Data analysis method and device, electronic equipment and storage medium

Abstract

The invention provides a data analysis method and device, electronic equipment and a storage medium, and relates to the technical field of meta universe and image processing. According to the scheme, firstly, network data and image data of the meta universe at the current moment are obtained, then a network evaluation value is determined based on the network data, an image evaluation value is determined based on the image data, then network optimization is conducted on the meta universe under the condition that the network evaluation value is smaller than a preset network threshold value, and the corresponding network evaluation value after optimization is obtained. The method comprises the steps of optimizing a network evaluation value and an image evaluation value, determining a comprehensive evaluation value based on the optimized corresponding network evaluation value and the image evaluation value, and finally adjusting the image quality of the meta universe based on the current network evaluation value under the condition that the comprehensive evaluation value is smaller than a preset comprehensive evaluation threshold value. Therefore, through the data analysis method provided by the invention, accurate, reliable and dynamic adjustment of the network and the image quality of the meta-universe is realized, the performance of the meta-universe is improved, and the user experience is improved.

Description

Technical Field

[0001] This disclosure relates to the fields of metaverse and image processing technology, specifically to a data analysis method, apparatus, electronic device, and storage medium. Background Technology

[0002] Currently, the network configuration and image rendering parameters in Metaverse are usually set statically. However, due to issues such as network latency, lag, or low image quality, Metaverse struggles to achieve high-quality image display, fails to provide a good user experience, and negatively impacts the user experience. Summary of the Invention

[0003] This disclosure aims to at least partially address one of the technical problems in the related art.

[0004] The first aspect of this disclosure provides a data analysis method, including: Obtain network data and image data of the metaverse at the current moment, wherein the network data includes at least one of the number of online users, network congestion and frame rate, and the image data includes at least one of the clarity, smoothness and texture complexity; The network evaluation value is determined based on the network data, and the image evaluation value is determined based on the image data; If the network evaluation value is less than a preset network threshold, the metaverse is optimized to obtain the optimized network evaluation value. Based on the optimized network evaluation value and the image evaluation value, a comprehensive evaluation value is determined; If the overall evaluation value is less than a preset overall evaluation threshold, the image quality of the metaverse is adjusted based on the current network evaluation value.

[0005] A second aspect of this disclosure provides a data analysis apparatus, comprising: The acquisition module is used to acquire network data and image data of the metaverse at the current moment. The network data includes at least one of the number of online users, network congestion, and frame rate, and the image data includes at least one of the clarity, smoothness, and texture complexity. The first determining module is used to determine a network evaluation value based on the network data and an image evaluation value based on the image data. The optimization module is used to optimize the metaverse when the network evaluation value is less than a preset network threshold, so as to obtain the network evaluation value after optimization. The second determining module is used to determine a comprehensive evaluation value based on the optimized network evaluation value and the image evaluation value. The adjustment module is used to adjust the image quality of the metaverse based on the current network evaluation value when the comprehensive evaluation value is less than a preset comprehensive evaluation threshold.

[0006] 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 that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method described in the above embodiments.

[0007] 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 the computer to perform the method described in the above embodiments.

[0008] 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 above embodiments.

[0009] The data analysis methods, apparatus, electronic devices, and storage media disclosed herein have the following beneficial effects: In this embodiment, the network data and image data of the metaverse at the current moment are first acquired. Then, a network evaluation value is determined based on the network data, and an image evaluation value is determined based on the image data. If the network evaluation value is less than a preset network threshold, the metaverse network is optimized to obtain the optimized network evaluation value. Based on the optimized network evaluation value and the image evaluation value, a comprehensive evaluation value is determined. Finally, if the comprehensive evaluation value is less than a preset comprehensive evaluation threshold, the image quality of the metaverse is adjusted based on the current network evaluation value. Thus, the data analysis method proposed in this disclosure achieves accurate and reliable dynamic adjustment of the network and image quality of the metaverse, improving the performance of the metaverse and enhancing the user experience.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0011] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 This is a flowchart illustrating a data analysis method provided in an embodiment of the present disclosure; Figure 2This is a flowchart illustrating a data analysis method provided in an embodiment of the present disclosure; Figure 3 This is a flowchart illustrating a data analysis method provided in an embodiment of the present disclosure; Figure 4 This is a flowchart illustrating a data analysis method provided in an embodiment of the present disclosure. Figure 5 This is a flowchart illustrating a data analysis method provided in an embodiment of the present disclosure. Figure 6 This is a schematic diagram of the process for acquiring network data and image data in a data analysis method provided in an embodiment of the present disclosure; Figure 7 This diagram illustrates the relationship between the comprehensive evaluation value, the image evaluation value, and the network evaluation value in the data analysis method proposed in this disclosure. Figure 8 This is a schematic diagram of the structure of the data analysis device provided in the embodiments of this disclosure; Figure 9 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0012] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0013] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0014] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the laws, regulations and standards of the country and region, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0015] The data analysis method, apparatus, electronic device, and storage medium of this disclosure are described below with reference to the accompanying drawings.

[0016] Figure 1This is a flowchart illustrating a data analysis method provided in an embodiment of the present disclosure.

[0017] like Figure 1 As shown, this data analysis method may include the following steps: Step 101: Obtain the network data and image data of the metaverse at the current moment.

[0018] The metaverse, also known as the meta-universe, the metaphysical universe, the extrasensory space, and the virtual space, is a virtual world constructed using digital technology that maps to or transcends the real world and can interact with it.

[0019] The network data can be data used to evaluate the network performance of the metaverse, and may include at least one of the following: number of online users, network congestion, and frame rate. This disclosure does not limit this.

[0020] Among them, network congestion can be used to describe the degree of performance degradation of a network under overload conditions.

[0021] The image data can be image rendering data of the metaverse, which can be used to evaluate the image rendering quality of the metaverse, and can include at least one of sharpness, smoothness, and texture complexity. This disclosure does not limit this aspect.

[0022] Clarity can be used to evaluate the quality of a video or image; smoothness can be used to evaluate the continuity of a video; and texture complexity can be used to evaluate the complexity of an image.

[0023] In this disclosure, by acquiring network data and image data of the metaverse at the current moment, a data foundation is provided for subsequent evaluation of the network performance and image rendering quality of the metaverse.

[0024] Step 102: Determine the network evaluation value based on the network data, and determine the image evaluation value based on the image data.

[0025] The network evaluation value can be used to assess the network performance of the metaverse. In other words, the higher the network evaluation value, the better the network performance of the metaverse; the lower the network evaluation value, the worse the network performance of the metaverse.

[0026] The image evaluation value can be used to assess the image rendering quality of the metaverse. In other words, the higher the image evaluation value, the better the image rendering quality of the metaverse; the lower the image evaluation value, the worse the image rendering quality of the metaverse.

[0027] In this disclosure, after obtaining the network data and image data of the metaverse at the current moment, the network data and image data can be evaluated and analyzed separately to determine the corresponding network evaluation value and image evaluation value. Based on the network evaluation value and image evaluation value, the network performance and image rendering quality of the metaverse can be quantitatively evaluated, providing a data foundation for subsequent optimization of the metaverse.

[0028] In this disclosure, the specific methods for evaluating and analyzing network data and image data to obtain corresponding evaluation values ​​can be preset as needed. For example, the network data and image data can be weighted and fused separately to obtain the corresponding evaluation values, or other data operations can be performed on the network data and image data separately to obtain the corresponding evaluation values. This disclosure does not limit the specific methods used.

[0029] By comprehensively evaluating network performance and image rendering quality, potential problems can be identified and resolved in a timely manner, network configuration and image rendering can be optimized, and the application performance of Metaverse can be improved.

[0030] Step 103: If the network evaluation value is less than the preset network threshold, perform network optimization on the metaverse to obtain the optimized network evaluation value.

[0031] The network threshold can be a critical value for network evaluation used to judge the network performance of the metaverse, and it can be preset as needed. That is to say, when the network evaluation value is less than the network threshold, it indicates poor network performance, and when the network evaluation value is greater than or equal to the network threshold, it indicates good network performance. This disclosure does not limit it in this respect.

