Network communication optimization system and method based on data analysis

By analyzing the house structure and user mobile terminal locations, automatically selecting the best routing equipment and distributing bandwidth, the data rate problem caused by low signal strength in distributed routers is solved, and network communication efficiency and user experience are improved.

CN119094428AInactive Publication Date: 2024-12-06CHUANGZAN TECH (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411333798.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-24
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

When a distributed router connects in real time with a user's mobile terminal, it is easy to cause low data download and upload speed due to low signal strength, and fails to effectively realize network communication optimization.

Method used

By obtaining house layout structure data and historical user mobile terminal location information, building a house structure model, analyzing and binding the location of the routing device, predicting the location of the user mobile terminal, selecting the best routing device, and distributing bandwidth according to the traffic prediction model, realizing automation routing device selection and bandwidth optimization.

Benefits of technology

It improves the connection signal strength of the user's mobile terminal, reduces network coverage costs, reduces system failure rate, improves user experience and computing efficiency, and ensures more efficient network communication.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119094428A_ABST
    Figure CN119094428A_ABST
Patent Text Reader

Abstract

The invention discloses a network communication optimization system and method based on data analysis, and relates to the technical field of network communication.The method comprises the steps that layout structure data of a house is obtained to construct a house structure model, and the position coordinates of routing equipment are analyzed according to the position coordinates of historical user mobile terminals; carrying out position coordinate binding on corresponding routing equipment in the house structure model; extracting basic information of routing equipment historically scanned by the real-time user mobile terminal, and analyzing historical position information of the real-time user mobile terminal in combination with the house structure model; predicting movement of the real-time user mobile terminal according to the historical position information of the real-time user mobile terminal; the optimal routing equipment of the real-time user mobile terminal is analyzed; and obtaining a historical traffic use condition of the user mobile terminal, constructing a traffic prediction model of the user mobile terminal, and carrying out bandwidth allocation on the user mobile terminal according to a prediction result. The fault rate of the system is reduced and the operation efficiency of the system is improved; and the overall use experience is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of network communication, and in particular to a network communication optimization system and method based on data analysis. Background Art

[0002] Distributed routers are a type of router with distributed routing processing capabilities. They are distributed through multiple physical locations to share routing information and load between routers, providing higher scalability and redundancy. Distributed routers are often used in environments such as large enterprises, campus networks, and data centers to provide high reliability and high performance routing services.

[0003] However, when using distributed routers, the user's mobile terminal often needs to connect to another routing device only when the routing device to which it is currently connected has no signal at all. When the network is available, the user's mobile terminal will not automatically select a routing device with a strong signal for connection. When the user is in an area with low signal strength of the currently connected routing device, it is easy for the user to be in a situation of low data download and upload rates for a long time, which is not conducive to achieving network communication optimization.

[0004] Therefore, the present invention discloses a network communication optimization system and method based on data analysis to solve the above problems. Summary of the invention

[0005] The object of the present invention is to provide a network communication optimization system and method based on data analysis to solve the problems raised in the prior art.

[0006] A network communication optimization method based on data analysis, the method comprising the following steps: S1: Obtain the layout structure data of the house to build a house structure model, obtain the location coordinates of the historical user mobile terminal and the basic information of the scanned routing device, analyze the location coordinates of the routing device according to the location coordinates of the historical user mobile terminal, and bind the location coordinates of the corresponding routing device in the house structure model; S2: extracting basic information of routing devices historically scanned by the real-time user mobile terminal, analyzing historical location information of the real-time user mobile terminal in combination with the house structure model; predicting movement of the real-time user mobile terminal based on the historical location information of the real-time user mobile terminal; S3: Analyze the best routing device of the real-time user mobile terminal according to the movement prediction result of the real-time user mobile terminal, the house structure model and the routing device information; S4: Obtain historical traffic usage of the user mobile terminal connected to the best routing device, build a traffic prediction model for the user mobile terminal, predict the traffic for each user mobile terminal through the traffic prediction model, and allocate bandwidth to the user mobile terminal according to the prediction results.

[0007] The present invention application is authorized by the user before data collection.

[0008] According to the above scheme, S1 includes the following contents: S101: Acquire layout structure data of a target house, and construct a house structure model using BIM technology; the layout structure data of the house includes the position coordinates of each corner of the house and the distribution of walls inside the house; establish a plane coordinate system for the house ground in the house structure model; S102: Mark the location coordinates of the i-th historical user mobile terminal as (X i , Y i ), extract the basic information of the routing device scanned by the i-th historical user mobile terminal; the basic information of the routing device includes the name of the routing device and the signal strength of the routing device; the j-th routing device scanned by the i-th historical user mobile terminal is recorded as RD j , the scanned signal strength is recorded as SS (i,j) ; Calculate the distance between the historical user mobile terminal and the routing device based on the signal strength, denoted as S (i,j) ; According to the historical user mobile terminal location coordinates and the historical user mobile terminal and the distance between the routing device to form a terminal data pair, recorded as [RD j :(X i , Y i , S (i,j) )]; Extract all the RDs associated with the routing device j The relevant data pairs generate a terminal connection set, denoted as [RD j : (X1, Y1, S (1,j) ), (X2, Y2, S (2,j) ),…,(X I , Y I , S (I,j) )], i∈[1,I], where I represents the routing device RD scanned j The total number of historical user mobile terminals; j∈[1, J], where J represents the total number of routing devices; S103: randomly extract three data pairs from the connection set, and analyze the virtual position of the routing device using the triangulation method based on the three data pairs; group all virtual positions into a set, which is recorded as the virtual position set; construct a virtual polygon based on the virtual position set, and the edges and interior of the virtual polygon contain all virtual positions in the virtual position set, and mark the geometric center coordinates of the virtual polygon as the routing device RD j The location coordinates of By analyzing the location coordinates of the routing device through the historical location coordinates of historical user mobile terminals, the routing device does not need to be compatible with the positioning system, which can effectively reduce the overall funds required for network coverage, reduce problems in daily operations due to incompatibility, and reduce the failure rate of the system.

