KR20200119180A - A wireless terminal for providing dynamic changing connections to wireless networks based on quality expectations and a method for operating it - Google Patents

Abstract

According to an embodiment of the present invention, an operation method of a device for providing quality prediction information accessible to a plurality of wireless networks comprises the steps of: collecting variable information for each wireless network; obtaining quality prediction information for each accessible network according to quality prediction processing using the variable information; and providing the quality prediction information for each wireless network to a wireless terminal. The wireless terminal is a device for determining a first wireless network to transmit data among the plurality of wireless networks based on the quality prediction information for each network.

Description

A quality prediction information providing device that provides dynamic wireless network variable access based on quality prediction, and its operation method {A WIRELESS TERMINAL FOR PROVIDING DYNAMIC CHANGING CONNECTIONS TO WIRELESS NETWORKS BASED ON QUALITY EXPECTATIONS AND A METHOD FOR OPERATING IT}

The present invention relates to an apparatus for providing quality prediction information and an operating method thereof. More specifically, the present invention relates to an apparatus for providing quality prediction information for providing a dynamic wireless network variable access based on quality prediction and a method of operating the same.

With the rapid development of electronic and communication technologies, a service using a wireless network is developing into a communication service that transmits and receives data wirelessly, such as packet data.

Accordingly, the data usage of mobile terminals and the number of devices connected to the Internet are increasing exponentially, and the importance of the wireless Internet is becoming more and more prominent in the lives of modern people. If technologies such as VR, AR, IoT, and autonomous driving are actively commercialized with the advent of 5G mobile mobile communication and 6G Wi-Fi (802.11 ax, etc.) in the future, the dependence on the wireless network and expectations for the cost and quality of the network Will continue to increase.

With the increase in wireless Internet demand, wireless networks are provided in various forms, protocols, and communication methods. In particular, base station-based mobile communication networks and WIFI standard-based wireless networks based on AP (ACCESS POINT) Due to infrastructure investment in networks, wireless networks can now be used anywhere in the world.

However, due to the rapid increase in the use of wireless networks, in order to maintain or improve its quality, mobile carriers, etc., are investing excessive infrastructure construction costs to establish new communication networks, which leads to the cost burden of consumers. to be.

Accordingly, wireless network users are choosing and using a wireless network in consideration of cost burden. In particular, a WIFI standard network that has no cost or is cheaper than a high-cost wireless network based on a mobile communication network is intended to be used. However, in the case of a WIFI standard network, there is a problem in that the quality of the network cannot be stably maintained due to decentralized ownership and operation. For example, when connected to a WIFI AP with a weak signal or low performance, wireless Internet may not be used several times a day.

Due to this problem, the user directly observes the access speed of wireless networks, selects and uses the fastest and most cost-effective network, and sets to switch back to the mobile communication network when experiencing a decrease in speed.

However, this method has a problem in that the user cannot always use a fast and efficient network, so that the quality deterioration process is at least temporarily experienced, and the reconnection process and connection delay that occur when the network is switched causes a fast and seamless (SEAMLESS) wireless Internet. There is a problem that it is difficult to use and provide.

In addition, the quality of a wireless network should be determined not only by a simple speed, but also by various variables such as cost, responsiveness, and device performance, but currently, there is a limit in which the network can only be determined by only the signal strength, which is a primary variable experienced by the user.

The present invention was devised to solve the above-described problems, and a quality prediction model according to a network-specific setting variable corresponding to a plurality of accessible wireless networks is determined in advance, and quality prediction information for each network compared to an input variable based on this And a quality prediction information providing device that provides a dynamic wireless network variable access based on quality prediction that can minimize the access delay caused by network switching by allowing the user to always switch to the fastest and most efficient network by calculating Its purpose is to provide a method of operation.

The method according to an embodiment of the present invention for solving the above-described problems, in the method according to the embodiment of the present invention, in the operating method of the apparatus for providing quality prediction information accessible to a plurality of wireless networks, Collecting variable information; Obtaining quality prediction information for each accessible network according to quality prediction processing using the variable information; And providing the quality prediction information for each wireless network to a wireless terminal device, wherein the wireless terminal device comprises: a first wireless network to transmit the data packet among the plurality of wireless networks based on the quality prediction information for each network And wirelessly transmits the data packet to a target device using the determined first wireless network.

An apparatus according to an embodiment of the present invention for solving the above-described problems is an apparatus for providing quality prediction information accessible to a plurality of wireless networks, comprising: a variable information processing unit for collecting variable information for quality prediction for each wireless network; A quality prediction module that obtains quality prediction information for each accessible network according to a quality prediction process using the variable information; An information service providing unit that provides the quality prediction information for each wireless network to one or more wireless terminal devices, wherein the wireless terminal device transmits the data packet among the plurality of wireless networks based on the quality prediction information for each network. 1 It is a device that determines a wireless network and wirelessly transmits the data packet to a target device by using the determined first wireless network.

Meanwhile, the method according to an embodiment of the present invention for solving the above-described problems may be implemented with a program for executing the method on a computer and a recording medium in which the program is recorded.

According to an embodiment of the present invention, a quality prediction model according to a set variable for each network corresponding to a plurality of accessible wireless networks may be pre-determined, and based on this, quality prediction information for each network compared to a current input variable may be calculated. Dynamically variable access of wireless networks can be provided by pre-predicting the quality degradation for each network through a process based on various variables.

Accordingly, according to an embodiment of the present invention, it is possible to enable a fast network switch before the user experiences an actual quality deterioration, and minimize an access delay caused by the network switch.

1 is a conceptual diagram schematically showing an entire system according to an embodiment of the present invention.
2 is a block diagram showing in more detail a wireless terminal device according to an embodiment of the present invention.
3 and 4 are flowcharts illustrating a method of operating a wireless terminal device according to an embodiment of the present invention.
5 is a conceptual diagram schematically illustrating a system based on an apparatus for providing quality prediction information according to an embodiment of the present invention.
6 is a block diagram specifically showing an apparatus for providing quality prediction information according to an embodiment of the present invention.
7 is a flowchart illustrating an operation of an apparatus for providing quality prediction information according to an embodiment of the present invention.
8 is a block diagram illustrating a learning-based quality prediction module according to an embodiment of the present invention in more detail.
9 to 10 are diagrams for explaining a data merging and sharing process of a learning-based quality prediction model according to an embodiment of the present invention.

The following content merely illustrates the principles of the present invention. Therefore, those skilled in the art can implement the principles of the present invention and invent various devices included in the concept and scope of the present invention, although not clearly described or illustrated herein. In addition, it is understood that all conditional terms and examples listed in this specification are, in principle, expressly intended only for the purpose of making the concept of the present invention understood, and are not limited to the embodiments and states specifically listed as such. Should be.

In addition, it is to be understood that all detailed descriptions listing specific embodiments as well as principles, aspects and embodiments of the present invention are intended to include structural and functional equivalents of these matters. It should also be understood that these equivalents include not only currently known equivalents, but also equivalents to be developed in the future, that is, all devices invented to perform the same function regardless of structure.

Thus, for example, the block diagrams herein are to be understood as representing a conceptual perspective of exemplary circuits embodying the principles of the invention. Similarly, all flowcharts, state transition diagrams, pseudocodes, etc. are understood to represent various processes performed by a computer or processor, whether or not the computer or processor is clearly depicted and that can be represented substantially in a computer-readable medium. Should be.