[0032] In this disclosure, after determining the current network evaluation value of the metaverse, if the network evaluation value is less than a preset network threshold, it can be determined that the network evaluation value is small, corresponding to poor network performance. At this point, network optimization can be performed on the metaverse to improve its network performance, providing a foundation for improving the metaverse's performance. After optimizing the metaverse network, the optimized network evaluation value can be obtained.

[0033] Step 104: Determine the comprehensive evaluation value based on the optimized network evaluation value and image evaluation value.

[0034] The overall evaluation value can be used to assess the overall performance of the metaverse. In other words, the higher the overall evaluation value, the better the overall performance of the metaverse; the lower the overall evaluation value, the worse the overall performance of the metaverse.

[0035] In some possible implementations, when determining the comprehensive evaluation value based on the optimized network evaluation value and the image evaluation value, this disclosure can first perform an exponential operation on the absolute value of the difference between the network evaluation value and the image evaluation value to obtain the corresponding sixth value, and then perform a logarithmic operation on the square root of the ratio of the image evaluation value and the sixth value to obtain the comprehensive evaluation value. As shown in the following formula (1), where formula (1) is only an example and is not intended to be limiting: , (1) in, For comprehensive evaluation, Image evaluation value, This is the network evaluation value.

[0036] Step 105: If the comprehensive evaluation value is less than the preset comprehensive evaluation threshold, adjust the image quality of the metaverse based on the current network evaluation value.

[0037] The comprehensive evaluation threshold can be used as a critical value for judging the overall performance of the metaverse, and it can be preset as needed. For example, the comprehensive evaluation threshold can be obtained from a database, represented by the average of comprehensive evaluation values ​​over a historical period, etc., and this disclosure does not limit it in this way.

[0038] In this disclosure, after determining the comprehensive evaluation value, if the comprehensive evaluation value is less than a preset comprehensive evaluation threshold, it can be determined that the comprehensive evaluation value is small and the overall performance of the metaverse is currently poor. At this point, the image quality of the metaverse can be adjusted. When adjusting the image quality, in order to ensure that the adjusted image quality matches the current network performance, the image quality of the metaverse can be adjusted based on the current network evaluation value. This allows for optimization of network configuration and image rendering after a comprehensive evaluation of network performance and image rendering quality, achieving high-quality image rendering and helping to improve the application performance of the metaverse.

[0039] Adjusting image quality helps maintain network stability and reliability. By reducing image quality, data transmission volume is decreased, network pressure is alleviated, and service interruptions or performance degradation are effectively avoided, thereby improving the overall performance of the metaverse. Real-time monitoring and adjustment based on comprehensive evaluation values ​​helps enhance server stability and reliability, improving the continuity and smoothness of the user experience, and ultimately increasing user satisfaction. Precise adjustments help to more effectively utilize limited network and computing resources.

[0040] In some possible implementations, when adjusting image quality, the user can be informed of changes in network conditions through interface prompts or message boxes, and the reason for the adjustment can be explained to improve user satisfaction. Users can also be reminded to select priority aspects, such as image quality priority or smoothness priority. The steps for adjusting image quality can be determined based on the user's chosen steps; for example, if image quality priority is selected, the specific steps for adjusting image quality might be: adjusting processing effects; adjusting frame rate; and adjusting resolution. This disclosure does not limit the scope of the implementation.

[0041] In this embodiment, the network data and image data of the metaverse at the current moment are first acquired. Then, a network evaluation value is determined based on the network data, and an image evaluation value is determined based on the image data. If the network evaluation value is less than a preset network threshold, the metaverse network is optimized to obtain the optimized network evaluation value. Based on the optimized network evaluation value and the image evaluation value, a comprehensive evaluation value is determined. Finally, if the comprehensive evaluation value is less than a preset comprehensive evaluation threshold, the image quality of the metaverse is adjusted based on the current network evaluation value. Thus, by determining the network evaluation value and image evaluation value based on the real-time network data and image data of the metaverse, optimizing the metaverse network when the network evaluation value is substandard, determining the comprehensive evaluation value based on the optimized network evaluation value and the image quality adjustment based on the network evaluation value when the comprehensive evaluation value is substandard, accurate and reliable dynamic adjustment of the network and image quality of the metaverse is achieved. This enhances the image quality in the metaverse, improves its performance, and enhances the user experience.

[0042] Figure 2 This is a flowchart illustrating a data analysis method provided in one embodiment of the present disclosure.

[0043] like Figure 2 As shown, this data analysis method may include the following steps: Step 201: Obtain the network data and image data of the metaverse at the current moment.

[0044] The specific implementation of step 201 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0045] Step 202: Obtain the reference number of online users and the reference frame rate from the preset database.

[0046] The specific structure and type of the database can be preset as needed, and it can store preset reference network data, reference image data, and other data. This disclosure does not limit this.

[0047] The reference number of online users and the reference frame rate can both be preset as needed, such as being determined based on system capabilities or historical experience, and the reference frame rate can be the system's maximum frame rate, etc. This disclosure does not limit them.

[0048] In this disclosure, after obtaining the network data of the metaverse at the current moment, the current network performance of the metaverse can be determined by evaluating the network data. When evaluating the network data, a reference number of online users and a reference frame rate can first be obtained from a database to provide a data foundation for subsequent network evaluation and obtaining network evaluation values.

[0049] Step 203: Determine the normalized value of the number of online users based on the number of online users and the reference number of online users, and determine the frame rate percentage based on the frame rate and the reference frame rate.

[0050] Among them, the normalized value of online users can make the evaluation of online users comparable and meaningful, thereby improving the reliability and accuracy of the network evaluation values ​​obtained subsequently.

[0051] In this disclosure, when determining the normalized value of the number of online users based on the number of online users and a reference number of online users, it can be determined by a ratio. That is, the value obtained by calculating the ratio of the number of online users to the reference number of online users can be determined as the normalized value of the number of online users, and this disclosure does not limit this.

[0052] For example, if the number of online users is 9,000 and the reference number of online users is 10,000, then the normalized value of the number of online users is 0.9. This value can be used to determine that the current number of online users has reached 90% of the target, etc. This disclosure does not limit this.

[0053] Among them, the frame rate percentage can be used to quantify the difference between the current frame rate and the reference frame rate, i.e., the performance ceiling, and can be used to judge the performance utilization rate of the metaverse.

[0054] In this disclosure, when determining the frame rate percentage based on the frame rate and the reference frame rate, it can also be determined by a ratio. That is, the value obtained by comparing the frame rate with the reference frame rate can be determined as the frame rate percentage, and this disclosure does not limit this.

[0055] Step 204: Obtain the first value after exponentially calculating the frame rate percentage, and the second value after exponentially calculating the sum of the normalized value of the number of online users and the network congestion.

[0056] In this disclosure, when performing exponential calculations on the frame rate percentage, the calculation can be performed based on a preset base and the frame rate percentage as the exponent. The preset base can be set as needed. For example, the preset base can be... This disclosure does not impose any limitations on this matter.

[0057] In this disclosure, when performing exponential calculations on the sum of the normalized number of online users and the network congestion level, the exponent can be based on a preset base and the sum of the normalized number of online users and the network congestion level. The preset base can be set as needed. For example, the preset base can be 2; this disclosure does not limit this setting.

[0058] In other words, the base when performing exponential calculation on the frame rate percentage can be different from the exponent when performing exponential calculation on the sum of the normalized value of the number of online users and the network congestion. This disclosure does not impose any restrictions on this.

[0059] Step 205: Perform hyperbolic tangent operation on the first value and the second value respectively to obtain the corresponding frame rate hyperbolic tangent value and user hyperbolic tangent value.

[0060] Among them, the hyperbolic tangent value can perform non-linear range compression and mapping of data, and can be used in fields such as data analysis and machine learning.

[0061] In this disclosure, the corresponding frame rate hyperbolic tangent value is obtained by performing a hyperbolic tangent operation on the first value. The corresponding user hyperbolic tangent value is obtained by performing a hyperbolic tangent operation on the second value.

[0062] Step 206: Perform a logarithmic operation on the sum of the frame rate hyperbolic tangent and the user hyperbolic tangent to obtain the network evaluation value.