[0009] By randomly extracting three pairs of data from the connection set to generate a virtual location and further analyzing the virtual location, the accuracy of the location coordinates of the routing device can be effectively improved.

[0010] S104: Repeat S102 and S103, analyze and calculate the location coordinates of all routing devices in the target house, and bind the location coordinates of the corresponding routing devices in the house structure model.

[0011] According to the above scheme, S2 includes the following contents: S201: extract the basic information of the routing device scanned by the real-time user mobile terminal at the same historical moment, calculate the distance between the real-time user mobile terminal and the routing device at the historical moment according to the signal strength in the basic information of the routing device scanned at the historical moment, and form a routing data pair, recorded as (RDN a , R.S. a ); where RDN a Indicates the name of the ath routing device scanned by the real-time user mobile terminal, RS a Indicates the routing device RDN a The distance to the real-time user mobile terminal; a∈[1, A], where A represents the total number of routing devices scanned by the real-time user mobile terminal at the same historical moment, A<J; S202: Arrange the routing data pairs generated by the routing devices scanned by the real-time user mobile terminal at the same historical moment in order from near to far distance to form a routing connection sequence, which is recorded as [(RDN1, RS1), (RDN2, RS2), …, (RDN A , R.S. A )]; S203: Compare the routing connection sequence of the real-time user mobile terminal with the historical routing connection sequence in the database, and search for the historical routing connection sequence with the same routing device name as that appearing in the routing connection sequence of the real-time user mobile terminal; calculate the correlation value between the routing connection sequence of the real-time user mobile terminal and the historical routing connection sequence with the same routing device name and sorting method; the database contains the location coordinates of the historical user mobile terminal and the historical routing connection sequence generated by the historical user mobile terminal at the location coordinates; the specific calculation formula of the correlation value CO is as follows: CO=∑\s\do 3(a=1)A [(RS a -RRS a)×exp(-RS a ÷∑\s\do 3(a=1)A RS a )]; RRS a Represents the routing device RDN in the historical routing connection sequence of the historical user mobile terminal a The distance from the historical user's mobile terminal; By searching for a historical routing connection sequence with the same routing device name as that appearing in the routing connection sequence of the real-time user mobile terminal and calculating the correlation value, it is not necessary to search for a historical routing connection sequence with the same signal strength of each routing device, which can effectively reduce the query amount and improve the operation efficiency of the system. S204: extracting N historical user mobile terminals with the smallest correlation value with the real-time user mobile terminal, where N is a system preset constant; extracting the location coordinates of the N historical user mobile terminals, taking the location coordinates of the historical user mobile terminals as the center of the circle, and n ×r is the radius of the circle; CO n Represents the correlation value between the real-time user mobile terminal and the nth historical user mobile terminal, r gradually increases from zero until N circles intersect at one point, and the position coordinates of the intersection point are used as the position coordinates of the real-time user mobile terminal at the historical moment; extract and use the real-time user mobile terminal position coordinates within the time range T before the real-time moment to train the LSTM model, where T is a system preset constant; use the LSTM model to predict the position coordinates at the next moment. By establishing an LSTM model, the user's location coordinates at the next moment can be effectively predicted, providing effective data support for subsequent optimal route selection.

[0012] According to the above scheme, S3 includes the following: S301: constructing a routing strength layout model according to the house structure model, the location coordinates of historical user mobile terminals in the database, and the historical routing connection sequence of historical user mobile terminals at the location coordinates; the routing strength layout model includes the location coordinates of each location point of the house and the signal strength of each routing device at the corresponding location coordinates; S302: According to the predicted location coordinates and the routing strength layout model, the signal strength corresponding to each routing device at the predicted location coordinates is obtained; and the routing idleness values ​​of the M routing devices closest to the predicted location are calculated: IL m ={α1×[(∑\s\do 3(m=1)M SS m )÷SS m ]}×(α2×BI m ); Among them, IL mrepresents the idleness value of the routing device closest to the predicted position m among the M routing devices; α1 and α2 represent idleness coefficients; the idleness coefficients are system preset constants; SS m Indicates the signal strength of the mth closest routing device to the predicted location among M routing devices; BI m Indicates the bandwidth idle rate of the mth closest routing device to the predicted position among M routing devices; m∈[1,M]; M is a system preset constant; The routing device with the largest routing idleness value is used as the best routing device for the real-time user mobile terminal, and the real-time user mobile terminal is connected to the best routing device.

[0013] By calculating the routing idleness value through the signal strength and bandwidth idleness rate of the routing device, it can effectively avoid the situation where the routing device has a strong signal but many users use it, and improve the accuracy of selecting the best routing device. It is no longer necessary for the user's mobile terminal to connect to another routing device only when the routing device connected to it in real time has no signal at all. The routing device with a strong signal is automatically selected for connection, which improves the user experience.

