View data storage and switching optimization system and method based on deep learning

Abstract

The invention discloses a view data storage and switching optimization system and method based on deep learning, and relates to the field of data storage and switching optimizing.According to the view data storage and switching optimization system and method based on deep learning, views of current reference views to be selected and replaced are screened, then the current reference views are replaced or fragmented again according to the use effect after replacement, and the replacement efficiency of the reference views is improved. The use effect of the current reference view is further ensured; by comparing the current use effect parameter with the use effect parameter before replacement, whether the current reference view can improve the switching efficiency and the view updating efficiency can be determined; the difference data between the current use effect parameter and the use effect parameter before replacement is compared with the first effect difference threshold value and the second effect difference threshold value, and different comparison results are processed in different modes, so that the diversity of processing schemes is improved; and the problems of improving the switching efficiency and the view updating efficiency of the current reference view can be solved more accurately.

Description

Technical Field

[0001] The present invention belongs to the field of data storage and switching optimization, and in particular, relates to a view data storage and switching optimization system and method based on deep learning. Background Art

[0002] 3D visualization scenes often involve the optimization of large amounts of data models. It is common for the number of rendered triangles to be in the millions or tens of millions. For such large amounts of data scenes, if you want to store and switch views through simple data storage, you need a lot of memory to support it. Moreover, when switching views, due to the large amount of data, there are many object states that need to be set synchronously, which will result in slow view switching, even program freezes, and browser crashes, giving users a very bad experience. Summary of the invention

[0003] In response to the problems in the related art, the present invention proposes a view data storage and switching optimization system and method based on deep learning to overcome the above-mentioned technical problems existing in the existing related technology.

[0004] To solve the above technical problems, the present invention is achieved through the following technical solutions: The present invention is a view data storage and switching optimization method based on deep learning, comprising the following steps: S1, collecting the usage frequency change equations of multiple scene views to be selected over time, the average object activity data and the space coverage data at multiple time points, and obtaining the current usage frequency change equation set, the current average object activity data set and the current average space coverage data set; S2, collecting probability data of each candidate scene view being used as a reference view, the time-varying equation of the usage frequency of each candidate scene view, the average object activity data at multiple time points, and the spatial coverage data, and constructing the final view-based probability mapping equation; S3, selecting the current reference view according to the final view-based probability mapping equation, the current frequency of use change equation set, the current average object activity data set, and the current average space coverage rate data set; S4, determining whether it is necessary to switch or slice the current reference view by collecting effect parameters after using the current reference view, and obtaining a determination result; S5. Slice the current reference view according to the determination result to obtain a final number of slices of the current view; This solution first screens the current views to be selected for replacing the baseline view based on historical data, and based on the historical data, ensures the rationality of the selected current baseline view; after the selection is completed, the current baseline view is replaced or split again according to the usage effect after the replacement, further ensuring the usage effect of the current baseline view.

[0005] Preferably, the S1 comprises the following steps: S11, setting the 3D scene to be optimized and the corresponding several views to obtain a set of scene views to be selected; and then setting several parameter types that affect the possibility of a view being used as a reference view to obtain a set of parameter types that affect the selection of the reference view. , a 1. a 2. a 3 represents the view usage frequency, object activity and space coverage respectively; S12, setting a first current statistical period; in conjunction with the first current statistical period and the reference view selection influencing parameter type set, obtaining a usage frequency variation equation of each view in the selected scene view set over time, average object activity data at multiple time points, and spatial coverage data, to obtain a current usage frequency variation equation set, a current average object activity data set, and a current average spatial coverage data set; In this solution, several views of the three-dimensional scene to be optimized are selected, and several base view selection influencing parameters are set, so as to select the most suitable view as the base view from the set of views to be selected, thereby reducing the amount of incremental view data when the view is replaced later, thereby improving the efficiency of view switching and the data processing capacity of the server; for the view usage frequency, since the number of views accessed at the most recent moment is more important, by collecting the equation for the change of the usage frequency of each view to be selected over time, it is convenient to build a more accurate view selection model later.

[0006] Preferably, S2 comprises the following steps: S21, setting a historical statistical period; in conjunction with the candidate scene view set and the reference view selection influencing parameter type set, collecting probability data of each candidate scene view being used as a reference view within the historical statistical period, the equation of how the usage frequency of each candidate scene view changes over time, average object activity data at multiple time points, and spatial coverage data, to obtain a historical candidate scene view as a reference probability data set , Historical frequency of use change equation set , Historical Average Object Activity Dataset and historical average spatial coverage datasets ; ; ; ; ; in, , , , Respectively represent the first i The historical candidate scene views of the candidate scene views are used as the basis probability data, the historical usage frequency change equation over time, the average object activity data at multiple historical time points, and the spatial coverage data. Indicates the total number of scene views to be selected; S22, using the historical candidate scene view as a base probability data set, the historical usage frequency change equation set, the historical average object activity data set, and the historical average space coverage rate data set to construct a final view-based probability mapping equation and a final usage frequency weight change equation set; By constructing the probability mapping equation of the final view as the basis, a calculation tool is provided for calculating the selection probability of each candidate scene view for the subsequent selection of the current baseline view from the candidate scene view set, and then the most suitable baseline view is selected; among them, by collecting the probability data of each candidate scene view being used as the baseline view in the historical statistical period, the equation of the change of the usage frequency of each candidate scene view over time, the average object activity data at multiple time points and the spatial coverage data, data support is provided for the subsequent construction of the probability mapping equation of the final view as the basis.