[0063] In this disclosure, when performing a logarithmic operation on the sum of the frame rate hyperbolic tangent and the user hyperbolic tangent, the base of the logarithmic operation can be set as needed. For example, the base can be... This disclosure does not impose any limitations on this matter.

[0064] Therefore, through the above mathematical operation process, the network evaluation value obtained can be shown in the following formula (2), where formula (2) is not limited here: , (2) in, This is the network evaluation value. For network congestion, For online users, For reference, the number of online users, For frame rate, For reference frame rate, It is a natural constant.

[0065] The network evaluation values ​​can be illustrated below with reference to Table (1). Table (1) is merely an example and is not intended to impose any limitations: Table (1)

[0066] FPS stands for Frames Per Second, also known as frame rate.

[0067] As shown in Table (1), taking a reference number of online users of 30 and a reference frame rate of 60 FPS as an example, in the first and second sets of data, when the number of online users and the frame rate remain unchanged, the smaller the network congestion, the larger the network evaluation value, indicating that the network performance of the metaverse is better; in the second and third sets of data, when the network congestion and the frame rate remain unchanged, the smaller the number of online users, the larger the network evaluation value, indicating that the network performance of the metaverse is better; in the third and fourth sets of data, when the network congestion and the number of online users remain unchanged, the smaller the frame rate, the smaller the network evaluation value, indicating that the network performance of the metaverse is worse. Therefore, the network evaluation value is positively correlated with the frame rate and negatively correlated with the network congestion and the number of online users.

[0068] When the number of online users on a network increases, more users share the network bandwidth, leading to a strain on network resources and increased congestion. When network congestion increases, some frame data packets are lost or cannot be transmitted to the receiving end in time, causing frames in videos or games to fail to refresh in time, resulting in a decrease in frame rate. A higher frame rate means more image information is transmitted per second, resulting in a larger data volume and a higher demand for network bandwidth, which may lead to network congestion.

[0069] The above process effectively quantifies network evaluation values. By monitoring network data in real time and calculating network evaluation values, changes in network performance can be reflected instantly, providing timely information support for adjusting image quality. By comprehensively considering multiple factors such as concurrent users, network congestion, and frame rate, network performance can be evaluated more comprehensively, avoiding the bias caused by a single indicator. A comprehensive understanding of network performance helps to identify network bottlenecks in a timely manner, thereby effectively avoiding congestion during data transmission and ensuring smooth and efficient data transmission.

[0070] Step 207: Determine the image evaluation value based on the image data.

[0071] Step 208: If the network evaluation value is less than the preset network threshold, perform network optimization on the metaverse to obtain the optimized network evaluation value.

[0072] Step 209: Determine the comprehensive evaluation value based on the optimized network evaluation value and image evaluation value.

[0073] Step 210: If the comprehensive evaluation value is less than the preset comprehensive evaluation threshold, adjust the image quality of the metaverse based on the current network evaluation value.

[0074] The specific implementation of steps 207 to 210 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0075] In this embodiment, the network data and image data of the metaverse at the current moment are first acquired, and the reference number of online users and reference frame rate are obtained from a preset database. Then, based on the number of online users and the reference number of online users, a normalized value for the number of online users is determined, and based on the frame rate and the reference frame rate, the frame rate percentage is determined. Next, a first value obtained by exponentially calculating the frame rate percentage and a second value obtained by exponentially calculating the sum of the normalized value of the number of online users and the network congestion are obtained. Hyperbolic tangent operations are then performed on the first and second values ​​respectively to obtain the corresponding hyperbolic tangent values ​​for the frame rate and the user. Then, the sum of the hyperbolic tangent values ​​for the frame rate and the user is logarithmically calculated to obtain a network evaluation value, and an image evaluation value is determined based on the image data. If the network evaluation value is less than a preset network threshold, the metaverse is optimized to obtain an optimized network evaluation value. Finally, based on the optimized network evaluation value and the image evaluation value, a comprehensive evaluation value is determined, and if the comprehensive evaluation value is less than a preset comprehensive evaluation threshold, the image quality of the metaverse is adjusted based on the current network evaluation value. Therefore, by performing a series of mathematical operations on real-time network data from the metaverse and reference network data in the database, a network evaluation value is obtained. This comprehensively considers multiple factors to ensure that the network evaluation value can more comprehensively assess network performance, effectively avoiding the one-sidedness caused by a single indicator. When the network evaluation value fails to meet the standard, network optimization is performed. Based on the optimized network evaluation value and the image evaluation value, a comprehensive evaluation value is determined. Then, the image quality of the metaverse is dynamically adjusted based on the comprehensive evaluation value, thereby improving the comprehensiveness and reliability of the data analysis method.

[0076] Figure 3 This is a flowchart illustrating a data analysis method provided in one embodiment of the present disclosure.

[0077] like Figure 3 As shown, this data analysis method may include the following steps: Step 301: Obtain the network data and image data of the metaverse at the current moment.

[0078] Step 302: Determine the network evaluation value based on the network data.

[0079] The specific implementation of steps 301 to 302 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0080] Step 303: Perform exponential operations on clarity, smoothness, and texture complexity to obtain the corresponding third, fourth, and fifth values.

[0081] In this disclosure, when performing exponential calculations on sharpness, smoothness, and texture complexity, the calculations can be performed based on a preset base, using sharpness, smoothness, or texture complexity as the exponent. The preset base can be set as needed. For example, the base can be 2; this disclosure does not limit this setting.

[0082] In other words, when performing exponential operations on clarity, smoothness, and texture complexity, the base can be the same, and this disclosure does not impose any restrictions on this.

[0083] The third value is the result of exponentially calculating the sharpness; the fourth value is the result of exponentially calculating the smoothness; and the fifth value is the result of exponentially calculating the texture complexity.

[0084] Step 304: Perform hyperbolic tangent operation on the third, fourth and fifth values ​​respectively to obtain the corresponding hyperbolic tangent values ​​for clarity, smoothness and complexity.

[0085] In this disclosure, the corresponding hyperbolic tangent value for sharpness is obtained by performing a hyperbolic tangent operation on the third value. The corresponding hyperbolic tangent value for smoothness is obtained by performing a hyperbolic tangent operation on the fourth value. The corresponding hyperbolic tangent value for complexity is obtained by performing a hyperbolic tangent operation on the fifth value.

[0086] Step 305: Perform a logarithmic operation on the sum of the hyperbolic tangent values ​​of sharpness, smoothness, and complexity to obtain the image evaluation value.

[0087] In this disclosure, when performing a logarithmic operation on the sum of the hyperbolic tangent values ​​of clarity, fluency, and complexity, the base of the logarithmic operation can be set as needed. For example, the base can be a constant e, and this disclosure does not limit this.

[0088] Therefore, the image evaluation value obtained through the above mathematical operation process can be represented by the following formula (3), where formula (3) is only an example and is not limited here: , (3) in, Image evaluation value, For texture complexity, For smoothness, For clarity.

[0089] As shown in formula (3), the image evaluation value increases with the increase of sharpness, texture complexity, and smoothness, indicating that the image quality is better. Higher sharpness requires more pixels to be rendered, increasing the burden on the graphics card, which may lead to a lower frame rate and thus a lower smoothness. Higher texture complexity requires more computation from the graphics card, which may lead to a lower frame rate and thus a lower smoothness. If the texture complexity is higher, the rendering task is heavier, which leads to a decrease in frame rate and thus a decrease in smoothness. In order to maintain overall smoothness, sharpness or texture complexity is usually reduced to maintain a high frame rate.

[0090] This enables the effective quantification of image evaluation values. By monitoring image data and calculating image evaluation values ​​in real time, changes in image quality can be reflected instantly, providing information support for improving user experience. By comprehensively considering the impact of multiple key factors such as sharpness, texture complexity, and smoothness, image quality can be evaluated more comprehensively, avoiding the one-sidedness caused by a single indicator.