[0014] According to the above scheme, S4 includes the following contents: S401: extract the historical traffic usage of the d-th user mobile terminal connected to the best routing device, and build a traffic prediction model for the d-th user mobile terminal: TR d =β d 1×TT d +β d 2; where β d 1 and β d 2 represents the fitting coefficient, TT d The independent variable representing time, TR d represents the dependent variable of the unit time flow, and uses the least squares method to predict the β in the flow prediction model of the d-th user's mobile terminal. d 1 and β d 2. Perform calculations and solve; S402: The system presets a duration t, and calculates the total traffic of each user's mobile terminal within the time range of T0 to T0+t according to the traffic prediction model of each user's mobile terminal; T0 represents the current time; the total traffic of the dth user's mobile terminal within the time range of T0 to T0+t is recorded as TNTR d ; By building a traffic prediction model for the user's mobile terminal based on the user's historical traffic usage, it is possible to effectively predict the user's traffic usage in the future and provide effective data support for subsequent bandwidth allocation.

[0015] S403: Allocate bandwidth to each user's mobile terminal. The bandwidth calculation formula is as follows: BW d =[TNTR d ÷(∑\s\do 3(d=1)D TNTR d )]×ZBW×θ; Where BW d represents the bandwidth of the dth user mobile terminal, d∈[1,D]; D represents the total number of user mobile terminals connected to the optimal routing device; ZBW represents the total bandwidth of the optimal routing device; θ represents the control coefficient, which is a system preset constant.

[0016] By allocating bandwidth to user mobile terminals based on traffic usage, bandwidth can be effectively allocated to each user, improving the overall user experience.

[0017] Another aspect of the present application provides a network communication optimization system based on data analysis, the system is applied to the implementation of the above-mentioned network communication optimization method based on data analysis, the system includes a database, a routing layout analysis module, a user movement analysis module, a routing selection analysis module and a bandwidth allocation module; The database is used to store house structure data and system historical operation data; The routing layout analysis module is used to obtain the layout structure data of the house to build a house structure model, obtain the location coordinates of the historical user mobile terminal and the basic information of the scanned routing device, analyze the location coordinates of the routing device according to the location coordinates of the historical user mobile terminal, and bind the location coordinates of the corresponding routing device in the house structure model; The user movement analysis module is used to extract basic information of routing devices historically scanned by the real-time user mobile terminal, analyze the historical location information of the real-time user mobile terminal in combination with the house structure model; and predict the movement of the real-time user mobile terminal based on the historical location information of the real-time user mobile terminal; The routing selection analysis module is used to analyze the best routing device of the real-time user mobile terminal according to the movement prediction result of the real-time user mobile terminal, the house structure model and the routing device information; The bandwidth allocation module is used to obtain the historical traffic usage of the user mobile terminal connected to the best routing device, build a traffic prediction model for the user mobile terminal, predict the traffic for each user mobile terminal through the traffic prediction model, and allocate bandwidth to the user mobile terminal according to the prediction results.

[0018] According to the above scheme, the routing layout analysis module includes a house structure model building unit and a device coordinate binding unit; The house structure model building unit is used to obtain the layout structure data of the target house and build the house structure model by using BIM technology; the layout structure data of the house includes the position coordinates of each corner of the house and the distribution of the walls inside the house; a plane coordinate system is established for the house ground in the house structure model; The device coordinate binding unit is used to analyze the location coordinates of all routing devices in the target house according to the location coordinates of the historical user mobile terminal and the basic information of the routing devices scanned by the historical user mobile terminal; and bind the location coordinates of the corresponding routing devices in the house structure model.

[0019] According to the above solution, the user motion analysis module includes a user mobile terminal association unit and a user motion model prediction unit; The user mobile terminal association unit is used to form a routing connection sequence according to the basic information of the routing device scanned by the real-time user mobile terminal at the same historical moment, search the database for a historical routing connection sequence with the same routing device name as that appearing in the routing connection sequence of the real-time user mobile terminal; and calculate the association degree; The user motion model prediction unit is used to extract N historical user mobile terminals with the smallest correlation value with the real-time user mobile terminal, analyze the position coordinates of the real-time user mobile terminal at historical moments, extract and use the real-time user mobile terminal position coordinates within a time range T before the real-time moment to train the LSTM model, where T is a system preset constant; and use the LSTM model to predict the position coordinates at the next moment.

[0020] According to the above scheme, the routing selection analysis module includes a routing strength layout model building unit and a routing device selection unit; The strength layout model construction unit is used to construct a routing strength layout model according to the house structure model and the location coordinates of the historical user mobile terminal in the database and the historical routing connection sequence of the historical user mobile terminal at the location coordinates; the routing strength layout model includes the location coordinates of each location point of the house and the signal strength of each routing device at the corresponding location coordinates; The routing device selection unit is used to obtain the signal strength corresponding to each routing device of the predicted location coordinates according to the predicted location coordinates and the routing strength layout model; calculate the routing idleness values ​​of the M routing devices closest to the predicted location coordinates, use the routing device with the largest routing idleness value as the best routing device for the real-time user mobile terminal, and connect the real-time user mobile terminal to the best routing device.

