Monitoring video management system based on video cloud storage

Abstract

The invention discloses a monitoring video management system based on video cloud storage, and relates to the technical field of distributed storage, a cloud storage service request terminal obtains monitoring video data uploaded by a user subjected to identity authentication and transmits the monitoring video data to a cloud storage master control platform, and a service master control unit carries out cloud storage on the basis of a load balancing algorithm. Dynamically evaluating each storage server, selecting an optimal storage server cluster as a basic storage unit, and allocating a corresponding storage weight; a storage log analysis module is arranged to perform big data analysis on historical storage logs, quantify data capacity change characteristics in the transcoding process of different video formats, and generate transcoding capacity linear characteristics or fitting linear characteristics of each storage server for specific video formats; and the service general control unit calculates the iteration change capacity and the iteration balance capacity of each basic storage unit, dynamically adjusts the actual storage resource allocation, and expands the supplementary storage unit when necessary, thereby optimizing the global storage resource scheduling.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed storage, and particularly to a monitoring video management system based on video cloud storage. Background Art

[0002] With the rapid development of security monitoring technology, the scale of monitoring video data has shown an explosive growth. The traditional local storage method can no longer meet the storage requirements of massive video data. Therefore, cloud storage technology has gradually become the mainstream solution for monitoring video management. Among them, the distributed storage architecture is widely used in video cloud storage systems due to its high scalability, high reliability, and flexibility; In a distributed storage environment, monitoring video data is usually scattered and stored in multiple data centers. However, since different data centers may carry different business systems, their requirements for video formats are also different. For example, some data centers may require storing videos in the H.264 encoding format, while others may use formats such as H.265 or AV1. Therefore, when monitoring videos are uploaded to the cloud storage system, video transcoding usually needs to be performed according to the format requirements of the target data center; Currently, a common video distribution method is based on load balancing technology, that is, according to the current storage load conditions of each data center, the uploaded monitoring videos are segmented and distributed to different data centers according to a fixed capacity size. For example, the system will monitor indicators such as the remaining storage space and network bandwidth of each data center, and dynamically adjust the distribution ratio of video data accordingly. However, this method does not consider the change in data capacity after transcoding: the compression efficiency of different video formats varies greatly. For example, after transcoding the same original video into the H.265 format, its data volume may be reduced by 50% compared to the H.264 format, and the AV1 format may further reduce the storage occupancy. The existing technology only distributes based on the original video capacity and does not consider the actual storage requirements after transcoding, which easily leads to the problem of uneven distribution of storage resources; To solve the above problems, the present invention proposes a solution. Summary of the Invention

[0003] The purpose of the present invention is to provide a monitoring video management system based on video cloud storage to solve the problems raised in the above background art.

[0004] The present invention provides a monitoring video management system based on video cloud storage, including: A cloud storage master control platform for providing distributed storage services to several requesting users. The cloud storage master control platform includes a service master control unit and several storage centers, and one storage center corresponds to one storage server; The service master control unit is used to, after receiving the transmitted cloud service video data of the requesting user, use load balancing technology to select several storage servers from all the storage servers selected and deployed by the cloud storage master control platform according to the resource requirements of the distributed storage service as the basic storage units of the cloud service video data and assign storage weights to them; The service master control unit is also used to generate a cloud storage iterative balancing strategy for the cloud service video data according to a preset generation step after obtaining several basic storage units of the cloud service video data and their storage weights. The cloud storage iterative balancing strategy includes several basic storage units and their cloud storage capacities; The master control unit is also used to determine the number of cut parts of the cloud service video data and the data capacity size of each corresponding part after generating the cloud storage iterative balancing strategy; Cut the cloud service video data according to the determined number of cut parts and the data capacity size of each corresponding part to obtain several cloud storage block data of the cloud service video data; The service master control unit transmits all the cut storage block data to the basic storage units corresponding to the consistent cloud storage capacity for storage according to the cloud storage capacity of each basic storage unit included in the cloud storage iterative balancing strategy according to the data capacity size of each storage block data; The storage log analysis module is used to store the storage logs of all cloud service video data; The storage log analysis module is also used to analyze all the stored storage logs to obtain transcoding feature information of several storage servers based on all video formats.

