foot steps, etc. of the user 11. For example, the wearable electronic device 12 can be a bracelet that can detect signals associated with the hand movements (such as gestures) of the user. The user 11 can wear the wearable electronic device 12 on their right hand, that is, the wearable electronic device 12 can detect signals associated with the posture of the user 11 from the right hand of the user 11.

[0031] In some embodiments, the wearable electronic device 12 can be worn on the wrist of the user 11. The position where the wearable electronic device 12 is worn is generally consistent with the position of wearing a watch, that is, at the forearm near the wrist joint, at the plane formed by the ulna and the radius. Since there is a relatively flat contact surface at the bifurcation of the extensor digitorum muscle behind the ulna, the wearable electronic device 12 can be firmly attached to the muscle at the bifurcation of the extensor digitorum muscle behind the ulna. In this way, the user can easily fix the wearable electronic device 12 on the wrist and facilitate wearing.

[0032] In some embodiments, the wearable electronic device 12 can detect signals associated with the posture of the user 11 from the user's wrist. For example, the signal associated with the posture of the user 11 can be an electromyogram (EMG) or a mechanomyogram (MMG). In some embodiments, the wearable electronic device 12 can continuously detect signals associated with the posture of the user 11. In another embodiment, the wearable electronic device 12 can detect at a predefined frequency. The wearable electronic device 12 can be firmly worn on the user's wrist, so that the sensors therein can detect electromyogram or mechanomyogram signals when the user makes a specific gesture and the muscles around the wrist actuate. In some embodiments, the sensors of the wearable electronic device 12 can include a gyroscope, an accelerometer, a signal sensor, or other suitable sensors. In some embodiments, the wearable electronic device 12 can use an Inertial Measurement Unit (IMU) to measure acceleration and angular velocity, and then estimate the user's posture.

[0033] Similarly, when the wearable electronic device is worn on other parts of the user, it can detect signals associated with the user's posture in a similar or different way, and then analyze and determine the user's posture. For example, the wearable electronic device 12 can be an ankle bracelet (not shown), worn on the user's ankle to detect signals associated with the user's foot movements (such as, foot movement or jumping movement, etc.). In other embodiments, the wearable electronic device 12 can be a necklace (not shown), worn on the user's neck to detect signals associated with the user's neck movements (such as, neck rotation, etc.). In other embodiments, the wearable electronic device 12 can be a headband (not shown), worn on the user's head to detect signals associated with the user's head movements (such as, nodding or shaking the head, etc.).

[0034] The display 13 can be a television, a smart TV, a computer screen, a tablet computer, or other display screen. The computing device 14 can be a server computer, a client computer, a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), or a smart phone. In some embodiments, the display 13 can be coupled to the computing device 14. In one embodiment, the computing device 14 can be integrated inside the display 13. In one embodiment, the computing device 14 can be disposed outside the display 13. In some embodiments, the display 13 can be an output of the computing device 14. For example, the computing device 14 can execute program instructions and output content to the display 13.

[0035] In some embodiments, the wearable electronic device 12 can be communicatively connected to the computing device 14. The wearable electronic device 12 can be connected to the computing device 14 either wired or wirelessly. In some embodiments, the wearable electronic device 12 and the computing device 14 cooperate to determine the posture of the user 11, and use the recognized user 11 posture (recognition mark) as an input command to control the computing device 14. For example, the user 11 can control the operation of the computing device 14 by making different postures (gestures), and the content displayed on the display 13 changes accordingly according to the operation of the computing device 14. That is to say, the user 11 can control the content displayed on the display 13 by detecting the posture of the user 11 through the wearable electronic device 12.

[0036] In some embodiments, the display 13 displays one or more objects 131 and 132 and a cursor 133. For example, the object 131 can be a table, and the object 132 can be a square or a sphere placed on the table. The cursor 133 can move in response to a signal representing the posture (or gesture) of the user 11 detected by the wearable electronic device 12. That is, the user 11 can control the cursor 133 by changing the position of the wearable electronic device 12 (for example, changing the position of the hand). In some embodiments, the user 11 can perform actions such as clicking, calling up a menu, swiping a menu, previous, next, previous page, next page, tapping the object 131, grabbing the object 132, throwing the object 132, rotating the object 132, etc. by changing the posture (gesture). The actions listed here are only examples, and the present invention is not limited thereto.

[0037] In some embodiments, the wearable electronic device 12 can independently determine the posture of the user 11, and use the recognized posture of the user 11 (recognition mark) as an input command to control the computing device 14. In some embodiments, the wearable electronic device 12 may include a module with computing functions. In this way, the wearable electronic device 12 can partially process the detected original signal associated with the user 11's posture and transmit the processed signal to the computing device 14. The computing device 14 can further process the signal or perform operations according to the received signal.

[0038] In some embodiments, the wearable electronic device 12 can process the original signal associated with the user 11's posture, thereby obtaining a recognized specific gesture pattern (recognition mark), and transmitting the specific gesture pattern to the computing device 14. In some embodiments, the gesture pattern may include recognized static gestures and dynamic gestures. The computing device 14 can perform corresponding operations according to the received gesture pattern.

[0039] In some embodiments, the wearable electronic device 12 can directly transmit the original signal associated with the user 11's posture to the computing device 14, and the various modules in the computing device 14 perform signal processing and recognition, thereby obtaining a specific gesture pattern (recognition mark). The computing device 14 can perform corresponding operations in response to the specific gesture pattern.

[0040] Figure 2 The system architecture diagram of the user posture recognition system 2 according to some embodiments of the present invention is shown. As Figure 2 shown, the user posture recognition system 2 includes a sensing module 21, a signal filtering module 22, a recognition module 23, a configuration module 24, and a communication module 25. In some embodiments, the above-mentioned modules may be included in a wearable electronic device (such as Figure 1 the wearable electronic device 12). For example, all modules are set in a chip and set on the wearable electronic device. In another embodiment, the modules can also be set in two or more different devices. For example, some modules (referred to as group A) can be set in a wearable electronic device (such as Figure 1 the wearable electronic device 12), and other modules (referred to as group B) are set in a computer or other computing device (such as Figure 1 the computing device 14). The signal / data processed by the modules in group A can be transmitted to the modules in group B for subsequent processing. In some embodiments, the wearable electronic device at least includes the sensing module 21. In some embodiments, the wearable electronic device may include the sensing module 21 and the signal filtering module 22.