[0091] By assessing the image complexity of different scenarios, computational resources can be allocated rationally to ensure the smoothness and realism of rendering effects. A comprehensive evaluation of image rendering smoothness and clarity helps to promptly identify and resolve stuttering and quality loss during the rendering process, ensuring an improved visual experience for users in scenarios such as watching videos and playing games.

[0092] Step 306: If the network evaluation value is less than the preset network threshold, perform network optimization on the metaverse to obtain the optimized network evaluation value.

[0093] Step 307: Determine the comprehensive evaluation value based on the optimized network evaluation value and image evaluation value.

[0094] Step 308: If the comprehensive evaluation value is less than the preset comprehensive evaluation threshold, adjust the image quality of the metaverse based on the current network evaluation value.

[0095] The specific implementation of steps 306 to 308 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0096] In this embodiment, the network data and image data of the metaverse at the current moment are first acquired, and a network evaluation value is determined based on the network data. Then, the sharpness, smoothness, and texture complexity are exponentially calculated to obtain the corresponding third, fourth, and fifth values. The third, fourth, and fifth values ​​are then subjected to hyperbolic tangent operations to obtain the corresponding hyperbolic tangent values ​​for sharpness, smoothness, and complexity. Next, the sum of the hyperbolic tangent values ​​for sharpness, smoothness, and complexity is logarithmically calculated to obtain the image evaluation value. If the network evaluation value is less than a preset network threshold, the metaverse is optimized to obtain the optimized network evaluation value. Finally, based on the optimized network evaluation value and the image evaluation value, a comprehensive evaluation value is determined. If the comprehensive evaluation value is less than a preset comprehensive evaluation threshold, the image quality of the metaverse is adjusted based on the current network evaluation value. Therefore, after determining the network evaluation value based on real-time network data from the metaverse, mathematical operations are performed to determine the image evaluation value by comprehensively considering the sharpness, smoothness, and texture complexity in the image data. This effectively avoids the one-sidedness of a single indicator and improves the comprehensiveness and reliability of the image evaluation value. Then, a comprehensive evaluation value is determined based on the network evaluation value and the image evaluation value, and the image quality is adjusted based on the comprehensive evaluation value, thereby improving the comprehensiveness and reliability of the data analysis method.

[0097] Figure 4 This is a flowchart illustrating a data analysis method provided in one embodiment of the present disclosure.

[0098] like Figure 4 As shown, this data analysis method may include the following steps: Step 401: Obtain the network data and image data of the metaverse at the current moment.

[0099] Step 402: Determine the network evaluation value based on the network data, and determine the image evaluation value based on the image data.

[0100] The specific implementation of steps 401 to 402 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0101] Step 403: If the network evaluation value is less than the preset network threshold, perform at least one of the following optimizations on the metaverse based on the preset optimization strategy to obtain the corresponding optimized network evaluation value: bandwidth, routing, and caching.

[0102] The optimization strategy can be preset as needed. For example, the optimization strategy can be a multi-level optimization strategy, such as optimizing bandwidth, routing and caching in sequence, etc., and it can also include specific optimization strategies, which are not limited in this disclosure.

[0103] In some possible implementations, based on a preset optimization strategy, at least one of the following optimizations is performed on the metaverse to obtain the corresponding optimized network evaluation values: bandwidth, routing, and caching. Specific implementations can be shown below; these are merely examples and not limitations: Based on a preset bandwidth optimization strategy, the data bandwidth of the metaverse is optimized, and the first network evaluation value corresponding to the optimization is determined. When this value is greater than the network threshold, it can be determined that the network evaluation value corresponding to the bandwidth optimization meets the standard and can be determined as the final network evaluation value, that is, the network evaluation value corresponding to the optimization.

[0104] The bandwidth optimization strategy can be preset as needed. For example, the bandwidth optimization strategy can divide the metaverse data into core data and non-core data, with core data as high-priority data and non-core data as low-priority data, and dynamically allocate bandwidth through a preset priority algorithm to ensure the transmission stability of high-priority data. This disclosure does not limit this aspect.

[0105] The core data can be time-sensitive data. For example, it can be user interaction, real-time audio and video streams, and data loaded in key scenarios, etc. This disclosure does not limit this.

[0106] Non-core data can be non-time-sensitive data. For example, it can be resource preloading and log transmission, etc. This disclosure does not limit it.

[0107] The priority algorithm can be preset as needed, and this disclosure does not limit it.

[0108] If the first network evaluation value is less than the network threshold, it can be determined that the network evaluation value after bandwidth optimization is low and the network optimization effect is poor. At this time, the data routing of the metaverse can be further optimized to determine the second network evaluation value after optimization. If this value is greater than the network threshold, it is determined as the final network evaluation value.

[0109] In this disclosure, when optimizing data routing in the metaverse, multipath transmission technology can be used for optimization, and the status of network paths can be monitored in real time to select paths with low latency and low packet loss rate for data transmission; the optimal path can be dynamically selected through software-defined networking technology, but this disclosure does not limit this.

[0110] If the second network evaluation value is less than the network threshold, it can be determined that the network evaluation value after route optimization is still low and the network optimization effect is poor. At this time, the data cache of the metaverse can be optimized based on the preset hierarchical caching strategy to determine the third network evaluation value after optimization. When this value is greater than the network threshold, it is determined as the final network evaluation value.

[0111] The tiered caching strategy can be pre-configured as needed. For example, a tiered caching strategy could cache low-latency data on edge nodes and high-latency data on central nodes; this disclosure does not limit this approach.

[0112] If the third network evaluation value is less than the network threshold, it can be determined that the network evaluation value is still low after bandwidth, routing and cache optimization, and the network optimization effect is not high. At this time, the entire process of data flow in the metaverse can be investigated based on the evaluation indicators in the network evaluation value, the content to be optimized can be located and optimized until the re-determined network evaluation value is greater than the network threshold, and it is determined as the final network evaluation value.

[0113] The evaluation metrics in the network evaluation values ​​can be online user count, network congestion, and frame rate-related metrics, and this disclosure does not limit them.

[0114] The entire data flow process can be the whole lifecycle process including data generation, storage, processing, transmission, application and destruction, and this disclosure does not limit it.

[0115] Therefore, by sequentially optimizing bandwidth, routing, and adjusting caching strategies, network performance issues can be addressed in a targeted manner based on real-time conditions. This avoids wasting time and resources on a single optimization method, improves the efficiency of network performance optimization, and enhances network performance to support high-quality image rendering.

[0116] Step 404: Determine the comprehensive evaluation value based on the optimized network evaluation value and image evaluation value.

[0117] Step 405: If the comprehensive evaluation value is less than the preset comprehensive evaluation threshold, adjust the image quality of the metaverse based on the current network evaluation value.

[0118] The specific implementation of steps 404 to 405 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0119] In this embodiment, the network data and image data of the metaverse at the current moment are first acquired. Then, a network evaluation value is determined based on the network data, and an image evaluation value is determined based on the image data. If the network evaluation value is less than a preset network threshold, at least one of the following optimizations is performed on the metaverse based on a preset optimization strategy to obtain the optimized network evaluation value: bandwidth, routing, and caching. Based on the optimized network evaluation value and image evaluation value, a comprehensive evaluation value is determined. Finally, if the comprehensive evaluation value is less than a preset comprehensive evaluation threshold, the image quality of the metaverse is adjusted based on the current network evaluation value. Thus, after determining the network evaluation value and image evaluation value, if the network evaluation value is not up to standard, the bandwidth, routing, and caching of the metaverse are optimized as needed until the optimized network evaluation value meets the standard, thereby achieving multi-level optimization of the metaverse network and improving network quality. Then, based on the network evaluation value and image evaluation value, a comprehensive evaluation value is determined, and the image quality of the metaverse is adjusted based on the comprehensive evaluation value, thereby achieving dynamic adjustment of the network quality and image quality of the metaverse, improving network quality and image quality, and enhancing the performance of the metaverse.

[0120] Figure 5 This is a flowchart illustrating a data analysis method provided in one embodiment of the present disclosure.

[0121] like Figure 5 As shown, this data analysis method may include the following steps: Step 501: Obtain the network data and image data of the metaverse at the current moment.

