Intelligent ring interaction method and device and electronic equipment

By collecting finger touch gestures and sounds through the IMU sensor and sound sensor of the smart ring, and combining them with the algorithm processing module to identify the object surface, the problem of the smart ring being unable to recognize the object surface is solved, and active interaction and function control are realized.

CN119024969APending Publication Date: 2024-11-26TSINGHUA UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411244374.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-05
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The smart ring cannot recognize the surface of the object it touches, resulting in limited interaction and affecting the user experience.

Method used

The smart ring uses an IMU sensor to collect finger touch gestures and a sound sensor to collect touch sounds. The algorithm processing module then identifies these sounds, enabling active interaction with the surface of an object.

Benefits of technology

It enables the smart ring to actively interact with different object surfaces, and can issue different interaction commands by touching different object surfaces, thus actively controlling the ring's detection function.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119024969A_ABST
    Figure CN119024969A_ABST
Patent Text Reader

Abstract

The invention provides an intelligent ring interaction method and device and electronic equipment, an intelligent ring is worn on an index finger of a finger, and the intelligent ring comprises an IMU sensor, a sound sensor and an algorithm processing module; the method comprises the following steps: acquiring a touch gesture executed by a finger through an IMU (Inertial Measurement Unit) sensor of the intelligent ring; collecting a touch sound generated when the finger executes the touch gesture through the sound sensor; the touch gesture and the touch sound generated by the touch gesture are input into the algorithm processing module, and the algorithm processing module is used for recognizing the surface of an object touched by the finger. According to the invention, active interaction with the intelligent ring can be realized by utilizing different gestures and sounds generated by touching the surfaces of different objects, and the intelligent ring is actively controlled to selectively start and stop various human body detection functions according to the willingness of a user in an active interaction mode.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of smart wearable devices, and in particular to a smart ring interaction method, device and electronic equipment. Background Art

[0002] Smart wearable devices are increasingly used in sports and health. As a new type of smart wearable device, smart rings, like smart bracelets, smart watches and other smart wearable devices, can realize functions such as sports step counting, calorie consumption, heart rate monitoring, and sleep monitoring. In order to distinguish different functions, the same gesture needs to output different function instructions for different touched surfaces, but smart rings cannot identify the touched surface. Summary of the invention

[0003] In order to solve the above-mentioned technical problems, the embodiments of the present invention provide a smart ring interaction method, device and electronic device.

[0004] In a first aspect, an embodiment of the present invention provides a smart ring interaction method, wherein the smart ring is worn on an index finger, and the smart ring comprises: an IMU sensor, a sound sensor, and an algorithm processing module; the method comprises:

[0005] Acquire the touch gesture performed by the finger through the IMU sensor of the smart ring;

[0006] collecting, by means of the sound sensor, a touch sound emitted when the finger performs the touch gesture;

[0007] The touch gesture and the touch sound generated by the touch gesture are input into the algorithm processing module, and the algorithm processing module is used to identify the surface of the object touched by the finger.

[0008] In a second aspect, a smart ring interaction device is provided, the device comprising:

[0009] A gesture acquisition module, which acquires the touch gesture performed by the finger through the IMU sensor of the smart ring;

[0010] A sound collection module, which collects the touch sound emitted by the finger when performing the touch gesture through the sound sensor;

[0011] The identification module inputs the touch gesture and the touch sound generated by the touch gesture into the algorithm processing module, and uses the algorithm processing module to identify the surface of the object touched by the finger.

[0012] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above-described smart ring interaction methods.

[0013] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps in any one of the smart ring interaction methods described above are implemented.

[0014] In the solutions provided in the first to fourth aspects of the present application, different touch gestures of different fingers are collected through the IMU sensor of the smart ring, and different touch sounds emitted by different touch gestures are collected through the sound sensor, and finally the touch gestures and touch sounds are input into the algorithm processing module, and the algorithm processing module is used to identify the surface of the object touched by the finger. Compared with the method in the related art that the human body can only passively accept the detection of various human body data by the smart ring, the surface of the object touched by the finger can be identified by using different touch gestures and different touch gestures and the sounds emitted by touching different object surfaces, so as to realize active interaction with the smart ring, and actively control the opening and closing of various detection functions of the smart ring through active interaction, so as to realize different interaction instructions to control the smart ring by contacting different object surfaces.