[0041] In some embodiments, the sensing module 21 may be configured to detect signals associated with the user's posture. The postures of the user detected by the sensing module 21 may include gestures, sitting postures, footsteps, etc. For example, the sensing module 21 may be installed on a bracelet to detect signals associated with the user's hand movements (such as gestures). In one embodiment, the sensing module 21 may be installed on an ankle bracelet to detect signals associated with the user's foot movements (such as foot movement or jumping movements, etc.). In some embodiments, the postures of the wearer (user) may be detected jointly or independently by one or more wearable electronic devices including the sensing module 21.

[0042] In some embodiments, the sensing module 21 may detect signals (such as myoelectric signals) associated with the user's posture from the user's wrist. The sensing module 21 may continuously detect signals associated with the user's posture, but the present invention is not limited thereto. In another embodiment, the sensing module 21 may detect at a predefined frequency.

[0043] In some embodiments, the sensing module 21 may continuously detect target myoelectric signals from the muscles around the user's wrist using a specific sampling frequency. The sensing module 21 may use a lower sampling frequency to detect myoelectric signals. For example, the sensing module 21 may use a sampling frequency of about 200 Hz. Since the sensing module 21 uses a lower sampling frequency, it also has lower power consumption, thereby effectively reducing the power consumption of the wearable electronic device.

[0044] Since the wearable electronic device can be stably worn on the user's wrist, the sensing module 21 provided on the wearable electronic device can surely contact the skin at the plane formed by the ulna and the radius. When the user makes a gesture, the sensing module 21 can stably detect myoelectric signals when the wrist flexor and wrist extensor muscles that control wrist flexion and extension and / or the finger flexor and finger extensor muscles that control each finger act. Therefore, the wearable electronic device provided with the sensing module 21 can effectively detect myoelectric signals from the user's wrist. Similarly, if the wearable electronic device is worn on other parts of the user, myoelectric signals of the user can be detected in a similar manner, and then the user's posture can be analyzed and determined.

[0045] In some embodiments, the signal filtering module 22 may be electrically connected to the sensing module 21. The signal filtering module 22 may receive and filter out the noise in the signals associated with the user's posture detected by the sensing module 21. The signal filtering module 22 may include a band-pass filter, a high-pass filter, or a low-pass filter. For example, the signal filtering module 22 may filter out the noise of the myoelectric signals detected by the sensing module 21.

[0046] In some embodiments, the signal filtering module 22 and the sensing module 21 may be disposed in different devices, and the signal filtering module 22 may communicate with the sensing module 21 in a wired or wireless manner. In this way, the signal filtering module 22 can receive the signals detected by the sensing module 21 that are associated with the user's posture and filter out the noise therein. Filtering out the noise by the signal filtering module 22 can improve the recognition accuracy of subsequent user postures (recognition marks).

[0047] In another embodiment, the signal filtering module 22 may perform noise reduction, rectification, and / or amplification on the signals associated with the user's posture. The signal filtering module 22 can perform preliminary processing on the signals associated with the user's posture to facilitate the recognition accuracy of subsequent user postures (recognition marks).

[0048] The recognition module 23 may be electrically connected to the sensing module 21. In some embodiments, the recognition module 23 may be connected to the sensing module 21 through the signal filtering module 22 to receive the signals associated with the user's posture that have been filtered out of noise. In some embodiments, the recognition module 23 and the sensing module 21 may be disposed in different devices, and the recognition module 23 may communicate with the sensing module 21 in a wired or wireless manner. In some embodiments, the recognition module 23 may be directly communicatively connected to the sensing module 21.

[0049] The recognition module 23 is configured to identify / classify the signals associated with the user's posture into general recognition marks (or general marks) according to a classification model. In some embodiments, the general marks correspond to gesture patterns. That is to say, the general marks represent different gestures of the user. For example, the recognition module 23 may identify the signals associated with the user's posture as the user's gestures. The classification model used by the recognition module 23 may be a posture classification model. In some embodiments, the classification model used by the recognition module 23 may be a gesture classification model, that is, a gesture classification model obtained by training with gesture feature data. The recognition module 23 may classify the signals associated with the user's posture according to the classification model and determine which general mark (i.e., predefined posture or gesture) the signal corresponds to based on the classification result.

[0050] The recognition module 23 can perform recognition based on a trained posture classification model or gesture classification model. When performing recognition, the recognition module 23 is based on the classification model. The classification model can be established before the recognition module 23 performs recognition. In some embodiments, relevant data of the classification model can be written into the recognition module 23, and the classification model is trained with a sufficient number of specific posture feature data or gesture feature data as input, so as to establish a trained classification model in the recognition module 23. For example, the recognition module 23 can use classification algorithms of machine learning such as K Nearest Neighbor (KNN), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA), and use the posture training feature data or gesture training feature data as training data to input into the classification algorithms of machine learning, so as to generate a posture classification model or a gesture classification model. The manner in which the recognition module 23 generates a posture classification model or a gesture classification model is not limited to the above. In some embodiments, the training process of the classification model can be omitted, and the recognition module 23 can directly store and apply a trained classification model.

[0051] After the gesture classification model or the posture classification model is established, the recognition module 23 can start recognition based on the trained classification model. In some embodiments, the recognition module 23 can identify a signal associated with the user's posture as a plurality of general markers according to the classification model. The recognition module 23 can identify a signal associated with the user's gesture as a plurality of general markers (i.e., gesture patterns) according to the gesture classification model. The gesture pattern is a gesture predefined in the recognition module 23, and it can use a general recognition marker as a label. In some embodiments, the gesture classification model can recognize gesture patterns such as finger snapping, index finger and thumb tapping, palm grasping, palm opening, etc. (see Figures 9A - 17B ).

[0052] The configuration and operation of the configuration module 24 will be described in the following paragraphs with reference to Figure 3 , Figure 4 , and Figures 5A - 5C .

