Network data optimization management system and method based on artificial intelligence

Abstract

The invention discloses a network data optimization management system and method based on artificial intelligence, and relates to the technical field of network data optimization management, and the method comprises the steps: S10, predicting a network data optimization index of each network node; s20, predicting the network data optimization index of each network node; s30, determining the network data to be optimized of each network node; and S40, performing optimization management on the to-be-optimized network data. According to the invention, the historical network flow set of each network node is adjusted according to the redirection condition of each network node, the adjusted historical network flow set can better reflect the flow consumption condition of the network node during network data transmission, and the flow consumption of the network node during network data transmission can be effectively reduced according to the real-time operation data of the network node. And the data processing capacity rate of the network node can ensure that the network data transmitted by the network node can be optimized and managed before the flow exceeds the limit.

Description

Technical Field

[0001] The present invention relates to the technical field of network data optimization management, and in particular to an artificial intelligence-based network data optimization management system and method. Background Art

[0002] Network data optimization management refers to the processing and optimization of data in the network through various technologies and methods to improve the overall performance and efficiency of the network.

[0003] Nowadays, when optimizing and managing network data, the choice of whether to optimize and manage the network data transmitted by the network node is made by judging whether the traffic consumption value of the network node is within the set range. It is also impossible to determine the optimization management method for each network parameter based on the transmission parameters of the network data. At the same time, the existing technology cannot quickly find the network data to be optimized transmitted by the network node. Summary of the invention

[0004] The purpose of the present invention is to provide a network data optimization management system and method based on artificial intelligence to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a network data optimization management method based on artificial intelligence, the method comprising: S10: in the target network area, obtaining historical operation data of each network node and the redirection situation of each network node, adjusting the historical operation data of each network node based on the obtained information, and predicting the data processing capacity of each network node according to the adjustment result; S20: collecting real-time operation data of each network node, and predicting the network data optimization index of each network node based on the collected information; S30: Determine the network data to be optimized of each network node; S40: Optimizing and managing the network data to be optimized.

[0006] Further, the S10 includes: S101: Divide the selected historical operation time period [h, t] of the network node by time interval d to obtain a plurality of time division areas, obtain the time point at which each network node is redirected, and the redirection object of each network node at each redirection time point, and place the obtained redirection time point in the matching time division area; S102: Collect the historical network traffic of the network node numbered i at each partition point to obtain a historical network traffic set M i , M i ={x 1i ,x 2i,…,x mi}, combined with the redirection objects corresponding to each redirection time point, the historical network traffic set is adjusted, and the historical network traffic set obtained after adjustment is M´ i , M´ i ={x´ 1i ,x´ 2i ,…,x´ mi}; S103: For the set M´ i , if x´ ji >R*u i , then for the set M´ i x´ stored in ji Mark, if 0≤x´ ji ≤R*u i , then there is no need to i x´ stored in ji Marking is performed, and based on the marking processing results, the data processing capacity of each network node is predicted, where u i It represents the maximum network traffic that the network node numbered i can consume, and R represents the proportional coefficient.

[0007] According to the redirection of the network node, the historical network traffic set of the network node is adjusted and processed. The adjusted historical network traffic set can better represent the traffic consumption of the network node, ensuring that the predicted data processing capacity of the network node is more in line with the actual value.

[0008] Furthermore, the specific method of adjusting the historical network traffic set in S102 is: The set M i x stored in ji Replace with x´ ji ; When the redirection object is a network node numbered k: ; When the redirection object is the network node numbered i: ; Where j=1,2,…,m, indicates that each partition point is numbered in chronological order, m indicates the total number of partition points, i=1,2,…,n, indicates the number of each network node in the target network area, n indicates the total number of network nodes in the target network area, and x ji 、x mi represents the historical network traffic value of the network node numbered i collected at the partition points numbered j and m, respectively, and w i→krepresents the network traffic value required to redirect from the network node numbered i to the network node numbered k, w k→i represents the network traffic value consumed when the network node numbered i receives the redirection network request sent by the network node numbered k, k=1,2,…,n and k≠i, r jk =0 or r jk =e, when r jk = 0, it means that there is a redirection time corresponding to the redirection object k in the time segment [s+(j-1)*d,s+j*d] corresponding to the partition point numbered j. jk =e, it means that there is no redirection time corresponding to the redirection object k in the time segment [s+(j-1)*d,s+j*d] corresponding to the division point numbered j.