In addition, the explicit use of terms presented as processor, control, or similar concepts should not be interpreted exclusively by referring to hardware capable of executing software, and without limitation, digital signal processor (DSP) hardware, ROM for storing software. It should be understood to implicitly include (ROM), RAM, and non-volatile memory. Other commonly used hardware may also be included.

The above-described objects, features, and advantages will become more apparent through the following detailed description in connection with the accompanying drawings, whereby those of ordinary skill in the technical field to which the present invention pertains can easily implement the technical idea of the present invention. There will be. In addition, in describing the present invention, when it is determined that a detailed description of a known technology related to the present invention may unnecessarily obscure the subject matter of the present invention, a detailed description thereof will be omitted.

Hereinafter, a preferred embodiment according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram schematically showing an entire system according to an embodiment of the present invention.

Referring to FIG. 1, a system according to an embodiment of the present invention includes a quality prediction module 200, a wireless terminal device 100, and a connection target device 300, and a wireless terminal device 100 and a connection target device 300 may be configured to be connectable through one or more wireless networks among a plurality of wireless networks 200a, 200b, ... 200n.

First, each wireless network includes a local area network (LAN), a wide area network (WAN), a value added network (VAN), a personal area network (PAN), and a mobile communication network. Mobile radiocommunication network) or a satellite communication network may be implemented as various types of wireless networks, and each base station or access point (AP) device for providing the same may be provided in a remote location.

In particular, in order to provide a local area communication network, the wireless network may include a WIFI wireless network based on a WIFI standard, and each access point may broadcast device information for operating a Wi-Fi service coverage.

Meanwhile, the wireless terminal device 100 may be a wireless terminal device of a user who requests transmission and reception of a wireless data packet by determining a first wireless network 200a to be connected to the access target device 300 among wireless networks. Here, the wireless terminal device 100 may be implemented as various devices such as a smart phone, a tablet computer, a notebook computer, a personal digital assistant (PDA), a portable multimedia player (PMP), and smart glasses.

In addition, according to an embodiment of the present invention, the wireless terminal device 100 may collect and transmit a quality model setting variable for each wireless network to the quality prediction module 200, and the quality prediction module 200 Accordingly, a quality prediction model for each wireless network may be determined in advance.

Here, the quality prediction module 200 may obtain a model setting variable and determine a quality prediction learning model that learns and calculates relationship information between various variables, and the learning process is a supervised or non-supervised artificial neural network training process, regression analysis Learning, deep learning analysis, and the like can be exemplified. In addition, the learning model may be a model that is trained and built in advance, is determined according to variable information collected in real time, or is continuously trained and updated by using the variable information in a pre-built learning model. This will be described in more detail later.

In another embodiment, the quality prediction module 200 may obtain a model setting variable and determine a quality prediction model in the form of a function using various variables as input values. The applied function of the corresponding quality prediction model may be a linear function, a logarithmic function, and the like, which will be described in more detail later.

Here, each of the variables may be diversified into physical variable information, constant element information, variable element information, etc. for each communication section for quality prediction.

In addition, the wireless terminal device 100 collects the model input variable of the wireless terminal device 100 in response to the data packet to be transmitted wirelessly, and applies the model input variable to a quality prediction model for each wireless network, Obtains quality prediction information, determines a first wireless network 200a to transmit the data packet from among the plurality of wireless networks based on the quality prediction information for each network, and uses the determined first wireless network May be wirelessly transmitted to the connection target device 300.

Accordingly, the wireless terminal device 100 can more accurately predict in advance the quality deterioration due to changes in model input variables such as network speed and signal strength through a quality prediction model according to preset model setting variables. As a result, it is possible to change the network quickly and efficiently while minimizing the experience of quality deterioration of the user through dynamic variable control of the wireless network.

2 is a block diagram showing in more detail a wireless terminal device according to an embodiment of the present invention.

Referring to FIG. 2, a wireless terminal device 100 according to an embodiment of the present invention includes a control unit 110, a communication unit 120, a model setting variable processing unit 130, a model input variable processing unit 140, and a network determination unit. 150, a quality prediction module 200, a database 160, and a user setting unit 170.

The controller 110 overall controls the operation of each component of the wireless terminal device 100 and execution of functions. For example, the control unit 110 may be implemented as a processor for controlling all or part of the acquisition of packet data to be transmitted, processing of model setting variables, processing of model input variables, network determination, and user setting functions, or a program for executing the same. have.

In addition, all or part of the functions of the control unit 110 may be implemented as a software module installed in the wireless terminal device 100, and the software module operates in an application layer to perform network variable control through network socket binding control, or Alternatively, it is possible to perform network variable control that operates in the OS layer to drive the network interface.

Further, the communication unit 120 connects to the wireless networks 200a, 200b, ... 200n under the control of the control unit 110, or connects to a wired network to connect to/from the network where the connection target device 300 is located. It may include one or more communication modules that enable wireless data packet communication.

In particular, the communication unit 120 may include a wireless Internet module for accessing at least one of the wireless networks 200a, 200b, ... 200n and a wireless Internet protocol, and the wireless Internet module is a WLAN (Wireless LAN) ( Wi-Fi), Wireless broadband (Wibro), World Interoperability for Microwave Access (Wimax), and a network module based on a High Speed Downlink Packet Access (HSDPA) scheme may be exemplified.

In addition, the communication unit 120 may include a short-range communication module for connecting to at least one of the wireless networks 200a, 200b, ... 200n and short-range communication through a short-range communication protocol, and short-range communication technology Examples of examples include Bluetooth, Radio Frequency Identification (RFID), infrared data association (IrDA), Ultra Wideband (UWB), ZigBee, and the like.

On the other hand, the communication unit 120 may include a mobile communication module for mobile communication access to at least one of the wireless networks (200a, 200b, ... 200n) and a mobile communication protocol, for this purpose, a base station on a mobile communication network, an external It is possible to transmit and receive a wireless signal with at least one of the terminal, the connection target device or the server The wireless signal may include a voice call signal, a video call signal, or various types of data according to transmission/reception of text/multimedia messages.

Further, the communication unit 120 can selectively variably control a communication module for wirelessly transmitting data packets under the control of the control unit 110, which is based on the quality prediction information for each network analyzed by the quality prediction module 200. Can be determined accordingly.

To determine the quality prediction information for each network, the quality prediction module 200 collects the model setting variables obtained from the model setting variable processing unit 130, and determines a quality prediction model for each wireless network based on the collected model setting variables. , Can be stored in the database 160.

In addition, the quality prediction module 200 may calculate quality prediction information for each wireless network by collecting model input variables obtained from the model input variable processing unit 140 and applying the collected model input variables to the determined quality prediction model. have. The quality prediction model to which the model input variable is applied may be stored in the database 160.

In one embodiment, the quality prediction module 200 collects the frequency band of the wireless network as a model setting variable, determines a network quality relational expression compared to the signal strength (RSSI) for the corresponding frequency band as an application function of the quality prediction model, , Signal strength can be used as a model input variable to predict the quality of the wireless network. Here, the relationship between signal strength and network quality may include a linear function, a logarithmic function, a sigmoid function, and an arctan function.