[0005] Furthermore, the storage server corresponding to one storage center only stores the monitoring video data of one video format.

[0006] Furthermore, the storage log contains the video format of the corresponding cloud service video data, the log information of several storage centers, and the log information contains the storage capacity and transcoding change amount.

[0007] Furthermore, the analysis steps for obtaining the transcoding feature information of several storage servers based on all video formats are as follows: S11: Mark all the storage servers selected and deployed by the cloud storage master control platform according to the resource requirements of the distributed storage service as A1, A2,..., Aa, a≥1, and randomly select one video format from all the video formats stored in the storage servers A1, A2,..., Aa as the format to be analyzed; S12: Extract all storage logs that contain the video format to be analyzed and the log information of storage server A1 from all the storage logs stored in the storage log analysis module, and mark them as B1, B2, ..., Bb respectively, where b≥1; S13: Sequentially extract the log information of storage server A1 from storage logs B1, B2, ..., Bb; then sequentially obtain the storage capacity and transcoding change rate contained in all the extracted log information from the extracted log information; mark all the obtained storage capacities as C1, C2, ..., Cb respectively, and mark all the obtained transcoding change amounts as D1, D2, ..., Db; S14: Determine whether storage server A1 has a linear characteristic based on the transcoding change amount and the storage capacity. The determination steps are as follows: S141: Take the storage capacity as one variable and the transcoding change amount as another variable. According to the storage capacities C1, C2, ..., Cb and the transcoding change amounts D1, D2, ..., Db, calculate the Pearson correlation coefficient E1 of the storage capacity and the transcoding change amount; S142: If E1 satisfies 1≥E1≥P1>0 or -1≤E1≤P2<0, it is determined that storage server A1 has a linear characteristic. At this time, use the formula to calculate and obtain the transcoding capacity linear characteristic F1 of storage server A1, where P1 and P2 are the preset first and second linear standard determination values respectively; S143: If E1 does not satisfy 1≥E1≥P1>0 or -1≤E1≤P2<0, it is determined that storage server A1 does not have a linear characteristic. At this time, calculate z transcoding capacity fitting linear characteristics of storage server A1 based on the preset linear fitting values Z1, Z2, ..., Zz according to the preset calculation rules; S15: Generate transcoding characteristic information of storage server A1 based on the to-be-analyzed format according to the result of determining whether storage server A1 has a linear characteristic; S16: Sequentially extract the log information of storage servers A2, A3, ..., Aa from storage logs B1, B2, ..., Bb according to S12, and sequentially generate transcoding characteristic information of storage servers A2, A3, ..., Aa based on the to-be-analyzed format according to S13 to S15; S17: Sequentially select the video formats stored in storage servers A1, A2, ..., Aa as the to-be-analyzed format, and sequentially generate transcoding characteristic information of storage servers A1, A2, ..., Aa based on all video formats according to S12 to S16.