[0009] Furthermore, the specific method of predicting the data processing capacity of each network node based on the marking processing result in S103 is: For the set M´ i The historical network traffic values ​​marked in are summed up, and the summation result is recorded as F i , according to Q i =(F i / f i ) / u i Predicting the data processing capacity of the network node numbered i; Among them, f i Represents the set M´ i The total number of historical network flow values ​​of the tags present in Q i Indicates the data processing capacity of the network node numbered i. By predicting the data processing capacity of the network node based on the marked historical network traffic value, it is helpful to predict the real-time network data optimization index of the network node, and realize the accurate analysis of the optimization status of the network data transmitted by the network node.

[0010] Further, the S20 includes: S201: Calculate the running data x of the network node numbered i at time t it To collect, if x it / u i >Q i , it means that the network data transmitted by the network node numbered i at time t needs to be optimized, otherwise, it does not need to be optimized; S202: According to U it =1-exp{-[(x it / u i )-Q i]}Predict the network data optimization index of the network node numbered i at time t, exp() represents an exponential function with the real number e as the base, U it Represents the network data optimization index of the network node numbered i at time t.

[0011] Further, the S30 includes: S301: According to U it The order of network data optimization for each network node is determined in descending order of value; S302: Acquire the transmission data of the network node numbered i at time t, and number the acquired transmission data according to the transmission data type. The numbering result is: p=1,2,…,q; q represents the total number, and the network traffic y consumed by the transmission data of the pth type when transmitted by the network node numbered i is calculated. ip , and the number of transmissions of the pth type of transmission data at the network node numbered i, c ip , the coefficient to be optimized R for the pth type of transmission data at time t ipt Make predictions; S303: When 0.7<R ipt ≤1, it means that the pth type of transmission data obtained at time t is the network data to be optimized for the network node numbered i. When 0≤R ipt When <1, it indicates that the p-th type of transmission data acquired at time t is not the network data to be optimized of the network node numbered i.

[0012] Further, the S302 obtains the coefficient R to be optimized for the p-th type of transmission data at time t. ipt The specific formula for prediction is: R ipt =[1-exp(-c ip )]*[y ip / max{y i1 ,y i2 ,…,y iq}]; Among them, y iq It represents the network traffic consumed by the qth type of transmission data during transmission, and max represents the maximum value symbol.

[0013] Further, the S40 includes: When c ip >When setting the threshold, the acquired transmission data of type p is cached in the network node numbered i; When ip >u i*0.2, before the network node numbered i transmits the p-th type of transmission data, data compression processing is performed on the p-th type of transmission data.

[0014] A network data optimization management system based on artificial intelligence, the system comprising a data processing capacity prediction module, a network data optimization index prediction module, a network data to be optimized determination module and an optimization management module; The data processing capacity prediction module is used to obtain the historical operation data of each network node and the redirection situation of each network node in the target network area, adjust the historical operation data of each network node based on the obtained information, and predict the data processing capacity of each network node according to the adjustment result; The network data optimization index prediction module is used to predict the network data optimization index of each network node; The to-be-optimized network data determination module is used to determine the to-be-optimized network data of each network node; The optimization management module is used to perform optimization management on the network data to be optimized.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention adjusts and processes the historical network traffic set of each network node according to the redirection situation of each network node. The adjusted historical network traffic set can better reflect the traffic consumption of the network node when transmitting network data. By comparing the ratio of the real-time operation data of the network node to the maximum network traffic value that the network node can consume with the data processing capacity of the network node, the network data optimization situation of the network node is determined. This process can ensure that the network node optimizes and manages the network data transmitted by the network node before the traffic exceeds the limit, thereby further improving the use effect of the system.

[0016] 2. The present invention determines the network data optimization order of each network node according to the real-time network data optimization index of each network node, and determines the network data to be optimized in the network node according to the transmission parameters of the network node for various types of transmission data. The transmission parameters used in this process can be directly obtained, which is conducive to quickly finding the network data to be optimized of the network node.

