Parameter updating method and device, electronic equipment, storage medium and product

Abstract

The invention provides a parameter updating method and device, electronic equipment, a storage medium and a product. The method comprises the following steps: acquiring user action data, wherein the user action data is acquired by at least two sets of acquisition equipment; extracting user posture data and user gesture data from the user action data; determining a user posture recognition score based on the user posture data, and determining a user gesture recognition score based on the user gesture data; in response to the fact that the user posture recognition score is smaller than a first preset score, posture recognition parameters of the virtual reality equipment are updated according to the user posture data, and in response to the fact that the user gesture recognition score is smaller than a second preset score, gesture recognition parameters of the virtual reality equipment are updated according to the user gesture data.

Description

Technical Field

[0001] This disclosure relates to the field of virtual reality technology, and in particular to a parameter updating method, apparatus, electronic device, storage medium, and product. Background Technology

[0002] In virtual reality interaction solutions, existing devices often rely on a single acquisition device to obtain user motion data, which makes it difficult to comprehensively capture multidimensional information about user limb movements and fine hand movements. This results in one-sided sources of motion data and insufficient accuracy, which in turn leads to limited device posture and gesture recognition accuracy and a poor user interaction experience. Summary of the Invention

[0003] This disclosure provides a parameter update method, apparatus, electronic device, storage medium, and product to solve the problem in the related art that the accuracy of user action data acquired by a single acquisition device is insufficient, resulting in limited accuracy of device posture and gesture recognition and poor user interaction experience.

[0004] A first aspect of this disclosure provides a parameter update method, the method comprising: User action data is acquired, and the user action data is collected by at least two acquisition devices; Extract user posture data and user gesture data from user action data; Based on user posture data, a user posture recognition score is determined; based on user gesture data, a user gesture recognition score is determined. In response to a user's posture recognition score being less than a first preset score, the posture recognition parameters of the virtual reality device are updated based on the user's posture data; and in response to a user's gesture recognition score being less than a second preset score, the gesture recognition parameters of the virtual reality device are updated based on the user's gesture data.

[0005] In one embodiment, acquiring user action data includes: Acquire data on user interactions with virtual reality devices; By analyzing the interactive operation data, the performance evaluation results of the virtual reality device are obtained; In response to the virtual reality device's performance evaluation result being no less than the preset performance evaluation result, user action data is acquired.

[0006] In one embodiment, the interactive operation data includes the maximum frame rate of transmitted images, the highest network latency, the average refresh rate of the display screen, and the highest operating temperature of the virtual reality device during the interactive monitoring period. Analyzing the interactive operation data yields the performance evaluation results of the virtual reality device, including: Determine the weight set, which includes the first weight corresponding to the maximum frame rate of the transmitted images of the virtual reality device during the interaction monitoring period, the second weight corresponding to the maximum network latency, the third weight corresponding to the average refresh rate of the display screen, and the fourth weight corresponding to the maximum operating temperature. The performance evaluation results of the virtual reality device are determined based on the weight set, the maximum frame rate of the transmitted images of the virtual reality device during the interactive monitoring period, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature.

[0007] In one embodiment, after analyzing the interactive operation data to obtain the performance evaluation results of the virtual reality device, the method provided in this disclosure further includes: In response to the virtual reality device's performance evaluation result being lower than the preset performance evaluation result, an early warning message is generated for the interactive operation of the virtual reality device. The early warning message includes at least one of the following: a performance abnormality warning message pops up on the virtual reality device's display screen, or the refresh rate of the virtual reality device's display screen is adjusted.

[0008] In one embodiment, extracting user posture data and user gesture data from user action data includes: Feature extraction is performed on user action data to obtain user action features associated with user posture and user gestures; Based on user action characteristics, user actions are analyzed to obtain user posture data and user gesture data.

[0009] In one embodiment, user posture data includes the average head tilt angle, average arm movement speed, and average leg movement speed during the interaction process; user gesture data includes the average finger rotation angle and average gesture movement speed during the interaction process. Based on the user posture data, a user posture recognition score is determined; and based on the user gesture data, a user gesture recognition score is determined, including: The user posture recognition score is determined based on the maximum frame rate of the transmitted images of the virtual reality device during the interaction monitoring period, the average tilt angle of the user's head, the average movement speed of the arm, and the average movement speed of the leg during the interaction process. The user gesture recognition score is determined based on the maximum network latency, the average rotation angle of the user's fingers, and the average movement speed of the gesture during the interaction process.

[0010] A second aspect of this disclosure provides a parameter updating apparatus, the apparatus comprising: The acquisition unit is used to acquire user action data, which is collected by at least two acquisition devices. The extraction unit is used to extract user posture data and user gesture data from user action data; The determining unit is used to determine the user posture recognition score based on user posture data and the user gesture recognition score based on user gesture data. The update unit is used to update the posture recognition parameters of the virtual reality device based on the user posture data in response to the user posture recognition score being less than a first preset score, and to update the gesture recognition parameters of the virtual reality device based on the user gesture data in response to the user gesture recognition score being less than a second preset score.

[0011] A third aspect of this disclosure provides an electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the methods described in the first aspect of this disclosure.

[0012] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods described in the first aspect of this disclosure.

[0013] A fifth aspect of this disclosure provides a computer program product including a computer program that, when executed by a processor, implements the methods described in the first aspect of this disclosure.

[0014] In summary, this disclosure proposes a parameter update method, which includes: acquiring user action data, wherein the user action data is acquired by at least two acquisition devices; extracting user posture data and user gesture data from the user action data; determining a user posture recognition score based on the user posture data, and determining a user gesture recognition score based on the user gesture data; updating the posture recognition parameters of the virtual reality device according to the user posture data in response to the user posture recognition score being less than a first preset score, and updating the gesture recognition parameters of the virtual reality device according to the user gesture data in response to the user gesture recognition score being less than a second preset score.

[0015] According to the solution provided in this disclosure, user motion data is collected through at least two acquisition devices, ensuring the comprehensiveness and reliability of the data source. By combining the extraction and quantitative scoring of user posture data and user gesture data, an accurate evaluation of the device's recognition effect is achieved. The recognition parameters of the virtual reality device are updated based on the scoring results, which can adapt to the different body movement habits of different users, improve the recognition accuracy of the virtual reality device for user posture and gestures, and thus enhance the user interaction experience.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0018] Figure 1 A flowchart illustrating a parameter update method provided in an embodiment of this disclosure; Figure 2 A flowchart illustrating a method for acquiring user action data provided in an embodiment of this disclosure; Figure 3 A flowchart illustrating a parameter update method provided as an application example of this disclosure; Figure 4 This is a schematic diagram of the structure of a parameter updating device provided in an embodiment of the present disclosure; Figure 5 This is a schematic diagram of the hardware composition structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0019] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0020] The following is a brief introduction to one approach for parameter updating in related technologies: The proposed solution utilizes sensors in a Virtual Reality (VR) device to collect a user's three-axis acceleration data over a preset time period, generating a pose blend set. Then, pose adjustment values ​​are generated based on this blend set. These adjustment values ​​are used to correct the user's three-axis acceleration data over the preset time period, and a predicted action is generated for the VR device. This method aims to improve the accuracy of VR interaction and the user experience.

[0021] The above solution has the following drawbacks: Existing technologies often rely on data from a single sensor, neglecting the importance of multi-sensor data fusion. This limits the reliability and accuracy of sensor data, thereby affecting the stability and accuracy of VR interaction.