[0122] Step 502: Determine the network evaluation value based on the network data, and determine the image evaluation value based on the image data.

[0123] Step 503: If the network evaluation value is less than the preset network threshold, perform network optimization on the metaverse to obtain the optimized network evaluation value.

[0124] Step 504: Determine the comprehensive evaluation value based on the optimized network evaluation value and image evaluation value.

[0125] The specific implementation of steps 501 to 504 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0126] Step 505: If the comprehensive evaluation value is less than the preset comprehensive evaluation threshold, determine the network evaluation value level corresponding to the network evaluation value based on the preset multi-level adjustment strategy.

[0127] The multi-level adjustment strategy can be pre-set as needed, and may include multi-level network thresholds and the image quality level associated with each network threshold. For example, the multi-level adjustment strategy may include three levels of network thresholds, with the first-level network threshold associated with the first-level image quality level, the second-level network threshold associated with the second-level image quality level, and those higher than the second-level network threshold associated with the third-level image quality level. The first level corresponds to lower quality, the second level corresponds to higher quality, and the third level corresponds to the highest quality. This disclosure does not limit this aspect.

[0128] In this multi-level network threshold system, each threshold represents the upper limit of the network evaluation value corresponding to that level, and the lower limit of the network evaluation value corresponding to the next higher level. For example, when the network evaluation value is less than or equal to the first-level network threshold, the network evaluation value level is level one; when the network evaluation value is greater than the first-level network threshold and less than or equal to the second-level network threshold, the network evaluation value level is level two; and when the network evaluation value is greater than the second-level network threshold, the network evaluation value level can be determined to be level three.

[0129] The primary and secondary network thresholds can be pre-set using historical data, i.e., obtained from a pre-defined database. For example, the primary network threshold can be represented by 30% of the maximum network evaluation value within a historical time period, and the secondary network threshold by 70% of the maximum network evaluation value within the same historical time period. If no historical time period is available, the primary network threshold can be represented by 30% of the current network evaluation value, and the secondary network threshold by 70% of the current network evaluation value. This disclosure does not impose any limitations on this.

[0130] Therefore, by comparing the network evaluation value with the network threshold, it can be determined whether there is a performance bottleneck in the current network, avoiding unnecessary optimization operations and improving optimization efficiency.

[0131] Step 506: Obtain the image quality requirements associated with the network evaluation value level.

[0132] The image quality requirements may include frame rate, resolution, and processing effects, etc., which are not limited in this disclosure.

[0133] In this disclosure, the image quality requirement associated with each network evaluation value level can be determined based on the image quality requirement corresponding to the image quality level associated with that network evaluation value level, and this disclosure does not limit it in this way.

[0134] It should be noted that the image quality requirements corresponding to each image quality level can be preset according to the actual situation, and this disclosure does not limit this.

[0135] Step 507: Adjust the image quality of the metaverse based on image quality requirements.

[0136] In this disclosure, when adjusting the image quality of the metaverse based on image quality requirements, the image quality can be classified into levels based on the image evaluation value and a preset image threshold: A1, determine whether the image evaluation value is greater than the preset first-level image threshold. If the image evaluation value is not greater than the preset first-level image threshold, the corresponding image evaluation value is determined to be of first-level image quality, and this image quality level is associated with the first-level network evaluation value level; otherwise, proceed to A2; A2, determine whether the image evaluation value is greater than the preset second-level image threshold. If the image evaluation value is not greater than the preset second-level image threshold, the corresponding image evaluation value is determined to be of second-level image quality, and this image quality level is associated with the second-level network evaluation value level; otherwise, the corresponding image evaluation value is determined to be of third-level image quality, and the image quality level is associated with the third-level network evaluation value level. This disclosure does not limit this aspect.

[0137] Among them, Level 1 image quality, Level 2 image quality, and Level 3 image quality represent the classification of image quality levels, with Level 1 being the lowest and Level 3 being the highest.

[0138] The preset primary image threshold and preset secondary image threshold can be determined using historical data, i.e., from a preset database. For example, the preset primary image threshold can be represented by 30% of the maximum image evaluation value within a historical time period, and the preset secondary image threshold can be represented by 70% of the maximum image evaluation value within the same historical time period; the historical time period refers to the past month. If there is no historical time period, the preset primary network severity threshold is represented by 30% of the current image evaluation value, and the preset secondary network severity threshold is represented by 70% of the current image evaluation value. This disclosure does not impose any limitations on this.

[0139] This enables the classification of image quality levels. By setting preset first-level and second-level image thresholds, image quality is clearly divided into three levels: first-level, second-level, and third-level, which effectively improves the efficiency of image adjustment and provides effective information support for subsequent image quality adjustments.

[0140] By dynamically adjusting image quality based on network evaluation values ​​and corresponding multi-level network thresholds, network resources can be utilized more effectively. For example, when network performance is poor, the image quality can be adjusted to a lower quality level (Level 1), effectively reducing loading time, avoiding stuttering and latency, and thus improving the overall user experience. When network performance is good, the image quality can be adjusted to a higher quality level (Level 3), further enhancing the user's visual experience.

[0141] In this disclosure, when adjusting the image quality of the metaverse based on image quality requirements, if the current image quality is higher than the image quality requirement associated with the network evaluation value level, the image quality can be appropriately reduced to save resources. Taking image quality reduction as an example, processing effects can be reduced step-by-step, resolution can be reduced step-by-step, and frame rate can be reduced step-by-step until the image quality meets the requirements. Processing effects are reduced step-by-step according to their levels, which include highest, medium, low, and very low settings. The highest setting enables all advanced effects, such as real-time ray tracing; the medium setting disables resource-intensive effects, such as ray tracing, while retaining basic effects; the low setting reduces the quality and quantity of dynamic shadows, reflections, and particle effects, uses a simple lighting model, and reduces or disables anti-aliasing; and the very low setting disables most effects, retaining only basic rendering functions, such as disabling dynamic shadows. Gradually reducing resolution refers to lowering the resolution by a multiple of the square of the image resolution, for example, reducing the original resolution of 1920x1080 to 960x540, 480x270, or 240x135. Gradually reducing frame rate refers to lowering the frame rate by a multiple of the square of the frame rate, for example, reducing the original frame rate of 60 FPS to 30 FPS, 15 FPS, 10 FPS, with the lowest frame rate being 10 FPS. This disclosure does not limit this.

[0142] Furthermore, reducing image quality to Level 1 helps reduce data transfer volume and speeds up loading, effectively preventing stuttering and latency, and improving user experience. Lowering image quality also reduces the amount of data the server needs to process, thereby reducing server load and improving server stability and reliability.

[0143] In this disclosure, when adjusting the image quality of the metaverse based on image quality requirements, if the current image quality does not meet the requirements, the image quality can be appropriately optimized to improve it and enhance the user experience. Taking image quality optimization as an example, the frame rate, resolution, and processing effects can be increased incrementally until the image quality meets the requirements. Increasing the frame rate incrementally means increasing it in multiples of the square of the frame rate, for example, increasing the original frame rate of 15 FPS to 30 FPS, 60 FPS, or 120 FPS. Increasing the resolution incrementally means increasing it in multiples of the square of the image resolution, for example, increasing the original resolution of 240x135 to 480x270, 960x540, or 1920x1080. Processing effects are increased incrementally according to their level. This disclosure does not limit this.

[0144] Furthermore, by optimizing image quality to level two, users can obtain clearer and more detailed images, thereby enhancing their viewing experience. Ensuring image quality is improved when network conditions permit and maintained when conditions are not met helps provide a more stable viewing experience, thus improving the application performance of the metaverse.

[0145] Therefore, adjusting image quality according to actual network conditions can make more effective use of network resources, ensuring smoothness and visual experience for users in the metaverse, thereby improving user satisfaction.

[0146] In some possible implementations, after adjusting the image quality of the metaverse based on image quality requirements, in order to determine the performance of the metaverse after image quality adjustment, a comprehensive evaluation value after image quality adjustment can also be determined, and if the comprehensive evaluation value after image quality adjustment is less than the comprehensive evaluation threshold, feedback information is generated and returned.

