A method for predicting the length of time a user waits during a VR generation process

Abstract

The application provides a method for predicting user waiting time in a VR generation process, and belongs to the technical field of data processing. The method specifically comprises the following steps: performing update processing on generation data and corresponding generation time data in an update load interval; and based on the update processing result of the generation data in the update load interval, determining whether the update processing of the generation data needs to be performed in a running load interval other than the update load interval based on the variation of the adjustment factor of the predicted time in different running load intervals when the update processing of the adjustment factor of the predicted time can be performed, so that the accuracy of the prediction result of the user waiting time is improved.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, and in particular relates to a method for predicting user waiting time during VR generation. Background Technology

[0002] The generation of VR videos often involves complex image data processing, which makes predicting the user's waiting time during VR generation a pressing technical problem.

[0003] Existing technical solutions often predict user waiting time based on the amount of data to be processed. However, as the operating load increases, the user waiting time will inevitably change during the VR generation process. Therefore, how to determine the adjustment factor for user waiting time based on the change in operating load, so as to improve the accuracy of user waiting time prediction, has become an urgent technical problem to be solved.

[0004] Therefore, there is an urgent need for a method to predict the user's waiting time during the VR generation process. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted:

[0006] Specifically, this application provides a method for predicting user waiting time during VR generation, which includes:

[0007] S1 uses the operating data of the VR generation system as a basis to determine the changing data of the operating load of the VR generation system. Based on the changing data, when it is determined that the adjustment factor for the waiting time needs to be dynamically updated, the update load interval in the operating load interval is determined based on the historical generation data in different operating load intervals.

[0008] S2 performs data generation and corresponding generation duration data update processing within the update load interval. Based on the data generation update processing results within the update load interval, when determining whether the prediction duration adjustment factor can be updated, it determines whether data generation update processing is needed in the operating load intervals other than the update load interval based on the changes in the prediction duration adjustment factor in different operating load intervals.

[0009] The beneficial effects of this invention are as follows:

[0010] Based on the update processing results of the generated data within the update load interval, it is determined whether the adjustment factor for the prediction duration can be updated. This avoids the technical problem of instability caused by frequent updates of the adjustment factor for the prediction duration. By combining the update processing results of the generated data within different update load intervals, the adjustment factor can be updated even when the amount of updated data in different update load intervals is large, thus ensuring the reliability of the adjustment factor update processing.

[0011] Based on the variation of the prediction duration adjustment factor in different operating load intervals, it is determined whether data generation update processing is required in operating load intervals other than the update load interval. This avoids the technical problem of excessively high update delay of the adjustment factor due to the unstable prediction duration adjustment factor in the update load interval, which is caused by performing data generation update processing only in the update load interval.

[0012] Furthermore, the VR generation system is a system that uses images to generate VR videos.

[0013] Furthermore, the variation data of the operating load is determined based on the variation of the operating load of the VR generation system between adjacent time periods.

[0014] Furthermore, the dynamic updating of the adjustment factor for the waiting time needs to be determined, specifically including:

[0015] Based on the aforementioned change data, the variation in the operating load of the VR generation system between adjacent time periods is determined;

[0016] Based on the changes in the operating load, the time period of the operating load change of the VR generation system is determined;

[0017] Based on the period of change in the operating load of the VR generation system, determine whether the waiting time adjustment factor needs to be dynamically updated.

[0018] Furthermore, determining whether data update processing is needed in the operating load interval excluding the aforementioned update load interval specifically includes:

[0019] The variation of the adjustment factor for prediction duration in different operating load intervals is used to determine the variation of the adjustment factor for prediction duration in different generation processing duration intervals.

[0020] Based on the variation of the adjustment factor for the forecast duration within the operating load range, the fluctuation type of the adjustment factor within the operating load range is determined;

[0021] Based on the fluctuation type of the adjustment factor in the operating load interval, it is determined whether data update processing is required in the operating load interval excluding the update load interval.

[0022] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0023] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0024] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0025] Figure 1 This is a flowchart of a method for predicting user waiting time during VR generation;

[0026] Figure 2 It is a flowchart for dynamically updating the adjustment factor that determines the waiting time;

[0027] Figure 3 This is a flowchart illustrating the method for determining the updated load range within the running load range;

[0028] Figure 4 A flowchart for determining the update process of the adjustment factor that can be used for prediction duration. Detailed Implementation

[0029] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0030] In this application, based on the operating load data of the VR generation system during the generation process, the adjustment factor of the waiting time based on the load impact is dynamically updated in different operating load ranges, so that the predicted user waiting time can accurately reflect the impact of the operating load and improve the accuracy of the predicted processing results of the operating load.