[0022] To address the shortcomings of related technologies, this disclosure collects user motion data using at least two acquisition devices, ensuring the comprehensiveness and reliability of the data source. By combining the extraction and quantification scoring of user posture data and user gesture data, it achieves accurate evaluation of the device's recognition performance. Based on the scoring results, the recognition parameters of the virtual reality device are updated, which can adapt to the different body movement habits of users, improve the recognition accuracy of the virtual reality device for user posture and gestures, and thus enhance the user interaction experience.

[0023] The present disclosure will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0024] The parameter update method provided in this disclosure can be applied to virtual reality-related scenarios that require precise and personalized human-computer interaction, such as VR game entertainment scenarios, VR education and training scenarios, or VR rehabilitation training scenarios. The execution subject of the method can be a VR device with a built-in processor, data fusion analysis unit, and interactive control database, or it can be a smart terminal or server that is communicatively connected to the VR device.

[0025] like Figure 1 As shown, Figure 1 This is a flowchart illustrating a parameter update method provided in an embodiment of this disclosure. The parameter update method provided in this embodiment includes the following steps: Step 101: Acquire user action data, which is collected by at least two acquisition devices; In one embodiment, user motion data refers to raw data captured by multiple acquisition devices that reflects the movement state of the user's limbs and hands during interaction, including multi-dimensional information such as motion trajectory, speed, angle, and acceleration. The acquisition devices refer to sensing devices used to capture user motion, including but not limited to inertial sensors such as accelerometers, gyroscopes, magnetometers, motion capture cameras, sensor gloves, and wristbands.

[0026] In one embodiment, an accelerometer can be used to collect linear acceleration data of the user's movements, a gyroscope can be used to collect angular velocity data, and a magnetometer can be used to collect magnetic field strength data. The accelerometer, gyroscope, and magnetometer work together to capture the spatial motion state of the user's limbs, thereby obtaining user movement data.

[0027] In one embodiment, a motion capture camera can be used to capture the overall movement trajectory of a user's limbs through image recognition technology, and sensor gloves can be used to collect data on the bending angle, rotation angle, and movement speed of finger joints, thereby obtaining user motion data.

[0028] In one embodiment, a gyroscope can be used to capture limb rotation data, a motion capture device can be used to collect limb displacement data, and a temperature compensation sensor can be used to correct the interference of ambient temperature on the sensing data, so that the acquired user motion data is more accurate.

[0029] In one embodiment, an inertial measurement unit can be used to integrate an accelerometer and a gyroscope to output inertial data of limb movement in real time; an optical tracking sensor can be used to locate the spatial position of the limb using infrared or visible light technology, thereby obtaining user motion data.

[0030] Step 102: Extract user posture data and user gesture data from user action data; In one embodiment, the user posture data is feature data extracted from user action data that reflects the overall limb state of the user, such as the average tilt angle of the head, the average movement speed of the arms, and the average movement speed of the legs.

[0031] In one embodiment, the user gesture data is feature data extracted from user action data that reflects the movement state of the user's hand and fingers, such as the average finger rotation angle and the average movement speed of the gesture.

[0032] In one embodiment, environmental noise, such as equipment vibration and electromagnetic interference, in the original data can be filtered out first using the Kalman filter algorithm. Then, the Principal Component Analysis (PCA) algorithm is used to extract posture-related features and gesture-related features. Posture-related features include head tilt angle and limb movement speed, while gesture-related features include finger rotation angle and gesture movement speed.

[0033] In one embodiment, the user action data can also be synchronized in time and standardized in format by a data fusion analysis unit, and then the fused data can be classified by a Support Vector Machine (SVM) algorithm to obtain posture-related features and gesture-related features, thereby generating user posture data and user gesture data.

[0034] In one embodiment, the preprocessed user action data can also be input into a pre-trained convolutional neural network (CNN) model, and high-order features of pose and gesture can be automatically extracted through multi-layer convolution and pooling operations to obtain user pose data and user gesture data.

[0035] Step 103: Determine the user posture recognition score based on user posture data, and determine the user gesture recognition score based on user gesture data; In one embodiment, the posture recognition score is a quantitative index calculated based on user posture data, used to evaluate the accuracy of virtual reality devices in recognizing user postures. The score is positively correlated with the recognition accuracy.

[0036] In one embodiment, the gesture recognition score is a quantitative index calculated based on user gesture data, used to evaluate the accuracy of virtual reality devices in recognizing user gestures. The score is positively correlated with the recognition accuracy.

[0037] In one embodiment, the posture recognition score can be obtained by comparing the average head tilt angle, average arm movement speed, and average leg movement speed with preset reference values, calculating the deviation rate, multiplying by the corresponding correction factor, and summing the results. Similarly, the gesture recognition score can be obtained by comparing the average finger rotation angle and average gesture movement speed with preset reference values, calculating the deviation rate, and then combining this with a network latency impact factor, followed by a weighted summation. Both the correction factor and the network latency impact factor are values ​​between 0 and 1.

[0038] In one embodiment, the similarity between user gesture data and standard gesture templates in the interaction control database can be calculated, such as cosine similarity, and the similarity value is the gesture recognition score; the gesture recognition score is obtained by calculating the similarity between user gesture data and standard gesture templates, and a network latency correction coefficient can be introduced to adjust the recognition score.

[0039] Step 104: In response to the user's posture recognition score being less than the first preset score, update the posture recognition parameters of the virtual reality device based on the user's posture data; and in response to the user's gesture recognition score being less than the second preset score, update the gesture recognition parameters of the virtual reality device based on the user's gesture data.

[0040] In one embodiment, the virtual reality device is an intelligent hardware that uses computer technology to construct an immersive virtual environment and supports users to interact with the virtual scene in real time through natural interaction methods such as posture and gestures. It includes core components such as multi-sensor devices, data fusion and analysis units, and display and interaction modules, such as VR headsets and matching interactive gloves.

[0041] In one embodiment, the first preset score refers to the attitude recognition accuracy threshold stored in the device interaction control database. It is a benchmark value for determining whether the attitude recognition parameters need to be updated and is preset based on historical data and technical requirements.

[0042] In one embodiment, the second preset score refers to the gesture recognition accuracy threshold stored in the device interaction control database. It is a benchmark value for determining whether the gesture recognition parameters need to be updated and is preset based on historical data and technical requirements.

[0043] In one embodiment, posture recognition parameters refer to the algorithm configuration data used in the virtual reality device to recognize the user's posture, including posture reference data, feature weights, recognition thresholds, etc., such as the initially preset head reference tilt angle, arm reference movement speed, etc.

[0044] In one embodiment, gesture recognition parameters refer to the algorithm configuration data used in the virtual reality device to recognize user gestures, including gesture reference data, feature weights, recognition thresholds, etc., such as the initially preset finger reference rotation angle, gesture reference movement speed, etc.

[0045] In one embodiment, when the posture recognition score is lower than the first preset score, the average tilt angle of the current user's head, the average movement speed of the arm, and the average movement speed of the leg can be updated to the preset reference posture data of the device posture recognition algorithm; when the gesture recognition score is lower than the second preset score, the average rotation angle of the current user's fingers and the average movement speed of the gesture can be updated to the preset reference gesture data.