In another embodiment, the quality prediction module 200 may use a frequency band of a wireless network as a model setting variable, and determine a network quality relational expression versus signal strength for a corresponding frequency band as a quality prediction learning model. In addition, the relationship learning operation can be performed by using the signal strength and network quality, which are the input and output values of the relational expression as model input variables, as data for regression analysis learning on the relational expression, and learn the signal strength, which is a part of the model input variable. The quality of the wireless network can be predicted by using it as an input value of the relational expression.

Here, the model setting variable processing unit 130 and the model input variable processing unit 140 may collect, refine, and transmit various variables for quality prediction for each wireless network in the quality prediction module 200, which is a quality prediction module. It may be determined differently according to the learning process of 200 or the form of the applied function. As the learning process, artificial intelligence or artificial neural network learning can be exemplified, and variable setting and learning model configuration for this are important.

In addition, the quality prediction module 200 can collect and process model settings and input variables from internal information of the wireless terminal device 100, as well as a data set received from an external device at a remote location as a variable. By collecting and processing data or collecting and processing data input from users as variables, a quality prediction model for each wireless network is generated from variables collected and processed through various routes, and various input variables corresponding to the generated models and situations are generated. You can handle it.

Here, the model setting variable and the model input variable according to an embodiment of the present invention may be composed of basic variable information obtained primarily or variables that can be refined and obtained from the basic variable information, and the determination process of the prediction model W, the learning model generation method and type, the type and type of the applied function, application timing, application target, required output value, etc. can be determined independently and differently from each other.

Such variable information may include, for example, a constant element and a variable element, and the constant element and the variable element may be used as part or all of a model setting variable and a model input variable.

Here, the constant factor is a factor in which the degree of influence on the quality of the wireless communication network is invariant, and the wire cable performance information, the hardware performance information of the AP, and the communication protocol corresponding to the wireless section between the AP and the wireless terminal device (e.g., WIFI network In the case of, standard-based protocols such as 802.11n, 802.11ac, or encryption protocols such as OPEN, WEP, WPA2, and standard-based protocols such as GSM, LTE-A, and LTE for mobile communication networks), frequency band and channel information of the AP , The number of neighboring APs, and the like may be exemplified.

In addition, the variable factor is a factor in which the degree of influence on the quality of the wireless communication network is continuously variable. For example, difference information between the IP of the access target device and the IP of the AP, information on the number of AP access devices, and signal strength (RSSI) ) Information, frequency congestion information, TCP socket destination IP information, RTT information, window size information, transmission/reception data amount, time (TIME) information, time zone information, terminal movement pattern information, etc. Herein, the AP (Access Point) ) May mean a wireless network access point such as a WIFI router or a base station.

Accordingly, the quality prediction module 200 determines a quality prediction model for each wireless network by using the constant element as a quality model setting variable, and generates a quality prediction learning model or a relationship function between the variable element information and the quality information. I can.

In addition, the variable information may be classified and identified in various additional ways, and may be selectively determined according to the type and characteristic of the quality prediction model.

For example, the variable information may include variable information for each communication section. The variable information for each communication section is a physical variable corresponding to at least one of a wired section between a target device and an AP (Access Point) access point, an AP internal section, a wireless section between the AP and a wireless terminal device, and a wireless terminal device internal section. May contain information. Here, the AP access point may mean a wireless network access point such as a WIFI router or a base station.

More specifically, the physical variable information may include wired cable performance information corresponding to a wired section between the connection target device and the AP access point, and difference information between the IP of the connected device and the IP of the AP.

In addition, the physical variable information may include AP hardware capability information and number of connected devices corresponding to the AP internal section.

In addition, it may include at least one of protocol information, signal strength information, frequency band information, and channel/frequency congestion information corresponding to a radio section between the AP and the wireless terminal device.

Here, the protocol information may include a communication protocol, for example, in the case of a WIFI network, a protocol based on 802.11n and 802.11ac standards, and in the case of a mobile communication network, a standard-based protocol such as GSM, LTE-A, and LTE. This can be illustrated.

In addition, since the protocol information may include an encryption protocol, in the case of WIFI, an encryption protocol such as open type, WEP, and WPA2 may be exemplified.

Meanwhile, the constant element and the variable element may include at least one of radio module performance information, radio module characteristic information, and temperature information corresponding to an internal section of the radio terminal device 100, and the model setting variable processing unit 130 And the model input variable processing unit 140 may process the data request and purification process for generating these variables to the control unit 110, the control unit 110 from the process information and sensor data being processed, the requested variable Information may be obtained and provided to the model setting variable processing unit 130 and the model input variable processing unit 140.

In addition, the model input variable processing unit 140 may collect and refine the primary variables transmitted from the wireless terminal device 100 and the communication unit 120 to obtain frequency congestion as basic variable information.

For example, the basic variable information may include the degree of isotropy (effective aperture) of the antenna of the communication unit 120, the inherent gain of the antenna of the wireless terminal device 100 and the AP, and congestion of physical obstacles and surrounding frequencies. In addition, each variable may have a relational expression with the power intensity (milliWatt) of the radio wave emitted from a specific WIFI AP as shown in Equation 1 below.

Here, P _Transmitted is AP-specific emission power information, and may be different according to the AP protocol, spatial trim, modulation, and coding rate. In addition, G _{Antenna gain1} represents the antenna gain information specific to the AP, A _Effective represents the antenna's inherent effective aperture or isotropic degree of the wireless terminal device 100, and α represents a physical obstacle existing in the radio path or a peripheral frequency congestion. It can indicate the degree to be reduced by.

Here, A _Effective can be obtained through polarization of radio waves, the law of thermodynamics, Rayleigh-Jeans Formula, and Johnson-Nyquist noise calculations. ) Received power can be calculated by arithmetic processing.

)를 취하여 데시벨 밀리와트(decibel milliwatt, dBm)로 단위를 변경하면 상기 수학식 2는 아래와 같은 식으로 정리된다.Here, G _{Antenna gain2} denotes antenna gain information specific to a terminal of the wireless terminal device 100. And, milliWatt unit is log (10*

) And changing the unit to decibel milliwatt (dBm), Equation 2 is summarized as follows.

와

는 AP와 무선 단말 장치(100)의 안테나 고유 특성 정보이며, 파장

는

로 연산되므로, 주파수의 값으로부터 획득될 있다.

는 단말기와 해당 AP 사이 거리에 따라 변하는 값이며

는 경로상 존재하는 물리적 장애물 혹은 주변 주파수 혼잡 등으로 인해 감소되는 감소율에 대한 로그값이다.here,

Wow

Is antenna-specific characteristic information of the AP and the wireless terminal device 100, and

Is

Since it is calculated as, it can be obtained from the value of the frequency.

Is a value that changes according to the distance between the terminal and the AP

Is a logarithmic value of the reduction rate reduced due to physical obstacles or congestion of surrounding frequencies in the path.