[0031] Example 1

[0032] like Figure 1As shown, this application provides a method for predicting user waiting time during VR generation, specifically including:

[0033] S1 uses the operating data of the VR generation system as a basis to determine the changing data of the operating load of the VR generation system. Based on the changing data, when it is determined that the adjustment factor for the waiting time needs to be dynamically updated, the update load interval in the operating load interval is determined based on the historical generation data in different operating load intervals.

[0034] Furthermore, the VR generation system is a system that uses images to generate VR videos.

[0035] Furthermore, the variation data of the operating load is determined based on the variation of the operating load of the VR generation system between adjacent time periods.

[0036] Specifically, such as Figure 2 As shown, the dynamic update of the adjustment factor for determining the waiting time requires includes:

[0037] Based on the aforementioned change data, the variation in the operating load of the VR generation system between adjacent time periods is determined;

[0038] Based on the changes in the operating load, the time period of the operating load change of the VR generation system is determined;

[0039] Based on the period of change in the operating load of the VR generation system, determine whether the waiting time adjustment factor needs to be dynamically updated.

[0040] It is understood that the period of change in operating load is a period of time in which the change in operating load compared to the previous period of time does not meet the requirements. In one possible embodiment, if the absolute value of the rate of change of operating load compared to the previous period of time is greater than 5%, then the period of time is determined to be the period of change in operating load.

[0041] It should be noted that the rate of change is determined based on the absolute value of the difference between the operating load of the current unit time period and the operating load of the previous unit time period, and the ratio of the difference to the operating load of the previous unit time period.

[0042] Specifically, based on the varying operating load periods of the VR generation system, it is determined whether a dynamic update of the waiting time adjustment factor is needed, including:

[0043] Based on the data of the operating load variation period of the VR generation system, the proportion of the operating load variation period in the unit time period on different dates is determined and used as the operating load variation coefficient.

[0044] Based on the average value of the operating load variation coefficient on different dates, determine whether the waiting time adjustment factor needs to be dynamically updated.

[0045] In one possible embodiment, if the average value of the operating load variation coefficient on different dates is greater than a preset variation coefficient threshold, then because the operating load is fluctuating drastically, in order to ensure the accuracy of the predicted waiting time, it is determined that the waiting time adjustment factor needs to be dynamically updated.

[0046] Optionally, determine the dynamic update of the adjustment factor for the waiting time, specifically including:

[0047] Based on the aforementioned change data, the variation in the operating load of the VR generation system between adjacent time periods is determined;

[0048] Based on the changes in the operating load, the time period of the operating load change of the VR generation system is determined;

[0049] Based on the number of unit time periods between adjacent operating load change periods of the VR generation system, it is determined whether the waiting time adjustment factor needs to be dynamically updated.

[0050] It is understood that if the number of unit time periods between adjacent operating load change periods of the VR generation system is less than the preset time period number threshold, for example, less than 3, then it is determined that the waiting time adjustment factor needs to be dynamically updated.

[0051] Specifically, such as Figure 3 As shown, the method for determining the update load range within the operating load range is as follows:

[0052] Based on historical generation data within the operating load range, determine the number of VR video generation processes within the operating load range.

[0053] The number of generation processes within different generation processing time intervals is determined based on the generation processing time of VR videos corresponding to different generation processing processes.

[0054] The running load interval is determined as an update load interval based on the number of generation processes within different generation processing time intervals.

[0055] Specifically, the operating load range is determined based on the rated operating load of the VR generation system. Specifically, the range from 0 to the rated operating load is divided into multiple operating load ranges at equal intervals of 10%.

[0056] It is understood that the generation processing time interval is divided into a preset number of intervals based on the range of VR video generation processing time in history within the operating load interval of the VR generation system. In one possible embodiment, the preset number is 5.

[0057] It should be noted that the determination of whether the operating load interval is an update load interval is based on the number of generation processes within different generation processing time intervals, specifically including:

[0058] The discrete value of the distribution within the generation processing time interval is determined based on the ratio of the number of generation processing processes within the generation processing time interval to the number of generation processing processes within the operating load interval.