[0021] According to the above scheme, the bandwidth allocation module includes a traffic prediction model building unit and a bandwidth allocation unit; The traffic prediction model building unit is used to build a traffic prediction model for each user mobile terminal according to the historical traffic usage of each user mobile terminal connected to the optimal routing device; The bandwidth allocation unit is used to preset the system duration t, calculate the total flow of each user mobile terminal in the future time range according to the flow prediction model of each user mobile terminal, and allocate bandwidth according to the total flow of each user mobile terminal in the future time range.

[0022] To achieve the above object, the present invention provides the following technical solutions: Compared with the prior art, the beneficial effects of the present invention are as follows: by analyzing the location coordinates of the routing device through the historical location coordinates of the historical user mobile terminal, the routing device does not need to be compatible with the positioning system, which can effectively reduce the overall funds required for network coverage, reduce problems caused by incompatibility in daily operation, and reduce the failure rate of the system; further analysis of the virtual location can effectively improve the accuracy of the location coordinates of the routing device; by finding the historical routing connection sequence with the routing device name that is exactly the same as that appearing in the routing connection sequence of the real-time user mobile terminal; and calculating the correlation value; there is no need to find the historical routing connection sequence with the same signal strength of each routing device, which can effectively reduce the query amount and improve the operation efficiency of the system; through the signal strength of the routing device The routing idleness value is calculated based on signal strength and bandwidth idle rate, which can effectively avoid the situation where the routing device has a strong signal but many users are using it, and improve the accuracy of selecting the best routing device. It is no longer necessary to connect to another routing device only when the routing device to which the user's mobile terminal is connected in real time has no signal at all. The routing device with a strong signal is automatically selected for connection, which improves the user experience. Through the historical traffic usage of the user's mobile terminal, a traffic prediction model for the user's mobile terminal is constructed, which can effectively predict the user's traffic usage in the future time range, and provide effective data support for subsequent bandwidth allocation. By allocating bandwidth to the user's mobile terminal according to the traffic usage, the bandwidth can be effectively allocated to each user, improving the overall user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 A schematic diagram of a flow chart of a network communication optimization method based on data analysis according to the present invention; Figure 2 The present invention is a schematic diagram of the structure of a network communication optimization system based on data analysis. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] See also Figure 1 The present invention provides a technical solution: a network communication optimization method based on data analysis, the method comprising the following steps: S1: Obtain the layout structure data of the house to build a house structure model, obtain the location coordinates of the historical user mobile terminal and the basic information of the scanned routing device, analyze the location coordinates of the routing device according to the location coordinates of the historical user mobile terminal, and bind the location coordinates of the corresponding routing device in the house structure model; In S1, the following are included: S101: Obtaining the layout structure data of the target house, and constructing a house structure model using BIM technology; the layout structure data of the house includes the position coordinates of each corner of the house and the distribution of the walls inside the house; establishing a plane coordinate system for the house ground in the house structure model; S102: Mark the location coordinates of the i-th historical user mobile terminal as (X i , Y i ), extract the basic information of the routing device scanned by the i-th historical user mobile terminal; the basic information of the routing device includes the name of the routing device and the signal strength of the routing device; the j-th routing device scanned by the i-th historical user mobile terminal is recorded as RD j , the scanned signal strength is recorded as SS (i,j) ; Calculate the distance between the historical user mobile terminal and the routing device based on the signal strength, denoted as S (i,j) ; According to the historical user mobile terminal location coordinates and the historical user mobile terminal and the distance between the routing device to form a terminal data pair, recorded as [RD j :(X i , Y i , S (i,j) )]; Extract all the RDs associated with the routing device j The relevant data pairs generate a terminal connection set, denoted as [RD j : (X1, Y1, S (1,j) ), (X2, Y2, S (2,j) ),…,(X I , Y I , S (I,j) )], i∈[1,I], where I represents the routing device RD scanned jThe total number of historical user mobile terminals; j∈[1, J], where J represents the total number of routing devices; S103: randomly extract three data pairs from the connection set, and analyze the virtual position of the routing device using the triangulation method based on the three data pairs; group all virtual positions into a set, recorded as a virtual position set; construct a virtual polygon based on the virtual position set, and the edges and interior of the virtual polygon contain all virtual positions in the virtual position set, and mark the geometric center coordinates of the virtual polygon as the routing device RD j The location coordinates of S104: Repeat S102 and S103, analyze and calculate the location coordinates of all routing devices in the target house, and bind the location coordinates of the corresponding routing devices in the house structure model; the house structure model includes the name of the routing device and the location coordinates of the routing device.