[0046] In one embodiment, when the posture recognition score is lower than the first preset score, the feature weight of the corresponding dimension in the recognition algorithm can be adjusted according to the degree of deviation of each dimension of the posture data. For example, when the head tilt angle deviation is large, the weight of that dimension is increased. The same logic is used for the gesture recognition parameters to adjust the weight of finger action features and gesture movement speed features.

[0047] In one embodiment, the current user posture data and the corresponding recognition error can be used as training samples and input into the posture recognition algorithm model. The weight parameters of the model are then iteratively updated using the gradient descent method. The gesture recognition algorithm uses the same method to update the model parameters based on the user gesture data and the recognition error.

[0048] User motion data is acquired collaboratively by at least two acquisition devices to ensure the diversity and comprehensiveness of data sources. From this data, posture data reflecting the overall state of the user's limbs and gesture data detailing hand movements are extracted. Based on these two types of data, corresponding recognition scores are determined to quantitatively evaluate the device's recognition effectiveness. These scores are compared with preset scores. If the posture recognition score falls below a first preset score, the device's posture recognition parameters are optimized using the current user posture data. If the gesture recognition score is lower than a second preset score, the device's gesture recognition parameters are updated based on the current user gesture data. Acquisition devices may include inertial sensors, posture sensors, etc. Posture data may involve head and limb movement characteristics, while gesture data may include finger movement characteristics. This method enables adaptive adjustment of the device's recognition parameters.

[0049] By collecting data collaboratively from multiple devices, the completeness and reliability of user action information are improved. By using recognition scoring to trigger dynamic parameter updates, the adaptability and recognition accuracy of virtual reality devices to different user actions are improved, thereby enhancing the accuracy and personalization of device interaction control.

[0050] In one embodiment, such as Figure 2 As shown, user action data is obtained, including: Step 201: Obtain the interaction data between the user and the virtual reality device; In one embodiment, interactive operation data refers to a multi-dimensional data set reflecting the operating status and interactive performance of the VR device during the interaction monitoring period, which is used to evaluate whether the VR device can stably collect user action data.

[0051] In one embodiment, the interactive operation data may include the maximum frame rate of the transmitted images of the VR device during the interactive monitoring period, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature.

[0052] In one embodiment, operating temperature data can be collected using a temperature sensor equipped on the VR device. At the same time, the device's built-in performance monitoring software can record the frame rate data and network latency data of the transmitted screen in real time. The display screen refresh rate data can be obtained by calling the device's system application programming interface (API) function.

[0053] In one embodiment, hardware-related data such as device operating temperature and display screen refresh rate can be collected through a hardware monitoring module. Network testing tools, such as the Ping command and network latency monitoring plugins, can be used to simulate the data transmission process, obtain the highest network latency data, and use video stream analysis tools to count the maximum frame rate of the transmitted video.

[0054] In one embodiment, the VR device can also establish a communication connection with a third-party professional performance monitoring device, which can synchronously collect full-dimensional interactive operation data such as transmission frame rate, network latency, screen refresh rate and operating temperature during the interactive monitoring period to ensure the objectivity of data collection.

[0055] Step 202: Analyze the interactive operation data to obtain the performance evaluation results of the virtual reality device; In one embodiment, the performance evaluation result refers to a quantitative indicator obtained by comprehensively analyzing and calculating the interactive operation data, which is used to accurately reflect the stability, reliability and responsiveness of the VR device during the interaction process.

[0056] In one embodiment, the influencing factors or correction factors corresponding to each interactive operation data can be extracted from the interactive control database. The values ​​range from 0 to 1. The maximum frame rate of the transmitted screen, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature are multiplied by the corresponding factors respectively. Then, the results are integrated through rules such as linear weighted summation to obtain the performance evaluation results.

[0057] In one embodiment, historical interactive operation data and the corresponding actual performance of the device can also be used as training samples to train a performance evaluation model, such as a random forest model or a neural network model. The real-time collected interactive operation data can be input into the performance evaluation model to obtain the performance evaluation result.

[0058] In one embodiment, the interactive operation data can be divided into different performance levels, such as frame rate divided into high, medium and low levels, and latency divided into excellent, good and poor levels. Each level is assigned a corresponding quantitative score, and the total score of all data is calculated. The total score is used as the performance evaluation result of the VR device.

[0059] Step 203: In response to the virtual reality device's performance evaluation result being no less than the preset performance evaluation result, acquire user action data.

[0060] In one embodiment, the preset performance evaluation result is a performance benchmark threshold stored in the VR device interaction control database. It can be preset by historical interaction data, technical design standards and user requirements, and is used to determine whether the device performance meets the standard.

[0061] In one embodiment, if the performance evaluation result of the virtual reality device is not less than the preset performance evaluation result, it means that the current VR device has reached the expected standard in terms of performance and interaction, and can provide users with a stable and reliable interactive experience.

[0062] In one embodiment, the current VR device has reached the expected standards in terms of performance and interaction, and sends a start command to the VR device's data acquisition devices, such as accelerometers, gyroscopes, and magnetometers, to begin collecting user motion data.

[0063] In one embodiment, the current VR device has reached the expected standard in terms of performance and interaction. A short delay, such as 1-2 seconds, can be set to confirm that the device performance is stable. Then, the core sensors, such as inertial sensors, are activated first to collect basic motion data, and then auxiliary sensors, such as sensor gloves, are activated according to the interaction progress to collect detailed motion data.

[0064] In one embodiment, after the current VR device has reached the expected standards in terms of performance and interaction, it can also take into account auxiliary conditions such as the current network connection status and battery status of the VR device. If all auxiliary conditions are met, user action data will be collected. If the auxiliary conditions are not met, such as the battery is too low, the collection will be suspended and the user will be prompted to optimize the VR device status.

[0065] In one embodiment, when acquiring user action data, the interaction operation data between the user and the virtual reality device during the interaction monitoring period is first collected. The interaction operation data may include the maximum frame rate of the transmitted screen, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature. Subsequently, these interaction operation data are comprehensively analyzed to calculate the performance evaluation result of the virtual reality device. The performance evaluation result is a quantitative indicator reflecting the stability and reliability of the device during the interaction process. Only when the performance evaluation result is greater than or equal to the preset performance evaluation result in the interaction control database is the acquisition device equipped on the virtual reality device activated to collect the user's action data in real time during the interaction process, ensuring that the device is in a stable and reliable interactive state when the data is collected.

[0066] By first assessing device performance and then collecting user motion data, the problem of motion information distortion caused by collecting data when device performance is insufficient is avoided. This lays the foundation for the accurate extraction of subsequent posture and gesture data, while ensuring the smoothness of the user interaction experience.

[0067] In one embodiment, the interactive operation data includes the maximum frame rate of transmitted images, the highest network latency, the average refresh rate of the display screen, and the highest operating temperature of the virtual reality device during the interactive monitoring period. Analyzing the interactive operation data yields the performance evaluation results of the virtual reality device, including: Determine the weight set, which includes the first weight corresponding to the maximum frame rate of the transmitted images of the virtual reality device during the interaction monitoring period, the second weight corresponding to the maximum network latency, the third weight corresponding to the average refresh rate of the display screen, and the fourth weight corresponding to the maximum operating temperature. The performance evaluation results of the virtual reality device are determined based on the weight set, the maximum frame rate of the transmitted images of the virtual reality device during the interactive monitoring period, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature.