[0017] 3. The present invention determines the optimization method of the network data to be optimized through the transmission parameters of the network nodes, so as to achieve specialized optimization of the network data. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of the workflow of an artificial intelligence-based network data optimization management system and method of the present invention; Figure 2The present invention is a schematic diagram of the working principle structure of an artificial intelligence-based network data optimization management system and method. DETAILED DESCRIPTION

[0019] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0020] Example: Figure 1 and Figure 2 As shown, the present invention provides a network data optimization management system and method technical solution based on artificial intelligence, a network data optimization management method based on artificial intelligence, the method comprising: S10: in the target network area, obtaining historical operation data of each network node and the redirection situation of each network node, adjusting the historical operation data of each network node based on the obtained information, and predicting the data processing capacity of each network node according to the adjustment result; S10 includes: S101: Divide the selected historical operation time period [h, t] of the network node by the time interval d to obtain a plurality of time division areas, obtain the time point at which each network node is redirected, and the redirection object of each network node at each redirection time point, and place the obtained redirection time point in the matching time division area. When the network request is transferred from network node A to network node B, network node B is called the redirection object of network node A. For example, if the obtained redirection time point is 13:00 and the time division area is [12:40, 13:10], it is considered that the obtained redirection time point matches the time division area [12:40, 13:10]. S102: Collect the historical network traffic of the network node numbered i at each partition point to obtain a historical network traffic set M i , M i ={x 1i ,x 2i ,…,x mi}, combined with the redirection objects corresponding to each redirection time point, adjust the historical network traffic set. The specific method is as follows: The set M i x stored in ji Replace with x´ ji ; When the redirection object is a network node numbered k: ; When the redirection object is the network node numbered i: ; Where j=1,2,…,m, indicates that each partition point is numbered in chronological order, m indicates the total number of partition points, i=1,2,…,n, indicates the number of each network node in the target network area, n indicates the total number of network nodes in the target network area, and x ji 、x mi represents the historical network traffic value of the network node numbered i collected at the partition points numbered j and m, respectively, and w i→k represents the network traffic value required to redirect from the network node numbered i to the network node numbered k, w k→i It represents the network traffic value consumed when the network node numbered i receives the redirected network request sent by the network node numbered k. When the network node receives the network request, it will process these requests and return the corresponding data. This process consumes traffic. The traffic consumed in this process is called the network traffic value consumed when receiving the network request. The redirected network request refers to the network request that can be redirected. For example, when the network request 1 is transferred from the network node A to the network node B, the network request 1 is called a redirected network request. k=1,2,…,n and k≠i, r jk =0 or r jk =e, when r jk = 0, it means that there is a redirection time corresponding to the redirection object k in the time segment [s+(j-1)*d,s+j*d] corresponding to the partition point numbered j. jk = e, it means that there is no redirection time corresponding to the redirection object k in the time segment [s+(j-1)*d,s+j*d] corresponding to the segment point numbered j; The historical network traffic set obtained after adjustment is M´ i , M´ i ={x´ 1i ,x´ 2i ,…,x´ mi}.