[0015] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0017] Figure 1 A flow chart of a smart ring interaction method provided by an embodiment of the present invention is shown;

[0018] Figure 2 A schematic diagram showing the structural connection of a smart ring interaction device provided by an embodiment of the present invention is shown;

[0019] Figure 3 A schematic diagram of the structure of an electronic device for executing a smart ring interaction method provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In order to enable technicians in this technical field to better understand the solutions of the present invention, the present invention is further described in detail below in combination with the drawings and specific implementation methods.

[0021] Smart rings are a type of smart wearables that can monitor heart rate, blood oxygen, sleep, and steps taken. At the same time, unlike other smart mobile terminals, smart rings on the market cannot interact with the human body through touch screens. Users can only interact through a few interactive methods such as a single button on the smart ring, resulting in limited interactive effects of smart rings, affecting the actual user experience.

[0022] Based on this, the present invention proposes the following embodiments.

[0023] In the following embodiments, the term “smart ring” and the term “ring” have the same meaning.

[0024] Example 1

[0025] The present embodiment provides a smart ring interaction method, wherein the smart ring is worn on the index finger, and the smart ring comprises: an IMU sensor, a sound sensor, and an algorithm processing module, wherein the algorithm processing module is connected to the IMU sensor and the sound sensor respectively.

[0026] In this embodiment, the algorithm processing module is the execution subject, which can be installed in the ring or separately set on the intelligent computing device outside the ring. When set on the intelligent computing device outside the ring, the algorithm processing module and the ring are connected through a wireless transmission protocol, and the wireless transmission protocol includes but is not limited to: Bluetooth or ZigBee transmission. The intelligent computing device can be a fixed desktop computing device or a handheld mobile computing device, and the intelligent computing device is not specifically limited here.

[0027] The interactive methods that need to be performed during the use of the above-mentioned smart ring include:

[0028] Step 100: Acquire the touch gesture performed by the finger through the IMU sensor of the smart ring.

[0029] In the above step 100, the touch gesture refers to the different finger movements and postures made by the fingers in the process of touching the surfaces of different objects. The touch gesture can generate signals about acceleration and angular velocity during the movement. For example: the index finger does not lift up after touching the surface of the object, the index finger lifts up immediately after touching the surface of the object, the middle finger does not lift up after touching the surface of the object, the middle finger lifts up immediately after touching the thumb, the index finger clicks in the air, etc. "Object surface" refers to a virtual concept, which can be a tangible object or an invisible air (index finger clicking in the air). The surface of the object includes but is not limited to: the thumb, the skin surface of the arm, the surface of the arm clothing, the wooden table top and the marble table top.

[0030] Among them, when it is determined that the IMU sensor of the smart ring is touched, the acceleration and angular velocity output by the IMU sensor are obtained; among them, when the IMU sensor of the smart ring is touched, the acceleration increases to the maximum acceleration value, and the angular velocity also increases to the maximum angular velocity value, and then the acceleration decreases to the minimum acceleration value, and the acceleration and angular velocity oscillate up and down around their own reference values ​​respectively.

[0031] When the middle finger moves, the IMU sensor outputs low-peak acceleration and low-peak angular velocity respectively; when the index finger and the thumb touch each other, the IMU sensor outputs low-rate acceleration and low-rate angular velocity.

[0032] Specifically, in step 100, after the IMU sensor obtains different data generated by the finger performing the touch gesture, it is necessary to process the acceleration and angular velocity generated by the acquired touch gesture through the following steps (1) to (4):

[0033] (1) When the finger performs a touch gesture, the acceleration and angular velocity collected by the IMU sensor of the smart ring are obtained.

[0034] (2) Normalizing the acceleration and the angular velocity to obtain acceleration characteristics and angular velocity characteristics.

[0035] (3) Filter the acceleration and angular velocity to obtain the average amplitude of the acceleration and the average amplitude of the angular velocity.