[0068] In one embodiment, the interaction monitoring period is a fixed time interval preset for evaluating the interaction performance of virtual reality devices, such as 10 seconds or 30 seconds. Device operation data is continuously collected within the above fixed time interval to ensure the comprehensiveness and representativeness of the performance evaluation.

[0069] In one embodiment, the maximum frame rate of transmitted images refers to the highest number of frames per second (FPS) of virtual scene images transmitted by the virtual reality device within the interaction monitoring period. This directly affects the smoothness of the image; a higher value indicates a lower probability of image stuttering. The maximum network latency refers to the longest round-trip time for data packets to be transmitted from the user end to the device processing unit within the interaction monitoring period, measured in milliseconds. This reflects the real-time nature of network data transmission; a lower value indicates a faster interactive response. The average refresh rate of the display screen refers to the average number of times the virtual reality device's display screen refreshes its images per second within the interaction monitoring period, measured in Hertz. This determines the continuity of the visual experience and, together with the frame rate, affects the immersive effect. The maximum operating temperature refers to the highest operating temperature of the core components of the virtual reality device, such as the processor and sensors, within the interaction monitoring period, measured in degrees Celsius. This reflects the device's operating load; excessively high temperatures may lead to performance degradation or malfunction.

[0070] In one embodiment, the weight set is a parameter set consisting of a first weight, a second weight, a third weight, and a fourth weight corresponding to four types of interactive operational data, respectively. This set is used to quantify the impact of each type of data on device performance, with each weight value ranging from 0 to 1. The first weight refers to the parameter in the weight set corresponding to the maximum frame rate of the transmitted image, used to adjust the proportion of the impact of this frame rate data in the performance evaluation result. The second weight refers to the parameter in the weight set corresponding to the highest network latency, used to adjust the proportion of the impact of this latency data in the performance evaluation result. The third weight refers to the parameter in the weight set corresponding to the average refresh rate of the display screen, used to adjust the proportion of the impact of this refresh rate data in the performance evaluation result. The fourth weight refers to the parameter in the weight set corresponding to the highest operating temperature, used to adjust the proportion of the impact of this temperature data in the performance evaluation result.

[0071] In one embodiment, fixed weight values ​​can be preset in the interactive control database, such as a first weight of 0.1, a second weight of 0.3, a third weight of 0.2, and a fourth weight of 0.4, to determine the weight set; alternatively, by analyzing the correlation between historical interactive operation data and the actual performance of the device, a mapping set of various data and weights can be established. For example, in high frame rate scenarios, the first weight is high. Real-time interactive operation data is input into the mapping set, and the corresponding weight parameters are dynamically matched to form a weight set.

[0072] In one embodiment, different weight templates can be preset according to the application scenario of the virtual reality device, such as gaming and entertainment or education and training. Before the interaction begins, the system identifies the scenario type and calls the first to fourth weights in the corresponding template to form a weight set that adapts to the current scenario. For example, in a game scenario, the first and third weights are increased, which can increase the influence of frame rate and refresh rate.

[0073] In one embodiment, based on the weight set, the maximum frame rate of the transmitted images of the virtual reality device during the interactive monitoring period, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature, the mathematical expression for the performance evaluation result of the virtual reality device is determined as follows:

[0074] in, The performance and reliability indicators of VR devices, i.e., performance evaluation results. The maximum frame rate of the transmitted images by the VR device during the interaction monitoring period. The influencing factor corresponding to the maximum frame rate unit value of the transmission screen preset for the interactive control database. It is a natural constant. This refers to the highest network latency of the VR device during the interaction monitoring period. The influence factor corresponding to the preset maximum network latency unit value for the interactive control database. The average screen refresh rate displayed by the VR device during the interaction monitoring period. The preset display screen reference refresh rate for the interactive control database. A correction factor corresponding to the average refresh rate of the display screen preset for the interactive control database. This represents the highest operating temperature of the VR device during the interactive monitoring period. The preset operating temperature for the interactive control database. The correction factor corresponding to the preset maximum operating temperature for the interactive control database.

[0075] The shorter the network latency of a VR device during the interaction monitoring period, the shorter the time interval between user actions and device responses, and the lower the latency of image transmission. This reduces screen stuttering or delays caused by network issues, resulting in a smoother perceived frame rate. Lower network latency also helps ensure stable and continuous image updates at higher refresh rates, thus improving the visual experience. Consequently, a higher performance reliability index for the VR device indicates more stable and reliable performance during interaction. Therefore, by comprehensively considering the maximum frame rate of transmitted images, the highest network latency, the average refresh rate of the display screen, and the highest operating temperature of the virtual reality device during the interaction monitoring period, the performance of the VR device can be evaluated more accurately.

[0076] The values ​​of the influence factors corresponding to the maximum frame rate of the transmitted image, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature range from 0 to 1. A mapping set is established between the historical maximum frame rate of the transmitted image, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature, respectively, and the influence factors corresponding to these parameters are then used to obtain the influence factors corresponding to the maximum frame rate of the transmitted image, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature. Real-time maximum frame rate of the transmitted image, maximum network latency, average refresh rate of the display screen, and maximum operating temperature are input into the mapping set to obtain the influence factors corresponding to the maximum frame rate of the transmitted image, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature. All of these influence factors and correction factors are extracted from the interactive control database.

[0077] As shown in Table 1, Table 1 is a table of performance and interaction reliability indicators for VR devices.

[0078]

[0079] In one embodiment, the influence factor corresponding to the maximum frame rate unit value of the transmitted image is set to 0.1, the reference refresh rate of the display screen is 80 Hz, the correction factor corresponding to the average refresh rate of the display screen is 0.2, the influence factor corresponding to the maximum network latency unit value is 0.3, the allowable operating temperature is 25 degrees Celsius, and the correction factor corresponding to the maximum operating temperature is 0.4.

[0080] Based on the data in Table 1 above, it can be determined that the larger the maximum frame rate of the transmitted image, the higher the maximum network latency, and the smaller the deviation of the average refresh rate of the display screen and the maximum operating temperature from the reference refresh rate and the allowable operating temperature of the display screen, the greater the performance interaction reliability index of the VR device. This indicates that the VR device has reached a high level in multiple key performance indicators and can provide users with a smoother, more realistic, and more comfortable VR interaction experience.

[0081] In one embodiment, the interactive operation data includes the maximum frame rate of the transmitted images, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature of the virtual reality device during the interactive monitoring period. When determining the weight set, the first weight corresponds to the maximum frame rate of the transmitted images, the second weight corresponds to the maximum network latency, the third weight corresponds to the average refresh rate of the display screen, and the fourth weight corresponds to the maximum operating temperature. The value of each weight is in the range of 0 to 1, and it is extracted from the interactive control database through the mapping set of historical interactive operation data and weights. When calculating the performance evaluation result, each interactive operation data is multiplied by its corresponding weight, and then the product results are integrated to finally obtain the quantified performance evaluation result of the virtual reality device.

[0082] In one embodiment, after analyzing the interactive operation data to obtain the performance evaluation results of the virtual reality device, the parameter update method further includes: In response to the virtual reality device's performance evaluation result being lower than the preset performance evaluation result, an early warning message is generated for the interactive operation of the virtual reality device. The early warning message includes at least one of the following: a performance abnormality warning message pops up on the virtual reality device's display screen, or the refresh rate of the virtual reality device's display screen is adjusted.

[0083] In one embodiment, the warning message is a set of signals generated by the system to prompt the user or adjust the device status when the VR device performance evaluation result fails to meet the preset standard, so as to avoid the decline in interactive experience or device failure due to insufficient device performance.