값을 예측할 수 있으며, 이에 따라, 특정 AP와 단말기 간의 RSSI 정보로부터 상기 수학식 3의 해를 연산하면, 주파수 혼잡도인

을 유추 획득할 수 있다. 이에 따라, 모델 입력 변수 처리부(140)는 AP의 MCS(Modulation Coding Scheme) 인덱스에 대응하여 AP의 발산 파워 세기 정보로부터 산출되는 주파수 혼잡도 정보를 모델 입력 변수로 수집 및 정제할 수 있다.For example, the model input variable processing unit 140 from the MCS (Modulation Coding Scheme) Index to obtain variable information

The value can be predicted, and accordingly, when the solution of Equation 3 is calculated from the RSSI information between a specific AP and the terminal, the frequency congestion is

Can be obtained by analogy. Accordingly, the model input variable processing unit 140 may collect and refine the frequency congestion information calculated from the radiated power intensity information of the AP as a model input variable in response to the Modulation Coding Scheme (MCS) index of the AP.

In addition, the model setting variable processing unit 130 and the model input variable processing unit 140 collect the frequency band, Modulation Coding Scheme (MCS) Index, Bandwidth, and Guard Interval values as variable information as unique characteristic information for each AP. The minimum signal strength and maximum speed may be inferred, and the quality prediction module 200 may obtain quality prediction information for each wireless network by using the corresponding value as a model setting variable or a model input variable.

Meanwhile, the model input variable processing unit 140 may perform refinement processing from variable information processed through the communication unit 120 to collect RTT, window size, and transmission/reception data amount information of a TCP socket, and a quality prediction module 200 ) Calculates the quality prediction information for each network refined from the processed variable information of the communication unit 120 as a model input variable, and processes the training of a quality prediction model for each wireless network corresponding thereto.

For example, in TCP communication, the maximum throughput of a current socket may be defined in the form of a transmission packet (Packets in Flight), which is as follows.

The number of data sockets used by the communication unit 120 may be plural, and the speed at a specific time may be calculated as the sum or average of the maximum throughput of each socket. Accordingly, the model input variable processing unit 140 calculates the output information for each network as a model input variable through an average operation or a harmonic average operation in which a weight is applied to the amount of output information and transmission/reception data or other elements, and It can process the training of the quality prediction model for each network. Here, the weight may be processed as a separate function, and the weight value may also be used as a decay function-processed value that decays over time.

In addition, the variable information may include speed information at a specific point in time, and the speed information at a specific point in time is limited to the maximum link speed between the AP and the wireless terminal device 100 at the point in time. 130) or the model input variable processing unit 140.

For example, in Equation 5 below, in the model setting variable processing unit 130 or the model input variable processing unit 140, data-weighted average calculation processing of speed information for a specific signal strength (RSSI), but maximum connection This is an example of output when the calculation is processed to be limited to the link speed.

으로 정의될 수 있다.here,

Can be defined as

Accordingly, the quality prediction module 200 may process the learning of a learning model predicting speed quality versus signal strength by using the signal strength (RSSI) and speed collected from the model input variable processor 140 as model input variables. . As the learning process, a linear regression or logistic regression operation may be exemplified.

Accordingly, the quality prediction module 200 may construct a quality prediction model of a corresponding WIFI network for a specific signal strength (RSSI) and provide prediction information corresponding thereto.

Meanwhile, the quality prediction module 200 processes a Decay function based on the velocity samples of the last n data collected in real time through the model input variable processing unit 140 to predict the quality of the mobile communication network. A quality prediction learning model corresponding to the mobile communication network may be generated by acquiring an average value and performing regression learning on performance information corresponding to the moving average value corresponding thereto.

Here, the decay function may be a process such as an exponential moving average, and the quality prediction module 200 assigns a weight to the latest data sample and only a random number of samples Using this, a quality prediction learning model for predicting the quality of a mobile communication network can be generated. Here, the decay function process may include not only an exponential moving average, but also a simple moving average, a cumulative moving average, a weighted moving average, or various processes including the same. .

For example, in the case of an exponential moving average, the quality prediction module 200 calculates the maximum throughput calculated from the RTT, window size, and transmission/reception data amount of the TCP socket processed by the communication unit 120 through the model input variable processing unit 140. By using it as an input value, it is possible to generate a quality prediction learning model corresponding to a mobile communication network by performing regression learning processing of a function for a speed at a specific point in time.

where

의 근사치는 아래 수학식 8과 같이 정의할 수 있다.Here, if the Exponential Moving Average is calculated using the last N random number, the coefficient

The approximate value of can be defined as in Equation 8 below.

Meanwhile, as described above, the quality prediction module 200 according to an embodiment of the present invention may predict network quality through a quality prediction model based on an applied function or a quality prediction model based on learning. The shape of the quality prediction model, the shape and type of the applied function, the type of the learning process, etc. may differ according to the model setting variables.

When the quality prediction module 200 uses a quality prediction model based on an applied function, the applied function of the quality prediction model is a linear function based on frequency band and variable information, a linear function based on link speed and variable information, and based on the first frequency band. A log function, a second frequency band-based linear function, and the like may be exemplified.

For example, the applied function of the quality prediction model may include a linear function based on frequency band information and variable information. The frequency band information may be different for each network, such as 5GHz, 2,4GHz, etc., as defined in the WIFI standard. Accordingly, the quality prediction module 200 according to an embodiment of the present invention may determine, as the application function, a linear function for differently determining a variable limitation range according to frequency band information.

For example, the applied function may be a linear function in the form of α + β x RSSI, which represents a speed relation with respect to signal strength (RSSI) and uses constants α and β as variables, and forms different slopes for each frequency band. In order to be able to do so, the range of the minimum and maximum values of β may be differently limited according to the frequency band.

For example, the minimum and maximum value ranges of β may be set wider as the frequency band increases. In the case of the 5 GHz band, the minimum and maximum value ranges of β may be set higher than in the case of 2 GHz.

Also, for example, the quality prediction function may be determined as a linear function based on link speed and variable information. The link speed information may be used to limit the maximum value of a linear function of α + β x RSSI (signal strength) representing the above-described signal strength (RSSI) versus speed relationship.

Accordingly, the quality prediction module 200 according to an embodiment of the present invention may determine a linear function limiting the maximum value of the quality prediction result according to the link speed information as an application function of the quality prediction model.

And, for example, the applied function of the quality prediction model may be determined as a frequency band adaptive function that is selectively determined from a first frequency band-based log function and a second frequency band-based linear function. For example, in the case of a 5GHz band, a signal strength may be weaker than that of 2.4GHz and a speed quality may be rapidly degraded. Accordingly, the application function is a selective adaptive processing function that processes a logarithmic function corresponding to the first frequency band (5 GHz) and a linear function corresponding to the second frequency band (2.4 GHz). Can include.

Meanwhile, the constants α and β of the speed relational expression relative to the signal strength (RSSI) are exemplary values, and may be changed and set according to the type and shape of the acquisition variable.

When the quality prediction model 200 uses a quality prediction model based on learning, an artificial intelligence algorithm may be used as a learning process for generating a quality learning model for each network. Examples of artificial intelligence algorithms include an artificial neural network method in the form of supervised learning such as Logistic or Logarithmic Regression or Multilayer Perceptron (MLP), Support Vector Machine, Bayesian Networks, and Genetic Algorithm. I can.

In addition, an unsupervised learning method such as Dictionary Learning, Independent Component Analysis, Autoencoders, or various types of clustering may be used, and an analysis process such as Decision Trees and Anomaly Detection may be used.