[0007] Preferably, the S22 comprises the following steps: S221, constructing an initial view-based probability mapping equation by combining the historical candidate scene view-based probability dataset, the historical usage frequency change equation set, the historical average object activity dataset, and the historical average space coverage dataset; as follows, ; in, The initial view is the dependent variable of the base probability mapping equation, indicating that the candidate scene view is used as the reference view Probability data of Represents the mapping relationship of the initial view as the basis probability mapping equation; , , , are all independent variables of the equation; they represent the equation of the change of the weight value corresponding to the historical usage frequency over time, the equation of the change of the historical usage frequency over time, the historical average object activity data, and the historical average space coverage data respectively; S222: randomly generate a corresponding usage frequency weight change equation for each historical usage frequency change equation in the historical usage frequency change equation set, and obtain a usage frequency weight change equation set. , Indicates the first i The usage frequency weight change equation of the candidate scene views; Substitute the data of the historical usage frequency change equation set, the historical average object activity data set, the usage frequency weight change equation set and the historical average space coverage rate data set into the initial view-based probability mapping equation for mapping, and obtain the historical candidate scene view-based probability initial mapping data set , b i It represents the combination of the historical usage frequency change equation set, the historical average object activity data set, the usage frequency weight change equation set, and the historical average space coverage rate data set. i Substitute the data into the initial view as the basis probability mapping equation to obtain the data; S223, setting a mapping error threshold; calculating the error data between the historical candidate scene view as a base probability initial mapping data set and the historical candidate scene view as a base probability data set to obtain the initial mapping error data ; The calculation formula is as follows, ; When the initial mapping error data is less than the mapping error threshold, the initial view-based probability mapping equation is used as the final view-based probability mapping equation; otherwise, the initial view-based probability mapping equation and each usage frequency weight change equation in the usage frequency weight change equation set are adjusted until the initial mapping error data is less than the mapping error threshold; By setting the independent variables of the initial view as the base probability mapping equation to the historical usage frequency change equation, the historical average object activity data, the historical average spatial coverage data and the usage frequency weight change equation, and setting the dependent variable to the candidate scene view as the base probability data, the mapping from the historical usage frequency change equation, the historical average object activity data, the historical average spatial coverage data and the usage frequency weight change equation to the candidate scene view as the base probability data is realized; by substituting the collected relevant history into the constructed initial view as the base probability mapping equation, through preliminary mapping, the mapping accuracy of the initial view as the base probability mapping equation is detected; and then it is determined whether the initial view as the base probability mapping equation needs to be adjusted.

[0008] Preferably, S3 comprises the following steps: S31, setting the current original reference view; substituting each data in the current usage frequency change equation set, the current average object activity data set, the current average space coverage rate data set, and the final usage frequency weight change equation set into the final view-based probability mapping equation for mapping, to obtain the current selected scene view-based probability data set; S32, when the scene view to be selected corresponding to the largest base probability data in the current scene view to be selected base probability data set is the same as the current original reference view, the current reference view is not replaced; otherwise, the scene view to be selected corresponding to the largest base probability data in the current scene view to be selected base probability data set is used as the current reference view, and both are recorded as the current reference view; Since the setting of view usage weights is generally the same under other identical circumstances (such as the time difference between the call time and the time set as the baseline view), when performing probability data analysis on the current baseline view from the candidate scene view set, the final usage frequency weight change equation set continues to be used as the weight value corresponding to each current usage frequency change equation; by selecting the candidate scene view corresponding to the largest base probability data as the current baseline view, the historical selection habit is followed, and the baseline view with the most common historical selection habit means that the size of the corresponding view increment data when it is replaced is more reasonable, thereby ensuring that after the current baseline view is set, the view increment it brings is more reasonable, and to a certain extent, the efficiency of view switching is guaranteed.

[0009] Preferably, S4 comprises the following steps: S41, setting a second current statistical period; setting a number of time points in the second current statistical period to obtain a current time point set; setting a number of types of effect parameters that can reflect the effect after using the reference view to obtain a reference view effect parameter type set; S42: Collect effect parameters after using the current reference view in conjunction with the reference view effect parameter type set and the current time point set to obtain a currently used effect parameter matrix. ;as follows, ; in, Indicated in i The first j types of effect parameters after using the current reference view, , respectively represent the set effect parameter type and the total number of the current time point; then collect the average effect parameters of several time points before the current reference view is used to obtain the historical average effect parameter set , Indicates the first time point before the current reference view is used for acquisition j Calculate the difference between the historical average effect parameter set and each row of data in the currently used effect parameter matrix to obtain the current effect difference data set , Represents the historical average effect parameter set and the current use effect parameter matrix i The effect difference data between rows of data; the calculation formula is as follows, ; S43, setting a first effect difference threshold and a second effect difference threshold; when the current effect difference data set contains current effect difference data less than the second effect difference threshold, switching the current reference view back to the current original reference view; when the current effect difference data set contains current effect difference data greater than or equal to the second effect difference threshold and less than the first effect difference threshold, entering S5; otherwise, entering S44; S44, predicting the usage effect parameters at future time points according to the current usage effect parameter matrix and using the BP neural network model to obtain a future usage effect parameter matrix; then calculating the difference data between the historical average effect parameter set and each row of data in the future usage effect parameter matrix to obtain a future effect difference data set; when the future effect difference data set has future effect difference data less than the second effect difference threshold, proceed to S5; otherwise, no processing is performed; After the filtered view is used as the current baseline view, it is necessary to detect and determine the usage effect brought by the current baseline view, so as to determine whether the change to the current baseline view can improve the efficiency of switching and view updating; thereby providing a processing basis for the next step of processing; by setting the baseline view effect parameter type set, a collection basis is provided for the subsequent collection of data for determining the usage effect of the current baseline view; and by comparing the current usage effect parameters with the usage effect parameters before the change, it can be determined whether the current baseline view can improve the efficiency of switching and view updating; wherein, by setting a first effect difference threshold and a second effect difference threshold, the difference data between the current usage effect parameters and the usage effect parameters before the change are compared with the first effect difference threshold and the second effect difference threshold, and different comparison results are processed in different ways, thereby improving the diversity of processing solutions, and performing targeted processing for different situations, which is conducive to more accurately solving the problem of improving the efficiency of switching and view updating of the current baseline view; through prediction, efficiency problems that may arise in the future can be discovered and solved in a timely manner; Among them, if the current effect difference data is too small, the solution is to directly switch back to the current original reference view. Direct switching is more efficient, thereby ensuring the normal progress of the 3D view change operation.

