An augmented reality visual gait intervention control method based on dynamic difficulty adaptation

Abstract

This invention discloses an augmented reality visual gait intervention control method based on dynamic difficulty adaptation, belonging to the fields of augmented reality and neurorehabilitation medicine. The method includes: acquiring a real-time probability value representing the user's current risk of frozen gait; dynamically determining the visual parameters of a virtual visual cue pattern based on the relationship between the probability value and a preset threshold; controlling an augmented reality display device to render and overlay the pattern onto the user's field of vision; wherein the visual parameters include at least the projection spacing, and the projection spacing is negatively correlated with the probability value. This invention achieves adaptive matching of intervention intensity by dynamically associating visual cue parameters with real-time risk, providing low-invasive guidance at low risk and switching to a highly significant blocking mode at high risk; employing a continuous adjustment mechanism ensures a smooth transition of visual changes, effectively preventing habituation, maintaining long-term intervention effectiveness, while reducing cognitive load and improving patient compliance.

Description

Technical Field

[0001] This invention belongs to the field of augmented reality (AR). In the fields of technology, human-computer interaction and neurorehabilitation medicine, specifically, this invention relates to an augmented reality visual gait intervention control method based on dynamic difficulty adaptation. Background Technology

[0002] Parkinson's disease ( Patients in the middle and late stages often exhibit frozen gait. This leads to a significant increase in the risk of walking interruption and falls. Visual cues are one of the effective non-pharmacological interventions for improving frozen gait, such as projecting laser lines on the ground, displaying grid patterns, or using augmented reality (AR). The glasses overlay a virtual path onto the field of vision. Studies have shown that visual cues can guide patients initiating and sustaining gait by referencing external spatial contexts.

[0003] However, existing visual cueing technologies have the following significant drawbacks:

[0004] First, the prompting pattern is fixed and the visual parameters remain constant, which can easily lead to patients becoming habitual and significantly reduce the long-term intervention effect. Second, it lacks linkage with real-time risks and has an open-loop design, which cannot provide targeted intervention during the high-risk freezing period and instead causes visual interference during the safe period. Third, the static difficulty cannot adapt to the fluctuations of patients' symptoms during the "on-off" period and intraday changes, resulting in unstable intervention effects.

[0005] Therefore, there is an urgent need in this field for an adaptive visual intervention control method that can dynamically adjust according to the patient's real-time physiological state and has an anti-habituation mechanism. Summary of the Invention

[0006] This invention aims to solve the technical problems of existing visual gait intervention systems, such as habituation, diminishing effectiveness, and inability to match real-time risks, caused by fixed prompting patterns and lack of adaptability. It provides an augmented reality visual intervention control method based on dynamic difficulty adaptation.

[0007] To address the aforementioned technical problems, this invention provides an augmented reality visual gait intervention control method based on dynamic difficulty adaptation, characterized by comprising the following steps executed by a processor:

[0008] step Obtain the real-time probability value representing the risk of a user experiencing physical gait freeze. ;in ;

[0009] step According to the probability value The visual parameters of the virtual visual cue pattern to be rendered are dynamically determined based on its relationship with a preset threshold.

[0010] step The system controls the augmented reality display device to render and overlay the virtual visual cue pattern onto the user's field of vision based on the visual parameters.

[0011] The visual parameters include at least the spatial projection spacing of the virtual visual cue patterns, and the projection spacing is related to the probability value. Negative correlation, that is, when As the height increases, the projection spacing decreases.

[0012] Further, the steps The preset thresholds include the first threshold. Second threshold ,and The dynamic determination of visual parameters specifically includes:

[0013] when At that time, the visual parameters are determined to be the first set of visual parameters, which includes the first spacing value;

[0014] when When the visual parameter is determined to be a second set of visual parameters, which includes a second spacing value that is less than the first spacing value;

[0015] when At that time, according to the probability value The projection spacing is continuously adjusted so that it varies between the first spacing value and the second spacing value.