[0053] The user posture recognition system 2 can further include a communication module 25. The communication module 25 can be electrically connected to the recognition module 23 and the configuration module 24. In some embodiments, the communication module 25 is configured to transmit the configuration marker RM output by the configuration module 24 to a remote computing device. In one embodiment, each module of the user posture recognition system 2 can be included in a wearable electronic device and communicatively connected to another device (such as Figure 1 's computing device 14) through the communication module 25. The other device can be a computer, a remote electronic device, or other computing devices.

[0054] In another embodiment, the wearable electronic device at least includes a sensing module 21 and a communication module 25, while the signal filtering module 22, the identification module 23, and the configuration module 24 are disposed in another computing device (such as Figure 1 the computing device 14). The sensing module 21 can be communicatively connected to the modules in another computing device through the communication module 25, and then transmit the signal associated with the user's gesture detected by the sensing module 21 to another computing device for subsequent operations.

[0055] Figure 3 FIG. 3 illustrates a process of a user gesture recognition system according to some embodiments of the present invention. Process 3 describes the operation processes of the identification module 23 and the configuration module 24 in the Figure 2 user gesture recognition system 2. For the sake of clear illustration, Figure 3 the related operation processes of the sensing module 21, the signal filtering module 22, and the communication module 25 are omitted.

[0056] Referring to Figure 3 , the identification module 23 can receive a signal 31 associated with the user's gesture. The identification module 23 can identify / classify the signal 31 associated with the user's gesture as a general marker GM according to a classification model.

[0057] In some embodiments, the configuration module 24 can be electrically connected to the identification module 23. The configuration module 24 can receive the general marker GM identified by the identification module 23 from the identification module 23. In some embodiments, the configuration module 24 can be configured to configure the general marker GM as a configured identification marker (hereinafter referred to as a configuration marker) RM and output the configuration marker RM. In some embodiments, the configuration module 24 can configure the general marker GM as a configuration marker RM according to a context selection signal SS. In some embodiments, the configuration marker RM can correspond to a predefined gesture pattern. More specifically, the configuration marker RM can represent a predefined gesture pattern in a specific usage context. For example, the context selection signal SS can provide information indicating different contexts such as "factory application context", "teaching application context", or "game application context" to the configuration module 24, and the configuration module 24 thus configures the general marker GM differently according to different contexts (see Figure 5A , 5B , and 5C).

[0058] In some embodiments, according to the context selection signal SS, the configuration module 24 further configures the general marker GM as the configuration marker RM based on a fuzzy judgment algorithm. For example, the configuration module 24 can configure different general markers GM as the same configuration marker RM. In some embodiments, the configuration module 24 can configure two different but similar general markers (gestures) GM as the same configuration marker RM. In some embodiments, the configuration module 24 can judge the similarity of the general marker GM based on a fuzzy judgment algorithm. In another embodiment, the configuration module 24 can perform configuration based on predefined rule logic. For example, the predefined rule logic can be obtained by statistical analysis. In some embodiments, the rule logic of the configuration module 24 can be obtained by machine learning.

[0059] In some embodiments, each general marker GM corresponds to only one configuration marker RM. Conversely, each configuration marker RM can correspond to one or more general markers GM. The number of general markers GM is different from the number of configuration markers RM. In some embodiments, the number of general markers GM is greater than the number of configuration markers RM.

[0060] Figure 4 Illustrate a schematic diagram of the configuration concept of the configuration module 24 according to some embodiments of the present invention. Refer to Figure 4 In the illustrated embodiment, the general marker GM can include nine general markers G1 to G9, and the configuration marker RM can include four configuration markers R1 to R4. That is, the number of general markers GM is greater than the number of configuration markers RM. The configuration module 24 can configure each of the general markers G1 to G9 as one of the configuration markers R1 to R4. As described above, the configuration module 24 can select the signal SS according to the context and perform configuration using the predefined rule logic. Although Figure 4 the general marker GM drawn in includes nine general markers, the present invention is not limited thereto, and the general marker GM can include more or fewer general markers. Although Figure 4 the configuration marker RM drawn in includes four configuration markers, the present invention is not limited thereto, and the configuration marker RM can include more or fewer general markers.

[0061] Figure 5A , Figure 5B and Figure 5C Illustrate a schematic diagram of the general marker GM configured as the configuration marker RM according to some embodiments of the present invention. Figure 5A , Figure 5B and Figure 5C are embodiments configured according to the configuration module 24 shown in Figure 4 . Figure 5A , Figure 5B and Figure 5C can correspond to embodiments in which the general marker GM is configured as the configuration marker RM in different situations.

[0062] Figure 5A A schematic diagram showing that in usage scenario A, the general marker GM is configured as the configuration marker RM. Refer to Figure 5A , the configuration module 24 can configure the general marker G1 as the configuration marker R1. The general marker G2 can be configured as the configuration marker R2. The general marker G3 can be configured as R3. The general markers G4 - G9 can be configured as R4. In some embodiments, the configuration module 24 can perform the configuration based on predefined rule logic. In some embodiments, the configuration module 24 can configure the configuration marker RM based on a fuzzy judgment algorithm. For example, configure the general markers G4 - G9 as the configuration marker R4 based on the fuzzy judgment algorithm.

[0063] In some embodiments, the general marker G1 only corresponds to the configuration marker R1. The general marker G2 only corresponds to the configuration marker R2. The general marker G3 only corresponds to the configuration marker R3. The general markers G4 - G9 only correspond to the configuration marker R4. In some embodiments, the configuration marker R4 can correspond to the general markers G4 - G9.

[0064] In some embodiments, each of the configuration markers R1, R2, R3, and R4 can correspond to a subset of the general marker GM. For example, the configuration marker R1 corresponds to the general marker G1. The configuration marker R2 corresponds to the general marker G2. The configuration marker R3 corresponds to the general marker G3. The configuration marker R4 corresponds to multiple general markers G4 - G9.