[0008] Compared with the prior art, it has the following beneficial effects: The present invention obtains the monitored video data uploaded by the authenticated user through the cloud storage service request terminal and transmits it to the cloud storage general control platform. The service general control unit dynamically evaluates the remaining storage capacity, CPU utilization rate, and network bandwidth occupancy rate of each storage server based on the load balancing algorithm, combines the data capacity of the cloud service video data, and selects the optimal storage server cluster as the basic storage unit using the weighted round-robin algorithm and assigns corresponding storage weights. By setting up a storage log analysis module to perform big data analysis on historical storage logs, quantifying the data capacity change characteristics during the transcoding process of different video formats, generating the transcoding capacity linear characteristics or fitting linear characteristics of each storage server for a specific video format, the service general control unit calculates the iterative change capacity and iterative balance capacity of each basic storage unit, dynamically adjusts its actual storage resource allocation, and expands and supplements storage units when necessary, thereby optimizing the global storage resource scheduling. In this way, the consideration of the change in the data capacity of the transcoded monitored video data is introduced during the process of allocating cloud storage for cloud service video data, avoiding the uneven allocation of storage resources among each storage server caused by the conversion of video formats. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0010] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0011] Please refer to Figure 1 , this application provides a monitored video management system based on video cloud storage, including a cloud storage service request terminal, a cloud storage general control platform, and a storage log analysis module; The cloud storage service request terminal is used to obtain the pre-cloud storage monitored video data selected and uploaded by the request user who has passed the identity authentication. Among them, the identity authentication methods include, but are not limited to, username and password, dynamic token, fingerprint recognition, or mobile phone SMS verification code, etc.; The cloud storage service request terminal transmits the obtained pre-cloud storage monitored video data selected and uploaded by the request user as the cloud service video data of the request user to the cloud storage general control platform; A cloud storage master control platform is used to provide distributed storage services for several requesting users. The cloud storage master control platform includes a service master control unit and several storage centers. One storage center corresponds to one storage server. In this application, the storage server is selected and deployed by the cloud storage master control platform according to the resource requirements of the distributed storage service. It should be noted here that the video formats of the monitored videos stored in each storage center are not the same, and the storage server corresponding to one storage center only stores the monitored video data of one video format. Among them, the video formats include, but are not limited to, AVI, MP4, DAT, DVR, VCD, MOV, SVCD, VOB, DVD, DVTR, DVR, BBC, EVD, FLV, RMVB, WMV, MKV, and 3GP, etc. After receiving the monitored video data, any storage center first identifies its video format. If the identified video format is different from the video format it stores, the monitored video data is converted to the corresponding video format before being stored. After receiving the cloud service video data of the requesting user transmitted, the cloud storage master control platform transmits it to the service master control unit. After receiving the cloud service video data of the requesting user transmitted, the service master control unit uses load balancing technology to select several storage servers from all the storage servers selected and deployed by the cloud storage master control platform according to the resource requirements of the distributed storage service as the basic storage units for the cloud service video data and assigns storage weights to them, specifically as follows: After receiving the cloud service video data of the requesting user, based on the receiving moment, obtain the remaining storage capacity, CPU utilization rate, and network bandwidth occupancy rate of all the storage centers at the receiving moment and use them as the allocation basis. Use load balancing technology to assign storage weights to all the storage servers, and select several storage servers from all the storage servers as the basic storage units for the cloud service video data in combination with the data capacity size of the cloud service video data. In this application, the algorithm for using load balancing technology to assign storage weights to all the storage servers and select several storage servers is the weighted round-robin algorithm. After obtaining several basic storage units for the cloud service video data and their storage weights, the service master control unit generates a cloud storage iterative balancing strategy for the cloud service video data according to a preset generation step. The generation step is as follows: S21: Mark all the basic storage units for the cloud service video data selected in descending order of their storage weights as J1, J2,..., Jj, where 1 ≤ j ≤ a. S22: According to the data capacity size K1 of the cloud service video data, sequentially calculate and obtain the load balancing capacities M1, M2, ..., Mj of the basic storage units J1, J2, ..., Jj, where the calculation formula for the load balancing capacity is Mm = Lm × K1, 1 ≤ m ≤ j, and in the formula, Lm represents the storage weight of each basic storage unit among the basic storage units J1, J2, ..., Jj; S23: Obtain the transcoding feature information N1 of the basic storage unit J1 based on the video format from the service master control unit according to the video format of the cloud service video data; S24: Calculate and obtain the iterative change capacity R1 of the basic storage unit J1 based on the video format according to a preset calculation rule. The calculation rule is as follows: S241: If the transcoding capacity linear feature is carried in the transcoding feature information N1, extract the transcoding capacity linear feature Q1 from the transcoding feature information N1, and use the formula R1 = M1 - M1 / Q1 to calculate