In addition, the quality prediction module 200 may use a Reinforcement Learning algorithm using data collected in real time from each user as a model input variable.

In the case of regression, methods such as Projection, Maximum Likelihood, Generalized Methods of Moments including Ordinary Least Squares method may be exemplified.In the above-described Supervised, Unsupervised, and Reinforcement processing, the least squares method and the gradient descent method Through regression model, backpropagation method, deep learning, entropy minimization process, etc. may be included.

More specifically, the supervised learning and unsupervised learning processes of the quality prediction module 200 may be determined according to a value to be predicted, and quality prediction information, which is a performance index of a wireless network to be predicted, may be output in various forms. As the classification value based on speed, the amount of data available per hour (Mbps, Gbps, etc.), latency, throughput, bandwidth, etc. can be exemplified, and as classification criteria classification values, Good, Normal, Bad, etc. This can be illustrated.

For example, as supervised learning to predict the performance of a specific AP with a specific index (e.g., speed), a classification method can be used, and the performance of a specific access point can be determined by specific criteria (e.g., Good, Normal, Bad) can be exemplified.

Here, Classification is a supervised learning algorithm that classifies output into specific classes for specific inputs, such as Logistic Regression, Naive Bayes, Stochastic Gradient Descent, K-Nearest Neighbors, Decision Tree, Random Forest, Support Vector Machine, etc. This can be illustrated.

Accordingly, the quality prediction module 200 substitutes the model setting variable and the model input variable into the supervised learning model, so that various APs (e.g., Wi-Fi AP1, Wi-Fi AP2, LTE Cell Site, 5G Cell Site, etc.) ) Can be judged.

In addition, as a non-supervised learning for predicting the quality of a specific AP with a specific index (e.g., speed), clustering can be used, and the quality of a specific access point is classified and classified into clustered random criteria. The way to do it can be illustrated.

Accordingly, the quality prediction module 200 substitutes the model setting variable and the model input variable into the non-supervised learning model, and thus various APs (e.g., Wi-Fi AP1, Wi-Fi AP2, LTE Cell Site, 5G Cell A learning model that can output the result of determining which AP to use among sites, etc.) can be created.

Here, clustering is an unsupervised learning algorithm that divides the output into specific classes for specific inputs.K-means, Fuzzy K-means, Hierarchical clustering, Mixture of Gaussians, Mean-Shift Clustering, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), etc. may be exemplified.

Here, the quality prediction module 200 learns using some or all of the model input variables, applies some or all of the model input variables to the input layer of the quality prediction model, and predicts corresponding performance information for each network, The predicted performance information can be output.

Meanwhile, the network determination unit 150 compares the quality prediction information for each network according to preset user preference information or mode setting information, and transmits the optimal network according to the comparison result to a first wireless network to transmit a data packet. You can decide.

More specifically, the network determination unit 150 may determine a wireless network interface to be driven by the communication unit 120 or a network to which a socket generated for data packet transmission is bound according to a result of the comparison determination.

In addition, the network determiner 150 may compare and determine a network to be used based on at least one of quality information for each network, user preference information for speed and cost, and user setting mode information. The comparison determination process may be determined according to either a static determination or a learning determination.

The static determination method is determined, for example, according to variable comparison, and determination according to the user's speed and quality preference setting may be exemplified.

For example, when the user prefers speed, the network determination unit 150 may determine a network having a high quality variable, and when the user prefers cost, determine a WIFI network having a quality higher than a certain standard as the first network. However, if such a network does not exist, it can be processed to determine a mobile communication network. In addition, when quality and preference information is insufficient, the network determination unit 150 may set a plurality of sockets, bind to each connectable network, and determine a socket from which the first response comes earlier as the first network.

In addition, the network determination unit 150 may determine the user preference based on the learning determination, and the network determination unit 150 compensates for negative compensation such as a Wi-Fi Off behavior from a user input and a manual connection to another Wi-Fi ( Behaviors defined as Negative Reward) are learned as an indicator that the user does not prefer a specific network, and the learned user preference information may be used to determine the above-described first network.

In addition, the determination of the first wireless network by the network determination unit 150 may be periodically processed according to a certain time or may be processed at a specific time according to a certain condition in which quality deterioration of the current network is predicted. Through the processing, fast and real-time network change processing is possible. In addition, the communication unit 120 uses the determined first wireless network according to the decision of the network determination unit 150 to transmit the data packet to the access target device 300 Can be transmitted wirelessly.

For such processing, the communication unit 120 can process network control, and processes data transmission through the first wireless network in a manner that directly connects a specific network with hardware or controls the network layer by an application. can do.

In addition, the communication unit 120 may perform rapid termination processing of an existing connected wireless network, or may perform a rapid change or switch processing from the existing connected wireless network to the first wireless network. In addition, the communication unit 120 may process so that only the new connection to the determined first wireless network and data transmission/reception are performed while maintaining the connection of the existing network.

For example, in the case of an application method, the communication unit 120 may process data transmission through the first wireless network by creating a socket and binding to a specific network interface. In addition, the communication unit 120 may generate a plurality of identical sockets and bind them to a plurality of network interfaces, so that one or more Wi-Fi wireless communication networks and one or more cellular wireless communication networks can be used simultaneously.

In addition, the controller 110 may control the communication unit 120 to more quickly process the termination of communication through the existing network and the start of communication of the determined first wireless network. For example, if the existing wireless network is simply deactivated and the first wireless network is activated by a conventional network change process using the prior art, the termination of the socket through the existing wireless network is not immediately processed, and the termination can be confirmed. There is a problem of delaying the switching time.

Accordingly, according to an embodiment of the present invention, the control unit 110 cancels the connection with the existing wireless network through the communication unit 120 to collectively terminate the sockets through the existing wireless network, and the first wireless network You can activate the connection with. When sockets linked to the existing wireless network are collectively terminated, the currently running wireless network-related applications recognize or detect it and regenerate the sockets required to drive the application, so that the application that performed socket communication through the existing wireless network They can quickly resume communication over the first wireless network.

In addition, as described above, the control unit 110 may process a new connection to the first wireless network while being connected to the existing wireless network. In this case, the control unit 110 releases the connection to a separate existing network. Without it, a communication socket through the first wireless network may be created and packets to be transmitted may be retransmitted. For example, the controller 110 connects to another second WIFI network of high quality without disconnecting from the first WIFI while being connected to the first WIFI network, or performs packet transmission through an existing connected mobile communication network. , You can perform the opposite process.

In another embodiment, the controller 110 may directly terminate the socket through the existing wireless network through the communication unit 120 or transmit a reset signal to induce a socket reboot of the application.

For example, the control unit 110 recognizes that applications running on the wireless terminal device 100 require socket reboot by constructing an RST Flag data packet corresponding to a TCP socket and transmitting it to a socket through an existing wireless network, It can be induced to create a socket over the first wireless network to be switched.

In addition, the control unit 110 may temporarily store a data packet requested to be written before termination of the first wireless network connection in the socket through the existing wireless network, and retransmit the stored packet through the switched first wireless network. I can. For example, when a UDP DNS request packet or the like is temporarily stored and a response is not received, the communication unit 120 may be controlled to be retransmitted to a socket newly connected through the first network.