[0084] In one embodiment, displaying a performance abnormality warning message on the screen of the virtual reality device is a type of early warning message, which is to inform the user in a visual way about the current performance problems of the device, such as excessive temperature or excessive network latency, through text or graphic prompts.

[0085] For example, a text pop-up window can be displayed at the edge of the virtual reality device's screen, clearly indicating the type of abnormality, such as excessively high operating temperature (38°C), excessive network latency (120ms), and suggested actions, such as pausing use to cool down before trying again or checking the network connection.

[0086] In one embodiment, the VR device's built-in voice module can also play voice prompts synchronously, which, together with the text pop-up on the screen, can provide a double reminder to the user of device performance abnormalities, ensuring that the user is aware of the issue in a timely manner.

[0087] In one embodiment, the display screen refresh rate is the number of times the virtual reality device's display screen refreshes the image per second (in Hertz). Adjusting the display screen refresh rate of the virtual reality device will directly affect the continuity of the visual experience.

[0088] In one embodiment, the refresh rate can be adjusted in stages according to the degree of deviation between the performance evaluation result and the preset performance evaluation result. When the deviation is small, the refresh rate is reduced from 90Hz to 75Hz; when the deviation is large, the refresh rate is reduced from 90Hz to 60Hz to reduce the operating load of the VR device.

[0089] In one embodiment, a performance error warning message may first pop up on the screen to inform the user that the network latency is too high and the refresh rate has been automatically reduced to ensure smooth interaction. Then, the refresh rate is reduced from 100Hz to 80Hz, and the adjusted refresh rate value is displayed in real time.

[0090] In one embodiment, after obtaining the performance evaluation result of the virtual reality device, if the result is less than the preset performance evaluation result, a warning message will be automatically generated. Specifically, the performance anomaly warning message is displayed as a text prompt in the form of a pop-up window on the virtual reality device's display screen, informing the user of specific anomalies such as excessively high device operating temperature or excessive network latency. Adjusting the display screen refresh rate involves reducing the screen refresh rate according to preset rules based on the degree of deviation from the performance evaluation result, thereby reducing the device's operating load and preventing interaction interruptions due to performance overload.

[0091] The early warning system provided in this application can promptly notify users of abnormal device performance and proactively adjust device parameters, thereby preventing users from experiencing poor interactive experiences due to VR device malfunctions and improving the stability and security of VR device use.

[0092] In one embodiment, extracting user posture data and user gesture data from user action data includes: Feature extraction is performed on user action data to obtain user action features associated with user posture and user gestures; In one embodiment, feature extraction of user action data refers to filtering and refining key information that can characterize the essential attributes of user posture and gestures from user action data, and eliminating redundant data and environmental interference noise.

[0093] In one embodiment, environmental noise, such as equipment vibration and electromagnetic interference, in the raw data can be filtered out first using a Kalman filter algorithm, and then the PCA algorithm can be used to extract posture-related features and gesture-related features.

[0094] In one embodiment, the mean, variance, peak value, and temporal features of user action data, such as motion cycle and rate of change, can also be calculated. Combined with the physical motion laws of posture and gesture, feature parameters with strong correlation can be selected and fused to form user action features.

[0095] Based on user action characteristics, user actions are analyzed to obtain user posture data and user gesture data.

[0096] In one embodiment, user action features can be divided into a posture feature subset and a gesture feature subset, and then cosine similarity matching can be performed with standard posture feature templates and standard gesture feature templates in the interaction control database, respectively. Based on the matching results, standardized data such as the average head tilt angle and the average finger rotation angle are obtained, thereby obtaining user posture data and user gesture data.

[0097] In one embodiment, user action features can also be input into a trained classification model, such as a random forest classification model. Through feature weight calculation and category determination, the posture category and corresponding quantitative indicators, such as the average arm movement speed, and the gesture category and corresponding quantitative indicators, such as the average gesture movement speed, can be obtained, thereby obtaining user posture data and gesture data.

[0098] In one embodiment, when extracting user posture data and user gesture data from user action data, the raw action data collected by multiple sensors is first processed by time synchronization, format standardization and noise filtering. Then, limb movement features related to user posture and hand movement features related to user gesture are selected. Subsequently, the extracted action features are input into the action analysis model, and by comparing and matching with the preset posture feature templates and gesture feature templates in the interaction control database, combined with feature weight calculation, the user posture data and user gesture data are finally obtained.

[0099] By processing the data first, then extracting features and analyzing them, invalid data interference is effectively filtered out, ensuring the accuracy of posture and gesture data.

[0100] In one embodiment, user posture data includes the average head tilt angle, average arm movement speed, and average leg movement speed during the interaction process; user gesture data includes the average finger rotation angle and average gesture movement speed during the interaction process. Based on the user posture data, a user posture recognition score is determined; and based on the user gesture data, a user gesture recognition score is determined, including: The user posture recognition score is determined based on the maximum frame rate of the transmitted images of the virtual reality device during the interaction monitoring period, the average tilt angle of the user's head, the average movement speed of the arm, and the average movement speed of the leg during the interaction process. The user gesture recognition score is determined based on the maximum network latency, the average rotation angle of the user's fingers, and the average movement speed of the gesture during the interaction process.

[0101] In one embodiment, the average head tilt angle, average arm movement speed, and average leg movement speed of the user during the interaction process are all obtained through the gyroscope, accelerometer sensor, and motion capture device built into the VR device. If the performance interaction reliability index of the VR device is greater than or equal to the preset performance interaction reliability index threshold of the VR device in the interaction control database, the interaction process can be the aforementioned interaction monitoring cycle.

[0102] In one embodiment, the average head tilt angle refers to the average tilt angle of the user's head relative to a preset reference direction during the interaction monitoring period. It is obtained by collecting and calculating data through the built-in sensors of the VR device and reflects the spatial posture changes of the head. The average arm movement speed refers to the average movement speed of the user's arm in space during the interaction monitoring period and is used to capture the speed characteristics of arm movements. The average leg movement speed refers to the average movement speed of the user's leg in space during the interaction monitoring period and reflects the dynamic characteristics of leg movements.

[0103] In one embodiment, the mathematical expression for determining the user posture recognition score is as follows, based on the maximum frame rate of the transmitted images of the virtual reality device during the interaction monitoring period, the average tilt angle of the user's head during the interaction process, the average movement speed of the arms, and the average movement speed of the legs.

[0104] in, This refers to the user posture recognition index, or user posture recognition score. The average head tilt angle of the user during the interaction process. The preset head reference tilt angle for the interactive control database. A correction factor corresponding to the preset average head tilt angle for the interactive control database. The average arm movement speed of the user during the interaction process. The preset arm reference movement speed for the interactive control database, A correction factor is preset for the average arm movement speed in the interactive control database. The average speed of the user's legs during the interaction process. The preset leg reference movement speed for the interactive control database. A correction factor is preset for the average leg movement speed in the interactive control database. The maximum frame rate for transmitting images from the VR device during user interaction. The preset allowed frame rate for interactive control database, The correction factor corresponding to the maximum frame rate of the transmitted images preset for the interactive control database. This represents a comparison between the average head tilt angle and the reference head tilt angle. This is a comparison between the average arm movement speed and the reference arm movement speed. This represents a comparison between the average leg movement speed and the reference leg movement speed.