and obtain the iterative change capacity R1 of the basic storage unit J1 based on the video format, where M1 / Q1 is the iterative balancing capacity of the basic storage unit J1 based on the video format; S242: If z linear fitting values and their transcoding capacity fitting linear features are carried in the transcoding feature information N1, determine the iterative change capacity R1 and the iterative balancing capacity of the basic storage unit J1 based on the video format according to the load balancing capacity M1. Specifically: Determine several linear fitting values larger than it from the z linear fitting values according to the load balancing capacity M1, and extract the transcoding capacity fitting linear feature Q1 of the linear fitting value with the smallest value from the determined several linear fitting values, and use the formula R1 = M1 - M1 / Q1 to calculate and obtain the iterative change capacity R1 of the basic storage unit J1 based on the video format, where M1 / Q1 is the iterative balancing capacity of the basic storage unit J1 based on the video format; It should be noted here that only one of the rules in S241 and S242 is executed for one basic storage unit; S25: Sequentially calculate and obtain the iterative change capacities R2, R3, ..., Rj and the iterative balancing capacities of the basic storage units J2, J3, ..., Jj based on the video format according to S24; S26: Use the formula U1 = K1 - (R1 + R2 +... + Rj) to calculate and obtain the equilibrium determination scalar U1 of the cloud service video data; S27: Compare the sizes of U1 and 0. If U1 ≥ 0, generate the cloud storage iterative equilibrium strategy of the cloud service video data according to a preset first generation rule. The first generation rule is as follows: S31: If R1 ≥ 0, then use the value of M1 + R1 * Q1 as the cloud storage capacity of the basic storage unit J1; otherwise, use the absolute value of the load balancing capacity M1 - R1 * Q1 of the basic storage unit J1 as the cloud storage capacity of the basic storage unit J1. S32: Calculate and obtain the cloud storage capacities of the basic storage units J2, J3, ..., Jj in sequence according to S32. Generate the cloud storage iteration balance strategy for the cloud service video data based on the basic storage units J1, J2, ..., Jj and their corresponding cloud storage capacities. S33: Otherwise, generate the cloud storage iteration balance strategy for the cloud service video data according to the preset second generation rule. The second generation rule is as follows: S41: Mark all the remaining storage centers except the basic storage units J1, J2, ..., Jj in descending order of storage weight as V1, V2, ..., Vv, where v ≥ 1. S42: Calculate and obtain the load balancing capacities of the storage centers V1, V2, ..., Vv in sequence according to S22 based on the balance determination scalar U1 and the storage weights of the storage centers V1, V2, ..., Vv. It should be noted here that during the calculation process, referring to the calculation formula of S22, the balance determination scalar U1 replaces K1 in the formula and is calculated with the storage weight of the corresponding storage center to obtain the load balancing capacity of the corresponding storage center. S43: Calculate and obtain the iteration balance capacities W1, W2, ..., Wv and iteration change capacities X1, X2, ..., Xv of the storage centers V1, V2, ..., Vv in sequence according to S241 to S242. Select the storage centers with marked subscripts less than or equal to w as the basic storage units of the cloud service video data, and re-mark them as Y1, Y2, ..., Yw in ascending order of marked subscripts. w is the preset standard filling quantity. Compare the iteration change capacity X1 of the basic storage unit Y1 with 0. If X1 ≥ 0, then use the value of W1 + X1 * O1 as the cloud storage capacity of the basic storage unit Y1; otherwise, use the absolute value of W1 - M1 - R1 * O1 as the cloud storage capacity of the basic storage unit Y1. O1 is the transcoding capacity linear feature or transcoding capacity fitting linear feature of the basic storage unit J1. S45: Calculate and obtain the cloud storage capacities of the basic storage units Y1, Y2, ..., Yw in sequence according to S41 to S44. Generate the cloud storage iteration balance strategy for the cloud service video data based on the basic storage units J1, J2, ..., Jj, Y1, Y2, ..., Yw and their corresponding cloud storage capacities. The service master control unit determines the number of cut portions of the cloud service video data and the data capacity size of each corresponding portion according to the basic storage unit and its cloud storage capacity included in the cloud storage iterative balancing strategy of the cloud service video data; Cut the cloud service video data according to the determined number of cut portions and the data capacity size of each corresponding portion to obtain a number of cloud storage block data of the cloud service video data; The service master control unit stores all the cut storage block data into the corresponding basic storage units according to the cloud storage capacity of each basic storage unit included in the cloud storage iterative balancing strategy, and transmits each storage block data to the basic storage unit corresponding to the consistent cloud storage capacity for storage according to its data capacity size; A storage log analysis module is used to analyze the storage logs generated during the storage process of several monitoring video data. The storage log analysis module stores the storage logs of several cloud service video data. The storage logs include the video format of the corresponding cloud service video data, the log information of several storage centers, and the log information includes storage capacity and transcoding change amount; A storage log analysis module is used to analyze all the stored storage logs therein, and the analysis steps are as follows: S11: Mark all the storage servers selected and deployed by the cloud storage master control platform according to the resource requirements of the distributed storage service as A1, A2,..., Aa, where a≥1; Randomly select a video format from all the video formats stored in the storage servers A1, A2,..., Aa as the format to be analyzed; S12: Extract all the storage logs from all the storage logs stored in the storage log analysis module that contain the video format to be analyzed and the log information of the storage server A1, and mark them as B1, B2,..., Bb, where b≥1; S13: Sequentially extract the log information of the storage server A1 from the storage logs B1, B2,..., Bb; then sequentially obtain the