[0065] Figure 5B A schematic diagram showing that in usage scenario B, the general marker GM is configured as the configuration marker RM. Refer to Figure 5B, the configuration module 24 may configure the general tags G1 and G2 as the configuration tag R1. The general tags G3, G4 and G5 may be configured as the configuration tag R2. The general tag G6 may be configured as R3. The general tags G7, G8 and G9 may be configured as R4. In some embodiments, the configuration module 24 may configure the configuration tag RM based on the fuzzy judgment algorithm. For example, the general tags G1 and G2 are configured as the configuration tag R1 based on the fuzzy judgment algorithm. In some embodiments, the general tag G1 is similar to the general tag G2. In some embodiments, the posture / gesture represented by the general tag G1 is similar to the posture / gesture represented by the general tag G2. In one embodiment, the configuration module 24 may configure the general tags G3, G4 and G5 as the configuration tag R2 based on the fuzzy judgment algorithm. The general tags G3, G4 and G5 may correspond to similar postures / gestures. In one embodiment, the configuration module 24 may configure the general tags G7, G8 and G9 as the configuration tag R4 based on the fuzzy judgment algorithm. The general tags G7, G8 and G9 may correspond to similar postures / gestures. In another embodiment, the general tags G7, G8, and G9 that are not needed in this context may be classified as “others.” In this embodiment, the postures / gestures represented by the general tags G7, G8, and G9 may not be similar to each other.

[0066] In some embodiments, general marks G1 and G2 correspond only to configuration mark R1. In some embodiments, general marks G3, G4, and G5 correspond only to configuration mark R2. General mark G6 corresponds only to configuration mark R3. General marks G7, G8, and G9 correspond only to configuration mark R4.

[0067] In some embodiments, each configuration mark R1, R2, R3 and R4 may correspond to a subset of the marks GM. For example, configuration mark R1 corresponds to general marks G1 and G2. Configuration mark R2 corresponds to general marks G3, G4 and G5. Configuration mark R3 corresponds to general mark G6. Configuration mark R4 corresponds to general marks G7, G8 and G9.

[0068] Figure 5C FIG. 1 is a schematic diagram showing a general marker GM configured as a configuration marker RM in a usage scenario C. Figure 5C , the configuration module 24 can configure the general marks G1 and G2 as the configuration mark R1. The general mark G3 can be configured as the configuration mark R2. The general mark G4 can be configured as R3. The general marks G5, G6, G7, G8 and G9 can be configured as R4.

[0069] In some embodiments, general marks G1 and G2 correspond only to configuration mark R1. General mark G3 corresponds only to configuration mark R2. General mark G4 corresponds only to configuration mark R3. General marks G5, G6, G7, G8, and G9 correspond only to configuration mark R4.

[0070] In some embodiments, each of the configuration tags R1, R2, R3, and R4 may correspond to a subset of the general tag GM. For example, the configuration tag R1 corresponds to the general tags G1 and G2. The configuration tag R2 corresponds to the general tag G3. The configuration tag R3 corresponds to the general tag G4. The configuration tag R4 corresponds to the general tags G5, G6, G7, G8, and G9.

[0071] The user posture recognition system 2 can recognize a variety of general tags GM through the recognition module 23, and further configure / map the recognized general tags GM to specific configuration tags RM according to different usage scenarios by using the configuration module 24. In this way, there is no need to establish different models for different usage scenarios, and the time required for switching between different classification models can be saved, making the user experience of the user posture recognition system 2 better. Moreover, since the recognition module 23 can accurately distinguish different detailed postures / gestures, and then use the configuration module 24 to configure fewer configuration tags required for specific usage scenarios, such a recognition method can improve the recognition accuracy. For example, if the required usage scenario only needs four gesture recognition tags such as "scissors", "rock", "paper", and "other", when the user makes a "snap" gesture, the classification model of the recognition module 23 can recognize it as the "snap" recognition tag, rather than misrecognizing it as the "rock" recognition tag. Subsequently, the "snap" recognition tag is configured as the "other" recognition tag through the configuration module 24.

[0072] Figure 6A The flowchart of a method for recognizing a user's posture according to some embodiments of the present invention is shown. This method can be performed by Figure 2 the user posture recognition system 2 shown. Figure 6A The method can be an implementation manner in which each module of the user posture recognition system 2 is included in a wearable electronic device.

[0073] In operation 61, the sensing module 21 detects a signal associated with the user's posture. The user postures detected by the sensing module 21 may include gestures, sitting postures, footsteps, etc. For example, the sensing module 21 can be installed on a bracelet to detect signals associated with the user's hand movements (such as gestures). In some embodiments, the sensing module 21 can detect from the user's wrist. The sensing module 21 can continuously detect target myoelectric signals from the muscles around the user's wrist using a specific sampling frequency.

[0074] In operation 62, the signal filtering module 22 filters the noise in the signal associated with the user's gesture. In some embodiments, the signal filtering module 22 may be electrically connected to the sensing module 21 to receive and filter the noise in the signal detected by the sensing module 21 and associated with the user's gesture. For example, the signal filtering module 22 may filter the noise in the myoelectric signal detected by the sensing module 21 of the user.

[0075] In operation 63, the identification module 23 identifies the signal as a plurality of general markers GM according to a classification model, wherein each of the plurality of general markers GM corresponds to one of the user's gestures. In some embodiments, the identification module 23 may be connected to the sensing module 21 through the signal filtering module 22 to receive the signal associated with the user's gesture with the noise filtered out. The identification module 23 is configured to identify / classify the signal associated with the user's gesture as a general marker GM according to a classification model. In some embodiments, the general marker GM corresponds to a gesture pattern.

[0076] In operation 64, the configuration module 24 configures the plurality of general markers GM as a plurality of configuration markers RM. In some embodiments, the configuration module 24 may be electrically connected to the identification module 23. In some embodiments, the configuration module 24 may be configured to configure the general marker GM as a configuration marker RM based on a predefined rule logic. Each of the general markers GM corresponds to only one of the configuration markers RM. In some embodiments, the configuration module 24 may configure a first general marker and a second general marker as a first configuration marker based on a fuzzy judgment algorithm. In different usage scenarios, the configuration module 24 may correspondingly use different configuration logics to configure the same configuration marker GM as different configuration markers RM.