[0010] Preferably, the S5 comprises the following steps: S51, setting an initial current view slice number; using the initial current view slice number to slice and store the current reference view data; after the current reference view data is sliced ​​and stored, collecting the current effect parameters according to the reference view effect parameter type set to obtain a current sliced ​​effect parameter set; calculating the difference data between the current sliced ​​effect parameter set and the historical average effect parameter set to obtain the current sliced ​​difference data; S52: when the difference data after the current slice is greater than or equal to the first effect difference threshold, use the initial current view slice number as the final current view slice number; otherwise, adjust the initial current view slice number until the difference data after the current slice is greater than or equal to the first effect difference threshold; By adopting multi-base shard storage when the increment of a single base view is too large, the data can be dispersed to multiple nodes or tables, reducing the amount of data in a single node or table, thereby improving the query speed; if a shard fails, it will only affect the data of the shard, and will not affect the data of other shards, thereby improving the fault tolerance of the system; different shards can be allocated different hardware resources according to actual needs, such as memory, CPU, etc., to improve the utilization of hardware resources; because the data is distributed on multiple shards, the data volume of a single shard is relatively small, and the difficulty of maintenance and management is relatively low, thereby reducing the maintenance cost of the system.

[0011] Preferably, adjusting the initial number of current view slices in S52 comprises the following steps: S521: Set the value range of the initial current view fragment number to obtain the value range of the current fragment number. , , Respectively represent the lower limit and upper limit of the initial current view slice number; construct the view slice number to adjust the spotted hyena population; set the maximum number of iterations of the view slice number to adjust the spotted hyena population And the current number of iterations is , respectively recorded as the maximum number of iterations for shard adjustment and the current number of iterations for shard adjustment; the number of view shards adjusts the search space dimension of the spotted hyena population to one dimension; S522: Setting the number of view slices according to the current slice number value interval adjusts the initial position of each spotted hyena in the spotted hyena population to obtain a second initial position set , e i Indicates that the number of view fragments is adjusted in the spotted hyena population. i The initial position of the spotted hyena, Indicates that the number of view shards adjusts the size of the spotted hyena population; e i The calculation formula is as follows, ; In the formula, Indicates for e i Generate a random number between 0 and 1; S523: Constructing a fitness function for adjusting the number of view fragments for the spotted hyena population ;as follows, ; In the formula, Indicates that the number of current view slices obtained in each round of iteration is used to slice the current reference view and calculate the difference data between the effect parameter corresponding to the current reference view after slicing and the historical average effect parameter set; S524, start iteration, before iteration, set the slice adjustment current iteration number to 1; in the first round of iteration, use the view slice number to adjust the fitness function of the spotted hyena population Calculate the fitness value of each spotted hyena's initial position in the second initial position set to obtain a third fitness value set; use the maximum fitness value in the third fitness value set and the corresponding initial position of the spotted hyena as the third global optimal fitness and the third global optimal position respectively; update the initial position of each spotted hyena in the second initial position set according to the third global optimal fitness and the third global optimal position; after the update is completed, adjust the current iteration number of the slice by 1 and enter the next round of iteration; In each other iteration, the number of view fragments is used to adjust the fitness function of the spotted hyena population. Calculate the fitness value of the position of each spotted hyena in the spotted hyena population adjusted by the number of view slices updated in the previous iteration process to obtain a fourth fitness value set; use the maximum fitness value in the fourth fitness value set and the corresponding position of the spotted hyena as the fourth global optimal fitness and the fourth global optimal position respectively; update the position of each spotted hyena in the spotted hyena population adjusted by the number of view slices updated in the previous iteration process according to the fourth global optimal fitness and the fourth global optimal position; after the update is completed, add 1 to the current iteration number of the slice adjustment and enter the next iteration; S525, when When , stop the iteration and get the second final global best fitness and the second final global best position; otherwise, continue to iterate until ; taking the second final global best fitness as the difference data of the current slice after optimization; when the difference data of the current slice after optimization is greater than or equal to the first effect difference threshold, slicing the current reference view data using the second final global best position and storing it to obtain the final number of current view slices; otherwise, returning to S524 to continue iterating until the difference data of the current slice after optimization is greater than or equal to the first effect difference threshold; The initial current view slice number is optimized by multiple iterations using the spotted hyena optimization algorithm, and the difference data between the effect parameters after adopting the current baseline view and the initial current view slice number is used as the fitness function; therefore, as the iteration proceeds, the difference data between the effect parameters after adopting the current baseline view and the initial current view slice number becomes larger and larger, that is, the effect after adopting the current baseline view becomes better and better.