[0016] Furthermore, the visual parameters also include the color of the virtual visual cue pattern, wherein the color is a first color in the first set of visual parameters and a second color different from the first color in the second set of visual parameters; when At that time, the color gradually changes from the first color to the second color.

[0017] Furthermore, the first color is green, and the second color is red or orange.

[0018] Furthermore, the visual parameters also include the transparency of the virtual visual cue pattern, and the transparency is a first transparency value in the first set of visual parameters and is less than the first transparency value in the second set of visual parameters.

[0019] Furthermore, the visual parameters also include the edge luminescence intensity of the virtual visual cue pattern, and the edge luminescence intensity in the second set of visual parameters is greater than the luminescence intensity in the first set of visual parameters.

[0020] Furthermore, the virtual visual cue pattern is a horizontal guide line segment or a virtual path.

[0021] Furthermore, the method also includes receiving user-personalized parameters from external input, the personalized parameters being used to set a baseline value for the visual parameters.

[0022] Compared with the prior art, the present invention has the following significant technical advancements and beneficial effects:

[0023] By dynamically linking visual cue parameters with the real-time freezing risk probability, adaptive matching of intervention intensity is achieved. Low-risk situations provide low-invasive subconscious guidance, while high-risk situations switch to a highly significant blocking mode to seize cortical processing resources. A continuous adjustment mechanism is adopted to ensure a smooth transition of visual changes and reduce cognitive load. By dynamically adjusting the line spacing, patients are guided to subconsciously adjust their gait, effectively preventing habituation and maintaining the long-term effectiveness of the intervention. Attached Figure Description

[0024] Figure 1 This is a schematic diagram of the overall process of the control method described in this invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0026] Example 1: Implementation of Dynamic Visual Intervention Based on AR Glasses

[0027] This embodiment describes how to integrate... The control method described in this invention is implemented on smart glasses with display functionality. The glasses have a built-in spatial computing chip, optical projection engine, and wireless communication module, enabling them to communicate in real time with upstream EEG signal processing devices (such as smartphones or dedicated processors) and receive the probability value of the risk of being frozen.

[0028] Hardware environment: A lightweight holographic waveguide Smart glasses, equipped with embedded processors (such as Qualcomm) The platform runs a dedicated control application. The glasses connect to external edge computing devices via low-latency Bluetooth to obtain real-time probability of freezing risks. .

[0029] Software preset parameters:

[0030] First threshold:

[0031] Second threshold:

[0032] Basic spacing: (Guiding distance corresponding to the patient's natural stride)

[0033] High-risk spacing:

[0034] Basic color: Green ( : )

[0035] High-risk color: Red : )

[0036] Basic transparency:

[0037] High-risk transparency:

[0038] Method execution steps:

[0039] 1. Steps Get real-time risk probability

[0040] The control application continuously monitors real-time data streams from the edge computing device via a Bluetooth interface. Whenever a new risk probability value is received... (This value is derived from the upstream EEG analysis model every 50) Once calculated, the rendering update process is immediately triggered.

[0041] 2. Steps Visual parameter mapping

[0042] According to the received The value is used to perform the following logical judgments and calculations:

[0043] 2.1 If The system determines the status as "low-risk" and directly uses the preset low-risk parameters: rendering spacing. The color is green, and the transparency is... . The glasses project a series of parallel, horizontally guiding lines onto the ground directly in front of the user's field of vision, with a spacing of approximately 60 mm between the lines. The color is a semi-transparent green, subtly indicating stride length.

[0044] 2.2 If The system has determined the status to be "high-risk warning" and immediately switched to the high-risk parameter: rendering spacing. The color is red, and the transparency is... At this point, the spacing between the lines projected by the glasses shortens to 30. The color turns a striking red with very low transparency, creating a strong visual warning that forces patients to increase their pace to cross these lines.