[0059] When there are multiple generation processing time intervals where the distributed discrete values ​​do not meet the requirements, the running load interval is determined as the update load interval.

[0060] It is understood that when the discrete value of the generation processing time interval is less than a preset discrete threshold, for example, less than 0.1, the generation processing time interval is determined to be a generation processing time interval whose discrete value does not meet the requirements.

[0061] S2 performs data generation and corresponding generation duration data update processing within the update load interval. Based on the data generation update processing results within the update load interval, when determining whether the prediction duration adjustment factor can be updated, it determines whether data generation update processing is needed in the operating load intervals other than the update load interval based on the changes in the prediction duration adjustment factor in different operating load intervals.

[0062] Specifically, such as Figure 4 As shown, the update process for the adjustment factor that can be used to adjust the prediction duration is determined, specifically including:

[0063] Based on the update processing results of the generated data within the update load interval, determine the number of updates in the generation processing process within different generation processing time intervals within the update load interval.

[0064] The update matching factor within the generation processing time interval is determined based on the ratio of the number of updates to the number of original generation processing processes within the generation processing time interval.

[0065] By utilizing different update load intervals and update matching factors within different generation processing duration intervals, update matching coefficients for different update load intervals are determined. Based on these update matching coefficients, it is determined whether the adjustment factor for the prediction duration can be updated.

[0066] Specifically, when there is an update load interval where the update matching coefficient is greater than the preset matching coefficient threshold, i.e., an update load interval greater than 0.05, it is determined that the adjustment factor of the prediction duration can be updated. That is, the number of images and image memory in the updated generation process are used as inputs, and the generation duration data corresponding to the generation process is used as outputs to construct a training set, and the prediction model of the adjustment factor of the prediction duration is trained using the training set.

[0067] In one possible embodiment, the update matching coefficient of the update load interval is the average value of the update matching factor of the update load interval in different generation processing time intervals.

[0068] Furthermore, when there is no update load interval with an update matching coefficient greater than a preset matching coefficient threshold, the number of update load intervals with update matching coefficients within the preset matching coefficient interval is determined based on the update matching coefficients of different update load intervals. When the number of update load intervals with update matching coefficients within the preset matching coefficient interval meets the requirements, in one possible embodiment, when the number of new load intervals with update matching coefficients between 0.02 and 0.05 is not less than 2, it is determined that the adjustment factor for the prediction duration can be updated. That is, the number of images and image memory in the updated generation process are used as inputs, and the generation duration data corresponding to the generation process is used as outputs to construct a training set, and the prediction model for the adjustment factor of the prediction duration is trained using the training set.

[0069] Additionally, it is understandable that if the number of update load intervals within the preset matching coefficient range does not meet the requirements, then it is determined that the adjustment factor for the prediction duration cannot be updated.

[0070] Specifically, determining whether data update processing is needed in the operating load interval excluding the aforementioned update load interval includes:

[0071] The variation of the adjustment factor for prediction duration in different operating load intervals is used to determine the variation of the adjustment factor for prediction duration in different generation processing duration intervals.

[0072] Based on the variation of the adjustment factor for the forecast duration within the operating load range, the fluctuation type of the adjustment factor within the operating load range is determined;

[0073] Based on the fluctuation type of the adjustment factor in the operating load interval, it is determined that the fluctuation type of the adjustment factor belongs to the update load interval of the factor fluctuation interval. Based on the rate of change of the adjustment factor in the update load interval of the factor fluctuation interval, it is determined whether data update processing is required in the operating load interval excluding the update load interval.

[0074] It should be noted that if the number of update load intervals in which the fluctuation type of the adjustment factor belongs to the factor fluctuation interval is greater than the preset fluctuation load interval number threshold, for example, greater than 2, then it is determined that all running load intervals other than the update load interval need to be updated with generated data. That is, the generated data is used to train the prediction model of the adjustment factor of the prediction duration, thereby ensuring the timeliness of the adjustment factor update process.