[0012] A view data storage and switching optimization system based on deep learning includes a base possibility influence parameter setting module, a current baseline view selection influence parameter collection module, a historical baseline view selection influence parameter collection module, a view base probability mapping equation construction module, a current baseline view setting module, an effect parameter determination module and a current baseline view slicing module.

[0013] The present invention has the following beneficial effects: 1. In the present invention, the view to be selected for replacing the baseline view is screened according to historical data, thereby ensuring the rationality of the selected current baseline view based on historical data; after the selection is completed, the current baseline view is replaced or sliced ​​again according to the use effect after the replacement, thereby further ensuring the use effect of the current baseline view.

[0014] 2. In the present invention, by comparing the current usage effect parameters with the usage effect parameters before replacement, it is possible to determine whether the current baseline view can improve the efficiency of switching and view updating; wherein, by setting a first effect difference threshold and a second effect difference threshold, the difference data between the current usage effect parameters and the usage effect parameters before replacement are compared with the first effect difference threshold and the second effect difference threshold, and different comparison results are processed in different ways, thereby improving the diversity of processing schemes, and performing targeted processing for different situations, which is conducive to more accurately solving the problem of improving the efficiency of switching and view updating of the current baseline view; through prediction, efficiency problems that may arise in the future can be discovered and solved in a timely manner.

[0015] 3. In the present invention, the spotted hyena optimization algorithm is used to iteratively adjust multiple constant coefficients of the initial view-based probability mapping equation and each frequency weight change equation in the frequency weight change equation set, and the mapping accuracy of the initial view-based probability mapping equation is used as the fitness function; therefore, as the iteration proceeds, the mapping accuracy of the initial view-based probability mapping equation becomes higher and higher, and finally the mapping requirements are met.