[0036] (4) Determine acceleration, angular velocity, acceleration feature, angular velocity feature, average amplitude of acceleration and average amplitude of angular velocity as raw data, perform feature extraction operation on the raw data to obtain raw data after feature extraction, and perform preprocessing operation on the raw data to obtain preprocessed raw data. In step (4), "acceleration" refers to unprocessed acceleration (after acquisition by IMU sensor). In particular, the acceleration and angular velocity acquired by the IMU sensor in step (1) can be subjected to Butterworth high-pass filtering (cut-off frequency 10 Hz) to achieve noise reduction processing of acceleration and angular velocity.

[0037] In the above step (1), the IMU sensor is an inertial sensor, which is mainly used to measure acceleration and angular velocity. The angle change and acceleration change of the finger can be captured by the IMU sensor in the smart ring worn on the finger. The IMU sensor transmits the collected data to the algorithm processing module via Bluetooth or other transmission methods.

[0038] In the above step (4), feature extraction operations are performed on the raw data, including but not limited to the following operations: calculating the mean, extreme value, and number of peaks. Preprocessing operations are performed on the raw data, including but not limited to the following operations: detrending and normalizing, and the raw data, processed raw data, and feature-extracted raw data are uniformly input into the neural network of the algorithm processing module. The neural network can capture the features of the above different data and classify them, and distinguish the touch of different fingers on different object surfaces.

[0039] In particular, for the convenience of subsequent description, the original data, the original data after feature extraction, and the pre-processed original data are collectively referred to as touch gesture data.

[0040] Step 101: Collect the touch sound generated when a finger performs a touch gesture through a sound sensor.

[0041] In this embodiment, the IMU sensor in step 100 alone cannot identify more object surfaces, so the sound sensor in step 101 is also required to collect the sound emitted when touching. When hitting different object surfaces, different touch sounds will be emitted due to the different materials of the object surface and the different sizes of the internal cavity. The sound sensor also transmits the collected touch sounds to the algorithm processing module via Bluetooth or other transmission methods.

[0042] In the above step 101, before the sound sensor transmits the sound to the algorithm processing module for processing, the collected touch sound needs to be processed by performing the following steps (1) to (3):

[0043] (1) The sound sensor collects the touch sound emitted when the finger performs a touch gesture.

[0044] (2) Perform noise reduction on the touch sound to obtain the original sound.

[0045] (3) Perform Fourier transform on the touch sound to obtain spectrum data.

[0046] In the above step (1), when a finger touches the surface of an object, in addition to different sounds due to the different materials of the object's surface, the volume of the sound will also be affected by factors such as the finger's touch strength and touch speed. The sounds emitted during the above touches will be collected by the sound sensor and used as the touch sounds emitted when the finger performs the touch gesture.

[0047] In the above step (2), the noise reduction process means that when the sound sensor collects the sound emitted by the finger touching the surface of the object, it also simultaneously collects the ambient noise of the environment in which the finger is located. In order to avoid interference from the ambient noise, the sound collected by the sound sensor needs to be filtered to retain only the sound of the finger touching the surface of the object.

[0048] Step 102: input the touch gesture and the touch sound generated by the touch gesture into an algorithm processing module, and use the algorithm processing module to identify the surface of the object touched by the finger.

[0049] In the above step 102, the algorithm processing module refers to a processing module running a neural network algorithm, and both the touch gesture data collected by the IMU sensor and the sound data collected by the sound sensor are time series data. After the time series data is received by the algorithm processing module, it will be cut into a one-second long window segment containing touch action data. In order to reduce the touch recognition delay, it is necessary to avoid placing the data peak in the center of the window, but to place it at 70% of the window, so as to ensure that the action data is completed while significantly reducing the delay. In particular, the 70% position of the window is the position captured 0.3 seconds after the peak appears, and it is common knowledge in the field that 0.3 seconds is the shortest time to ensure the integrity of various types of tapping signals.

[0050] Specifically, when the algorithm processing module is used to identify the surface of the object touched by the finger, the following steps A to F need to be performed:

[0051] Step A: input the original data, the original data after feature extraction and the original data after preprocessing into the algorithm processing module.

[0052] Step B: input the original sound and spectrum data into the algorithm processing module.

[0053] Step C: obtaining the object surface material classification table pre-stored in the algorithm processing module.