[0105] The greater the deviation between the average head tilt angle during interaction and the preset head reference tilt angle, the more difficult it may be to accurately identify the user's actual posture. This deviation may lead to errors in the VR device's judgment of the user's head position and direction. Similarly, a large difference between the average arm movement speed and the reference arm movement speed can make it difficult for the VR device to accurately determine the user's arm posture and intention, resulting in errors in the VR device's estimation of the user's arm position, direction, and speed. Likewise, a large difference between the average leg movement speed and the reference leg movement speed can make it difficult to accurately determine the user's leg posture and intention, potentially leading to errors in the VR device's estimation of the user's leg position, direction, and speed. Errors: The average head tilt angle, average arm movement speed, and average leg movement speed all affect the overall posture recognition accuracy. Furthermore, if the maximum frame rate of the transmitted image is lower than the allowed frame rate, the VR device cannot capture all the details of the user's movements, leading to posture recognition errors. A low frame rate can also increase the latency when the VR device processes user input, resulting in stuttering, crashes, and other issues. Therefore, analyzing these four parameters helps the VR device more accurately capture and analyze user movements. By reducing errors and increasing the sampling frequency, the VR device can more accurately determine the user's current posture and intentions, thereby improving the overall posture recognition accuracy.

[0106] The correction factors corresponding to the average head tilt angle, average arm movement speed, average leg movement speed, and maximum frame rate of the transmitted image range from 0 to 1. A mapping set is established by mapping the historical average head tilt angle, average arm movement speed, average leg movement speed, and maximum frame rate of the transmitted image to the correction factors corresponding to the average head tilt angle, average arm movement speed, average leg movement speed, and maximum frame rate of the transmitted image, respectively. The real-time average head tilt angle, average arm movement speed, average leg movement speed, and maximum frame rate of the transmitted image are then mapped to the refresh rate of the display screen to obtain the correction factors corresponding to the average head tilt angle, average arm movement speed, average leg movement speed, and maximum frame rate of the transmitted image. All of the above correction factors are extracted from the interactive control database.

[0107] In one embodiment, the average finger rotation angle refers to the average rotation angle of a single or multiple fingers of the user relative to a reference position within the interaction monitoring period. This can be collected by a sensor glove or wristband to capture the details of the finger rotation movements. The average gesture movement speed refers to the average movement speed of the user's hand as a whole to complete a specific gesture movement within the interaction monitoring period, reflecting the smoothness and speed of the gesture movement.

[0108] In one embodiment, the average finger rotation angle and average gesture speed of the user during the interaction process are captured by gloves or wristbands equipped with sensors such as accelerometers, gyroscopes, and magnetometers. These sensors can monitor the finger rotation angle and movement speed in real time and transmit the data to a data fusion analysis unit for processing, thereby obtaining the average finger rotation angle and average gesture speed. However, when the network latency of the VR device is high, the user's finger movements may not be transmitted to the data fusion analysis unit in a timely manner, resulting in a slower response from the VR device. This latency causes the user to experience noticeable stuttering and discontinuity during the interaction. For the average finger rotation angle and average gesture speed, network latency may prevent the VR device from accurately capturing and analyzing the user's finger movements. Due to the delay in data packet transmission and processing, the VR device may not be able to obtain the latest position and posture information of the user's fingers in a timely manner, leading to errors in the recognition results.

[0109] In one embodiment, the mathematical expression for determining the user gesture recognition score is as follows, based on the highest network latency, the average finger rotation angle of the user during the interaction process, and the average movement speed of the gesture;

[0110] in, This refers to the user gesture recognition index, or user gesture recognition score. The average finger rotation angle during the user's interaction. The preset finger reference rotation angle for the interactive control database. A correction factor corresponding to the average finger rotation angle preset for the interactive control database. The average speed of the user's gestures during the interaction process. The preset gesture reference speed for the interactive control database The correction factor corresponding to the average movement speed of gestures preset in the interactive control database. The maximum network latency for the VR device during user interaction. The preset network latency allowance for the interactive control database The correction factor corresponding to the preset maximum network latency for the interactive control database.

[0111] Network latency means a longer time for data sent from the user's device (such as finger position, rotation angle, etc.) to reach the server or processing unit. This latency can cause the user's hand position to change while the VR device is processing this data, resulting in data synchronization errors. The greater the maximum network latency exceeds the allowable latency, the greater the deviation between the average finger rotation angle and the reference finger rotation angle, and the greater the deviation between the average gesture speed and the reference gesture speed. High latency also slows down the VR device's response to user input, making it unable to accurately and instantly capture the user's hand movements, thus affecting the accuracy and smoothness of gesture recognition and resulting in a lower gesture recognition index.

[0112] The correction factors corresponding to the average finger rotation angle, the average gesture speed, and the highest network latency range from 0 to 1. A mapping set is established by mapping the historical average finger rotation angle, average gesture speed, and highest network latency to the correction factors corresponding to the average finger rotation angle, average gesture speed, and highest network latency, respectively. The real-time average finger rotation angle, average gesture speed, and highest network latency are then input into the mapping set to obtain the correction factors corresponding to the average finger rotation angle, average gesture speed, and highest network latency. All of these correction factors are extracted from the interactive control database.

[0113] In one embodiment, user posture data includes average head tilt angle, average arm movement speed, and average leg movement speed; user gesture data includes average finger rotation angle and average gesture movement speed. When determining the user posture recognition score, the maximum frame rate of the transmitted image during the interaction monitoring period is combined with the average head tilt angle, average arm movement speed, and average leg movement speed, respectively, using corresponding correction factors, and the results are calculated in the manner described above. When determining the user gesture recognition score, the highest network latency is combined with the average finger rotation angle and average gesture movement speed, respectively, using corresponding correction factors, and the results are quantified in the manner described above. Each correction factor is extracted from the historical data mapping set of the interaction control database.

[0114] By combining equipment operating parameters with user action data to determine posture recognition scores and gesture recognition scores, the scoring results can comprehensively reflect the impact of equipment performance and user action characteristics on recognition effectiveness, thereby improving the objectivity and accuracy of posture recognition scores and gesture recognition scores.

[0115] In one embodiment, in response to a user posture recognition score being less than a first preset score, updating the posture recognition parameters of the virtual reality device based on user posture data includes: if the user posture recognition index (i.e., the user posture recognition score) is greater than or equal to a preset user posture recognition index threshold (i.e., the first preset score) in the interaction control database, then there is no need to optimize the posture interaction control of the VR device based on the user posture data; if the user posture recognition index is less than the preset user posture recognition index threshold in the interaction control database, then there is a need to optimize the posture interaction control of the VR device based on the user posture data.

[0116] If the user posture recognition index is greater than or equal to the preset user posture recognition index threshold in the interaction control database, it means that the user's posture during the interaction with the VR device has been accurately captured and analyzed, and the recognition result has reached the standard set by the system. Therefore, there is no need to optimize the interaction control of the VR device based on the user's posture. If the user posture recognition index is less than the preset user posture recognition index threshold in the interaction control database, it means that the VR device's accuracy in recognizing the user's current posture has not reached the expected standard. In this case, it is necessary to optimize the posture interaction control of the VR device based on the user posture data. Specifically, the optimization involves readjusting the parameters in the VR device's posture recognition algorithm, such as changing the initially preset user reference posture data, that is, using the user's average head tilt angle, average arm movement speed, and average leg movement speed as user reference posture data to improve the ability to recognize the user's posture and make the user's personalized experience stronger.