Here, the switched first wireless network is a network different from the existing wireless network, and any type of network may be determined as the first wireless network. Accordingly, the communication protocol of the first wireless network may be the same as or different from the existing wireless network.

Meanwhile, the user setting unit 170 can set a user mode for network switching, and thus mode information may be transmitted to the network determination unit 150 and used as a variable for determining the first network.

For example, the user mode may be any one of a speed mode, a balanced mode, or a cost mode.

The fast mode may be set when a terminal user who has no limit on the use of mobile communication data uses a short-range wireless communication network to amplify the speed. In this case, the user setting unit 170 may set a mobile communication network and a short-range wireless communication network to be mixed, thereby providing a faster speed and quality than a case of using a single wireless communication network.

The balance mode may be a setting in which a terminal user having a limitation in using mobile communication data uses a short-range wireless communication network to amplify speed, but preferentially uses a short-range wireless communication network based on a certain speed or quality. The user setting unit 170 is used only when the speed of the short-range wireless communication network is greater than or equal to the first speed, and when the speed is less than or equal to the first speed, the user setting unit 170 sets the mobile communication network to be mixed and provides the optimum speed and quality according to the situation. can do.

On the other hand, the price mode is a case in which a user with limited mobile communication data use uses a short-range wireless communication network as much as possible to save data, and the user setting unit 170 is a second speed that interferes with Internet use. Connection to the mobile communication network can be made only in the following cases.

3 and 4 are flowcharts illustrating a method of operating a wireless terminal device according to an embodiment of the present invention.

Referring to FIG. 3, first, the wireless terminal device 100 collects a wireless network quality model setting variable through the model setting variable processing unit 130 (S101).

Then, the wireless terminal device 100 performs refinement processing corresponding to the wireless network quality model setting variable through the model setting variable processing unit 130 (S102). Then, the wireless terminal device 100 determines a quality prediction model for each wireless network based on the model setting variable through the quality prediction module 200 (S103).

Thereafter, the wireless terminal device 100 collects and refines the model input variables of the wireless terminal device 100 through the model input variable processing unit 140 (S105).

Then, the wireless terminal device 100 acquires quality prediction information for each accessible network according to the application of the quality prediction model of the model input variable through the quality prediction module 200 (S107).

Thereafter, the wireless terminal device 100 determines an optimal wireless network according to the user mode or preference setting of the wireless terminal through the network determination unit 150 (S109), and the control unit 110 determines data using the determined wireless network. Prepare for packet transmission (S111).

Then, the communication unit 120 transmits the data packet through the determined wireless network (S113).

Here, FIG. 4 is for describing a socket-based wireless network transmission process of the wireless terminal device 100 in more detail, and the controller 110 creates a socket for transmitting a wireless data packet (S151).

Then, the network determination unit 150 compares the network quality prediction information and user preference information that is statically determined or formed by learning, item by item, and determines one or more wireless networks (S153).

Here, the user preference information may be determined by the above-described user mode setting information, and a plurality of wireless networks may be determined.

Thereafter, the communication unit 120 binds and connects the generated socket to a network interface corresponding to the determined wireless network (S155).

Accordingly, the communication unit 120 may wirelessly transmit the data packet through the connected socket (S157).

5 is a conceptual diagram schematically showing a system based on an apparatus for providing quality prediction information according to another embodiment of the present invention, and FIG. 6 is a block diagram showing in detail an apparatus for providing quality prediction information according to an embodiment of the present invention.

5 and 6 illustrate a system in which the apparatus 400 for providing quality prediction information is configured as a separate device at a remote location. Referring to FIG. 5 first, a system according to another embodiment of the present invention includes a quality prediction module ( 200) including a quality prediction information providing device 400, a wireless terminal device 100, and a connection target device 300, and the wireless terminal device 100 and the connection target device 300 include a plurality of wireless networks ( 200a, 200b, ... 200n) may be configured to be connected through one or more wireless networks, and the apparatus 400 for providing quality prediction information includes a plurality of wireless networks 200a, 200b, ... 200n, respectively Can be connected. Also, the apparatus 400 for providing quality prediction information may provide a separate wired network connection.

Here, each of the wired/wireless networks that can be accessed is a local area network (LAN), a wide area network (WAN), a value added network (VAN), and a personal area network (PAN). ), a mobile radiocommunication network, a satellite communication network, and the like, and each base station or access point (AP) device for providing the same may be provided in a remote location.

In particular, in order to provide a local area communication network, the wireless network may include a WIFI wireless network based on a WIFI standard, and each access point may broadcast device information for operating a Wi-Fi service coverage.

Meanwhile, the wireless terminal device 100 may be a wireless terminal device of a user who requests transmission/reception of a wireless data packet by determining a first wireless network 200a to be connected to the access target device 300 among wireless networks. Here, the wireless terminal device 100 may be implemented as various devices such as a smart phone, a tablet computer, a notebook computer, a personal digital assistant (PDA), a portable multimedia player (PMP), and smart glasses.

In addition, according to an embodiment of the present invention, the apparatus 400 for providing quality prediction information may process a quality model setting variable for each wireless network and transmit it to the quality prediction module 200, and the quality prediction module 200 sets the model. Depending on the variable, the quality prediction model for each wireless network may be determined.

Here, the quality prediction module 200 may collect various variables for determining a quality prediction model, and each variable may be diversified into physical variable information, constant element information, variable element information, etc. for each communication section for quality prediction. have.

In addition, the wireless terminal device 100 determines a model input variable of the wireless terminal device 100 in response to a data packet to be transmitted wirelessly, and determines the model input variable for each wireless network provided from the quality prediction information providing device 400. Applying to a quality prediction model, obtains quality prediction information for each accessible network, and determines a first wireless network 200a to transmit the data packet among the plurality of wireless networks based on the quality prediction information for each network, and the The data packet may be wirelessly transmitted to the access target device 300 by using the determined first wireless network.

Here, the quality prediction information providing device 400 may include the above-described quality prediction module 200, and the quality prediction module 200 is processed by the model setting variable processing unit 430 of the quality prediction information providing device 400 The above-described quality prediction model may be determined according to the determined variable, and prediction information may be output according to the model input variable determined by the model input variable processor 440.

To this end, the information service provider 470 may provide a quality prediction model for each wireless network or may provide quality prediction information for each network corresponding to a model input variable according to a request from the wireless terminal device 100.

Accordingly, the wireless terminal device 100 receives the information service from the apparatus 400 for providing quality prediction information, and learns a relationship between at least one variable among network speed, signal strength, or preset model input variables, or a function Based on the application, it is possible to more accurately predict the quality deterioration according to the model input variable in advance, and the dynamic variable control of the wireless network accordingly enables rapid and efficient network change while minimizing the user's experience of quality deterioration. .

More specifically, referring to FIG. 6, the apparatus 400 for providing quality prediction information according to an embodiment of the present invention includes a control unit 410, a communication unit 420, a model setting variable processing unit 430, and a model input variable processing unit ( 440), a quality prediction module 200, a database 460, and an information service provider 470.

The control unit 410 generally controls the operation of each component of the apparatus 400 for providing quality prediction information and execution of functions. For example, the controller 410 may be implemented as a processor for controlling all or part of a model setting variable processing, model input variable processing, and information service providing function, or a program for executing the same.