[0054] Step D: input the acquired raw data, the raw data after preprocessing, the raw data after feature extraction, the raw sound and the spectrum data into the neural network algorithm to obtain a judgment result of whether the finger touches the surface of the object.

[0055] Step E: When the judgment result is no, it indicates that the finger has not touched any surface, which means that the finger has not issued any interactive instructions to the smart ring and the smart ring has no response.

[0056] Step F: When the judgment result is yes, the original data, the original data after preprocessing, the original data after feature extraction, the original sound and the spectrum data are put into the classification table, and the specific type of the surface of the object touched by the finger is found.

[0057] In the above step C, the classification table contains multiple tables, each of which includes object surfaces of different materials and the acceleration and angular velocity of the touch gesture corresponding to the object surfaces of different materials, as well as the original sound and spectrum data of the touch sound. Therefore, after the finger performs the touch gesture and makes the touch sound, it will automatically correspond to the tables in different classification tables after matching by the algorithm processing module to find the corresponding object surface material. Among them, different touch gestures are artificially defined and pre-set in the classification table. The object surfaces of different materials and the acceleration and angular velocity of the touch gesture corresponding to the object surfaces of different materials, as well as the original sound and spectrum data of the touch sound are pre-set in the classification table after a large number of experiments.

[0058] To summarize, an embodiment of the present invention provides a smart ring interaction method, which collects different touch gestures of different fingers through an IMU sensor, and collects different touch sounds emitted by different touch gestures through a sound sensor, and finally inputs the touch gestures and touch sounds into an algorithm processing module, and uses the algorithm processing module to identify the surface of the object touched by the finger. Compared with the related art in which the human body can only passively accept various human body data detected by the smart ring, active interaction with the smart ring can be achieved by using different gestures and sounds emitted by touching different object surfaces, and the opening and closing of various detection functions of the smart ring can be actively controlled through active interaction, so that different interaction instructions can be implemented to control the smart ring by touching different object surfaces.

[0059] Example 2

[0060] A smart ring interaction device, the device comprising:

[0061] The gesture acquisition module 200 acquires the touch gesture performed by the finger through the IMU sensor of the smart ring;

[0062] The sound collection module 201 collects the touch sound emitted by the finger when performing the touch gesture through the sound sensor;

[0063] The identification module 202 inputs the touch gesture and the touch sound generated by the touch gesture into the algorithm processing module, and uses the algorithm processing module to identify the surface of the object touched by the finger.

[0064] Further, the gesture acquisition module 200 includes: acquiring the acceleration and angular velocity collected by the IMU sensor of the smart ring during the process of the finger performing the touch gesture;

[0065] The acceleration and the angular velocity are normalized to obtain acceleration characteristics and angular velocity characteristics.

[0066] Performing filtering processing on the acceleration and the angular velocity to obtain an average amplitude of the acceleration and an average amplitude of the angular velocity;

[0067] The acceleration, angular velocity, acceleration feature, angular velocity feature, the average amplitude of the acceleration and the average amplitude of the angular velocity are determined as raw data, a feature extraction operation is performed on the raw data to obtain raw data after feature extraction, and a preprocessing operation is performed on the raw data to obtain preprocessed raw data.

[0068] Furthermore, the sound collection module 201 includes: obtaining the sound sensor to collect the touch sound emitted by the finger when performing the touch gesture; performing noise reduction processing on the touch sound to obtain the original sound; and performing Fourier transform processing on the touch sound to obtain spectrum data.

[0069] Furthermore, the identification module 202 includes:

[0070] Inputting the original data, the original data after feature extraction and the original data after preprocessing into the algorithm processing module;

[0071] Inputting the original sound and the spectrum data into the algorithm processing module;

[0072] Obtaining an object surface material classification table pre-stored in the algorithm processing module;

[0073] Inputting the acquired original data, the pre-processed original data, the feature-extracted original data, the original sound and the spectrum data into the neural network algorithm to obtain a judgment result of whether the finger touches the surface of the object;

[0074] When the judgment result is yes, the original data, the pre-processed original data, the feature-extracted original data, the original sound and the spectrum data are put into the classification table, and the specific type of the object surface touched by the finger is found out.