[0117] In one embodiment, in response to a user gesture recognition score being less than a second preset score, updating the gesture recognition parameters of the virtual reality device based on user gesture data includes: if the user gesture recognition index (i.e., the user gesture recognition score) is greater than or equal to a preset user gesture recognition index threshold value (i.e., the second preset score) in the interaction control database, then there is no need to optimize the gesture interaction control of the VR device based on the user gesture data; if the user gesture recognition index is less than the preset user gesture recognition index threshold value in the interaction control database, then there is a need to optimize the gesture interaction control of the VR device based on the user gesture data.

[0118] If the user gesture recognition index is greater than or equal to the preset user gesture recognition index threshold in the interaction control database, it means that the VR device can recognize the user's gestures very accurately. This high accuracy allows the VR device to directly and accurately understand the user's intentions and perform corresponding interactive control accordingly. Therefore, there is no need to optimize the VR device's interactive control based on the user's gesture recognition. If the user gesture recognition index is less than the preset user gesture recognition index threshold in the interaction control database, it means that the VR device's recognition accuracy of the user's gestures has not reached the expected standard. In this case, it is necessary to optimize the VR device's gesture interactive control based on the user's gesture data. Specifically, the optimization involves readjusting the parameters in the VR device's gesture recognition algorithm, such as the initially preset user reference gesture data, that is, using the user's average finger rotation angle and average gesture movement speed as user reference posture data to improve the recognition ability of user gestures and make the user's personalized experience stronger.

[0119] For example, the parameter update method includes VR device interaction monitoring, motion data fusion analysis, data processing, and optimized interaction control. Specifically, VR device interaction monitoring involves real-time monitoring of the interaction between the user and the VR device during the monitoring period, obtaining interaction data, and performing comprehensive analysis to obtain a performance interaction reliability index for the VR device. This index is then compared with a preset threshold in the interaction control database. If the performance interaction reliability index is lower than the threshold, an early warning is issued; otherwise, user motion data is collected in real-time using the VR device's sensors. Motion data fusion analysis involves using a data fusion analysis unit within the VR device... The system performs fusion analysis on user action data to obtain user posture data and user gesture data; data processing: the data processing device receives user posture data and user gesture data through the Internet of Things and analyzes them separately to obtain user posture recognition index and user gesture recognition index; optimize interaction control: the user posture recognition index is compared with the preset user posture recognition index threshold value in the interaction control database. Based on the comparison result, it is determined whether to optimize the posture interaction control of the VR device based on the user posture data. The user gesture recognition index is compared with the preset user gesture recognition index threshold value in the interaction control database. Finally, based on the comparison result, it is determined whether to optimize the gesture interaction control of the VR device based on the user gesture data.

[0120] In summary, the solution provided in this public disclosure is as follows: First, by collecting user motion data through at least two acquisition devices, the comprehensiveness and reliability of the data source are ensured. By combining the extraction and quantitative scoring of user posture data and user gesture data, an accurate evaluation of the device's recognition effect is achieved. The recognition parameters of the virtual reality device are updated based on the scoring results, which can adapt to the different body movement habits of different users, improve the recognition accuracy of the virtual reality device for user posture and gestures, and thus enhance the user interaction experience.

[0121] Secondly, by assessing device performance before collecting user motion data, the problem of motion information distortion caused by collecting data when device performance is insufficient is avoided, laying the foundation for accurate extraction of subsequent posture and gesture data, while ensuring the smoothness of user interaction experience.

[0122] Furthermore, the early warning system provided in this application can promptly provide feedback to users and proactively adjust device parameters when device performance is abnormal, thereby preventing users from experiencing poor interactive experiences due to VR device malfunctions and improving the stability and security of VR device use.

[0123] Furthermore, by combining device operating parameters with user action data to determine posture recognition scores and gesture recognition scores, the scoring results can comprehensively reflect the impact of device performance and user action characteristics on recognition effectiveness, thereby improving the objectivity and accuracy of posture recognition scores and gesture recognition scores.

[0124] The following application example further illustrates the parameter update method provided in this disclosure: like Figure 3 As shown, Figure 3 This is a flowchart illustrating a parameter update method provided as an application example of this disclosure. The parameter update method provided in this application example includes the following steps: Step 301: Obtain the interaction operation data between the user and the virtual reality device. The interaction operation data includes the maximum frame rate of the transmitted images, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature of the virtual reality device during the interaction monitoring period. Step 302: Determine the weight set, which includes the first weight corresponding to the maximum frame rate of the transmitted images of the virtual reality device during the interaction monitoring period, the second weight corresponding to the highest network latency, the third weight corresponding to the average refresh rate of the display screen, and the fourth weight corresponding to the highest operating temperature. Step 303: Based on the weight set, the maximum frame rate of the transmitted images of the virtual reality device during the interactive monitoring period, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature, determine the performance evaluation result of the virtual reality device. Step 304: In response to the performance evaluation result of the virtual reality device being no less than the preset performance evaluation result, acquire user action data, which is collected by at least two acquisition devices; Step 305: Extract features from user action data to obtain user action features associated with user posture and user gestures; Step 306: Based on user action characteristics, analyze user actions to obtain user posture data and user gesture data. User posture data includes the average tilt angle of the user's head, the average movement speed of the arms, and the average movement speed of the legs during the interaction process. User gesture data includes the average rotation angle of the user's fingers and the average movement speed of the gestures during the interaction process. Step 307: Determine the user posture recognition score based on the maximum frame rate of the transmitted images of the virtual reality device during the interaction monitoring period, the average tilt angle of the user's head, the average movement speed of the arm and the average movement speed of the leg during the interaction process, and determine the user gesture recognition score based on the maximum network latency, the average rotation angle of the user's fingers and the average movement speed of the gesture during the interaction process. Step 308: In response to the user's posture recognition score being less than the first preset score, update the posture recognition parameters of the virtual reality device based on the user's posture data; and in response to the user's gesture recognition score being less than the second preset score, update the gesture recognition parameters of the virtual reality device based on the user's gesture data.

[0125] To implement the parameter update method provided in this disclosure, this disclosure also provides a parameter update device, such as... Figure 4 As shown. Figure 4 This is a schematic diagram of a parameter updating device provided in an embodiment of the present disclosure. The parameter updating device 400 includes: Acquisition unit 401 is used to acquire user action data, which is acquired by at least two acquisition devices. Extraction unit 402 is used to extract user posture data and user gesture data from user action data; The determining unit 403 is used to determine a user posture recognition score based on user posture data and a user gesture recognition score based on user gesture data. The update unit 404 is used to update the posture recognition parameters of the virtual reality device according to the user posture data in response to the user posture recognition score being less than the first preset score, and to update the gesture recognition parameters of the virtual reality device according to the user gesture data in response to the user gesture recognition score being less than the second preset score.

[0126] In one embodiment, the acquisition unit 401 is specifically used for: Acquire data on user interactions with virtual reality devices; By analyzing the interactive operation data, the performance evaluation results of the virtual reality device are obtained; In response to the virtual reality device's performance evaluation result being no less than the preset performance evaluation result, user action data is acquired.