[0045] 2.3 If The system enters dynamic continuous adjustment mode. According to... Calculate the current rendering parameters:

[0046] 2.3.1 Spacing Calculation:

[0047]

[0048] when hour, ;

[0049] when hour, Intermediate value linear interpolation.

[0050] 2.3.2 Color Calculation: Using... Linear interpolation makes the color change from green ( (Time) Smoothly transitions to red ( hour).

[0051] 2.3.3 Transparency Calculation:

[0052]

[0053] As the risk increases, the transparency decreases, and the lines become clearer.

[0054] Through this continuous adjustment, as the risk gradually increases, patients will perceive that the guiding lines under their feet gradually become denser, the color changes from green to red, and the lines become more solid. This change is synchronized with the changes in their internal neural state, forming a kind of implicit "difficulty cue".

[0055] 3. Steps Real-time rendering output

[0056] The glasses' spatial computing engine calculates the precise position of the virtual lines in the real-world coordinate system in real time, based on the parameters (spacing, color, transparency) and the current head posture and spatial anchor points, and then calls the optical engine for projection rendering. The entire process has extremely low latency (typically in the millisecond range), ensuring that visual cues are synchronized with the patient's head movements.

[0057] Personalized configuration:

[0058] During initial use, rehabilitation therapists can set personalized parameters for the patient using the accompanying mobile application. For example, for patients with small strides, the basic distance can be adjusted. Adjusted to 50 For patients who are insensitive to red, high-risk colors can be changed to orange or yellow. These personalized configurations serve as the system baseline for use by the aforementioned dynamic adjustment algorithm.

[0059] Through the above steps, this embodiment achieves closed-loop control by dynamically and continuously adjusting the difficulty of visual cues based on the patient's real-time risk probability of freezing, effectively avoiding habituation and achieving precise intervention for risk matching.

[0060] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. An augmented reality visual gait intervention control method based on dynamic difficulty adaptation, characterized in that, This includes the following steps performed by the processor: step Obtain the real-time probability value representing the risk of a user experiencing physical gait freeze. ;in ; step According to the probability value The visual parameters of the virtual visual cue pattern to be rendered are dynamically determined based on its relationship with a preset threshold. step The system controls the augmented reality display device to render and overlay the virtual visual cue pattern onto the user's field of vision based on the visual parameters. The visual parameters include at least the spatial projection spacing of the virtual visual cue patterns, and the projection spacing is related to the probability value. Negative correlation, that is, when As the height increases, the projection spacing decreases.

2. The method according to claim 1, characterized in that, The steps The preset thresholds include the first threshold. Second threshold ,and The dynamic determination of visual parameters specifically includes: when At that time, the visual parameters are determined to be the first set of visual parameters, which includes the first spacing value; when When the visual parameter is determined to be a second set of visual parameters, which includes a second spacing value that is less than the first spacing value; when At that time, according to the probability value The projection spacing is continuously adjusted so that it varies between the first spacing value and the second spacing value.

3. The method according to claim 2, characterized in that, The visual parameters also include the color of the virtual visual cue pattern, wherein the color is a first color in the first set of visual parameters and a second color different from the first color in the second set of visual parameters; when At that time, the color gradually changes from the first color to the second color.

4. The method according to claim 3, characterized in that, The first color is green, and the second color is either red or orange.

5. The method according to claim 2, characterized in that, The visual parameters also include the transparency of the virtual visual cue pattern, wherein the transparency is a first transparency value in the first set of visual parameters and is less than the first transparency value in the second set of visual parameters.

6. The method according to claim 2, characterized in that, The visual parameters also include the edge luminescence intensity of the virtual visual cue pattern, and the edge luminescence intensity in the second set of visual parameters is greater than the luminescence intensity in the first set of visual parameters.

7. The method according to claim 2, characterized in that, The virtual visual cue pattern is a horizontal guide line segment or a virtual path.

8. The method according to claim 1, characterized in that, The method also includes receiving user-personalized parameters from external input, the personalized parameters being used to set a baseline value for the visual parameters.

Images