[0075] To summarize, an embodiment of the present invention provides a smart ring interaction device, which collects different touch gestures of different fingers through an IMU sensor, and collects different touch sounds emitted by different touch gestures through a sound sensor, and finally inputs the touch gestures and touch sounds into an algorithm processing module, and uses the algorithm processing module to identify the surface of the object touched by the finger. Compared with the related art in which the human body can only passively accept various human body data detected by the smart ring, active interaction with the smart ring can be achieved by using different gestures and sounds emitted by touching different object surfaces, and the opening and closing of various detection functions of the smart ring can be actively controlled through active interaction, so that different interaction instructions can be implemented to control the smart ring by touching different object surfaces.

[0076] Example 3

[0077] This embodiment proposes a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the smart ring interaction method described in the above embodiment 1 are executed. For specific implementation, please refer to method embodiment 1, which will not be repeated here.

[0078] In addition, see Figure 3 The structural diagram of an electronic device shown in FIG. 1 is a schematic diagram of a structure of an electronic device. This embodiment further provides an electronic device, which includes a bus 300 , a processor 301 , a transceiver 302 , a bus interface 303 , a memory 304 and a user interface 305 . The electronic device includes a memory 304 .

[0079] In this embodiment, the electronic device further includes: one or more programs stored in the memory 304 and executable on the processor 301, configured so that the processor executes the one or more programs to perform the following steps (1) to (3):

[0080] (1) Acquire the touch gesture performed by the finger through the IMU sensor of the smart ring.

[0081] (2) The microphone collects the touch sound generated when the finger performs the touch gesture.

[0082] (3) The touch gesture and the touch sound generated by the touch gesture are input into the algorithm processing module, and the algorithm processing module is used to identify the surface of the object touched by the finger.

[0083] The transceiver 302 is used to receive and send data under the control of the processor 301 .

[0084] Among them, the bus architecture (represented by bus 300), bus 300 can include any number of interconnected buses and bridges, and bus 300 links various circuits including one or more processors represented by processor 301 and memory represented by memory 304. Bus 300 can also link various other circuits such as peripherals, voltage regulators, and power management circuits together, which are all well known in the art, so this embodiment will not be further described. Bus interface 303 provides an interface between bus 300 and transceiver 302. Transceiver 302 can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. For example: transceiver 302 receives external data from other devices. Transceiver 302 is used to send data processed by processor 301 to other devices. Depending on the nature of the computing system, a user interface 305, such as a keypad, display, speaker, microphone, joystick, can also be provided.

[0085] The processor 301 is responsible for managing the bus 300 and general processing, such as running the general operating system 3041 as mentioned above. The memory 304 can be used to store data used by the processor 301 when performing operations.

[0086] Optionally, the processor 301 may be, but is not limited to: a central processing unit, a single-chip microcomputer, a microprocessor or a programmable logic device.

[0087] It can be understood that the memory 304 in the embodiment of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct RAM bus random access memory (DRRAM). The memory 304 of the system and method described in the present embodiment is intended to include, but is not limited to, these and any other suitable types of memory.

[0088] In some implementations, the memory 304 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof: an operating system 3041 and an application program 3042 .

[0089] Among them, the operating system 3041 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 3042 includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. The program for implementing the method of the embodiment of the present application can be included in the application 3042.

[0090] The above is only a specific implementation of the embodiment of the present invention, but the protection scope of the embodiment of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the embodiment of the present invention, which should be included in the protection scope of the embodiment of the present invention. Therefore, the protection scope of the embodiment of the present invention should be based on the protection scope of the claims.

Claims

1. A smart ring interaction method, characterized in that: The smart ring is worn on the index finger, and the smart ring includes: an IMU sensor, a sound sensor and an algorithm processing module; the method includes: Acquire the touch gesture performed by the finger through the IMU sensor of the smart ring; collecting, by means of the sound sensor, a touch sound emitted when the finger performs the touch gesture; The touch gesture and the touch sound generated by the touch gesture are input into the algorithm processing module, and the algorithm processing module is used to identify the surface of the object touched by the finger.