[0075] Furthermore, if the number of update load intervals in which the fluctuation type of the adjustment factor belongs to the factor fluctuation interval is not greater than the preset threshold for the number of fluctuation load intervals, the average of the rate of change of the adjustment factor in the prediction duration within different generation processing duration intervals in the update load interval is used as the average rate of change. The adjustment factor fluctuation value is determined by the sum of the average rates of change of all the update load intervals in which the fluctuation type of the adjustment factor belongs to the factor fluctuation interval. When the adjustment factor fluctuation value is greater than the preset fluctuation threshold, for example, greater than 0.25, it is determined that the generation data update processing needs to be performed in all running load intervals except the update load interval. That is, the generation data is used to train the prediction model of the adjustment factor in the prediction duration, thereby ensuring the timeliness of the adjustment factor update processing.

[0076] Furthermore, when the fluctuation value of the adjustment factor is not greater than the preset change threshold, and when there is a generation processing time interval in the operating load interval where the distributed discrete value does not meet the requirements, it is determined that the generation data needs to be updated in the operating load interval. That is, the generation data is used to train the prediction model of the adjustment factor of the prediction time, thereby ensuring the timeliness of the adjustment factor update processing.

[0077] Additionally, it can be understood that when there is no generation processing time interval in the operating load interval where the distributed discrete values ​​do not meet the requirements, it is determined that no data update processing is required in the operating load interval.

[0078] Example 2

[0079] Furthermore, the update process for adjusting the prediction duration is determined, specifically including:

[0080] Based on the update processing results of the generated data within the update load interval, determine the number of updates in the generation processing process within different generation processing time intervals within the update load interval.

[0081] The update matching factor within the generation processing time interval is determined based on the ratio of the number of updates to the number of original generation processing processes within the generation processing time interval.

[0082] By utilizing different update load intervals and updating matching factors within different generation processing duration intervals, it can be determined whether the adjustment factor for the prediction duration can be updated.

[0083] Furthermore, the number of updates in the generation process within the generation processing time interval is the number of updates in the generation process where the generation processing time of the VR video falls within the generation processing time interval.

[0084] Furthermore, when there is no update load interval where the number of updates in the generation process meets the requirements, that is, the number of updates in the generation process is too small in different update load intervals, it is determined that the adjustment factor for the prediction duration cannot be updated.

[0085] Additionally, it can be understood that when there exists an update load interval where the number of updates in the generation process meets the requirements, and the number of update load intervals where the number of updates in the generation process meets the requirements is greater than a preset load interval threshold, then the number of updates in the VR video generation process is relatively large. Therefore, it is determined that the adjustment factor for the prediction duration can be updated. That is, the number of images and image memory in the updated generation process are used as inputs, and the generation duration data corresponding to the generation process is used as outputs to construct a training set, and the prediction model for the adjustment factor of the prediction duration is trained using the training set.

[0086] Furthermore, when the number of update load intervals that meet the requirements of the generation process is not greater than the preset load interval number threshold, and when there are update load intervals in different generation process duration intervals where the update matching factor is greater than the preset matching factor threshold, then there are update load intervals with a high amount of training data. Therefore, in order to ensure the accuracy of the prediction duration adjustment factor, it is determined that the prediction duration adjustment factor can be updated. That is, the number of images and image memory in the updated generation process are used as inputs, and the generation duration data corresponding to the generation process is used as outputs to construct a training set, and the training set is used to train the prediction model of the prediction duration adjustment factor.

[0087] Furthermore, when there is no update load interval where the update matching factor is greater than the preset matching factor threshold in different generation processing time intervals, the update matching coefficient of the update load interval is determined based on the update matching factor in different generation processing time intervals. When there is an update load interval where the update matching coefficient is greater than the preset matching coefficient threshold, it is determined that the adjustment factor of the prediction time can be updated. That is, the number of images and image memory in the updated generation processing process are used as inputs, and the generation time data corresponding to the generation processing process is used as outputs to construct a training set, and the prediction model of the adjustment factor of the prediction time is trained using the training set.

[0088] In one possible embodiment, the update matching coefficient of the update load interval is the average value of the update matching factor of the update load interval in different generation processing time intervals.

[0089] Furthermore, when there is no update load interval where the update matching coefficient is greater than the preset matching coefficient threshold, the number of update load intervals where the update matching coefficient is within the preset matching coefficient interval is determined based on the update matching coefficient of different update load intervals. When the number of update load intervals where the update matching coefficient is within the preset matching coefficient interval meets the requirements, it is determined that the adjustment factor of the prediction duration can be updated. That is, the number of images and image memory in the generation process after the update are used as inputs, and the generation duration data corresponding to the generation process is used as outputs to construct a training set, and the prediction model of the adjustment factor of the prediction duration is trained using the training set.

