Hand personalized geometric model construction method for multi-finger collaborative interaction system and intelligent finger ring device
By automatically creating a personalized hand geometry model through a smart ring device, the problems of low accuracy, poor portability, and complex initialization of multi-finger collaborative interaction systems are solved, achieving a high-precision, portable, and personalized interactive experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 李宗桦
- Filing Date
- 2026-02-09
- Publication Date
- 2026-04-17
AI Technical Summary
Existing multi-finger collaborative interaction systems rely on general models, resulting in low accuracy. They also rely on external devices for calibration, leading to poor portability. Furthermore, their initialization processes are cumbersome and lack personalization and adaptive capabilities, which affect interaction accuracy and user experience.
Employing a smart ring device that integrates an inertial measurement unit and a physical sensor switch, it automatically builds a personalized geometric model based on the fist-clenching posture and the triggering of the switch, and then adaptively updates it via wireless communication, achieving high-precision personalized modeling and portable calibration.
It achieves high-precision personalized modeling, simplifies the initialization process, improves portability and adaptability, ensures long-term stability of interaction accuracy, and is suitable for a variety of upper-level interaction applications.
Smart Images
Figure CN121879581A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the fields of human-computer interaction, wearable computing and motion capture technology, and in particular, a method for constructing a personalized geometric model of the hand and an intelligent ring device for a multi-finger collaborative interaction system. Background Technology
[0002] In wearable ring-based virtual interaction systems, a key prerequisite for achieving high-precision finger movement recognition and spatial positioning is providing the system with an accurate and stable hand spatial reference frame. Existing technical solutions mainly suffer from the following shortcomings: Relying on pre-set general models results in low accuracy: Most systems use pre-set general geometric models based on average hand size to estimate fingertip positions. Due to significant individual differences in user hand size, finger length ratio, and joint range of motion, using a general model introduces systematic errors, leading to inaccurate fingertip position estimations. This severely impacts interactive experiences that require high precision, such as contactless zooming and virtual grasping.
[0003] Reliance on external calibration devices leads to poor portability: Some high-precision solutions require external cameras (such as RGB-D cameras), magnetic field generators, or dedicated calibration devices for spatial calibration of the hand or ring. This method undermines the self-contained and portable advantages of wearable systems, making it impossible to achieve "use and go" anytime, anywhere. Furthermore, the calibration process is complex, resulting in a poor user experience.
[0004] The initialization process is cumbersome or missing: When using some multi-ring systems for the first time, users need to manually select the finger to wear the ring or perform complex and unintuitive calibration actions in a specific software interface. This results in a high learning cost and can easily lead to subsequent interactive functions becoming disordered due to incorrect wearing or inaccurate calibration.
[0005] Lack of personalization and adaptability: The system cannot adapt to subtle changes in posture caused by sensor drift, slight loosening of the ring, or hand fatigue during long-term use, resulting in a decrease in interaction accuracy over time and requiring users to perform frequent and tedious recalibration.
[0006] Therefore, there is an urgent need for a method and device that can quickly, automatically, and non-intrusively build a personalized geometric model of a user's hand and adaptively maintain the accuracy of the model, so as to provide a reliable spatial reference for high-precision multi-finger collaborative interaction at the upper level. Summary of the Invention
[0007] The purpose of this invention is to provide a method for constructing a personalized geometric model of the hand for a multi-finger collaborative interaction system. The system includes multiple smart rings worn on different fingers of the user. Each smart ring is equipped with an inertial measurement unit and a physical sensor switch. The method includes the following steps: Calibration triggering steps: The user is prompted to maintain a preset static hand posture and trigger the physical sensor switch of the smart ring on the corresponding finger in the predetermined finger sequence; Spatial data recording steps: At the moment when each physical induction switch is triggered, record the spatial attitude data collected by the inertial measurement unit of the corresponding smart ring; Relative parameter calculation steps: Based on the predetermined finger sequence, the recorded spatial posture data, and the known or wirelessly measured connection topology between each smart ring, a personalized parameter set representing the user's hand shape is calculated. The personalized parameter set includes at least the relative spatial position and relative angle between different fingers. Model storage step: Store the personalized parameter set as the user's personalized initial geometric model of the hand, which will be used to provide a reference for spatial coordinate transformation during subsequent interactions.
[0008] Furthermore, the preset static hand posture is the user's clenched fist posture.
[0009] Furthermore, the predetermined finger sequence is from thumb, index finger, middle finger, ring finger to little finger.
[0010] Furthermore, the physical sensor switch is located on the outer side of the smart ring housing, corresponding to the back of the user's hand.
[0011] Furthermore, the connection topology measured by the wireless communication is determined through connection relationships established by UWB, NFC, or Zigbee communication protocols.
[0012] Furthermore, it also includes a recalibration step: During system use, in response to a user’s specific recalibration gesture, the personalized initial geometric model of the hand is updated based on newly acquired data to correct errors caused by sensor drift or loosening of the fit.