[0077] In operation 65, the communication module 25 transmits the plurality of configuration markers RM to a remote electronic device. In some embodiments, the communication module 25 may be communicatively connected to another device to transmit the configuration marker to the another device. The another device may be a computer, a remote electronic device, or other computing devices. In some embodiments, Figure 1 the wearable electronic device 12 may include the communication module 25 to wirelessly transmit the configuration marker RM to a computing device 14 outside the wearable electronic device 12. The computing device 14 may be located remotely from the wearable electronic device 12.

[0078] Figure 6B FIG. shows a flowchart of a method for identifying a user's gesture according to some embodiments of the present invention. This method may be performed by Figure 2 the user gesture identification system 2. Figure 6BThe implementation aspect shown by the method is jointly operated by the wearable electronic device and the computing device included in the user posture recognition system 2. In some embodiments, the wearable electronic device at least includes a sensing module 21 and a communication module 25 (or communication interface). The computing device may at least include an identification module 23 and a configuration module 24. In some embodiments, the signal filtering module 22 may be selectively included in the wearable electronic device or the computing device. In some embodiments, the user posture recognition system 2 can be applied to Figure 1 the scenario where, that is, the user posture recognition system 2 can include a wearable electronic device 12 and a computing device 14.

[0079] In operation 61', signals associated with the user's posture are detected by the sensors of the wearable electronic device. In some embodiments, the sensors can be disposed within the wearable electronic device and include the sensing module 21. The user postures detected by the sensing module 21 can include gestures, sitting postures, footsteps, etc. For example, the sensing module 21 can be installed on a bracelet to detect signals (such as gestures) associated with the user's hand movements. In some embodiments, the sensing module 21 can detect myoelectric signals from the user's wrist. The sensing module 21 can continuously detect target myoelectric signals from the muscles around the user's wrist using a specific sampling frequency.

[0080] In operation 62', the signals associated with the user's posture are transmitted to a remote computing device by the communication interface of the wearable electronic device. The sensing module 21 can be electrically connected to the communication module 25 (or communication interface). The sensing module 21 can communicate with the modules in the computing device through the communication module 25, and then transmit the signals associated with the user's posture detected by the sensing module 21 to the computing device. In some embodiments, the communication module 25 can transmit the original signals associated with the user's posture to the computing device. In another embodiment, the communication module 25 can transmit the preliminarily processed signals to the computing device.

[0081] In operation 63', the noise in the signals associated with the user's posture is filtered by the signal filtering module of the remote computing device. In some embodiments, the signal filtering module 22 can receive the signals associated with the user's posture detected by the sensing module 21 and filter out the noise therein. For example, the noise in the myoelectric signals detected by the sensing module 21 can be filtered by the signal filtering module 22.

[0082] In operation 64', the identification module of the remote computing device identifies the signal as a plurality of general markers according to a classification model, wherein each of the plurality of general markers corresponds to one of the postures of the user. In some embodiments, the identification module 23 may be connected to the signal filtering module 22 to receive the signal associated with the user posture with noise filtered out. The identification module 23 is configured to identify / classify the signal associated with the user posture as a general marker GM according to the classification model. In some embodiments, the general marker GM may correspond to a gesture pattern.

[0083] In operation 65', the configuration module of the remote computing device configures the plurality of general markers as a plurality of configuration markers. In some embodiments, the configuration module 24 may be electrically connected to the identification module 23. In some embodiments, the configuration module 24 may be configured to configure the general marker GM as a configuration marker RM. Each of the general markers GM corresponds to only one of the configuration markers RM. In some embodiments, the configuration module 24 may configure a first general marker and a second general marker as a first configuration marker based on a fuzzy judgment algorithm. In some embodiments, in different scenarios, the configuration module 24 may configure the same configuration marker GM as different configuration markers RM.

[0084] Figure 7 A schematic diagram of a wearable electronic device 70 according to some embodiments of the present invention is shown. In some embodiments, the wearable electronic device 70 may be Figure 1 an embodiment of the wearable electronic device 12. In some embodiments, the wearable electronic device 70 may be applied to Figure 2 the user posture identification system 2. Referring to Figure 7 , the wearable electronic device 70 may include a computing device 71, a sensor 72, and a communication interface 73.

[0085] The sensor 72 may include Figure 2 the sensing module 21, which is configured to detect a signal associated with the user's posture. The sensor 72 may detect the user's gestures, sitting postures, footsteps, etc. For example, if the wearable electronic device 70 is a bracelet, the sensor 72 may detect a signal associated with the user's hand movement. In some embodiments, the user's posture may be detected jointly or independently by one or more wearable electronic devices.

[0086] In some embodiments, the sensor 72 can detect myoelectric signals from the user's wrist. The sensor 72 on the wearable electronic device can be in contact with the skin at the wrist. When the user makes a gesture, the sensor 72 can stably detect myoelectric signals when the muscles controlling the wrist and / or individual fingers are actuated. Similarly, if the wearable electronic device is worn on other parts of the user, signals associated with the user's posture can be detected in a similar manner, and then the user's posture can be analyzed and determined. In some embodiments, the sensor 72 can include a gyroscope, an accelerometer, a telecommunication signal sensor, or other suitable sensors.

[0087] In some embodiments, the computing device 71 can include a processor, an input / output interface, a memory, and the like. The computing device 71 can include one or more modules as Figure 2 disclosed. In some embodiments, the computing device 71 can at least include an identification module 23 and a configuration module 24. In some embodiments, the computing device 71 can be electrically connected to the sensor 72. The computing device 71 can receive the signals associated with the user's posture detected by the sensor 72 and process the signals. In some embodiments, the identification module 23 of the computing device 71 can be configured to identify / classify the signals associated with the user's posture as a general marker GM according to a classification model. In some embodiments, the configuration module 24 can be configured to configure the general marker GM as a configuration marker RM.

[0088] The communication interface 73 can include a communication module 25 as Figure 2 disclosed. In some embodiments, the communication interface 73 can be electrically connected to the computing device 71. In some embodiments, the communication interface 73 can output / transmit the configuration marker RM generated by the computing device 71 to other computing devices (such as Figure 1 the computing device 14).