[0016] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic diagram of a flow chart of a view data storage and switching optimization method based on deep learning of the present invention; Figure 2 A schematic diagram of a process for constructing a final view-based probability mapping equation for the present invention; Figure 3 A schematic diagram of a process of switching or slicing the current reference view according to the present invention; Figure 4 This is a module schematic diagram of a view data storage and switching optimization system based on deep learning in the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0020] Embodiment 1 See also Figure 1-3 , this embodiment is a view data storage and switching optimization method based on deep learning, comprising the following steps: S1, collecting the usage frequency change equations of multiple scene views to be selected over time, the average object activity data and the space coverage data at multiple time points, and obtaining the current usage frequency change equation set, the current average object activity data set and the current average space coverage data set; The S1 comprises the following steps: S11, setting the 3D scene to be optimized and the corresponding several views to obtain a set of scene views to be selected; and then setting several parameter types that affect the possibility of a view being used as a reference view to obtain a set of parameter types that affect the selection of the reference view. , a 1. a 2. a 3 represents the view usage frequency, object activity and space coverage respectively; S12, setting the first current statistical period; in conjunction with the first current statistical period and the reference view selection influencing parameter type set, obtaining the usage frequency variation equation of each view in the selected scene view set over time, the average object activity data and the spatial coverage data at multiple time points, and obtaining the current usage frequency variation equation set, the current average object activity data set and the current average spatial coverage data set; for the object activity data, it is necessary to determine which objects are frequently modified in the view, such as objects with many attribute changes such as visibility and position; the more active objects there are, the more effective the view may be as a reference view, because there will be less incremental data; for the spatial coverage, it is necessary to consider the spatial range covered by the camera perspective of the view and the three-dimensional bounding box coverage of the object in the view; a view with a high coverage rate may be more suitable as a reference, because the amount of incremental storage data can be reduced; S2, collecting probability data of each candidate scene view being used as a reference view, the time-varying equation of the usage frequency of each candidate scene view, the average object activity data at multiple time points, and the spatial coverage data, and constructing the final view-based probability mapping equation; The S2 comprises the following steps: S21, setting a historical statistical period; in conjunction with the candidate scene view set and the reference view selection influencing parameter type set, collecting probability data of each candidate scene view being used as a reference view within the historical statistical period, the equation of how the usage frequency of each candidate scene view changes over time, average object activity data at multiple time points, and spatial coverage data, to obtain a historical candidate scene view as a reference probability data set , Historical frequency of use change equation set , Historical Average Object Activity Dataset and historical average spatial coverage datasets ; ; ; ; ; in, , , , Respectively represent the first i The historical candidate scene views of the candidate scene views are used as the basis probability data, the historical usage frequency change equation over time, the average object activity data at multiple historical time points, and the spatial coverage data. Indicates the total number of scene views to be selected; S22, using the historical candidate scene view as a base probability data set, the historical usage frequency change equation set, the historical average object activity data set, and the historical average space coverage rate data set to construct a final view-based probability mapping equation and a final usage frequency weight change equation set; The S22 comprises the following steps: S221, constructing an initial view-based probability mapping equation by combining the historical candidate scene view-based probability dataset, the historical usage frequency change equation set, the historical average object activity dataset, and the historical average space coverage dataset; as follows, ; in, The initial view is the dependent variable of the base probability mapping equation, indicating that the candidate scene view is used as the reference view Probability data of Indicates the mapping relationship of the initial view as the basis probability mapping equation; for example, the independent variables of the initial view as the basis probability mapping equation are proportional to each other, inversely proportional to each other, and proportional to or inversely proportional to the product of the independent variables; , , , are all independent variables of the equation; they represent the equation of the change of the weight value corresponding to the historical usage frequency over time, the equation of the change of the historical usage frequency over time, the historical average object activity data, and the historical average space coverage data respectively; S222, randomly generate a corresponding usage frequency weight change equation for each historical usage frequency change equation in the historical usage frequency change equation set, and obtain a usage frequency weight change equation set , Indicates the first i The usage frequency weight change equation of the candidate scene views; Substitute the data of the historical usage frequency change equation set, the historical average object activity data set, the usage frequency weight change equation set and the historical average space coverage rate data set into the initial view-based probability mapping equation for mapping, and obtain the historical candidate scene view-based probability initial mapping data set , b iIt represents the combination of the historical usage frequency change equation set, the historical average object activity data set, the usage frequency weight change equation set, and the historical average space coverage rate data set. i Substitute the data into the initial view as the basis probability mapping equation to obtain the data; S223, setting a mapping error threshold; calculating the error data between the historical candidate scene view as a base probability initial mapping data set and the historical candidate scene view as a base probability data set to obtain the initial mapping error data ; The calculation formula is as follows, ; When the initial mapping error data is less than the mapping error threshold, the initial view-based probability mapping equation is used as the final view-based probability mapping equation; otherwise, the initial view-based probability mapping equation and each usage frequency weight change equation in the usage frequency weight change equation set are adjusted until the initial mapping error data is less than the mapping error threshold; In S223, adjusting the initial view-based probability mapping equation and each usage frequency weight change equation in the usage frequency weight change equation set includes the following steps: S2231, setting the initial view as the base probability mapping equation and using a plurality of constant coefficient value intervals of each use frequency weight change equation in the use frequency weight change equation set, obtaining a first constant coefficient value interval set And the second constant coefficient value interval matrix ; They are as follows, ; ; in, , They represent the first i The lower and upper limits of the constant coefficients; , Respectively represent the first j The frequency weight change equation i The lower and upper limits of the constant coefficients, , They represent the total number of constant coefficients of the initial view-based probability mapping equation and each frequency weight change equation; Construct a base probability frequency weight mapping constant coefficient to adjust the spotted hyena population; set the maximum number of iterations of the base probability frequency weight mapping constant coefficient to adjust the spotted hyena population c 1 and the current number of iterations is c2, respectively recorded as the maximum number of iterations of coefficient adjustment and the current number of iterations of coefficient adjustment; the base probability frequency weight mapping constant coefficient adjusts the search space dimension of the spotted hyena population and same; S2232: According to the first constant coefficient value interval set and the second constant coefficient value interval matrix, the base probability frequency weight mapping constant coefficient is set to adjust the initial position of each spotted hyena in the spotted hyena population, and obtain the first initial position matrix set , The base probability weight mapping constant coefficient adjusts the spotted hyena population. k The initial position matrix of the spotted hyena, The constant coefficient of the base probability weight map adjusts the size of the spotted hyena population; as follows, ; in, , They represent the base probability weight mapping constant coefficients to adjust the spotted hyena population k The initial position of the spotted hyena is the first probability mapping equation based on the initial view. i constant coefficient dimension and the frequency weight change equation set j The frequency weight change equation i The position components in the constant coefficient dimension; the calculation formulas are as follows, ; ; In the formula, rand k1i , rand k2ji Respectively for , Generate a random number between 0 and 1; S2233, setting the base probability weight mapping constant coefficient to adjust the fitness function of the spotted hyena population ;as follows, ; in, d Set a set of constant coefficients of the probability mapping equation based on the initial view obtained in each round of iteration and a set of constant coefficients of each frequency weight change equation in the frequency weight change equation set to be substituted into the probability mapping equation based on the initial view and the corresponding frequency weight change equation, and then combine the historical frequency change equation set, the historical average object activity data set, and the historical average space coverage rate data set to input the error between the mapped data and the actual data into the probability mapping equation based on the initial view; S2234, start iteration, before iteration, set the coefficient adjustment current iteration number to 1; in the first round of iteration, use the base probability frequency weight mapping constant coefficient to adjust the fitness function of the spotted hyena population Calculate the fitness value of the initial position matrix of each spotted hyena in the first initial position matrix set to obtain a first fitness value set; use the maximum fitness in the first fitness value set and the initial position matrix of the corresponding spotted hyena as the first global optimal fitness and the first global optimal position respectively; update the initial position matrix of each spotted hyena in the first initial position matrix set according to the first global optimal fitness and the first global optimal position; after the update is completed, adjust the coefficient by adding 1 to the current iteration number and enter the next round of iteration; In each other round of iteration, the base probability weight mapping constant coefficient is used to adjust the fitness function of the spotted hyena population. Calculate the fitness value of the position matrix of each spotted hyena in the spotted hyena population by adjusting the base probability frequency weight mapping constant coefficient updated in the previous round of iteration to obtain a second fitness value set; use the maximum fitness in the second fitness value set and the corresponding spotted hyena position matrix as the second global optimal fitness and the second global optimal position respectively; adjust the position matrix of each spotted hyena in the spotted hyena population by adjusting the base probability frequency weight mapping constant coefficient updated in the previous round of iteration according to the second global optimal fitness and the second global optimal position; after the update is completed, adjust the current iteration number by adding 1 to the coefficient and enter the next iteration; S2235, when When , stop the iteration and obtain the first final global optimal position and the first final global optimal fitness; otherwise, return to S2234 and continue to iterate until until the time; using the first final global best fitness as the optimized mapping error data; when the optimized mapping error data is less than the mapping error threshold, substituting each position component of the first final global best position into the initial view-based probability mapping equation and each use frequency weight change equation in the use frequency weight change equation set to obtain the final view-based probability mapping equation and the final use frequency weight change equation set; The spotted hyena optimization algorithm can quickly converge to the local optimal solution in the local search stage, which improves the search efficiency of the algorithm; it can be extended to higher dimensions and show good performance when dealing with high-dimensional optimization problems; it can converge to the optimal solution in a shorter time, which improves the efficiency of the algorithm; it has fewer parameters, is easy to implement and adjust, and reduces the complexity of the algorithm; it has strong robustness to the selection of the initial population and the change of parameters, and can find the optimal solution under different initial conditions; based on the above advantages, the spotted hyena optimization algorithm is used in this scheme to iteratively adjust the initial view as the basis probability mapping equation and the multiple constant coefficients of each frequency weight change equation in the frequency weight change equation set, and the mapping accuracy of the initial view as the basis probability mapping equation is used as the fitness function; therefore, with the progress of iterations, the mapping accuracy of the initial view as the basis probability mapping equation becomes higher and higher, and finally meets the mapping requirements; S3, selecting the current reference view according to the final view-based probability mapping equation, the current frequency of use change equation set, the current average object activity data set, and the current average space coverage rate data set; The S3 comprises the following steps: S31, setting the current original reference view; substituting each data in the current usage frequency change equation set, the current average object activity data set, the current average space coverage rate data set, and the final usage frequency weight change equation set into the final view-based probability mapping equation for mapping, to obtain the current selected scene view-based probability data set; S32, when the scene view to be selected corresponding to the largest base probability data in the current scene view to be selected base probability data set is the same as the current original reference view, the current reference view is not replaced; otherwise, the scene view to be selected corresponding to the largest base probability data in the current scene view to be selected base probability data set is used as the current reference view, and both are recorded as the current reference view; S4, determining whether it is necessary to switch or slice the current reference view by collecting effect parameters after using the current reference view, and obtaining a determination result; The S4 comprises the following steps: S41, setting a second current statistical period; setting a number of time points in the second current statistical period to obtain a current time point set; setting a number of types of effect parameters that can reflect the effect after using the reference view to obtain a reference view effect parameter type set; the reference view effect parameter type set includes memory usage, switching delay, and incremental data volume, etc.; S42: Collect effect parameters after using the current reference view in conjunction with the reference view effect parameter type set and the current time point set to obtain a currently used effect parameter matrix. ;as follows, ; in, Indicated in i The first j types of effect parameters after using the current reference view, , respectively represent the set effect parameter type and the total number of the current time point; then collect the average effect parameters of several time points before the current reference view is used to obtain the historical average effect parameter set , Indicates the first time point before the current reference view is used for acquisition j Calculate the difference between the historical average effect parameter set and each row of data in the currently used effect parameter matrix to obtain the current effect difference data set , Represents the historical average effect parameter set and the current use effect parameter matrix i The effect difference data between rows of data; the calculation formula is as follows, ; S43, setting a first effect difference threshold and a second effect difference threshold; when the current effect difference data set contains current effect difference data less than the second effect difference threshold, switching the current reference view back to the current original reference view; when the current effect difference data set contains current effect difference data greater than or equal to the second effect difference threshold and less than the first effect difference threshold, entering S5; otherwise, entering S44; S44, predicting the usage effect parameters at future time points according to the current usage effect parameter matrix and using the BP neural network model to obtain a future usage effect parameter matrix; then calculating the difference data between the historical average effect parameter set and each row of data in the future usage effect parameter matrix to obtain a future effect difference data set; when the future effect difference data set has future effect difference data less than the second effect difference threshold, proceed to S5; otherwise, no processing is performed; S5. Slice the current reference view according to the determination result to obtain a final number of slices of the current view; The S5 comprises the following steps: S51, setting an initial current view slice number; using the initial current view slice number to slice and store the current reference view data; after the current reference view data is sliced ​​and stored, collecting the current effect parameters according to the reference view effect parameter type set to obtain a current sliced ​​effect parameter set; calculating the difference data between the current sliced ​​effect parameter set and the historical average effect parameter set to obtain the current sliced ​​difference data; S52: when the difference data after the current slice is greater than or equal to the first effect difference threshold, use the initial current view slice number as the final current view slice number; otherwise, adjust the initial current view slice number until the difference data after the current slice is greater than or equal to the first effect difference threshold; The step of adjusting the initial number of slices of the current view in S52 includes the following steps: S521: Set the value range of the initial current view fragment number to obtain the value range of the current fragment number. , , Respectively represent the lower limit and upper limit of the initial current view slice number; construct the view slice number to adjust the spotted hyena population; set the maximum number of iterations of the view slice number to adjust the spotted hyena population And the current number of iterations is , respectively recorded as the maximum number of iterations for shard adjustment and the current number of iterations for shard adjustment; the number of view shards adjusts the search space dimension of the spotted hyena population to one dimension; S522: Setting the number of view slices according to the current slice number value interval adjusts the initial position of each spotted hyena in the spotted hyena population to obtain a second initial position set , e i Indicates that the number of view fragments is adjusted in the spotted hyena population. i The initial position of the spotted hyena, Indicates that the number of view shards adjusts the size of the spotted hyena population; e i The calculation formula is as follows, ; In the formula, Indicates for e i Generate a random number between 0 and 1; S523: Constructing a fitness function for adjusting the number of view fragments for the spotted hyena population ;as follows, ; In the formula, Indicates that the number of current view slices obtained in each round of iteration is used to slice the current reference view and calculate the difference data between the effect parameter corresponding to the current reference view after slicing and the historical average effect parameter set; S524, start iteration, before iteration, set the slice adjustment current iteration number to 1; in the first round of iteration, use the view slice number to adjust the fitness function of the spotted hyena population Calculate the fitness value of each spotted hyena's initial position in the second initial position set to obtain a third fitness value set; use the maximum fitness value in the third fitness value set and the corresponding initial position of the spotted hyena as the third global optimal fitness and the third global optimal position respectively; update the initial position of each spotted hyena in the second initial position set according to the third global optimal fitness and the third global optimal position; after the update is completed, adjust the current iteration number of the slice by 1 and enter the next round of iteration; In each other iteration, the number of view fragments is used to adjust the fitness function of the spotted hyena population. Calculate the fitness value of the position of each spotted hyena in the spotted hyena population adjusted by the number of view slices updated in the previous iteration process to obtain a fourth fitness value set; use the maximum fitness value in the fourth fitness value set and the corresponding position of the spotted hyena as the fourth global optimal fitness and the fourth global optimal position respectively; update the position of each spotted hyena in the spotted hyena population adjusted by the number of view slices updated in the previous iteration process according to the fourth global optimal fitness and the fourth global optimal position; after the update is completed, add 1 to the current iteration number of the slice adjustment and enter the next iteration; S525, when When , stop the iteration and get the second final global best fitness and the second final global best position; otherwise, continue to iterate until until the time; use the second final global best fitness as the difference data of the optimized current slice; when the difference data of the optimized current slice is greater than or equal to the first effect difference threshold, use the second final global best position to slice and store the current reference view data to obtain the final current view slice number; otherwise, return to S524 and continue to iterate until the difference data of the optimized current slice is greater than or equal to the first effect difference threshold.