storage capacity and transcoding change rate included therein from the extracted all log information; Mark all the obtained storage capacities as C1, C2,..., Cb, and mark all the obtained transcoding change amounts as D1, D2,..., Db. Here, it should be noted that the storage capacity C1 and the transcoding change amount D1 are obtained from the same log information. Establish a corresponding relationship between the storage capacity C1 and the transcoding change amount D1, and so on for the storage capacity C2 and the transcoding change amount D2, C3 and D3,..., Cb and Db; S14: Determine whether the storage server A1 has a linear characteristic based on the transcoding change amount and the storage capacity, and the determination steps are as follows: S141: Take the storage capacity as one variable and the transcoding change amount as another variable. According to the storage capacities C1, C2, …, Cb and the transcoding change amounts D1, D2, …, Db, calculate the Pearson correlation coefficient E1 of the storage capacity and the transcoding change amount; S142: If E1 satisfies 1 ≥ E1 ≥ P1 > 0 or -1 ≤ E1 ≤ P2 < 0, then determine that the storage server A1 has a linear characteristic. At this time, use the formula to calculate and obtain the transcoding capacity linear characteristic F1 of the storage server A1; where P1 and P2 are respectively the preset first and second linear standard determination values; S143: If E1 does not satisfy 1 ≥ E1 ≥ P1 > 0 or -1 ≤ E1 ≤ P2 < 0, then determine that the storage server A1 does not have a linear characteristic. At this time, calculate several transcoding capacity fitting linear characteristics of the storage server A1 according to the preset calculation rules. The calculation rules are as follows: SS11: Calculate a transcoding capacity fitting linear characteristic of the storage server A1 according to the linear fitting value Z1, and mark it as I1. Specifically: Extract the storage capacities less than or equal to the linear fitting value Z1 from the storage capacities C1, C2, …, Cb, and re-mark all the extracted storage capacities as G1, G2, …, Gg respectively, where 1 ≤ g ≤ b; sequentially obtain the transcoding change amounts H1, H2, …, Hg corresponding to the storage capacities G1, G2, …, Gg; Use the formula to calculate and obtain the transcoding capacity fitting linear characteristic I1 of the storage server A1 based on the linear fitting value Z1, and establish the corresponding relationship between the transcoding capacity fitting linear characteristic I1 and the linear fitting value Z1; SS12: Sequentially calculate and obtain the transcoding capacity fitting linear characteristics of the storage server A1 based on the linear fitting values Z2, Z3, …, Zz according to SS11, where the linear fitting values Z1, Z2, …, Zz, z ≥ 1 are preset by the administrator, and numerically Z1 < Z2 < Z3 < … < Zz; S15: Generate the transcoding characteristic information of the storage server A1 based on the format to be analyzed according to the result of determining whether the storage server A1 has a linear characteristic. Specifically, if it is determined that the storage server A1 has a linear characteristic, the transcoding characteristic information includes the transcoding capacity linear characteristic F1; otherwise, the transcoding characteristic information includes z linear fitting values and their transcoding capacity fitting linear characteristics; S16: Sequentially extract the log information of the storage servers A2, A3, …, Aa from the storage logs B1, B2, …, Bb according to S12, and sequentially generate the transcoding characteristic information of the storage servers A2, A3, …, Aa based on the format to be analyzed according to S13 to S15; S17: Select the video formats stored in storage servers A1, A2, ..., Aa one after another as the formats to be analyzed, and generate the transcoding feature information of storage servers A1, A2, ..., Aa based on all video formats in sequence according to S12 to S16; The storage log analysis module transmits the generated transcoding feature information of storage servers A1, A2, ..., Aa based on all video formats to the service master control unit for storage; Some data in the above formula are numerically calculated after removing their dimensions, and the content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0012] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A monitoring video management system based on video cloud storage, characterized in that Including: A cloud storage master control platform for providing distributed storage services for a number of requesting users. The cloud storage master control platform includes a service master control unit and a number of storage centers, and one storage center corresponds to one storage server. The service master control unit is used to, after receiving the cloud service video data of the requesting user transmitted, use load balancing technology to select a number of storage servers from all the storage servers selected and deployed by the cloud storage master control platform according to the resource requirements of the distributed storage service as the basic storage units of the cloud service video data and assign storage weights to them. The service master control unit is also used to, after obtaining a number of basic storage units of the cloud service video data and their storage weights, generate a cloud storage iterative balancing strategy for the cloud service video data according to a preset generation step. The cloud storage iterative balancing strategy includes a number of basic storage units and their cloud storage capacities. The master control unit is also used to, after generating the cloud storage iterative balancing strategy, determine the number of cut parts of the cloud service video data and the data capacity size corresponding to each part. Cut the cloud service video data according to the determined number of cut parts and the data capacity size corresponding to each part to obtain a number of cloud storage block data of the cloud service video data. The service master control unit transmits all the cut storage block data to the basic storage units corresponding to the consistent cloud storage capacity according to the cloud storage capacity of each basic storage unit included in the cloud storage iterative balancing strategy for storage according to their data capacity sizes. A storage log analysis module for storing the storage logs of all cloud service video data. The storage log analysis module is also used to analyze all the stored storage logs to obtain transcoding feature information of a number of storage servers based on all video formats.