[0089] Figure 8 FIG. shows a schematic diagram of a computing device 80 according to some embodiments of the present invention. In some embodiments, the computing device 80 can be Figure 1 the computing device 14. In some embodiments, the computing device 80 can be applied to Figure 2 the user posture identification system 2.

[0090] The computing device 80 may be capable of executing one or more programs, operations, or methods of the present invention. The computing device 80 may be a server computer, a client computer, a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a cellular phone, or a smart phone. The computing device 80 includes a processor 81, an input / output interface 82, a communication interface 83, and a memory 84. The input / output interface 82 is coupled to the processor 81. The input / output interface 82 may allow a user to manipulate the computing device 80 to execute the programs, operations, or methods of the present invention. In some embodiments, the input / output interface 82 may include a display. The communication interface 83 is coupled to the processor 81. The communication interface 83 allows the computing device 80 to communicate with other devices external to the computing device 80, such as receiving or transmitting data including images and / or any basic features. In some embodiments, the communication interface 83 may support one or more of the following protocols: Universal Serial Bus (USB), Ethernet, Bluetooth, IEEE 802.11, 3GPP Long Term Evolution (LTE) (4G), and 3GPP New Radio (5G). The memory 84 may be a non-transitory computer-readable storage medium. The memory 84 is coupled to the processor 81. The memory 84 stores program instructions executable by one or more processors (e.g., the processor 81). In some embodiments, the memory 84 stores a classification model or algorithm executable by one or more processors (e.g., the processor 81). For example, when executing the program instructions stored on the memory 84, the processor 81 is caused to execute one or more programs, operations, or methods disclosed in the present invention.

[0091] Figures 9A - 9B A schematic diagram showing a gesture pattern according to some embodiments of the present invention. Figure 9A and Figure 9B Shows the continuous movement of the "index finger and thumb tapping" gesture. Refer to Figure 9A and Figure 9B , the user's index finger and thumb bend, approach, and touch each other from an idle state within a specific time. In some embodiments, the signal generated by the gesture pattern of the index finger and thumb tapping can be sensed by the sensing module 21 and sent to the recognition module 23. After receiving it, the recognition module 23 recognizes / classifies it as a general label according to the gesture classification model. In some embodiments, the gesture pattern of "index finger and thumb tapping" can be defined to perform operations desired for different usage scenarios. For example, the gesture pattern of "index finger and thumb tapping" can be defined to execute the "OK" command in a menu.

[0092] Figures 10A - 10B A schematic diagram showing a gesture pattern according to some embodiments of the present invention. Figure 10A and Figure 10B Shows the continuous movement of the "flick" gesture. Refer to Figure 10A, the fingertips (or finger pads) of the user's middle finger and thumb come into contact. Refer to Figure 10A and Figure 10B , within a specific time, the user bends the middle finger to the center of the palm and makes contact therewith. In some embodiments, the user bends the middle finger to the junction between the base of the thumb and the palm. In some embodiments, the user's flicking gesture can produce a sound. In some embodiments, the signal (such as, an electromyogram signal) generated by the flicking gesture pattern can be sensed by the sensing module 21 and then sent to the identification module 23. After receiving it, the identification module 23 identifies / classifies it into a general marker according to the gesture classification model. In some embodiments, the "flicking" gesture pattern can be defined to perform operations desired in different scenarios. For example, the "flicking" gesture pattern can be defined to execute a "reset" command, causing the cursor corresponding to the wearable electronic device / user's hand to return to the center of the display.

[0093] Figures 11A - 11B FIG. shows a schematic diagram of a gesture pattern according to some embodiments of the present invention. Figure 11A and Figure 11B FIG. shows the continuous movement of the "palm grip" gesture. Refer to Figure 11A and Figure 11B , from the idle state, within a specific time, the user bends the fingers to the center of the palm, forming a fist posture. In some embodiments, the user's grip is completed in a short time and presents a fist posture. In one embodiment, the user places the thumb outside the fist when making a fist. In another embodiment, the user places the thumb inside the fist (i.e., covered by the other four fingers) when making a fist. In some embodiments, the signal (such as, an electromyogram signal) generated by the "palm grip" gesture pattern can be sensed by the sensing module 21 and then sent to the identification module 23. After receiving it, the identification module 23 identifies / classifies it into a general marker according to the gesture classification model. In some embodiments, the "palm grip" gesture pattern can be used to "grab" an object in the display (such as Figure 1 an object on the desktop).

[0094] Figures 12A - 12B FIG. shows a schematic diagram of a gesture pattern according to some embodiments of the present invention. Figure 12A and Figure 12B FIG. shows the continuous movement of the "palm opening" gesture. Refer to Figure 12A and Figure 12B, the user's hand straightens the fingers from the idle state within a specific time, forming an open palm gesture. In some embodiments, the opening of the user's palm can be completed in a short time. In one embodiment, the user can straighten the fingers from a clenched fist gesture to an open palm gesture. In some embodiments, the signal (e.g., myoelectric signal) generated by the "open palm" gesture pattern can be sensed by the sensing module 21 and sent to the identification module 23. After receiving it, the identification module 23 identifies / classifies it as a general marker according to the gesture classification model. In some embodiments, the "open palm" gesture pattern can be used to "throw" the object already grabbed in the display.

[0095] Figures 13A - 13B Schematic diagram showing a gesture pattern according to some embodiments of the present invention. Figure 13A and Figure 13B Showing the continuous movement of the "index finger hook" gesture. Refer to Figure 13A and Figure 13B , the user's hand bends the index finger from the idle state within a specific time, forming an index finger hook gesture. In some embodiments, the movement of the user's index finger can be completed in a short time. In one embodiment, the user can straighten the fingers from a clenched fist gesture to an open palm gesture. In some embodiments, the signal (e.g., myoelectric signal) generated by the "index finger hook" gesture pattern can be sensed by the sensing module 21 and sent to the identification module 23. After receiving it, the identification module 23 identifies / classifies it as a general marker according to the gesture classification model. In some embodiments, the "index finger hook" gesture pattern can make the object already grabbed in the display "rotate".