[0013] The present invention also provides a smart ring device for performing personalized geometric model construction of the hand, comprising at least two smart ring units, each of the smart ring units comprising: Annular shell; An inertial measurement unit is built into the housing; A physical induction switch is located on the outside of the housing; A pressure or bending sensor is disposed inside the annular housing to detect finger movements; A microcontroller, connected to the inertial measurement unit and the physical sensor switch, is configured to: when the physical sensor switch is triggered, record the data of the inertial measurement unit and send the data along with a trigger identifier; The wireless communication module is used to transmit data between ring units and with the main control device; Power module.
[0014] Furthermore, the connection topology between different smart ring units is established via UWB, Bluetooth, or Zigbee wireless communication.
[0015] By adopting the above technical solution, the present invention has the following beneficial effects: Compared with the prior art, the solution provided by the present invention has the following beneficial effects: Achieving high-precision personalized modeling: By guiding the user to perform a simple preset action (such as clenching a fist and triggering switches in sequence), the system can automatically capture the user's real geometric parameters (such as the relative position and angle between the fingers) and establish a personalized initial hand model. This fundamentally eliminates the individual errors caused by the general model and lays a solid foundation for advanced interactive functions such as millimeter-level precision fingertip distance estimation.
[0016] Truly self-contained and portable: The entire calibration process is completed entirely by the ring's own sensors (IMU, inductive switches) and internal wireless communication, without the need for any external cameras, base stations or dedicated calibration tools, perfectly maintaining the portability and usability of wearable devices.
[0017] The initialization process is natural and efficient: the calibration action is designed to be ergonomic (such as clenching a fist), the triggering logic is intuitive (touching the sensor switches in sequence), the user learning cost is zero, and high-precision initialization can be completed in seconds, which greatly improves the user experience and system availability.
[0018] It has adaptive recalibration capability: By introducing a recalibration mechanism triggered by specific gestures, the system can dynamically correct model errors during long-term use, resist sensor drift and wear changes, ensure the long-term stability of interaction accuracy, and achieve intelligent maintenance of "one calibration, long-term accuracy".
[0019] Provides generalized support for upper-layer applications: The constructed personalized geometric model serves as a standardized spatial benchmark, which can seamlessly serve a variety of upper-layer interactive algorithms (such as void control and action recognition), significantly improving the robustness and accuracy of these applications, and has important foundational support value. Attached Figure Description
[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0021] Figure 1 A schematic diagram illustrating the process of constructing a personalized geometric model of a hand for a multi-finger collaborative interaction system; Figure 2 A schematic diagram of the intelligent ring unit structure of the intelligent ring device constructed based on the geometric model of the present invention; Figure 3 This is a schematic diagram of the smart ring of the present invention worn on each finger. Detailed Implementation
[0022] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0023] See Figure 1 As shown, this invention provides a method for constructing a personalized geometric model of the hand for a multi-finger collaborative interaction system. The system includes multiple smart rings worn on different fingers of the user. Each smart ring is equipped with an inertial measurement unit and a physical sensor switch. The method includes the following steps: S11, Calibration triggering step: prompt the user to maintain a preset static hand posture and trigger the physical sensor switch of the smart ring on the corresponding finger in sequence according to the predetermined finger order; S12, Spatial data recording step: At the moment when each of the physical induction switches is triggered, record the spatial attitude data collected by the inertial measurement unit of the corresponding smart ring. S13, relative parameter calculation step: Based on the predetermined finger sequence, the recorded spatial posture data, and the known or wirelessly measured connection topology between each smart ring, calculate a personalized parameter set that characterizes the user's hand shape. The personalized parameter set includes at least the relative spatial position and relative angle between different fingers. S14, Model storage step: Store the personalized parameter set as the user's personalized initial geometric model of the hand, which is used to provide a reference for spatial coordinate transformation in subsequent interaction processes.
[0024] Regarding the recalibration trigger method, you can define that triggering the thumb switch three times in quick succession will trigger recalibration.
[0025] In one embodiment, the preset static hand posture is the user's clenched fist posture.
[0026] In one embodiment, the predetermined finger sequence is from thumb, index finger, middle finger, ring finger to little finger.
[0027] Of course, gestures can also be customized, such as waving three fingers upwards to return to the desktop. This invention supports the thumb, index finger, middle finger, ring finger, and little finger wearing the rings in coordination, preferably the thumb, index finger, and middle finger.
[0028] In one embodiment, the physical sensor switch is located on the outer side of the smart ring housing, corresponding to the back of the user's hand.
[0029] In one embodiment, the connection topology measured by the wireless communication is determined by the connection relationship established through UWB, NFC, or Zigbee communication protocols.
[0030] In one embodiment, a recalibration step is also included: During system use, in response to a user’s specific recalibration gesture, the personalized initial geometric model of the hand is updated based on newly acquired data to correct errors caused by sensor drift or loosening of the fit.