2. The monitoring video management system based on video cloud storage according to claim 1, characterized in that, The storage server corresponding to one storage center only stores the monitoring video data of one video format.

3. The monitoring video management system based on video cloud storage according to claim 1, wherein The storage log includes the video format corresponding to the cloud service video data, the log information of a number of storage centers, and the log information includes the storage capacity and the transcoding change amount.

4. The monitoring video management system based on video cloud storage according to claim 3, characterized in that, The analysis steps for obtaining the transcoding feature information of a number of storage servers based on all video formats are as follows: S11: Mark all the storage servers selected and deployed by the cloud storage master control platform according to the resource requirements of the distributed storage service as A1, A2,..., Aa, a≥1, and randomly select one video format from all the video formats stored in the storage servers A1, A2,..., Aa as the format to be analyzed. S12: Extract all the storage logs whose included video format is the format to be analyzed and whose log information includes the storage server A1 from all the storage logs stored in the storage log analysis module and mark them as B1, B2,..., Bb, b≥1. S13: Sequentially extract the log information of storage server A1 from storage logs B1, B2, ..., Bb; then sequentially obtain the storage capacity and transcoding change rate included in all the extracted log information from the extracted log information; mark all the obtained storage capacities as C1, C2, ..., Cb respectively, and mark all the obtained transcoding change amounts as D1, D2, ..., Db respectively; S14: Determine whether storage server A1 has a linear feature based on the transcoding change amount and the storage capacity. The determination steps are as follows: S141: Take the storage capacity as one variable and the transcoding change amount as another variable. According to the storage capacities C1, C2, ..., Cb and the transcoding change amounts D1, D2, ..., Db, calculate the Pearson correlation coefficient E1 of the storage capacity and the transcoding change amount; S142: If E1 satisfies 1≥E1≥P1>0 or -1≤E1≤P2<0, it is determined that the storage server A1 has a linear characteristic. At this time, use the formula to calculate and obtain the transcoding capacity linear characteristic F1 of the storage server A1, where P1 and P2 are the preset first and second linear standard determination values respectively; S143: If E1 does not satisfy 1≥E1≥P1>0 or -1≤E1≤P2<0, then determine that storage server A1 does not have a linear feature. At this time, calculate z transcoding capacity fitting linear features of storage server A1 according to the preset calculation rules based on the preset linear fitting values Z1, Z2, ..., Zz; S15: Generate transcoding feature information of storage server A1 based on the to-be-analyzed format according to the result of determining whether storage server A1 has a linear feature; S16: Sequentially extract the log information of storage servers A2, A3, ..., Aa from storage logs B1, B2, ..., Bb according to S12, and sequentially generate transcoding feature information of storage servers A2, A3, ..., Aa based on the to-be-analyzed format according to S13 to S15; S17: Select the video formats stored in storage servers A1, A2, ..., Aa in sequence as the to-be-analyzed format, and sequentially generate transcoding feature information of storage servers A1, A2, ..., Aa based on all video formats according to S12 to S16.