[0026] S2: extracting basic information of routing devices historically scanned by the real-time user mobile terminal, analyzing historical location information of the real-time user mobile terminal in combination with the house structure model; predicting movement of the real-time user mobile terminal based on the historical location information of the real-time user mobile terminal; In S2, the following contents are included: S201: extract the basic information of the routing device scanned by the real-time user mobile terminal at the same historical moment, calculate the distance between the real-time user mobile terminal and the routing device at the historical moment according to the signal strength in the basic information of the routing device scanned at the historical moment, and form a routing data pair, recorded as (RDN a , R.S. a ); where RDN a Indicates the name of the ath routing device scanned by the real-time user mobile terminal, RS a Indicates the routing device RDN a The distance to the real-time user mobile terminal; a∈[1, A], where A represents the total number of routing devices scanned by the real-time user mobile terminal at the same historical moment, A<J; S202: Arrange the routing data pairs generated by the routing devices scanned by the real-time user mobile terminal at the same historical moment in order from near to far distance to form a routing connection sequence, which is recorded as [(RDN1, RS1), (RDN2, RS2), …, (RDN A , R.S. A )]; S203: Compare the routing connection sequence of the real-time user mobile terminal with the historical routing connection sequence in the database, and find the historical routing connection sequence with the same routing device name as that appearing in the routing connection sequence of the real-time user mobile terminal; calculate the correlation value between the routing connection sequence of the real-time user mobile terminal and the historical routing connection sequence with the same routing device name and sorting method; the database contains the location coordinates of the historical user mobile terminal and the historical routing connection sequence generated by the historical user mobile terminal at the location coordinates; the specific calculation formula of the correlation value CO is as follows: CO=∑\s\do 3(a=1)A [(RS a -RRS a )×exp(-RS a ÷∑\s\do 3(a=1)A RS a )]; RRS a Represents the routing device RDN in the historical routing connection sequence of the historical user mobile terminal a The distance from the historical user's mobile terminal; S204: extract N historical user mobile terminals with the smallest correlation value with the real-time user mobile terminal, where N is a system preset constant; extract the location coordinates of the N historical user mobile terminals, take the location coordinates of the historical user mobile terminals as the center of the circle, and n ×r is the radius of the circle; CO n Represents the correlation value between the real-time user mobile terminal and the nth historical user mobile terminal, r gradually increases from zero until N circles intersect at one point, and the position coordinates of the intersection point are used as the position coordinates of the real-time user mobile terminal at the historical moment; extract and use the real-time user mobile terminal position coordinates within the time range T before the real-time moment to train the LSTM model, where T is a system preset constant; use the LSTM model to predict the position coordinates at the next moment.

[0027] S3: Analyze the best routing device of the real-time user mobile terminal according to the movement prediction result of the real-time user mobile terminal, the house structure model and the routing device information; In S3, include the following: S301: constructing a routing strength layout model according to the house structure model, the location coordinates of historical user mobile terminals in the database, and the historical routing connection sequence of historical user mobile terminals at the location coordinates; the routing strength layout model includes the location coordinates of each location point of the house and the signal strength of each routing device at the corresponding location coordinates; S302: According to the predicted location coordinates and the routing strength layout model, the signal strength corresponding to each routing device at the predicted location coordinates is obtained; and the routing idleness values ​​of the M routing devices closest to the predicted location are calculated: IL m ={α1×[(∑\s\do 3(m=1)M SS m )÷SS m ]}×(α2×BI m ); Among them, IL m represents the idleness value of the routing device closest to the predicted position among the M routing devices; α1 and α2 represent the idleness coefficients; the idleness coefficients are system preset constants; SS m Indicates the signal strength of the mth closest routing device to the predicted location among M routing devices; BI m Indicates the bandwidth idle rate of the mth closest routing device to the predicted position among M routing devices; m∈[1,M]; M is a system preset constant; Example 1: In this example, the names, signal strengths, and bandwidth idle rates of the three most recent routing devices are as follows: (BSSID1, -50dbm, 25%), (BSSID2, -60dbm, 50%), (BSSID3, -90dbm, 30%); α1 and α2 are both 1; Therefore IL1=1×[(∑\s\do 3(m=1)3 SS m )÷SS1]×1×BI1=(-50-60-90)÷(-50)×25%=1; IL2=1×[(∑\s\do 3(m=1)3 SS m )÷SS2]×1×BI2=(-50-60-90)÷(-60)×50%≈1.67; IL3=1×[(∑\s\do 3(m=1)3 SS m )÷SS3]×1×BI3=(-50-60-90)÷(-90)×30%≈0.67; Therefore, in this embodiment, the routing device BSSID2 is the best routing device for the real-time user mobile terminal, and the real-time user mobile terminal is connected to the routing device BSSID2.

[0028] S4: Obtain historical traffic usage of the user mobile terminal connected to the best routing device, build a traffic prediction model for the user mobile terminal, predict the traffic for each user mobile terminal through the traffic prediction model, and allocate bandwidth to the user mobile terminal according to the prediction results.

[0029] In S4, the following are included: S401: extract the historical traffic usage of the d-th user mobile terminal connected to the best routing device, and build a traffic prediction model for the d-th user mobile terminal: TR d =βd 1×TT d +β d 2; where β d 1 and β d 2 represents the fitting coefficient, TT d The independent variable representing time, TR d represents the dependent variable of the unit time flow, and uses the least squares method to predict the β in the flow prediction model of the d-th user's mobile terminal. d 1 and β d 2. Perform calculations and solve; S402: The system presets a duration t, and calculates the total traffic of each user's mobile terminal within the time range of T0 to T0+t according to the traffic prediction model of each user's mobile terminal; T0 represents the current time; the total traffic of the dth user's mobile terminal within the time range of T0 to T0+t is recorded as TNTR d ; S403: Allocate bandwidth to each user's mobile terminal. The bandwidth calculation formula is as follows: BW d =[TNTR d ÷(∑\s\do 3(d=1)D TNTR d )]×ZBW×θ; Where BW d represents the bandwidth of the dth user mobile terminal, d∈[1,D]; D represents the total number of user mobile terminals connected to the optimal routing device; ZBW represents the total bandwidth of the optimal routing device; θ represents the control coefficient, which is a system preset constant.