[0096] Figures 14A - 14B Schematic diagram showing a gesture pattern according to some embodiments of the present invention. Figure 14A and Figure 14B Showing the continuous movement of the "wave the palm towards the palm" gesture. Refer to Figure 14A and Figure 14B , the user bends the wrist from the idle state within a specific time and waves the hand towards the palm (for the right hand, it is a leftward wave). In some embodiments, the waving movement of the user can be completed in a short time. In some embodiments, the user's fingers can be in a natural and relaxed state. In some embodiments, the signal (e.g., myoelectric signal) generated by the "wave the palm towards the palm" gesture pattern can be sensed by the sensing module 21 and sent to the identification module 23. After receiving it, the identification module 23 identifies / classifies it as a general marker according to the gesture classification model. In some embodiments, the "wave the palm towards the palm" gesture pattern can be to execute the "browse left" command in the menu. In some embodiments, the "wave the palm towards the palm" gesture pattern can be used to execute the "previous page" command.

[0097] Figures 15A - 15BSchematic diagram showing a gesture pattern according to some embodiments of the present invention. Figure 15A and Figure 15B show the continuous movement of the gesture of "swinging the palm towards the back of the hand". Refer to Figure 15A and Figure 15B , the user bends the wrist within a specific time from the idle state and swings the hand towards the back of the hand (for the right hand, it is swinging to the right). In some embodiments, the swinging action of the user can be completed in a short time. In some embodiments, the user's fingers can be in a natural and relaxed state. In some embodiments, the signal (e.g., myoelectric signal) generated by the gesture pattern of "swinging the palm towards the back of the hand" can be sensed by the sensing module 21 and then sent to the recognition module 23. After receiving it, the recognition module 23 recognizes / classifies it as a general label according to the gesture classification model. In some embodiments, the gesture pattern of "swinging the palm towards the back of the hand" can be to execute the "browse right" instruction in the menu. In some embodiments, the gesture pattern of "swinging the palm towards the back of the hand" can be used to execute the "next page" instruction.

[0098] Figures 16A - 16B Schematic diagram showing a gesture pattern according to some embodiments of the present invention. Figure 16A and Figure 16B show the continuous movement of the gesture of "sliding the thumb towards the palm with a clenched fist". Refer to Figure 16A and Figure 16B , the user slides the thumb towards the palm within a specific time from the posture of holding a virtual fist (for the right hand, it is sliding to the left). In some embodiments, the thumb can slide over the index finger. The thumb can slide along the side of the index finger. In some embodiments, the thumb can slide over the knuckle joint of the index finger. The sliding action of the user's thumb can be completed in a short time. In some embodiments, the other four fingers of the user can be in a natural and relaxed state of holding a virtual fist. In another embodiment, the other four fingers of the user can be in a tightly clenched fist posture. In some embodiments, the signal (e.g., myoelectric signal) generated by the gesture pattern of "sliding the thumb towards the palm with a clenched fist" can be sensed by the sensing module 21 and then sent to the recognition module 23. After receiving it, the recognition module 23 recognizes / classifies it as a general label according to the gesture classification model. In some embodiments, the gesture pattern of "sliding the thumb towards the palm with a clenched fist" can be to execute the "previous one" instruction in the menu. In some embodiments, the gesture pattern of "sliding the thumb towards the palm with a clenched fist" can make the object grabbed on the display "rotate clockwise".

[0099] Figures 17A - 17B Schematic diagram showing a gesture pattern according to some embodiments of the present invention. Figure 17A and Figure 17B show the continuous movement of the gesture of "sliding the thumb towards the back of the hand with a clenched fist". Refer to Figure 17A and Figure 17B, the user slides the thumb towards the back of the hand in a gesture of a loosely clenched fist within a specific time period (for the right hand, it is a rightward slide). In some embodiments, the thumb may slide over the index finger. The thumb may slide along the side of the index finger. In some embodiments, the thumb may slide over the knuckle joint of the index finger. The action of the user sliding the thumb can be completed within a short time. In some embodiments, the other four fingers of the user may be naturally relaxed in a gesture of a loosely clenched fist. In another embodiment, the other four fingers of the user may be in a gesture of a tightly clenched fist. In some embodiments, the signal (e.g., myoelectric signal) generated by the gesture pattern of "clenching a fist and sliding the thumb towards the back of the hand" can be sensed by the sensing module 21 and then sent to the recognition module 23. After receiving it, the recognition module 23 identifies / classifies it as a general marker according to the gesture classification model. In some embodiments, the gesture pattern of "clenching a fist and sliding the thumb towards the back of the hand" can execute the "next" instruction in the menu. In some embodiments, the gesture pattern of "clenching a fist and sliding the thumb towards the back of the hand" can make the grabbed object on the display "rotate counterclockwise".

[0100] The features of the present invention are again referred to Figures 9A to 17B for illustration. For example, the recognition module 23 of the present invention can recognize 9 gesture patterns (i.e., recognize 9 general markers GM) drawn in Figures 9A to 17B . However, according to different application scenarios, the user gesture recognition system 2 of the present invention can reconfigure the general marker GM into a configuration marker RM via the configuration module 24, that is, select the gestures used in a specific application scenario (for example Figure 4 and 5A select 4 gesture patterns from 5C, corresponding to configuration markers R1 to R4). In this way, the user gesture recognition system 2 of the present invention does not need to establish a corresponding classification model for each specific situation, so as to save the time required for switching between different classification models. In addition, the user gesture recognition system 2 of the present invention can actually still accurately recognize a variety of gesture patterns (such as Figures 9A to 17B the 9 gesture patterns drawn in). Even if only about 4 to 5 gestures are used in a specific scenario, the probability of gesture misjudgment can still be reduced. This is significantly helpful for the user experience.