[0090] Additionally, it is understandable that if the number of update load intervals within the preset matching coefficient range does not meet the requirements, then it is determined that the adjustment factor for the prediction duration cannot be updated.

[0091] Example 3

[0092] Furthermore, determining whether data update processing is needed in the operating load interval excluding the aforementioned update load interval specifically includes:

[0093] The variation of the adjustment factor for prediction duration in different operating load intervals is used to determine the variation of the adjustment factor for prediction duration in different generation processing duration intervals.

[0094] Based on the variation of the adjustment factor for the forecast duration within the operating load range, the fluctuation type of the adjustment factor within the operating load range is determined;

[0095] Based on the fluctuation type of the adjustment factor in the operating load interval, it is determined whether data update processing is required in the operating load interval excluding the update load interval.

[0096] It should be noted that the fluctuation type of the adjustment factor in the operating load interval is determined based on the average rate of change of the adjustment factor of the prediction duration in different generation processing duration intervals in the operating load interval. If the average rate of change is greater than a threshold, for example, 10%, then the fluctuation type of the adjustment factor in the operating load interval is determined to be a factor fluctuation interval. If the average rate of change is not greater than the threshold, then the fluctuation type of the adjustment factor in the operating load interval is determined to be a factor stability interval.

[0097] It is understood that the rate of change is determined based on the absolute value of the difference between the adjustment factor of the prediction duration within the generation processing duration interval and the adjustment factor of the prediction duration before the update, and the ratio of the difference to the adjustment factor of the prediction duration before the update.

[0098] Specifically, based on the fluctuation type of the adjustment factor within the operating load interval, it is determined whether data update processing is required in operating load intervals other than the update load interval. This includes:

[0099] When the fluctuation type of the adjustment factor in different update load intervals all belong to the factor stability interval, the adjustment factor in different update load intervals is relatively stable, and the need for update processing is not high. Therefore, it is determined that no data update processing is required in the running load intervals other than the update load intervals. That is, no data needs to be used to train the prediction model of the adjustment factor of the prediction duration, thereby ensuring the stability and reliability of the adjustment factor update processing.

[0100] It is understood that the generated data includes the number of images, the size of the images, and the generation processing time of the different generation processes.

[0101] Additionally, it can be understood that when the fluctuation types of the adjustment factor in different update load intervals do not all belong to the factor stable interval, the update load intervals in which the fluctuation types of the adjustment factor belong to the factor fluctuation interval are obtained. If the number of update load intervals in which the fluctuation types of the adjustment factor belong to the factor fluctuation interval is greater than the preset threshold for the number of fluctuation load intervals, it is determined that data update processing needs to be performed in all running load intervals other than the aforementioned update load intervals. That is, the generated data is used to train the prediction model of the adjustment factor for the prediction duration, thereby ensuring the timeliness of the adjustment factor update processing.

[0102] Furthermore, if the number of update load intervals in which the fluctuation type of the adjustment factor belongs to the factor fluctuation interval is not greater than the preset threshold for the number of fluctuation load intervals, the average of the change rate of the adjustment factor in the prediction duration within different generation processing duration intervals in the update load interval is used as the average change rate. The adjustment factor fluctuation value is determined by the sum of the average change rates of all update load intervals in which the fluctuation type of the adjustment factor belongs to the factor fluctuation interval. When the adjustment factor fluctuation value is greater than the preset change threshold, it is determined that the generation data needs to be updated in all running load intervals except the update load interval. That is, the generation data is used to train the prediction model of the adjustment factor in the prediction duration, thereby ensuring the timeliness of the adjustment factor update processing.

[0103] Furthermore, when the fluctuation value of the adjustment factor is not greater than the preset change threshold, and when there is a generation processing time interval in the operating load interval where the distributed discrete value does not meet the requirements, it is determined that the generation data needs to be updated in the operating load interval. That is, the generation data is used to train the prediction model of the adjustment factor of the prediction time, thereby ensuring the timeliness of the adjustment factor update processing.