[0030] See also Figure 2 ,The present invention provides a technical solution: a network communication optimization system based on data analysis, the system includes a database, a routing layout analysis module, a user movement analysis module, a routing selection analysis module and a bandwidth allocation module; The database is used to store house structure data and system historical operation data; The routing layout analysis module is used to obtain the layout structure data of the house to build a house structure model, obtain the location coordinates of the historical user mobile terminal and the basic information of the scanned routing device, analyze the location coordinates of the routing device according to the location coordinates of the historical user mobile terminal, and bind the location coordinates of the corresponding routing device in the house structure model; The user movement analysis module is used to extract the basic information of the routing device historically scanned by the real-time user mobile terminal, analyze the historical location information of the real-time user mobile terminal in combination with the house structure model; and predict the movement of the real-time user mobile terminal based on the historical location information of the real-time user mobile terminal; The routing selection analysis module is used to analyze the best routing device of the real-time user mobile terminal according to the movement prediction result of the real-time user mobile terminal, the house structure model and the routing device information; The bandwidth allocation module is used to obtain the historical traffic usage of the user mobile terminal connected to the best routing device, build a traffic prediction model for the user mobile terminal, predict the traffic for each user mobile terminal through the traffic prediction model, and allocate bandwidth to the user mobile terminal according to the prediction results.

[0031] The routing layout analysis module includes a house structure model building unit and a device coordinate binding unit; The house structure model building unit is used to obtain the layout structure data of the target house and build the house structure model using BIM technology; the house layout structure data includes the position coordinates of each corner of the house and the distribution of the walls inside the house; a plane coordinate system is established for the house ground in the house structure model; The device coordinate binding unit is used to analyze the location coordinates of all routing devices in the target house according to the location coordinates of the historical user mobile terminal and the basic information of the routing devices scanned by the historical user mobile terminal; and to bind the location coordinates of the corresponding routing devices in the house structure model.

[0032] The user motion analysis module includes a user mobile terminal association unit and a user motion model prediction unit; The user mobile terminal association unit is used to form a routing connection sequence according to the basic information of the routing device scanned by the real-time user mobile terminal at the same historical moment, search the database for a historical routing connection sequence with the same routing device name as that appearing in the routing connection sequence of the real-time user mobile terminal; and calculate the association degree; The user motion model prediction unit is used to extract N historical user mobile terminals with the smallest correlation value with the real-time user mobile terminal, analyze the location coordinates of the real-time user mobile terminal at historical moments, extract and use the real-time user mobile terminal location coordinates within a time range T before the real-time moment to train the LSTM model, where T is a system preset constant; and use the LSTM model to predict the location coordinates at the next moment.

[0033] The routing selection analysis module includes a routing strength layout model building unit and a routing device selection unit; The strength layout model building unit is used to build a routing strength layout model according to the house structure model, the location coordinates of the historical user mobile terminal in the database, and the historical routing connection sequence of the historical user mobile terminal at the location coordinates; the routing strength layout model includes the location coordinates of each location point of the house and the signal strength of each routing device at the corresponding location coordinates; The routing device selection unit is used to obtain the signal strength corresponding to each routing device at the predicted location coordinates according to the predicted location coordinates and the routing strength layout model; calculate the routing idleness values ​​of the M routing devices closest to the predicted location coordinates, use the routing device with the largest routing idleness value as the best routing device for the real-time user mobile terminal, and connect the real-time user mobile terminal to the best routing device.

[0034] The bandwidth allocation module includes a traffic prediction model building unit and a bandwidth allocation unit; The traffic prediction model building unit is used to build a traffic prediction model for each user mobile terminal according to the historical traffic usage of each user mobile terminal connected to the best routing device; The bandwidth allocation unit is used to preset the system duration t, calculate the total traffic of each user's mobile terminal in the future time range according to the traffic prediction model of each user's mobile terminal, and allocate bandwidth according to the total traffic of each user's mobile terminal in the future time range.

[0035] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0036] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A network communication optimization method based on data analysis, characterized in that: The method comprises the following steps: S1: Obtain the layout structure data of the house to build a house structure model, obtain the location coordinates of the historical user mobile terminal and the basic information of the scanned routing device, analyze the location coordinates of the routing device according to the location coordinates of the historical user mobile terminal, and bind the location coordinates of the corresponding routing device in the house structure model; S2: extracting basic information of routing devices historically scanned by the real-time user mobile terminal, analyzing historical location information of the real-time user mobile terminal in combination with the house structure model; predicting movement of the real-time user mobile terminal based on the historical location information of the real-time user mobile terminal; S3: Analyze the best routing device of the real-time user mobile terminal according to the movement prediction result of the real-time user mobile terminal, the house structure model and the routing device information; S4: Obtain historical traffic usage of the user mobile terminal connected to the best routing device, build a traffic prediction model for the user mobile terminal, predict the traffic for each user mobile terminal through the traffic prediction model, and allocate bandwidth to the user mobile terminal according to the prediction results.