[0021] Embodiment 2 See also Figure 4This embodiment discloses a view data storage and switching optimization system based on deep learning, which can implement the method of the above embodiment, including a base possibility influence parameter setting module, a current reference view selection influence parameter acquisition module, a historical reference view selection influence parameter acquisition module, a view base probability mapping equation construction module, a current reference view setting module, an effect parameter determination module and a current reference view slicing module; The base possibility influencing parameter setting module sets several parameter types that influence the possibility of a view being used as a base view, and obtains a base view selection influencing parameter type set; The current reference view selection influencing parameter acquisition module acquires the usage frequency variation equations of multiple scene views to be selected over time, the average object activity data and the space coverage rate data at multiple time points according to the reference view selection influencing parameter type set, and obtains the current usage frequency variation equation set, the current average object activity data set and the current average space coverage rate data set; The historical reference view selection influencing parameter collection module collects probability data of each candidate scene view being used as a reference view, a usage frequency variation equation of each candidate scene view over time, average object activity data and space coverage data at multiple time points according to the reference view selection influencing parameter type set, and obtains a historical candidate scene view as a reference probability data set, a historical usage frequency variation equation set, a historical average object activity data set and a historical average space coverage data set; The view-based probability mapping equation construction module uses the historical candidate scene view-based probability data set, the historical usage frequency change equation set, the historical average object activity data set and the historical average space coverage rate data set to construct the final view-based probability mapping equation; The current reference view setting module selects the current reference view according to the final view-based probability mapping equation, the current frequency of use change equation set, the current average object activity data set, and the current average space coverage rate data set; The effect parameter determination module determines whether the current reference view needs to be switched or sliced ​​by collecting effect parameters after using the current reference view, and obtains a determination result; The current reference view slicing module slices the current reference view according to the determination result to obtain a final number of current view slices.