In addition, the communication unit 420 connects to the wireless terminal device 100 or wireless networks 200a, 200b, ... 200n, or connects to a wired network to enable wired/wireless data packet communication with each wireless network. It may include one or more communication modules.

In particular, the communication unit 420 may include a wireless Internet module for connecting to at least one of the wireless terminal device 100 or wireless networks 200a, 200b, ... 200n through a wireless Internet protocol, and a wireless Internet module Wireless LAN (WLAN) (Wi-Fi), Wireless broadband (Wibro), World Interoperability for Microwave Access (Wimax), and high speed downlink packet access (HSDPA) based network modules may be exemplified.

In addition, the communication unit 120 may include a short-range communication module for short-range communication access to at least one of the wireless terminal device 100 or wireless networks 200a, 200b, ... 200n, and a short-range communication protocol. As a short-range communication technology, Bluetooth, Radio Frequency Identification (RFID), infrared data association (IrDA), Ultra Wideband (UWB), ZigBee, and the like may be exemplified.

Meanwhile, the communication unit 120 may include a mobile communication module for mobile communication connection with at least one of the wireless terminal device 100 or wireless networks 200a, 200b, ... 200n, and For this reason, it is possible to transmit and receive wireless signals with at least one of a base station on a mobile communication network, an external terminal, a connection target device, and a server. The wireless signal may include a voice call signal, a video call signal, or various types of data according to transmission/reception of text/multimedia messages.

In addition, the communication unit 420 may provide the quality prediction information for each network to the wireless terminal device 100 under the control of the controller 410 or may provide prediction model information for determining the quality prediction information for each network. Information may be generated by the quality prediction module 200

In order to determine the quality prediction information for each network, the quality prediction module 200 collects and refines model setting variables obtained from the model setting variable processing unit 430 and the model input variable processing unit 440 and variable information for model input variables. A quality prediction model for each wireless network may be determined and stored in the database 460 based on the processed model setting variable and the model input variable.

Here, the model setting variable processing unit 430 and the model input variable processing unit 440 may collect, process, and transmit various variables for determining a quality prediction model for each wireless network in the quality prediction module 200, and The model input variable may be determined differently according to a learning model of the quality prediction module 200, a learning process, or applied functions. As the learning process, artificial intelligence or artificial neural network learning can be exemplified, and variable setting and learning model configuration for this are important. For this, the quality prediction module 200 and the quality prediction module 200 in the case of the wireless terminal device 100 Since the operation is similar, a detailed description will be omitted.

In addition, the information service providing unit 470 may provide an information service for transmitting the quality prediction model information for each wireless network generated by the quality prediction module 200 to the wireless terminal device 100.

In addition, the information service providing unit 470 may transmit information of the wireless terminal device 100 according to the request of the wireless terminal device 100 to the model input variable processing unit 440, and the model input variable processing unit 440 is a wireless terminal. By determining a model input variable corresponding to the device 100 information and passing the determined model input variable to the quality prediction module 200, the quality prediction module 200 may output the quality prediction information for each network.

In addition, the information service provider 470 may transmit the obtained network-specific quality prediction information to the wireless terminal device 100 through the communication unit 420.

Accordingly, the wireless terminal device 100, which receives the quality prediction information for each network or obtained from the model, compares according to preset user preference information or mode setting information, and transmits a data packet to the optimal network according to the comparison result. It can be determined as the first wireless network to be performed.

In addition, since the wireless terminal device 100 can transmit a wireless data packet through the determined network, a detailed description thereof will be omitted since this is the same as described in FIG. 2.

7 is a flowchart illustrating an operation of an apparatus for providing quality prediction information according to an embodiment of the present invention.

Referring to FIG. 7, the apparatus 400 for providing quality prediction information according to an embodiment of the present invention collects a quality model setting variable for each wireless network through the model setting variable processing unit 430 (S201).

Then, the model setting variable processing unit 430 performs a variable refinement process on the model setting variable in order to determine a quality prediction model (S202).

Then, the quality prediction module 200 of the apparatus 400 for providing quality prediction information determines a quality prediction model for each wireless network based on a preset model setting variable (S203).

Thereafter, the quality prediction information providing apparatus 400 collects and refines the model input variables according to the request of the wireless terminal device 100 through the model input variable processing unit 440 (S205).

Then, the apparatus 400 for providing quality prediction information acquires quality prediction information for each network according to the application of the quality prediction model of the model input variable (S207).

Thereafter, the apparatus 400 for providing quality prediction information provides quality prediction information for each network to the wireless terminal (S209).

In this way, by providing the apparatus 400 for providing quality prediction information, it is possible to provide a dynamic wireless network variable access based on a quality prediction learning model even if the learning-based quality prediction module is not installed inside the wireless terminal device 100, It is possible to reduce infrastructure and cost by enabling the collection of learning data and building a model without consuming power and resources of the wireless terminal device 100.

8 is a block diagram illustrating a learning-based quality prediction module according to an embodiment of the present invention in more detail.

Referring to FIG. 8, the quality prediction module 200 according to an embodiment of the present invention includes at least one input layer processor 210, at least one first intermediate layer processor 220a, 220b, ... 220n, and at least one A plurality of n-th intermediate layer processing units including second intermediate layer processing units 230a, 230b, ... 230n and an output layer processing unit 240 are included, and a feedback weight application unit 240 corresponding to the output layer is selectively selected. Can be included as.

The quality prediction module 200 converts at least one of a quality model input variable and an output variable (quality value) among the variables collected by the model input variable processing unit 440 into respective input layers, and convolutes the processed input layers. It is possible to construct an artificial neural network network that performs routing calculation and outputs it to an output layer related to network quality. For this, each intermediate layer processor may process an individual multiplication operation according to a neural network network, and the feedback weight application unit 245 may selectively perform a weight adjustment process according to an evaluation of an output layer.

Through the iterative processing of such a learning process, a wireless network quality prediction model corresponding to an input variable and an output variable of a quality model for each wireless network can be constructed, and the constructed prediction model is stored in the wireless network quality prediction model storage unit 250. It may be stored or transmitted to a database of the wireless terminal device 100 or the apparatus 400 for providing quality prediction information, and may be used to predict the quality of each network according to the model input variables collected in real time.

In addition, the model input variables and corresponding quality information collected thereafter may be used for additional learning of the constructed wireless network quality prediction model. Accordingly, the wireless network quality prediction model according to an embodiment of the present invention is The quality prediction accuracy may be improved based on the model input variables collected as.

In addition, according to an embodiment of the present invention, based on a predetermined quality setting variable for each wireless network, a wireless network quality prediction model constructed externally according to preliminary learning is stored in the wireless network quality prediction model storage unit 250 in advance. May be. In this case, the quality prediction module 200 according to an embodiment of the present invention may determine a pre-built wireless network quality prediction model in response to the quality setting variable processed by the model setting variable processing unit 130.