5. The monitoring video management system based on video cloud storage according to claim 4, characterized in that, In S15, if it is determined that storage server A1 has a linear feature, then the transcoding feature information includes the transcoding capacity linear feature F1, otherwise the transcoding feature information includes z linear fitting values and their transcoding capacity fitting linear features.

6. The monitoring video management system based on video cloud storage according to claim 4, wherein, The generation steps of the cloud storage iterative equilibrium strategy for generating the cloud service video data are as follows: S21: Sequentially mark all the basic storage units of the selected cloud service video data as J1, J2, ..., Jj in descending order of the storage weights of all the basic storage units, where 1≤j≤a; S22: According to the data capacity size K1 of the cloud service video data, sequentially calculate and obtain the load balancing capacities M1, M2, ..., Mj of the basic storage units J1, J2, ..., Jj. The calculation formula for the load balancing capacity is Mm = Lm×K1, where 1≤m≤j, and in the formula, Lm represents the storage weight of each basic storage unit among the basic storage units J1, J2, ..., Jj; S23: Obtain the transcoding feature information N1 of the basic storage unit J1 based on the video format from the service master control unit according to the video format of the cloud service video data; S24: Calculate and obtain the iterative change capacity R1 of the basic storage unit J1 based on the video format according to a preset calculation rule; S25: Calculate and obtain the iterative change capacities R2, R3,..., Rj of the basic storage units J2, J3,..., Jj based on the video format and the iterative equilibrium capacity in sequence according to S24; S26: Calculate and obtain the equilibrium determination scalar U1 of the cloud service video data by using the formula U1 = K1 - (R1 + R2 +... + Rj); S27: Compare the magnitudes of U1 and 0. If U1 ≥ 0, generate the cloud storage iterative equilibrium strategy for the cloud service video data according to a preset first generation rule. The first generation rule is as follows: S31: If R1 ≥ 0, use the value of M1 + R1 * Q1 as the cloud storage capacity of the basic storage unit J1; otherwise, use the absolute value of the load balancing capacity M1 - R1 * Q1 of the basic storage unit J1 as the cloud storage capacity of the basic storage unit J1; S32: Calculate and obtain the cloud storage capacities of the basic storage units J2, J3,..., Jj in sequence according to S32; generate the cloud storage iterative equilibrium strategy for the cloud service video data based on the basic storage units J1, J2,..., Jj and their corresponding cloud storage capacities; Otherwise, generate the cloud storage iterative equilibrium strategy for the cloud service video data according to a preset second generation rule.