2. The smart ring interaction method according to claim 1, characterized in that: The acquiring the touch gesture performed by the finger through the IMU sensor of the smart ring includes: During the process of the finger performing the touch gesture, acquiring the acceleration and angular velocity collected by the IMU sensor of the smart ring; Normalizing the acceleration and the angular velocity to obtain acceleration characteristics and angular velocity characteristics; Performing filtering processing on the acceleration and the angular velocity to obtain an average amplitude of the acceleration and an average amplitude of the angular velocity; The acceleration, the angular velocity, the acceleration feature, the angular velocity feature, the average amplitude of the acceleration and the average amplitude of the angular velocity are determined as raw data, a feature extraction operation is performed on the raw data to obtain raw data after feature extraction, and a preprocessing operation is performed on the raw data to obtain preprocessed raw data.

3. The smart ring interaction method according to claim 2, characterized in that: The collecting, by the sound sensor, the touch sound emitted when the finger performs the touch gesture includes: Acquire the sound sensor to collect the touch sound emitted by the finger when performing the touch gesture; Performing noise reduction processing on the touch sound to obtain the original sound; The touch sound is subjected to Fourier transform processing to obtain spectrum data.

4. The smart ring interaction method according to claim 3, characterized in that: The step of inputting the touch gesture and the touch sound generated by the touch gesture into the algorithm processing module, and using the algorithm processing module to identify the surface of the object touched by the finger, comprises: Inputting the original data, the original data after feature extraction and the original data after preprocessing into the algorithm processing module; Inputting the original sound and the spectrum data into the algorithm processing module; Obtaining an object surface material classification table pre-stored in the algorithm processing module; Inputting the acquired original data, the pre-processed original data, the feature-extracted original data, the original sound, and the spectrum data into a neural network algorithm to obtain a result of determining whether the finger touches the surface of the object; When the judgment result is yes, the original data, the pre-processed original data, the feature-extracted original data, the original sound and the spectrum data are put into the classification table, and the specific type of the object surface touched by the finger is found out.

5. A smart ring interactive device, characterized in that: The device comprises: A gesture acquisition module, which acquires touch gestures performed by fingers through the IMU sensor of the smart ring; A sound collection module collects the touch sound made by the finger when performing a touch gesture through a sound sensor; The identification module inputs the touch gesture and the touch sound generated by the touch gesture into the algorithm processing module, and uses the algorithm processing module to identify the surface of the object touched by the finger.

6. The device according to claim 5, characterized in that The gesture acquisition module comprises: During the process of the finger performing the touch gesture, acquiring the acceleration and angular velocity collected by the IMU sensor of the smart ring; Normalizing the acceleration and the angular velocity to obtain acceleration characteristics and angular velocity characteristics; Performing filtering processing on the acceleration and the angular velocity to obtain an average amplitude of the acceleration and an average amplitude of the angular velocity; The acceleration, the angular velocity, the acceleration feature, the angular velocity feature, the average amplitude of the acceleration and the average amplitude of the angular velocity are determined as raw data, a feature extraction operation is performed on the raw data to obtain raw data after feature extraction, and a preprocessing operation is performed on the raw data to obtain preprocessed raw data.

7. The device according to claim 6, characterized in that The sound collection module comprises: Acquire the sound sensor to collect the touch sound emitted by the finger when performing the touch gesture; Performing noise reduction processing on the touch sound to obtain the original sound; The touch sound is subjected to Fourier transform processing to obtain spectrum data.

8. The device according to claim 7, characterized in that The resolution module comprises: Inputting the original data, the original data after feature extraction and the original data after preprocessing into the algorithm processing module; Inputting the original sound and the spectrum data into the algorithm processing module; Obtaining an object surface material classification table pre-stored in the algorithm processing module; Inputting the acquired original data, the pre-processed original data, the feature-extracted original data, the original sound, and the spectrum data into a neural network algorithm to obtain a result of determining whether the finger touches the surface of the object; When the judgment result is yes, the original data, the pre-processed original data, the feature-extracted original data, the original sound and the spectrum data are put into the classification table, and the specific type of the object surface touched by the finger is found out.

9. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the smart ring interaction method as described in any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the smart ring interaction method as described in any one of claims 1 to 4 are implemented.