[0147] It should be noted that the specific implementation of determining the comprehensive evaluation value after image quality adjustment can refer to the specific implementation in the above embodiments, and will not be elaborated here.

[0148] The feedback information is used to indicate that the current comprehensive evaluation value does not meet the standard.

[0149] The feedback information may include the current comprehensive evaluation value, the comprehensive evaluation threshold, the difference between the two, the specific data of each evaluation indicator in the comprehensive evaluation value, etc., which are not limited in this disclosure.

[0150] Among them, the comprehensive evaluation value is not up to standard, that is, the comprehensive evaluation value is less than the comprehensive evaluation threshold.

[0151] In this disclosure, if the overall evaluation value after image quality adjustment is less than the overall evaluation threshold, it can be determined that the overall performance of the metaverse after image quality adjustment is poor. At this time, feedback information can be generated and returned to relevant personnel for feedback, and the current adjustment process can be ended.

[0152] In this embodiment, the network data and image data of the metaverse at the current moment are first acquired. Then, a network evaluation value is determined based on the network data, and an image evaluation value is determined based on the image data. Next, if the network evaluation value is less than a preset network threshold, the metaverse network is optimized to obtain the optimized network evaluation value. Based on the optimized network evaluation value and the image evaluation value, a comprehensive evaluation value is determined. If the comprehensive evaluation value is less than a preset comprehensive evaluation threshold, a network evaluation value level corresponding to the network evaluation value is determined based on a preset multi-level adjustment strategy, and the image quality requirement associated with the network evaluation value level is obtained. Finally, the image quality of the metaverse is adjusted based on the image quality requirement. Therefore, when the comprehensive evaluation value is unsatisfactory, the image quality is adjusted based on the multi-level adjustment strategy and the network evaluation value to improve the accuracy of data analysis and enhance the performance of the metaverse.

[0153] Figure 6 This is a schematic diagram illustrating the process of acquiring network data and image data in a data analysis method provided in an embodiment of this disclosure.

[0154] like Figure 6 As shown, the process of acquiring network data and image data in this data analysis method may include the following steps: Step 601: Collect the initial network data and initial image data of the metaverse at the current moment.

[0155] The initial network data includes at least one of traffic, latency, jitter, and packet loss rate, and the initial image data includes at least one of frame rate and resolution.

[0156] In this disclosure, initial network data of the metaverse can be collected using network packet capture tools, and initial image data can be collected using multimedia processing tools; this disclosure does not limit the scope of the data collection.

[0157] Step 602: Obtain reference network data and reference image data from a preset database.

[0158] The reference network data includes at least one of reference bandwidth, reference latency, reference jitter, and reference packet loss rate, and the reference image data includes at least one of reference frame rate and reference resolution.

[0159] It should be noted that all reference data in the database can be preset according to actual needs, and this disclosure does not impose any restrictions on this.

[0160] The reference resolution can be the maximum resolution of the metaverse image, but this disclosure does not limit it.

[0161] Step 603: Summate the first ratio of traffic to reference bandwidth, the second ratio of delay to reference delay, the third ratio of packet loss rate to reference packet loss rate to obtain the network congestion level.

[0162] The first ratio can be used to represent the traffic percentage; the second ratio can be used to represent the latency normalization value; and the third ratio can be used to represent the packet loss rate normalization value.

[0163] In this disclosure, a first ratio is obtained by comparing the traffic with the reference bandwidth, a second ratio is obtained by comparing the delay with the reference delay, and a third ratio is obtained by comparing the packet loss rate with the reference packet loss rate. The network congestion degree is obtained by summing the first, second, and third ratios as shown in the following formula (4), where formula (4) is only an example and is not intended to limit the scope of the problem. , (4) in, For network congestion, For delay, For traffic, For packet loss rate, For reference delay, For reference bandwidth, For reference packet loss rate.

[0164] Step 604: Summate the first ratio, the third ratio, and the fourth ratio of the resolution to the reference resolution to obtain the sharpness.

[0165] The fourth ratio, which can be used to represent the resolution ratio, reflects the degree of utilization of the metaverse device's performance.

[0166] In this disclosure, a fourth ratio is obtained by comparing the resolution with the reference resolution, and the first, third, and fourth ratios are summed to obtain the sharpness as shown in the following formula (5). Formula (5) is only an example and is not intended to limit the scope of the application. , (5) in, For clarity, For resolution, This is the reference resolution.

[0167] Step 605: Sum the second ratio, the third ratio, the fifth ratio of jitter to reference jitter, and the sixth ratio of frame rate to reference frame rate to obtain the smoothness.

[0168] The fifth ratio can be used to represent the jitter normalization value.

[0169] In this disclosure, a fifth ratio is obtained by comparing the jitter with the reference jitter, and a sixth ratio is obtained by comparing the frame rate with the reference frame rate. Then, the second, third, fifth, and sixth ratios are summed to obtain the smoothness as shown in the following formula (6). Formula (6) is only an example and is not intended to limit the process. , (6) in, For smoothness, For shaking, For frame rate, To preset the jitter, This is the maximum frame rate.

[0170] Step 606: Determine the number of online users in the metaverse at the current moment, as well as the texture complexity of the image.

[0171] In this disclosure, sessions can be tracked using a preset method, creating a session each time a user visits and ending the session when the user leaves. The number of online users in the metaverse at the current moment is determined by counting the number of currently active sessions, but this disclosure does not limit this.

[0172] The preset method can be pre-configured according to actual needs. For example, the session can be tracked by using a HyperText Transfer Protocol Session (HttpSession) object, etc., but this disclosure does not limit it.

[0173] In this disclosure, when determining the texture complexity of an image, texture features can first be extracted from the image in the metaverse to obtain the local binary pattern values ​​of the image pixels. Then, the local binary pattern values ​​of the image pixels are statistically analyzed to obtain the local binary pattern histogram. After that, the entropy of the local binary pattern histogram of the image pixels is recorded as the texture complexity. This disclosure does not limit this process.

[0174] Specifically, texture feature extraction can be represented by using a local binary pattern to compare the grayscale values ​​of the surrounding pixels (e.g., 8 pixels in a 3x3 area) with the grayscale value of the center pixel, centering on each pixel in the image. If the surrounding pixel values ​​are not less than the center pixel value, the comparison result for that pixel is assigned a value of 1; otherwise, it is assigned a value of 0. The comparison results are then arranged clockwise starting from the top left corner to generate binary numbers, and all binary numbers are converted to decimal numbers as the local binary pattern value of the center pixel. This disclosure does not limit this process.

[0175] for example, ,from Start, with the middle pixel Perform grayscale value comparison and arrange the comparison results in clockwise order. Therefore, the binary number is 10110100.

[0176] Step 607: Obtain network data based on network congestion, frame rate, and number of online users, and obtain image data based on smoothness, clarity, and texture complexity.

[0177] In this disclosure, network data is obtained based on network congestion, frame rate, and number of online users, and image data is obtained based on smoothness, clarity, and texture complexity. This allows for a comprehensive evaluation of network performance and image rendering quality, providing a data foundation for subsequent data analysis.

[0178] In this embodiment, the initial network data and initial image data of the metaverse at the current moment are first collected, and reference network data and reference image data are obtained from a preset database. Then, the network congestion level is obtained by summing the first ratio of traffic to reference bandwidth, the second ratio of latency to reference latency, and the third ratio of packet loss rate to reference packet loss rate. The first ratio, the third ratio, and the fourth ratio of resolution to reference resolution are then summed to obtain sharpness. Subsequently, the smoothness level is obtained by summing the second ratio, the third ratio, the fifth ratio of jitter to reference jitter, and the sixth ratio of frame rate to reference frame rate. The number of online users in the metaverse at the current moment and the texture complexity of the image are also determined. Finally, based on the network congestion level, frame rate, and number of online users, network data is obtained, and based on the smoothness level, sharpness level, and texture complexity, image data is obtained. Therefore, by collecting real-time initial network data and initial image data from the metaverse, and based on the corresponding reference data in the database, the network data and image data used for evaluation are determined, thereby improving the comprehensiveness and accuracy of the network data and image data used for evaluation. This provides an accurate and reliable data foundation for subsequent data analysis to evaluate and improve the network performance and image rendering quality of the metaverse.