2. The network communication optimization method based on data analysis according to claim 1, characterized in that: In S1, the following are included: S101: Acquire layout structure data of a target house, and construct a house structure model using BIM technology; the layout structure data of the house includes the position coordinates of each corner of the house and the distribution of walls inside the house; establish a plane coordinate system for the house ground in the house structure model; S102: Mark the location coordinates of the i-th historical user mobile terminal as (X i , Y i ), extract the basic information of the routing device scanned by the i-th historical user mobile terminal; the basic information of the routing device includes the name of the routing device and the signal strength of the routing device; the j-th routing device scanned by the i-th historical user mobile terminal is recorded as RD j , the scanned signal strength is recorded as SS (i,j) ; Calculate the distance between the historical user mobile terminal and the routing device based on the signal strength, denoted as S (i,j) ; According to the historical user mobile terminal location coordinates and the historical user mobile terminal and the distance between the routing device to form a terminal data pair, recorded as [RD j :(X i , Y i , S (i,j) )]; Extract all the RDs associated with the routing device j The relevant data pairs generate a terminal connection set, denoted as [RD j : (X1, Y1, S (1,j) ), (X2, Y2, S (2,j) ),…,(X I , Y I , S (I,j) )], i∈[1,I], where I represents the routing device RD scanned j The total number of historical user mobile terminals; j∈[1, J], where J represents the total number of routing devices; S103: randomly extract three data pairs from the connection set, and analyze the virtual position of the routing device using the triangulation method based on the three data pairs; group all virtual positions into a set, which is recorded as the virtual position set; construct a virtual polygon based on the virtual position set, and the edges and interior of the virtual polygon contain all virtual positions in the virtual position set, and mark the geometric center coordinates of the virtual polygon as the routing device RD j The location coordinates of S104: Repeat S102 and S103, analyze and calculate the location coordinates of all routing devices in the target house, and bind the location coordinates of the corresponding routing devices in the house structure model.

3. The network communication optimization method based on data analysis according to claim 2, characterized in that: In S2, the following contents are included: S201: extract the basic information of the routing device scanned by the real-time user mobile terminal at the same historical moment, calculate the distance between the real-time user mobile terminal and the routing device at the historical moment according to the signal strength in the basic information of the routing device scanned at the historical moment, and form a routing data pair, recorded as (RDN a , R.S. a ); where RDN a Indicates the name of the ath routing device scanned by the real-time user mobile terminal, RS a Indicates the routing device RDN a The distance to the real-time user mobile terminal; a∈[1, A], where A represents the total number of routing devices scanned by the real-time user mobile terminal at the same historical moment, A<J; S202: Arrange the routing data pairs generated by the routing devices scanned by the real-time user mobile terminal at the same historical moment in order from near to far distance to form a routing connection sequence, which is recorded as [(RDN1, RS1), (RDN2, RS2), …, (RDN A , R.S. A )]; S203: Compare the routing connection sequence of the real-time user mobile terminal with the historical routing connection sequence in the database, and search for the historical routing connection sequence with the same routing device name as that appearing in the routing connection sequence of the real-time user mobile terminal; calculate the correlation value between the routing connection sequence of the real-time user mobile terminal and the historical routing connection sequence with the same routing device name and sorting method; the database contains the location coordinates of the historical user mobile terminal and the historical routing connection sequence generated by the historical user mobile terminal at the location coordinates; the specific calculation formula of the correlation value CO is as follows: CO=∑\s\do 3(a=1)A [(RS a -RRS a )×exp(-RS a ÷∑\s\do 3(a=1)A RS a )]; RRS a Represents the routing device RDN in the historical routing connection sequence of the historical user mobile terminal a The distance from the historical user's mobile terminal; S204: extracting N historical user mobile terminals with the smallest correlation value with the real-time user mobile terminal, where N is a system preset constant; extracting the location coordinates of the N historical user mobile terminals, taking the location coordinates of the historical user mobile terminals as the center of the circle, and n ×r is the radius of the circle; CO n Represents the correlation value between the real-time user mobile terminal and the nth historical user mobile terminal, r gradually increases from zero until N circles intersect at one point, and the position coordinates of the intersection point are used as the position coordinates of the real-time user mobile terminal at the historical moment; extract and use the real-time user mobile terminal position coordinates within the time range T before the real-time moment to train the LSTM model, where T is a system preset constant; use the LSTM model to predict the position coordinates at the next moment.

4. The network communication optimization method based on data analysis according to claim 3 is characterized in that: In S3, include the following: S301: constructing a routing strength layout model according to the house structure model, the location coordinates of historical user mobile terminals in the database, and the historical routing connection sequence of historical user mobile terminals at the location coordinates; the routing strength layout model includes the location coordinates of each location point of the house and the signal strength of each routing device at the corresponding location coordinates; S302: According to the predicted location coordinates and the routing strength layout model, the signal strength corresponding to each routing device at the predicted location coordinates is obtained; and the routing idleness values ​​of the M routing devices closest to the predicted location are calculated: IL m ={α1×[(∑\s\do 3(m=1)M SS m )÷SS m ]}×(α2×BI m ); Among them, IL m represents the idleness value of the routing device closest to the predicted position m among the M routing devices; α1 and α2 represent idleness coefficients; the idleness coefficients are system preset constants; SS m Indicates the signal strength of the mth closest routing device to the predicted location among M routing devices; BI m Indicates the bandwidth idle rate of the mth closest routing device to the predicted position among M routing devices; m∈[1,M]; M is a system preset constant; The routing device with the largest routing idleness value is used as the best routing device for the real-time user mobile terminal, and the real-time user mobile terminal is connected to the best routing device.