[0101] Although the present invention has been described and illustrated with reference to its specific embodiments, such description and illustration are not restrictive. Those skilled in the art should understand that various changes can be made and equivalents can be substituted without departing from the true spirit and scope of the present invention as defined by the appended claims. The illustrations may not necessarily be drawn to scale. Due to manufacturing processes and tolerances, there may be differences between the artistic representation and the actual device in the present invention. There may be other embodiments of the present invention that are not specifically illustrated. The specification and drawings should be regarded as illustrative rather than restrictive. Modifications can be made to adapt a particular situation, material, composition of matter, method, or process to the objectives, spirit, and scope of the present invention. All such modifications are intended to be within the scope of the appended claims. Although the methods disclosed herein have been described with reference to specific operations performed in a specific order, it should be understood that these operations can be combined, subdivided, or reordered to form equivalent methods without departing from the teachings of the present invention. Therefore, unless specifically indicated herein, the order and grouping of operations are not limitations of the present invention.

[0102] Description of the Reference Numerals

[0103] 1: Usage scenario

[0104] 2: User posture recognition system

[0105] 3: Process

[0106] 11: User

[0107] 12: Wearable electronic device

[0108] 13: Display

[0109] 14: Computing device

[0110] 21: Sensing module

[0111] 22: Signal filtering module

[0112] 23: Identification module

[0113] 24: Configuration module

[0114] 25: Communication module

[0115] 31: Signal

[0116] 61: Operation

[0117] 62: Operation

[0118] 63: Operation

[0119] 64: Operation

[0120] 65: Operation

[0121] 61': Operation

[0122] 62': Operation

[0123] 63': Operation

[0124] 64': Operation

[0125] 65': Operation

[0126] 70: Wearable electronic device

[0127] 71: Computing device

[0128] 72: Sensor

[0129] 73: Communication interface

[0130] 80: Computing device

[0131] 81: Processor

[0132] 82: Input / output interface

[0133] 83: Communication interface

[0134] 84: Memory

[0135] 131: Object

[0136] 132: Object

[0137] 133: Cursor

[0138] G1: General marker

[0139] G2: General marker

[0140] G3: General marker

[0141] G4: General marker

[0142] G5: General marker

[0143] G6: General marker

[0144] G7: General marker

[0145] G8: General marker

[0146] G9: General marker

[0147] GM: General marker

[0148] R1: Configuration marker

[0149] R2: Configuration marker

[0150] R3: Configuration marker

[0151] R4: Configuration marker

[0152] RM: Configuration Marker

[0153] SS: Situation Selection Signal

Claims

1. A wearable electronic device, which comprises: a sensing module configured to detect signals associated with a user's posture; an identification module electrically connected to the sensing module and configured to identify the signals as a plurality of general tags according to a classification model, each of the plurality of general tags corresponding to one of the postures of the user; and a configuration module electrically connected to the identification module and configured to configure the plurality of general tags as a plurality of configuration tags and output the plurality of configuration tags.

2. The wearable electronic device according to claim 1, wherein each of the plurality of general tags corresponds to only one of the plurality of configuration tags.

3. The wearable electronic device according to claim 1, wherein one of the plurality of configuration tags corresponds to one or more of the plurality of general tags.

4. The wearable electronic device according to claim 1, wherein the number of the plurality of general tags is greater than the number of the plurality of configuration tags.

5. The wearable electronic device according to claim 1, wherein the plurality of general tags correspond to a plurality of dynamic gesture patterns.

6. The wearable electronic device according to claim 1, wherein the configuration module is configured to configure a first general tag and a second general tag of the plurality of general tags as a first configuration tag of the plurality of configuration tags.

7. The wearable electronic device according to claim 6, wherein the configuration module performs the configuration of the plurality of configuration tags based on a fuzzy judgment algorithm.

8. The wearable electronic device according to claim 1, wherein the signal associated with the user's posture is detected via the user's wrist, and the signal associated with the user's posture is one of an electromyogram signal (EMG) or a myokinematic signal (MMG).

9. The wearable electronic device according to claim 1, which further comprises: a communication module configured to transmit the plurality of configuration tags to a remote electronic device; a signal filtering module configured to filter noise in the signal associated with the user's posture.

10. A user posture identification system, the user posture identification system comprises: an identification module configured to identify signals from a user as a plurality of general tags representing a plurality of gesture patterns of the user according to a classification model; and a configuration module configured to configure the plurality of general tags as a plurality of configuration tags based on a fuzzy judgment algorithm.

11. The user posture identification system according to claim 10, which further comprises a wearable device, the wearable device comprises: a sensor configured to detect the signal from the user via the user's wrist, the signal being one of an electromyogram signal (EMG) or a myokinematic signal (MMG); and a communication interface configured to transmit the signal from the user.

12. The user posture identification system according to claim 11, wherein the communication interface is configured to transmit the plurality of configuration tags to a remote computing device.

13. The user posture recognition system according to claim 10, wherein each of the plurality of general markers corresponds to only one of the plurality of configuration markers.

14. The user posture recognition system according to claim 10, wherein one of the plurality of configuration markers corresponds to one or more of the plurality of general markers.

15. The user posture recognition system according to claim 10, wherein the configuration module is configured to configure a first general marker and a second general marker of the plurality of general markers as a first configuration marker of the plurality of configuration markers.

16. A method for recognizing a user's posture, the method comprising: detecting, by a sensing module, a signal associated with the user's posture; identifying, by an identification module, the signal as a plurality of general markers representing the user's posture, wherein each of the plurality of general markers corresponds to one of the postures of the user; and configuring, by a configuration module, the plurality of general markers as a plurality of configuration markers.

17. The method according to claim 16, further comprising: filtering, by a signal filtering module, noise in the signal associated with the user's posture; and transmitting, by a communication module, the plurality of configuration markers to a remote electronic device.

18. The method according to claim 16, wherein each of the plurality of general markers corresponds to only one of the plurality of configuration markers.

19. The method according to claim 16, wherein the configuration module configures a first general marker and a second general marker of the plurality of general markers as a first configuration marker of the plurality of configuration markers based on a fuzzy judgment algorithm.

20. The method according to claim 16, wherein the signal associated with the user's posture is detected via the user's wrist, and the signal associated with the user's posture is one of an electromyogram (EMG) or a myodynamogram (MMG).

Images