[0022] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0023] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A view data storage and switching optimization method based on deep learning, characterized in that: The following steps are involved: S1, collecting the usage frequency change equations of multiple scene views to be selected over time, the average object activity data and the space coverage data at multiple time points, and obtaining the current usage frequency change equation set, the current average object activity data set and the current average space coverage data set; S2, collecting probability data of each candidate scene view being used as a reference view, the time-varying equation of the usage frequency of each candidate scene view, the average object activity data at multiple time points, and the spatial coverage data, and constructing the final view-based probability mapping equation; S3, selecting the current reference view according to the final view-based probability mapping equation, the current frequency of use change equation set, the current average object activity data set, and the current average space coverage rate data set; S4, determining whether it is necessary to switch or slice the current reference view by collecting effect parameters after using the current reference view, and obtaining a determination result; S5. Slice the current reference view according to the determination result to obtain a final number of slices of the current view.

2. The method for storing and optimizing view data based on deep learning according to claim 1, characterized in that: The S1 comprises the following steps: S11, setting a 3D scene to be optimized and a number of corresponding views to obtain a set of scene views to be selected; and then setting a number of parameter types that affect the possibility of a view being used as a reference view to obtain a set of parameter types that affect the selection of a reference view; S12. Set a first current statistical period; select an influencing parameter type set in conjunction with the first current statistical period and the baseline view, obtain an equation for how the usage frequency of each view in the selected scene view set changes over time, average object activity data at multiple time points, and spatial coverage data, and obtain a current usage frequency change equation set, a current average object activity data set, and a current average spatial coverage data set.