[0179] The following is combined Figure 7 The relationship between the comprehensive evaluation value, the image evaluation value, and the first-level network evaluation value in the data analysis method proposed in this disclosure is illustrated with an example. Figure 7 This diagram illustrates the relationship between the comprehensive evaluation value, the image evaluation value, and the network evaluation value in the data analysis method proposed in this disclosure.

[0180] Figure 7 Including Figure 7 a, Figure 7 b, Figure 7 'a' is a schematic diagram showing how the overall evaluation value changes with the image evaluation value. Figure 7 b is a schematic diagram illustrating the change of the overall evaluation value with the performance difference, where the performance difference... Network evaluation value Image evaluation value The absolute value of the difference, i.e. .

[0181] As shown in Figure (a), when the performance difference is 0.1, the larger the image evaluation value, the larger the overall evaluation value, indicating better application performance of the metaverse. As shown in Figure (b), when the image evaluation value is 0.4, the larger the performance difference, the smaller the overall evaluation value, indicating poor application performance of the metaverse. Therefore, the overall evaluation value is negatively correlated with the performance difference and positively correlated with the image evaluation value.

[0182] A higher image evaluation value indicates higher image quality, but also means a larger data volume, leading to increased network load and a lower network evaluation value. The network evaluation value reflects network stability; a lower value may cause network performance fluctuations, affecting user experience and consequently lowering the experience evaluation value. Therefore, a smaller performance difference indicates a relatively balanced state between image quality and network condition. In this balanced state, the network can guarantee image data transmission while maintaining image quality to a certain extent. This ensures that users do not experience noticeable latency or stuttering, nor are they negatively impacted by low image quality, thus improving the application performance of the metaverse.

[0183] In some possible implementations, the data analysis method proposed in this disclosure is not only applicable to metaverse scenarios, but also to other fields requiring high-quality network transmission and image rendering, such as online games and high-definition video streaming. By dynamically adjusting network conditions and image quality, it can ensure that users can obtain a smooth and clear experience under different network environments. This disclosure does not limit this.

[0184] It should be noted that when the data analysis method proposed in this disclosure is applied to other fields, its specific implementation is similar to that in the metaverse field. It involves evaluating network and image data from related systems in other fields to obtain network and image evaluation values. If the network evaluation value is less than a network threshold, the network is optimized until it exceeds the threshold. Based on the optimized network and image evaluation values, a comprehensive evaluation value is determined. If the comprehensive evaluation value is less than the comprehensive evaluation threshold, the image quality is adjusted based on the current network evaluation value. Specific details can be found in the relevant descriptions in the embodiments of this disclosure, and will not be repeated here.

[0185] To implement the above embodiments, this disclosure also proposes a data analysis device.

[0186] Figure 8 This is a schematic diagram of the structure of the data analysis device provided in the embodiments of this disclosure.

[0187] like Figure 8 As shown, the data analysis device 800 includes: an acquisition module 801, a first determination module 802, an optimization module 803, a second determination module 804, and an adjustment module 805.

[0188] The acquisition module 801 is used to acquire network data and image data of the metaverse at the current moment. The network data includes at least one of the number of online users, network congestion and frame rate, and the image data includes at least one of the clarity, smoothness and texture complexity. The first determining module 802 is used to determine the network evaluation value based on network data and the image evaluation value based on image data; The optimization module 803 is used to optimize the metaverse network when the network evaluation value is less than a preset network threshold, and obtain the network evaluation value after optimization. The second determining module 804 is used to determine the comprehensive evaluation value based on the optimized network evaluation value and the image evaluation value. The adjustment module 805 is used to adjust the image quality of the metaverse based on the current network evaluation value when the comprehensive evaluation value is less than the preset comprehensive evaluation threshold.

[0189] In one possible implementation of this disclosure, the first determining module 802 is specifically used for: Retrieve reference online user count and reference frame rate from the pre-set database; Based on the number of online users and the reference number of online users, a normalized value for the number of online users is determined, and based on the frame rate and the reference frame rate, the frame rate percentage is determined. The first value is obtained by exponentially calculating the frame rate percentage, and the second value is obtained by exponentially calculating the sum of the normalized number of online users and the network congestion. Perform hyperbolic tangent operations on the first and second values ​​respectively to obtain the corresponding frame rate hyperbolic tangent value and user hyperbolic tangent value; The network evaluation value is obtained by performing a logarithmic operation on the sum of the frame rate hyperbolic tangent and the user hyperbolic tangent.

[0190] In one possible implementation of this disclosure, the first determining module 802 is specifically used for: The sharpness, smoothness, and texture complexity are exponentially calculated to obtain the corresponding third, fourth, and fifth values. Perform hyperbolic tangent operations on the third, fourth, and fifth values ​​respectively to obtain the corresponding hyperbolic tangent values ​​for clarity, smoothness, and complexity. The image evaluation value is obtained by taking the logarithm of the sum of the hyperbolic tangent values ​​of sharpness, smoothness, and complexity.

[0191] In one possible implementation of this disclosure, the optimization module 803 is specifically used for: If the network evaluation value is less than the preset network threshold, the metaverse is optimized based on the preset optimization strategy, and at least one of the following optimizations is performed to obtain the corresponding optimized network evaluation value: bandwidth, routing, and caching.

[0192] In one possible implementation of this disclosure, the optimization module 803 is specifically used for at least one of the following: Based on a preset bandwidth optimization strategy, the data bandwidth of the metaverse is optimized, and the first network evaluation value corresponding to the optimization is determined. When this value is greater than the network threshold, it is determined as the final network evaluation value. If the first network evaluation value is less than the network threshold, the data routing of the metaverse is optimized to determine the second network evaluation value after optimization. If this value is greater than the network threshold, it is determined as the final network evaluation value. If the second network evaluation value is less than the network threshold, the data cache of the metaverse is optimized based on the preset hierarchical caching strategy to determine the corresponding third network evaluation value after optimization. If this value is greater than the network threshold, it is determined as the final network evaluation value. If the third network evaluation value is less than the network threshold, the entire data flow process of the metaverse is investigated based on the evaluation indicators in the network evaluation value. The content to be optimized is located and optimized until the re-determined network evaluation value is greater than the network threshold, and then it is determined as the final network evaluation value.

[0193] In one possible implementation of this disclosure, the second determining module 804 is specifically used for: The sixth value is obtained by exponentially calculating the absolute value of the difference between the network evaluation value and the image evaluation value. The comprehensive evaluation value is obtained by taking the square root of the ratio of the image evaluation value to the sixth value and then performing a logarithmic operation on the result.

[0194] In one possible implementation of this disclosure, the adjustment module 805 is specifically used for: If the overall evaluation value is less than the preset overall evaluation threshold, the network evaluation value level corresponding to the network evaluation value is determined based on the preset multi-level adjustment strategy. Obtain the image quality requirements associated with the network evaluation value level; Based on image quality requirements, the image quality of the metaverse is adjusted.

[0195] In one possible implementation of this disclosure, the aforementioned acquisition module 801 is specifically used for: Collect initial network data and initial image data of the metaverse at the current moment. The initial network data includes at least one of traffic, latency, jitter and packet loss rate, and the initial image data includes at least one of frame rate and resolution. Retrieve reference network data and reference image data from a preset database. The reference network data includes at least one of reference bandwidth, reference latency, reference jitter, and reference packet loss rate. The reference image data includes at least one of reference frame rate and reference resolution. The network congestion level is obtained by summing the first ratio of traffic to reference bandwidth, the second ratio of delay to reference delay, the packet loss rate, and the third ratio of reference packet loss rate. The sharpness is obtained by summing the first ratio, the third ratio, and the fourth ratio of the resolution to the reference resolution. The smoothness is obtained by summing the second ratio, the third ratio, the fifth ratio of jitter to reference jitter, and the sixth ratio of frame rate to reference frame rate. Determine the number of online users in the metaverse at the current moment, and the texture complexity of the image; Network data is obtained based on network congestion, frame rate, and number of online users, and image data is obtained based on smoothness, clarity, and texture complexity.