[0127] In one embodiment, the acquisition unit 401 is specifically used for: Determine the weight set, which includes the first weight corresponding to the maximum frame rate of the transmitted images of the virtual reality device during the interaction monitoring period, the second weight corresponding to the maximum network latency, the third weight corresponding to the average refresh rate of the display screen, and the fourth weight corresponding to the maximum operating temperature. The performance evaluation results of the virtual reality device are determined based on the weight set, the maximum frame rate of the transmitted images of the virtual reality device during the interactive monitoring period, the maximum network latency, the average refresh rate of the display screen, and the maximum operating temperature.

[0128] In one embodiment, the parameter update device 400 further includes a generation unit, which is used to: In response to the virtual reality device's performance evaluation result being lower than the preset performance evaluation result, an early warning message is generated for the interactive operation of the virtual reality device. The early warning message includes at least one of the following: a performance abnormality warning message pops up on the virtual reality device's display screen, or the refresh rate of the virtual reality device's display screen is adjusted.

[0129] In one embodiment, the extraction unit 402 is specifically used for: Feature extraction is performed on user action data to obtain user action features associated with user posture and user gestures; Based on user action characteristics, user actions are analyzed to obtain user posture data and user gesture data.

[0130] In one embodiment, the determining unit 403 is specifically used for: The user posture recognition score is determined based on the maximum frame rate of the transmitted images of the virtual reality device during the interaction monitoring period, the average tilt angle of the user's head, the average movement speed of the arm, and the average movement speed of the leg during the interaction process. The user gesture recognition score is determined based on the maximum network latency, the average rotation angle of the user's fingers, and the average movement speed of the gesture during the interaction process.

[0131] It should be noted that the parameter updating device provided in the above embodiments is only illustrated by the division of the above program modules when updating parameters. In practical applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the parameter updating device can be divided into different program modules to complete all or part of the processing described above. In addition, the parameter updating device provided in the above embodiments and the parameter updating method provided in the embodiments of this disclosure belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0132] Figure 5 This is a schematic diagram of the hardware composition structure of the electronic device provided in the embodiments of this disclosure, such as... Figure 5 As shown, the electronic device 500 includes at least one processor 502; and a memory 501 communicatively connected to the at least one processor 502; wherein the memory 501 stores instructions executable by the at least one processor 502, the instructions being executed by the at least one processor 502 to implement the steps of the parameter update method of the embodiments of this disclosure.

[0133] Optionally, the electronic device may specifically be a parameter update device in the embodiments of this application, and the electronic device may implement the corresponding processes implemented by the parameter update device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0134] It is understood that the electronic device also includes a communication interface 503. Various components in the electronic device are coupled together via a bus system 504. It is understood that the bus system 504 is used to implement communication between these components. In addition to a data bus, the bus system 504 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 5 The general designated all buses as Bus System 504.

[0135] It is understood that memory 501 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be 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), Synchronous Static Random Access Memory (SSRAM), 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), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 501 described in this embodiment of the invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0136] The methods disclosed in the above embodiments can be applied to or implemented by processor 502. Processor 502 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above methods can be completed by integrated logic circuits in the hardware of processor 502 or by instructions in software form. Processor 502 may be a general-purpose processor, DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 502 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, specifically memory 501. Processor 502 reads information from memory 501 and, in conjunction with its hardware, completes the steps of the aforementioned methods.

[0137] In an exemplary embodiment, the electronic device may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), FPGAs, general-purpose processors, controllers, MCUs, microprocessors, or other electronic components to perform the aforementioned method.

[0138] This disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, which are used to cause a computer to execute the steps of the parameter update method of the present invention.

[0139] Optionally, the computer-readable storage medium can be applied to the parameter update device in the embodiments of this application, and the computer instructions cause the computer to execute the corresponding processes implemented by the parameter update device in the various methods of the embodiments of this application. For the sake of brevity, they will not be described in detail here.

[0140] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the parameter update method provided in this embodiment of the invention.

[0141] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0142] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0143] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0144] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0145] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0146] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A parameter update method, characterized in that, include: Acquire user action data, which is collected by at least two acquisition devices; Extract user posture data and user gesture data from the user action data; Based on the user posture data, a user posture recognition score is determined, and based on the user gesture data, a user gesture recognition score is determined. In response to the user posture recognition score being less than a first preset score, the posture recognition parameters of the virtual reality device are updated according to the user posture data; and in response to the user gesture recognition score being less than a second preset score, the gesture recognition parameters of the virtual reality device are updated according to the user gesture data.

2. The method according to claim 1, characterized in that, The acquisition of user action data includes: Acquire data on user interactions with virtual reality devices; The performance evaluation results of the virtual reality device are obtained by analyzing the interactive operation data. In response to the performance evaluation result of the virtual reality device being no less than the preset performance evaluation result, user action data is acquired.

3. The method according to claim 2, characterized in that, The interactive operation data includes the maximum frame rate of the transmitted images, the highest network latency, the average refresh rate of the display screen, and the highest operating temperature of the virtual reality device during the interactive monitoring period. The analysis of the interactive operation data to obtain the performance evaluation results of the virtual reality device includes: A weight set is determined, which includes a first weight corresponding to the maximum frame rate of the transmitted images of the virtual reality device during the interaction monitoring period, a second weight corresponding to the maximum network latency, a third weight corresponding to the average refresh rate of the display screen, and a fourth weight corresponding to the highest operating temperature. Based on the weight set, the maximum frame rate of the transmitted images of the virtual reality device during the interactive monitoring period, the highest network latency, the average refresh rate of the display screen, and the highest operating temperature, the performance evaluation result of the virtual reality device is determined.

4. The method according to claim 2, characterized in that, After analyzing the interactive operation data to obtain the performance evaluation results of the virtual reality device, the method further includes: In response to the performance evaluation result of the virtual reality device being less than the preset performance evaluation result, an early warning message is generated for the interactive operation of the virtual reality device. The early warning message includes at least one of the following: popping up a performance abnormality warning message on the display screen of the virtual reality device and adjusting the refresh rate of the display screen of the virtual reality device.

5. The method according to claim 1, characterized in that, The extraction of user posture data and user gesture data from the user action data includes: Feature extraction is performed on the user action data to obtain user action features associated with user posture and user gesture; Based on the user action characteristics, the user's actions are analyzed to obtain user posture data and user gesture data.

6. The method according to claim 3, characterized in that, The user posture data includes the average head tilt angle, average arm movement speed, and average leg movement speed during the interaction process. The user gesture data includes the average finger rotation angle and average gesture movement speed during the interaction process. The process of determining a user posture recognition score based on the user posture data and a user gesture recognition score based on the user gesture data includes: The user posture recognition score is determined based on the maximum frame rate of the transmitted images of the virtual reality device during the interaction monitoring period, the average tilt angle of the user's head during the interaction process, the average movement speed of the arm and the average movement speed of the leg. The user gesture recognition score is determined based on the maximum network latency, the average rotation angle of the user's fingers during the interaction process and the average movement speed of the gesture.

7. A parameter updating device, characterized in that, include: An acquisition unit is used to acquire user action data, which is acquired by at least two acquisition devices. The extraction unit is used to extract user posture data and user gesture data from the user action data; The determining unit is used to determine a user posture recognition score based on the user posture data, and to determine a user gesture recognition score based on the user gesture data; An update unit is configured to update the posture recognition parameters of the virtual reality device based on the user posture data in response to the user posture recognition score being less than a first preset score, and to update the gesture recognition parameters of the virtual reality device based on the user gesture data in response to the user gesture recognition score being less than a second preset score.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

Images