[0031] See Figure 2 As shown, the present invention also provides a smart ring device for performing personalized geometric model construction of the hand, comprising at least two smart ring units, each of the smart ring units comprising: Annular shell; An inertial measurement unit is built into the housing; A physical induction switch is located on the outside of the housing; A pressure or bending sensor is disposed inside the annular housing to detect finger movements; A microcontroller, connected to the inertial measurement unit and the physical sensor switch, is configured to: when the physical sensor switch is triggered, record the data of the inertial measurement unit and send the data along with a trigger identifier; The wireless communication module is used to transmit data between ring units and with the main control device; Power module; The wireless communication modules of the at least two smart ring units are interconnected to form a communication network; one of the smart ring units is designated as the master control unit, and its microcontroller is configured to receive trigger identifiers and spatial attitude data from other subordinate ring units, and execute the relative parameter calculation steps and model storage steps.
[0032] The inertial measurement unit, integrating a three-axis gyroscope, a three-axis accelerometer, and a microcontroller, is used to detect the spatial posture and motion trajectory of the hand. In one embodiment, the connection topology between different smart ring units is established via UWB, Bluetooth, or Zigbee wireless communication.
[0033] See Figure 3 As shown in the figure, the location of the physical sensor switch (on the back of the hand) is crucial for triggering calibration. The approximate wearing position of the ring on the finger (e.g., the second joint of the thumb, the second joint of other fingers) helps in understanding the spatial relationship between the sensors during "static hand postures" (e.g., clenching a fist).
[0034] It should be noted that the thumb is usually worn on the second joint, the one closest to the palm, while the rings on other fingers should mainly be on the second joint to facilitate the capture of clear movements. However, the actual product design does not restrict the second and third joints to have materials worn at the same time. On the one hand, the rings on the second and third joints can be connected by some soft materials to help fix the rings on the second joint so that they do not come loose. On the other hand, more sensors can be installed on the third joint to accurately distinguish the flexion and extension movements of the fingers, or to make room for more micro batteries.
[0035] The finger-adapter is made of metal, lightweight engineering plastic, or silicone; the inertial measurement unit detects the spatial posture and movement of the finger ring, which is equivalent to detecting the spatial posture and movement trajectory of the hand.
[0036] Upon first power-on, the user needs to clench their fist to trigger the sensor switch on up to five rings, from the thumb ring to the index, middle, and ring fingers, and finally the little finger, to initially determine the ring positioning and spatial positioning. The sensor switch is located on the back of the hand to perform distance and fine angle geometric positioning for different hand shapes, as well as palm and back-of-hand positioning.
[0037] The technical solution of this invention is compatible with current mainstream AR / VR devices, game consoles and personal computers through the standard HID protocol. For example, devices such as the Meta Quest series and PICO series have been verified to be able to recognize and use them normally.
[0038] The various embodiments in this specification are described in a related manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.
[0039] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications and equivalent substitutions made within the spirit and principles of the present invention are included within the scope of protection of the present invention.
[0040] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for constructing a hand individualized geometric model for a multi-finger cooperative interaction system, characterized in that, The system comprises multiple smart rings worn on different fingers of the user, each smart ring equipped with an inertial measurement unit and a physical sensor switch. The method includes the following steps: S11, Calibration triggering step: prompt the user to maintain a preset static hand posture and trigger the physical sensor switch of the smart ring on the corresponding finger in sequence according to the predetermined finger order; S12, Spatial data recording step: At the moment when each of the physical induction switches is triggered, record the spatial attitude data collected by the inertial measurement unit of the corresponding smart ring. S13, relative parameter calculation step: Based on the predetermined finger sequence, the recorded spatial posture data, and the known or wirelessly measured connection topology between each smart ring, calculate a personalized parameter set that characterizes the user's hand shape. The personalized parameter set includes at least the relative spatial position and relative angle between different fingers. S14, Model storage step: Store the personalized parameter set as the user's personalized initial geometric model of the hand, which is used to provide a reference for spatial coordinate transformation in subsequent interaction processes.
2. The method of claim 1, wherein, The preset static hand posture is the user's clenched fist posture.
3. The method of claim 1, wherein, The predetermined finger order is from thumb, index finger, middle finger, ring finger to little finger.
4. The method of claim 1, wherein, The physical sensor switch is located on the outer side of the smart ring housing, corresponding to the back of the user's hand.
5. The method of claim 1, wherein, The connection topology measured by the wireless communication is determined through the connection relationship established by the UWB, NFC, or Zigbee communication protocol.
6. The method according to any one of claims 1 to 5, characterized in that, It also includes a recalibration step: During system use, in response to a user’s specific recalibration gesture, the personalized initial geometric model of the hand is updated based on newly acquired data to correct errors caused by sensor drift or loosening of the fit.
7. A smart ring device for performing hand personalized geometry model building, characterized by, It includes at least two smart ring units, each of which includes: Annular shell; An inertial measurement unit is built into the housing; A physical induction switch is located on the outside of the housing; A pressure or bending sensor is disposed inside the annular housing to detect finger movements; A microcontroller, connected to the inertial measurement unit and the physical sensor switch, is configured to: when the physical sensor switch is triggered, record the data of the inertial measurement unit and send the data along with a trigger identifier; The wireless communication module is used to transmit data between ring units and with the main control device; Power module.
8. The apparatus of claim 7, wherein, Different smart ring units establish the connection topology relationship through UWB, Bluetooth or Zigbee wireless communication.