[0196] The functions and specific implementation principles of the modules described in this embodiment can be found in the above method embodiments, and will not be repeated here.

[0197] In this embodiment, the network data and image data of the metaverse at the current moment are first acquired. Then, a network evaluation value is determined based on the network data, and an image evaluation value is determined based on the image data. If the network evaluation value is less than a preset network threshold, the metaverse network is optimized to obtain the optimized network evaluation value. Based on the optimized network evaluation value and the image evaluation value, a comprehensive evaluation value is determined. Finally, if the comprehensive evaluation value is less than a preset comprehensive evaluation threshold, the image quality of the metaverse is adjusted based on the current network evaluation value. Thus, by determining the network evaluation value and image evaluation value based on the real-time network data and image data of the metaverse, optimizing the metaverse network when the network evaluation value is substandard, determining the comprehensive evaluation value based on the optimized network evaluation value and the image quality adjustment when the comprehensive evaluation value is substandard, accurate and reliable dynamic adjustment of the network and image quality of the metaverse is achieved, improving the performance of the metaverse and enhancing the user experience.

[0198] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0199] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0200] like Figure 9 As shown, device 900 includes a computing unit 901, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 902 or a computer program loaded from storage unit 908 into random access memory (RAM) 903. RAM 903 may also store various programs and data required for the operation of device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via bus 904. Input / output (I / O) interface 905 is also connected to bus 904.

[0201] Multiple components in device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of monitors, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0202] The computing unit 901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as data analysis methods. For example, in some embodiments, the data analysis method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the data analysis method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform data analysis methods by any other suitable means (e.g., by means of firmware).

[0203] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0204] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0205] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0206] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0207] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0208] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0209] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0210] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified. In the description of this disclosure, the words "if" and "suppose" as used may be interpreted as "when," "when," "in response to determination," or "in the circumstances."

[0211] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A data analysis method, characterized in that, include: Obtain network data and image data of the metaverse at the current moment, wherein the network data includes at least one of the number of online users, network congestion and frame rate, and the image data includes at least one of the clarity, smoothness and texture complexity; The network evaluation value is determined based on the network data, and the image evaluation value is determined based on the image data; If the network evaluation value is less than a preset network threshold, the metaverse is optimized to obtain the optimized network evaluation value. Based on the optimized network evaluation value and the image evaluation value, a comprehensive evaluation value is determined; If the overall evaluation value is less than a preset overall evaluation threshold, the image quality of the metaverse is adjusted based on the current network evaluation value.

2. The method as described in claim 1, characterized in that, Determining the network evaluation value based on the network data includes: Retrieve reference online user count and reference frame rate from the pre-set database; Based on the number of online users and the reference number of online users, a normalized value for the number of online users is determined, and based on the frame rate and the reference frame rate, the frame rate percentage is determined. The first value obtained by exponentially calculating the frame rate percentage, and the second value obtained by exponentially calculating the sum of the normalized value of the number of online users and the network congestion degree; Perform hyperbolic tangent operations on the first value and the second value respectively to obtain the corresponding frame rate hyperbolic tangent value and user hyperbolic tangent value; The network evaluation value is obtained by performing a logarithmic operation on the sum of the frame rate hyperbolic tangent value and the user hyperbolic tangent value.

3. The method as described in claim 1, characterized in that, Determining the image evaluation value based on the image data includes: The clarity, smoothness, and texture complexity are respectively subjected to exponential operations to obtain the corresponding third, fourth, and fifth values; Perform hyperbolic tangent operations on the third, fourth, and fifth values ​​respectively to obtain the corresponding hyperbolic tangent values ​​for clarity, smoothness, and complexity. The image evaluation value is obtained by performing a logarithmic operation on the sum of the hyperbolic tangent values ​​of sharpness, smoothness, and complexity.

4. The method as described in claim 1, characterized in that, When the network evaluation value is less than a preset network threshold, the metaverse is optimized to obtain the optimized network evaluation value, including: If the network evaluation value is less than a preset network threshold, the metaverse is optimized based on a preset optimization strategy, and at least one of the following optimizations is performed to obtain the optimized network evaluation value: bandwidth, routing, and caching.

5. The method as described in claim 4, characterized in that, The preset optimization strategy involves performing at least one of the following optimizations on the metaverse to obtain optimized network evaluation values: bandwidth, routing, and caching, including at least one of the following: Based on a preset bandwidth optimization strategy, the data bandwidth of the metaverse is optimized, and a first network evaluation value corresponding to the optimization is determined. When this value is greater than the network threshold, it is determined as the final network evaluation value. If the first network evaluation value is less than the network threshold, the data routing of the metaverse is optimized to determine the second network evaluation value after optimization. If this value is greater than the network threshold, it is determined as the final network evaluation value. If the second network evaluation value is less than the network threshold, the data cache of the metaverse is optimized based on a preset hierarchical caching strategy to determine the third network evaluation value after optimization. If this value is greater than the network threshold, it is determined as the final network evaluation value. If the third network evaluation value is less than the network threshold, the entire data flow process of the metaverse is investigated based on the evaluation indicators in the network evaluation value. The content to be optimized is located and optimized until the re-determined network evaluation value is greater than the network threshold, and then it is determined as the final network evaluation value.

6. The method as described in claim 1, characterized in that, The determination of the comprehensive evaluation value based on the optimized network evaluation value and the image evaluation value includes: The sixth value is obtained by performing an exponential operation on the absolute value of the difference between the network evaluation value and the image evaluation value. The comprehensive evaluation value is obtained by taking the square root of the ratio of the image evaluation value to the sixth value and then performing a logarithmic operation on the result.

7. The method as described in claim 6, characterized in that, When the overall evaluation value is less than a preset overall evaluation threshold, the image quality of the metaverse is adjusted based on the current network evaluation value, including: If the overall evaluation value is less than the preset overall evaluation threshold, the network evaluation value level corresponding to the network evaluation value is determined based on the preset multi-level adjustment strategy. Obtain the image quality requirements associated with the network evaluation value level; Based on the aforementioned image quality requirements, the image quality of the metaverse is adjusted.

8. The method as described in claim 1, characterized in that, The acquisition of network data and image data of the metaverse at the current moment includes: The metaverse is collected at the current moment, including initial network data and initial image data, wherein the initial network data includes at least one of traffic, latency, jitter and packet loss rate, and the initial image data includes at least one of frame rate and resolution. Reference network data and reference image data are obtained from a preset database. The reference network data includes at least one of reference bandwidth, reference latency, reference jitter, and reference packet loss rate. The reference image data includes at least one of reference frame rate and reference resolution. The network congestion degree is obtained by summing the first ratio of the traffic to the reference bandwidth, the second ratio of the delay to the reference delay, the packet loss rate, and the third ratio of the reference packet loss rate. The sharpness is obtained by summing the first ratio, the third ratio, and the fourth ratio of the resolution to the reference resolution. The smoothness is obtained by summing the second ratio, the third ratio, the fifth ratio of the jitter to the reference jitter, and the sixth ratio of the frame rate to the reference frame rate. Determine the number of online users in the metaverse at the current moment, and the texture complexity of the image; The network data is obtained based on the network congestion, the frame rate, and the number of online users, and the image data is obtained based on the smoothness, the clarity, and the texture complexity.

9. A data analysis device, characterized in that, include: The acquisition module is used to acquire network data and image data of the metaverse at the current moment. The network data includes at least one of the number of online users, network congestion, and frame rate, and the image data includes at least one of the clarity, smoothness, and texture complexity. The first determining module is used to determine a network evaluation value based on the network data and an image evaluation value based on the image data. The optimization module is used to optimize the metaverse when the network evaluation value is less than a preset network threshold, so as to obtain the network evaluation value after optimization. The second determining module is used to determine a comprehensive evaluation value based on the optimized network evaluation value and the image evaluation value. The adjustment module is used to adjust the image quality of the metaverse based on the current network evaluation value when the comprehensive evaluation value is less than a preset comprehensive evaluation threshold.

10. A computer program product, comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the method according to any one of claims 1-8.

Images