[0104] Additionally, it can be understood that when there is no generation processing time interval in the operating load interval where the distributed discrete values ​​do not meet the requirements, it is determined that no data update processing is required in the operating load interval.

[0105] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0106] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0107] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for predicting user waiting time during VR generation, characterized in that, Specifically, it includes: Based on the operating data of the VR generation system, the changing data of the operating load of the VR generation system is determined. Based on the changing data, when it is determined that the adjustment factor for the waiting time needs to be dynamically updated, the update load interval in the operating load interval is determined based on the historical generation data in different operating load intervals. Within the update load interval, the generation data and the corresponding generation duration data are updated. Based on the update result of the generation data within the update load interval, when it is determined whether the adjustment factor for the prediction duration can be updated, it is determined whether the generation data needs to be updated in the operating load interval other than the update load interval, based on the changes in the adjustment factor for the prediction duration in different operating load intervals. The update process for the adjustment factor that can be used to adjust the prediction duration includes: Based on the update processing results of the generated data within the update load interval, determine the number of updates in the generation processing process within different generation processing time intervals within the update load interval. The update matching factor within the generation processing time interval is determined based on the ratio of the number of updates to the number of original generation processing processes within the generation processing time interval. By utilizing different update load intervals and update matching factors within different generation processing duration intervals, update matching coefficients for different update load intervals are determined. Based on these update matching coefficients, it is determined whether the adjustment factor for the prediction duration can be updated.

2. The method for predicting user waiting time during VR generation as described in claim 1, characterized in that, The VR generation system is a system that uses images to generate and process VR videos.

3. The method for predicting user waiting time during VR generation as described in claim 1, characterized in that, The variation data of the operating load is determined based on the variation of the operating load of the VR generation system between adjacent time periods.

4. The method for predicting user waiting time during VR generation as described in claim 1, characterized in that, The dynamic updating of the adjustment factor for the waiting time needs to be determined, specifically including: Based on the aforementioned change data, the variation in the operating load of the VR generation system between adjacent time periods is determined; Based on the changes in the operating load, the time period of the operating load change of the VR generation system is determined; Based on the period of change in the operating load of the VR generation system, determine whether the waiting time adjustment factor needs to be dynamically updated.

5. The method for predicting user waiting time during VR generation as described in claim 4, characterized in that, The period of change in operating load refers to the period in which the change in operating load does not meet the requirements compared to the previous period.

6. The method for predicting user waiting time during VR generation as described in claim 4, characterized in that, Based on the varying operating load periods of the VR generation system, determine whether a dynamic update of the waiting time adjustment factor is needed, specifically including: Based on the data of the operating load variation period of the VR generation system, the proportion of the operating load variation period in the unit time period on different dates is determined and used as the operating load variation coefficient. Based on the average value of the operating load variation coefficient on different dates, determine whether the waiting time adjustment factor needs to be dynamically updated.

7. The method for predicting user waiting time during VR generation as described in claim 6, characterized in that, If the average value of the operating load variation coefficient on different dates is greater than the preset variation coefficient threshold, then it is determined that the waiting time adjustment factor needs to be dynamically updated.

8. The method for predicting user waiting time during VR generation as described in claim 1, characterized in that, Determining whether data generation update processing is required in the operating load interval excluding the aforementioned update load interval specifically includes: The variation of the adjustment factor for prediction duration in different operating load intervals is used to determine the variation of the adjustment factor for prediction duration in different generation processing duration intervals. Based on the variation of the adjustment factor for the forecast duration within the operating load range, the fluctuation type of the adjustment factor within the operating load range is determined; Based on the fluctuation type of the adjustment factor in the operating load interval, it is determined whether data update processing is required in the operating load interval excluding the update load interval.

9. The method for predicting user waiting time during VR generation as described in claim 8, characterized in that, The fluctuation type of the adjustment factor in the operating load range is determined based on the average rate of change of the adjustment factor for the prediction duration in different generation processing duration intervals within the operating load range.

10. The method for predicting user waiting time during VR generation as described in claim 8, characterized in that, Based on the fluctuation type of the adjustment factor within the operating load range, it is determined whether data update processing is required in operating load ranges other than the update load range, specifically including: When the fluctuation type of the adjustment factor in different update load intervals all belong to the factor stable interval, it is determined that no data update processing is required in the operating load intervals other than the update load intervals.

Images