[0021] S103: For the set M´ i , if x´ ji >R*u i , then for the set M´ i x´ stored in ji Mark, if 0≤x´ ji ≤R*u i , then there is no need to i x´ stored in ji Marking is performed, and based on the marking processing results, the data processing capacity of each network node is predicted. The specific method is as follows: For the set M´ iThe historical network traffic values ​​marked in are summed up, and the summation result is recorded as F i , according to Q i =(F i / f i ) / u i Predicting the data processing capacity of the network node numbered i; Among them, f i Represents the set M´ i The total number of historical network flow values ​​of the tags present in Q i Indicates the data processing capacity of the network node numbered i; Among them, u i It represents the maximum network traffic that the network node numbered i can consume, and R represents the proportionality coefficient; S20: collecting real-time operation data of each network node, and predicting the network data optimization index of each network node based on the collected information; The S20 includes: S201: Calculate the running data x of the network node numbered i at time t it To collect, if x it / u i >Q i , it means that the network data transmitted by the network node numbered i at time t needs to be optimized, otherwise, it does not need to be optimized; S202: According to U it =1-exp{-[(x it / u i )-Q i ]}Predict the network data optimization index of the network node numbered i at time t, exp() represents the exponential function with the real number e (e≈2.71828) as the base, U it Represents the network data optimization index of the network node numbered i at time t; S30: Determine the network data to be optimized of each network node; S30 includes: S301: According to U it The order of network data optimization for each network node is determined in descending order of value; S302: Acquire the transmission data of the network node numbered i at time t, and number the acquired transmission data according to the transmission data type. The numbering result is: p=1,2,…,q; q represents the total number, and the network traffic y consumed by the transmission data of the pth type when transmitted by the network node numbered i is calculated. ip, and the number of transmissions of the pth type of transmission data at the network node numbered i, c ip , the coefficient to be optimized R for the pth type of transmission data at time t ipt To make a prediction, the specific prediction formula is: R ipt =[1-exp(-c ip )]*[y ip / max{y i1 ,y i2 ,…,y iq}]; Among them, y iq Indicates the network traffic consumed by the qth type of transmission data during transmission, and max indicates the maximum value symbol; S303: When 0.7<R ipt ≤1, it means that the pth type of transmission data obtained at time t is the network data to be optimized for the network node numbered i. When 0≤R ipt When <1, it indicates that the p-th type of transmission data acquired at time t is not the network data to be optimized of the network node numbered i; S40: Optimizing and managing the network data to be optimized; S40 includes: When c ip >When setting the threshold, the acquired transmission data of type p is cached in the network node numbered i; When ip >u i *0.2, before the network node numbered i transmits the p-th type of transmission data, data compression processing is performed on the p-th type of transmission data.

[0022] A network data optimization management system based on artificial intelligence, the system includes a data processing capacity prediction module, a network data optimization index prediction module, a network data determination module to be optimized and an optimization management module; The data processing capacity prediction module is used to obtain the historical operation data of each network node and the redirection situation of each network node in the target network area, adjust the historical operation data of each network node based on the obtained information, and predict the data processing capacity of each network node according to the adjustment result; The network data optimization index prediction module is used to predict the network data optimization index of each network node; The network data to be optimized determining module is used to determine the network data to be optimized of each network node; The optimization management module is used to optimize the network data to be optimized.

[0023] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A network data optimization management method based on artificial intelligence, characterized in that: The method comprises: S10: in the target network area, obtaining historical operation data of each network node and the redirection situation of each network node, adjusting the historical operation data of each network node based on the obtained information, and predicting the data processing capacity of each network node according to the adjustment result; S20: collecting real-time operation data of each network node, and predicting the network data optimization index of each network node based on the collected information; S30: Determine the network data to be optimized of each network node; S40: Optimizing and managing the network data to be optimized.

2. The method for optimizing network data management based on artificial intelligence according to claim 1, characterized in that: The S10 includes: S101: Divide the selected historical operation time period [h, t] of the network node by time interval d to obtain a plurality of time division areas, obtain the time point at which each network node is redirected, and the redirection object of each network node at each redirection time point, and place the obtained redirection time point in the matching time division area; S102: Collect the historical network traffic of the network node numbered i at each partition point to obtain a historical network traffic set M i , M i ={x 1i ,x 2i ,…,x mi }, combined with the redirection objects corresponding to each redirection time point, the historical network traffic set is adjusted, and the historical network traffic set obtained after adjustment is M´ i , M´ i ={x´ 1i ,x´ 2i ,…,x´ mi }; S103: For the set M´ i , if x´ ji >R*u i , then for the set M´ i x´ stored in ji Mark, if 0≤x´ ji ≤R*u i , then there is no need to i x´ stored in ji Marking is performed, and based on the marking processing results, the data processing capacity of each network node is predicted, where u i It represents the maximum network traffic that the network node numbered i can consume, and R represents the proportional coefficient.