5. The network communication optimization method based on data analysis according to claim 4 is characterized in that: In S4, the following are included: S401: extract the historical traffic usage of the d-th user mobile terminal connected to the best routing device, and build a traffic prediction model for the d-th user mobile terminal: TR d =b d 1×TT d +b d 2; where β d 1 and β d 2 represents the fitting coefficient, TT d The independent variable representing time, TR d represents the dependent variable of the unit time flow, and uses the least squares method to predict the β in the flow prediction model of the d-th user's mobile terminal. d 1 and β d 2. Perform calculations and solve; S402: The system presets a time length t, and calculates the total traffic of each user's mobile terminal within the time range of T0 to T0+t according to the traffic prediction model of each user's mobile terminal; T0 represents the current time; the total traffic of the dth user's mobile terminal within the time range of T0 to T0+t is recorded as TNTR d ; S403: Allocate bandwidth to each user's mobile terminal. The bandwidth calculation formula is as follows: BW d =[TNTR d ÷(∑\s\do 3(d=1)D TNTR d )]×ZBW×θ; Where BW d represents the bandwidth of the dth user mobile terminal, d∈[1,D]; D represents the total number of user mobile terminals connected to the optimal routing device; ZBW represents the total bandwidth of the optimal routing device; θ represents the control coefficient, which is a system preset constant.

6. A network communication optimization system based on data analysis, the system is applied to the network communication optimization method based on data analysis as described in any one of claims 1 to 5, characterized in that: The system includes a database, a routing layout analysis module, a user movement analysis module, a routing selection analysis module and a bandwidth allocation module; The database is used to store house structure data and system historical operation data; The routing layout analysis module is used to obtain the layout structure data of the house to build a house structure model, obtain the location coordinates of the historical user mobile terminal and the basic information of the scanned routing device, analyze the location coordinates of the routing device according to the location coordinates of the historical user mobile terminal, and bind the location coordinates of the corresponding routing device in the house structure model; The user movement analysis module is used to extract basic information of routing devices historically scanned by the real-time user mobile terminal, analyze the historical location information of the real-time user mobile terminal in combination with the house structure model; and predict the movement of the real-time user mobile terminal based on the historical location information of the real-time user mobile terminal; The routing selection analysis module is used to analyze the best routing device of the real-time user mobile terminal according to the movement prediction result of the real-time user mobile terminal, the house structure model and the routing device information; The bandwidth allocation module is used to obtain the historical traffic usage of the user mobile terminal connected to the best routing device, build a traffic prediction model for the user mobile terminal, predict the traffic for each user mobile terminal through the traffic prediction model, and allocate bandwidth to the user mobile terminal according to the prediction results.

7. The network communication optimization system based on data analysis according to claim 6, characterized in that: The routing layout analysis module includes a house structure model building unit and a device coordinate binding unit; The house structure model building unit is used to obtain the layout structure data of the target house and build the house structure model by using BIM technology; the layout structure data of the house includes the position coordinates of each corner of the house and the distribution of the walls inside the house; a plane coordinate system is established for the house ground in the house structure model; The device coordinate binding unit is used to analyze the location coordinates of all routing devices in the target house according to the location coordinates of the historical user mobile terminal and the basic information of the routing devices scanned by the historical user mobile terminal; and bind the location coordinates of the corresponding routing devices in the house structure model.

8. The network communication optimization system based on data analysis according to claim 6, characterized in that: The user motion analysis module includes a user mobile terminal association unit and a user motion model prediction unit; The user mobile terminal association unit is used to form a routing connection sequence according to the basic information of the routing device scanned by the real-time user mobile terminal at the same historical moment, search the database for a historical routing connection sequence with the same routing device name as that appearing in the routing connection sequence of the real-time user mobile terminal; and calculate the association degree; The user motion model prediction unit is used to extract N historical user mobile terminals with the smallest correlation value with the real-time user mobile terminal, analyze the position coordinates of the real-time user mobile terminal at historical moments, extract and use the real-time user mobile terminal position coordinates within a time range T before the real-time moment to train the LSTM model, where T is a system preset constant; and use the LSTM model to predict the position coordinates at the next moment.

9. The network communication optimization system based on data analysis according to claim 6, characterized in that: The routing selection analysis module includes a routing strength layout model building unit and a routing device selection unit; The strength layout model construction unit is used to construct a routing strength layout model according to the house structure model and the location coordinates of the historical user mobile terminal in the database and the historical routing connection sequence of the historical user mobile terminal at the location coordinates; the routing strength layout model includes the location coordinates of each location point of the house and the signal strength of each routing device at the corresponding location coordinates; The routing device selection unit is used to obtain the signal strength corresponding to each routing device of the predicted location coordinates according to the predicted location coordinates and the routing strength layout model; calculate the routing idleness values ​​of the M routing devices closest to the predicted location coordinates, use the routing device with the largest routing idleness value as the best routing device for the real-time user mobile terminal, and connect the real-time user mobile terminal to the best routing device.

10. The network communication optimization system based on data analysis according to claim 6, characterized in that: The bandwidth allocation module includes a traffic prediction model building unit and a bandwidth allocation unit; The traffic prediction model building unit is used to build a traffic prediction model for each user mobile terminal according to the historical traffic usage of each user mobile terminal connected to the optimal routing device; The bandwidth allocation unit is used to preset the system duration t, calculate the total flow of each user mobile terminal in the future time range according to the flow prediction model of each user mobile terminal, and allocate bandwidth according to the total flow of each user mobile terminal in the future time range.