3. The method for storing and optimizing view data based on deep learning according to claim 2, characterized in that: The S2 comprises the following steps: S21, setting a historical statistical period; in conjunction with the candidate scene view set and the reference view selection influencing parameter type set, collecting probability data of each candidate scene view being used as a reference view, a usage frequency variation equation of each candidate scene view over time, average object activity data and space coverage data at multiple time points in the historical statistical period, and obtaining a historical candidate scene view as a base probability data set, a historical usage frequency variation equation set, a historical average object activity data set and a historical average space coverage data set; S22, using the historical candidate scene views as a base probability data set, the historical usage frequency change equation set, the historical average object activity data set and the historical average space coverage rate data set to construct a final view-based probability mapping equation and a final usage frequency weight change equation set.

4. The method for storing and optimizing view data based on deep learning according to claim 3, characterized in that: In S22, the final view-based probability mapping equation and the final set of frequency weight change equations are constructed using the spotted hyena optimization algorithm.

5. The method for storing and switching view data based on deep learning according to claim 4, characterized in that: The S3 comprises the following steps: S31, setting the current original reference view; substituting each data in the current usage frequency change equation set, the current average object activity data set, the current average space coverage rate data set, and the final usage frequency weight change equation set into the final view-based probability mapping equation for mapping, to obtain the current selected scene view-based probability data set; S32. When the scene view to be selected corresponding to the largest base probability data in the current scene view to be selected base probability data set is the same as the current original reference view, the current reference view is not replaced; otherwise, the scene view to be selected corresponding to the largest base probability data in the current scene view to be selected base probability data set is used as the current reference view, and both are recorded as the current reference view.

6. The method for storing and optimizing view data based on deep learning according to claim 5, characterized in that: The S4 comprises the following steps: S41, setting a second current statistical period; setting a number of time points in the second current statistical period to obtain a current time point set; setting a number of types of effect parameters that can reflect the effect after using the reference view to obtain a reference view effect parameter type set; S42, collecting effect parameters after using the current reference view in combination with the reference view effect parameter type set and the current time point set to obtain a currently used effect parameter matrix; then collecting average effect parameters at several time points before using the current reference view to obtain a historical average effect parameter set; calculating difference data between the historical average effect parameter set and each row of data in the currently used effect parameter matrix to obtain a current effect difference data set; S43, setting a first effect difference threshold and a second effect difference threshold; when the current effect difference data set contains current effect difference data less than the second effect difference threshold, switching the current reference view back to the current original reference view; when the current effect difference data set contains current effect difference data greater than or equal to the second effect difference threshold and less than the first effect difference threshold, entering S5; otherwise, entering S44; S44. Predict the usage effect parameters at future time points according to the current usage effect parameter matrix and adopt the BP neural network model to obtain the future usage effect parameter matrix; then calculate the difference data between the historical average effect parameter set and each row of data in the future usage effect parameter matrix to obtain a future effect difference data set; when the future effect difference data set has future effect difference data that is less than the second effect difference threshold, enter S5; otherwise, do not process.

7. The method for storing and optimizing view data based on deep learning according to claim 6, characterized in that: The S5 comprises the following steps: S51, setting an initial current view slice number; using the initial current view slice number to slice and store the current reference view data; after the current reference view data is sliced ​​and stored, collecting the current effect parameters according to the reference view effect parameter type set to obtain a current sliced ​​effect parameter set; calculating the difference data between the current sliced ​​effect parameter set and the historical average effect parameter set to obtain the current sliced ​​difference data; S52. When the difference data after the current slice is greater than or equal to the first effect difference threshold, the initial current view slice number is used as the final current view slice number; otherwise, the initial current view slice number is adjusted until the difference data after the current slice is greater than or equal to the first effect difference threshold.

8. The method for storing and switching view data based on deep learning according to claim 7, characterized in that: The step of adjusting the initial number of slices of the current view in S52 includes the following steps: S521, setting the value interval of the initial current view slice number to obtain the value interval of the current slice number; constructing the view slice number to adjust the spotted hyena population; setting the maximum number of iterations of the view slice number to adjust the spotted hyena population is And the current number of iterations is , respectively recorded as the maximum number of iterations for shard adjustment and the current number of iterations for shard adjustment; S522, adjusting the initial position of each spotted hyena in the spotted hyena population by setting the number of view slices according to the current slice number value interval, to obtain a second initial position set; S523, constructing a fitness function for adjusting the spotted hyena population by the number of view fragments; S524, start iteration, and before iteration, set the current iteration number of the slice adjustment to 1; in each round of iteration, use the view slice number to adjust the fitness function of the spotted hyena population to calculate the fitness value of the position of each spotted hyena in the view slice number adjustment spotted hyena population updated in the previous round of iteration, and update the position of each spotted hyena in the view slice number adjustment spotted hyena population updated in the previous round of iteration; S525, when When , stop the iteration and get the second final global best fitness and the second final global best position; otherwise, continue to iterate until until the time; use the second final global best fitness as the difference data of the optimized current slice; when the difference data of the optimized current slice is greater than or equal to the first effect difference threshold, use the second final global best position to slice and store the current reference view data to obtain the final current view slice number; otherwise, return to S524 and continue to iterate until the difference data of the optimized current slice is greater than or equal to the first effect difference threshold.

9. A system for implementing a view data storage and switching optimization method based on deep learning as described in any one of claims 1 to 8.

Images