3. The method for optimizing network data management based on artificial intelligence according to claim 2, characterized in that: The specific method of adjusting the historical network traffic set in S102 is: The set M i x stored in ji Replace with x´ ji ; When the redirection object is a network node numbered k: ； When the redirection object is the network node numbered i: ； Where j=1,2,…,m, indicates that each partition point is numbered in chronological order, m indicates the total number of partition points, i=1,2,…,n, indicates the number of each network node in the target network area, n indicates the total number of network nodes in the target network area, and x ji 、x mi represents the historical network traffic value of the network node numbered i collected at the partition points numbered j and m, respectively, and w i→k represents the network traffic value required to redirect from the network node numbered i to the network node numbered k, w k→i represents the network traffic value consumed when the network node numbered i receives the redirection network request sent by the network node numbered k, k=1,2,…,n and k≠i, r jk =0 or r jk =e, when r jk = 0, it means that there is a redirection time corresponding to the redirection object k in the time segment [s+(j-1)*d,s+j*d] corresponding to the partition point numbered j. jk =e, it means that there is no redirection time corresponding to the redirection object k in the time segment [s+(j-1)*d,s+j*d] corresponding to the division point numbered j.

4. The method for optimizing network data management based on artificial intelligence according to claim 3 is characterized in that: The specific method of predicting the data processing capacity of each network node based on the marking processing result in S103 is: For the set M´ i The historical network traffic values ​​marked in are summed up, and the summation result is recorded as F i , according to Q i =(F i / f i ) / u i Predicting the data processing capacity of the network node numbered i; Among them, f i Represents the set M´ i The total number of historical network flow values ​​of the tags present in Q i Indicates the data processing capacity of the network node numbered i.

5. The method for optimizing network data management based on artificial intelligence according to claim 4 is characterized in that: The S20 includes: S201: Calculate the running data x of the network node numbered i at time t it To collect, if x it / u i >Q i , it means that the network data transmitted by the network node numbered i at time t needs to be optimized, otherwise, it does not need to be optimized; S202: According to U it =1-exp{-[(x it / u i )-Q i ]}Predict the network data optimization index of the network node numbered i at time t, exp() represents an exponential function with the real number e as the base, U it Represents the network data optimization index of the network node numbered i at time t.

6. The method for optimizing network data management based on artificial intelligence according to claim 5, characterized in that: The S30 includes: S301: According to U it The order of network data optimization for each network node is determined in descending order of value; S302: Acquire the transmission data of the network node numbered i at time t, and number the acquired transmission data according to the transmission data type. The numbering result is: p=1,2,…,q; q represents the total number, and the network traffic y consumed by the transmission data of the pth type when transmitted by the network node numbered i is calculated. ip , and the number of transmissions of the pth type of transmission data at the network node numbered i, c ip , the coefficient to be optimized R for the pth type of transmission data at time t ipt Make predictions; S303: When 0.7<R ipt ≤1, it means that the pth type of transmission data obtained at time t is the network data to be optimized for the network node numbered i. When 0≤R ipt When <1, it indicates that the p-th type of transmission data acquired at time t is not the network data to be optimized of the network node numbered i.

7. The method for optimizing network data management based on artificial intelligence according to claim 6, characterized in that: The S302 obtains the coefficient R to be optimized for the p-th type of transmission data at time t. ipt The specific formula for prediction is: R ipt =[1-exp(-c ip )]*[and ip / max{and i1 ,and i2 ,…,and iq }]; Among them, y iq It represents the network traffic consumed by the qth type of transmission data during transmission, and max represents the maximum value symbol.

8. The method for optimizing network data management based on artificial intelligence according to claim 7, characterized in that: The S40 includes: When c ip >When setting the threshold, the acquired transmission data of type p is cached in the network node numbered i; When ip >u i *0.2, before the network node numbered i transmits the p-th type of transmission data, data compression processing is performed on the p-th type of transmission data.

9. A network data optimization management system based on artificial intelligence, characterized by: The system includes a data processing capacity prediction module, a network data optimization index prediction module, a network data to be optimized determination module and an optimization management module; The data processing capacity prediction module is used to obtain the historical operation data of each network node and the redirection situation of each network node in the target network area, adjust the historical operation data of each network node based on the obtained information, and predict the data processing capacity of each network node according to the adjustment result; The network data optimization index prediction module is used to predict the network data optimization index of each network node; The to-be-optimized network data determination module is used to determine the to-be-optimized network data of each network node; The optimization management module is used to perform optimization management on the network data to be optimized.

Images