7. The monitoring video management system based on video cloud storage according to claim 5, characterized in that S24. The calculation rule for calculating the iterative change capacity R1 is as follows: S241: If the transcoding capacity linear feature is carried in the transcoding feature information N1, extract the transcoding capacity linear feature Q1 from the transcoding feature information N1, and calculate and obtain the iterative change capacity R1 of the basic storage unit J1 based on the video format by using the formula R1 = M1 - M1 / Q1, where M1 / Q1 is the iterative equilibrium capacity of the basic storage unit J1 based on the video format; S242: If z linear fitting values and their transcoding capacity fitting linear features are carried in the transcoding feature information N1, determine several linear fitting values larger than it from the z linear fitting values according to the load balancing capacity M1, and extract the transcoding capacity fitting linear feature Q1 of the linear fitting value with the smallest value from the determined several linear fitting values, and calculate and obtain the iterative change capacity R1 of the basic storage unit J1 based on the video format by using the formula R1 = M1 - M1 / Q1, where M1 / Q1 is the iterative equilibrium capacity of the basic storage unit J1 based on the video format.

8. The monitoring video management system based on video cloud storage according to claim 6, characterized in that S33. The second generation rule for generating the cloud storage iterative equilibrium strategy of the cloud service video data is as follows: S41: Mark all the remaining storage centers except the basic storage units J1, J2,..., Jj as V1, V2,..., Vv in descending order of storage weights, where v ≥ 1; S42: Calculate and obtain the load balancing capacities of the storage centers V1, V2,..., Vv in sequence according to S22 by combining the equilibrium determination scalar U1 with the storage weights of the storage centers V1, V2,..., Vv; S43: Calculate and obtain the iterative equilibrium capacities W1, W2, ..., Wv and iterative change capacities X1, X2, ..., Xv of the storage centers V1, V2, ..., Vv in sequence according to S241 to S242. Select the storage centers with the marked subscripts less than or equal to w as the basic storage units for the cloud service video data, and relabel them as Y1, Y2, ..., Yw in ascending order of the marked subscripts; S44: Compare the iterative change capacity X1 of the basic storage unit Y1 with 0. If X1 ≥ 0, then use the value of W1 + X1 * O1 as the cloud storage capacity of the basic storage unit Y1. Otherwise, use the absolute value of W1 - M1 - R1 * O1 as the cloud storage capacity of the basic storage unit Y1, where O1 is the transcoding capacity linear feature or transcoding capacity fitting linear feature of the basic storage unit J1; S45: Calculate and obtain the cloud storage capacities of the basic storage units Y1, Y2, ..., Yw in sequence according to S41 to S44. Generate the cloud storage iterative equilibrium strategy for the cloud service video data based on the basic storage units J1, J2, ..., Jj, Y1, Y2, ..., Yw and their corresponding cloud storage capacities.

Images