The pre-built wireless network quality prediction model may be in the form of a functional model determined by learning, for example. Accordingly, when the quality prediction module 200 uses a quality prediction model based on a quality prediction model application function, the quality prediction model application function may be a learning-based function determined by a pre-built wireless network quality prediction model. The prediction module 200 first determines a wireless network quality prediction model based on the model setting variable in the model setting variable processing unit 130, and then applies the model input variable collected by the model input variable processing unit 140 to provide real-time quality. Although the output information for is obtained, a process of learning the wireless network quality prediction model again may be performed using the model input variable and the output information.

Therefore, the model setting variable according to an embodiment of the present invention may be used to predetermine or create a new wireless network quality prediction model. In addition, the model input variable may be applied to a generated or determined wireless network quality prediction model or used as an input variable for training.

For example, the network determination unit 150 may obtain real-time quality information for each wireless network according to the application of the wireless network quality prediction model according to the model input variable and use it for network determination, and at the same time, the quality prediction module ( 200) is capable of performing additional learning processing of a wireless network quality prediction model based on the input variable and the quality information.

9 to 10 are diagrams for explaining a data merging and sharing process of a learning-based quality prediction model according to an embodiment of the present invention.

The data on the performance of each wireless terminal device 100 and the AP may be used to predict the performance of the AP even if the device is not directly connected. Therefore, merge sharing of prediction models enables more accurate prediction of AP performance.

Accordingly, referring to FIGS. 9 and 10, the learning-based quality prediction model according to an embodiment of the present invention may be formed by merging shared data, and data exchange for this may be performed by the wireless terminal device 100 or It may be processed by the prediction information providing device 400.

First, FIG. 9 shows a case where the learning-based quality prediction module 200 is provided in the wireless terminal device 100 so that the learning-based quality prediction model sharing data is shared among other wireless terminal devices 100a. The quality prediction model data or training data learned in (100) may be shared and merged to be used in another wireless terminal device (100a). For example, data on the performance of the wireless terminal device 100 and APs of each wireless network may be transmitted to other wireless terminal devices 100a.

For example, the wireless terminal device 100 is based on learning data about the performance between the wireless terminal device 100 and the AP generated by the learning-based quality prediction module 200 (for example, speed, specific variables and performance). Function data indicating a related relationship) to the other wireless terminal device 100a connected to the network.

Here, each wireless terminal device may be connected to a data sharing network such as a block chain network, and each wireless terminal device may store learning model data in a shared DB based on a block chain network.

Thereafter, the specific wireless terminal device 100 may request data related to the performance of a specific AP from the shared network to determine a wireless network, and the shared network may request quality related to the performance of the specific AP based on the previously stored merged shared data. Data can be transmitted to the wireless terminal device 100.

In addition, the wireless terminal device 100 receiving performance or quality data of a specific AP may determine and connect to a first wireless network based on this. In addition, when the wireless terminal device 100 collects the additional data of the AP, it may transmit it to the shared network and merge it into the training data for a learning-based quality prediction model.

In the data merging process, the additional data may be merged by weighting according to the similarity between variables of the previously stored data (eg, model, number of connected devices, time zone) and variables of the wireless terminal device 100, The average value, minimum value or maximum value during may be used. The data merging process may be distributed in a shared network, or data merged in the wireless terminal device 100 may be transmitted to the shared network.

In addition, since the use of shared data is not essential, the wireless terminal device 100 may perform learning and prediction processing using only individually collected data.

On the other hand, FIG. 10 shows a case where the learning-based quality prediction module 200 is provided in the quality prediction information providing apparatus 400 so that the learning-based quality prediction model sharing data is shared with other wireless terminal devices 100a. The quality prediction model data or training data learned by the terminal device 100 and other wireless terminal devices 100a may be shared and merged through the quality prediction information providing apparatus 400.

For example, the apparatus 400 for providing quality prediction information collects data on the performance of each AP of each wireless network from the wireless terminal device 100 and other wireless terminal devices 100a, and Learning data (eg, speed, function data representing a relationship between specific variables and performance) can be merged.

In addition, the quality prediction information providing apparatus 400 provides learning model data according to merge learning to the wireless terminal device 100 and other wireless terminal devices 100a connected to the network. The provision of model data can be processed according to a certain period.

For example, in order to predict performance information of a specific AP for determining a wireless network in a specific wireless terminal device 100, model data provided from the information service providing unit 470 of the quality prediction information providing device 400 may be used. have.

When the wireless terminal device 100 collects the additional data of the AP, it may transmit it to the quality prediction information providing device 400 and merge it into training data for a learning-based quality prediction model.

In the data merging process, the additional data may be merged by weighting according to the similarity between variables of the previously stored data (eg, model, number of connected devices, time zone) and variables of the wireless terminal device 100, The average value, minimum value or maximum value during may be used. The data merging process may be processed by the apparatus 400 for providing quality prediction information, or data merged by the wireless terminal device 100 may be transmitted to the apparatus 400 for providing quality prediction information.

Meanwhile, the above-described method according to various embodiments of the present invention may be implemented as a program and provided to each server or devices while being stored in various non-transitory computer readable media. Accordingly, the user terminal 100 can access the server or device and download the program.

The non-transitory readable medium refers to a medium that stores data semi-permanently and can be read by a device, not a medium that stores data for a short moment, such as a register, cache, or memory. Specifically, the above-described various applications or programs may be provided by being stored in a non-transitory readable medium such as a CD, DVD, hard disk, Blu-ray disk, USB, memory card, and ROM.

In addition, although the preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the present invention belongs without departing from the gist of the present invention claimed in the claims. In addition, various modifications are possible by those of ordinary skill in the art, and these modifications should not be individually understood from the technical spirit or prospect of the present invention.

Claims (48)

In the operating method of the apparatus for providing quality prediction information accessible to a plurality of wireless networks,
Collecting variable information for each wireless network;
Obtaining quality prediction information for each accessible network according to quality prediction processing using the variable information; And
Providing the quality prediction information for each wireless network to a wireless terminal device,
The wireless terminal device is a device that determines a first wireless network to perform data transmission among the plurality of wireless networks based on the network-specific quality prediction information
A method of operating an apparatus for providing quality prediction information. The method of claim 1,
The quality prediction processing includes calculation processing of the quality prediction information for each network using a quality prediction function predetermined in response to the variable information.
A method of operating an apparatus for providing quality prediction information. The method of claim 2,
The quality prediction function includes at least one of a linear function, a log function, a sigmoid function, and an arctangent function capable of representing network quality information in comparison with a signal strength information (RSSI) variable.
A method of operating an apparatus for providing quality prediction information. The method of claim 3,
The quality prediction function includes at least one of a linear function based on frequency band information and variable information, a linear function based on link speed and variable information, a first frequency band based log function, and a second frequency band based linear function.
A method of operating an apparatus for providing quality prediction information. The method of claim 4,
The linear function based on the frequency band information and the variable information includes a linear function for forming a different slope for each frequency band by differently determining a variable limitation range according to the frequency band information for each network.
A method of operating an apparatus for providing quality prediction information. The method of claim 4,
The link speed and variable information-based linear function is a linear function that limits a maximum value range of a quality prediction result according to link speed information for each network.
A method of operating an apparatus for providing quality prediction information. The method of claim 4,
The quality prediction function includes a selective adaptive processing function for processing a logarithmic function corresponding to the first frequency band and a linear function corresponding to the second frequency band,
Characterized in that the first frequency band is higher than the second frequency band
A method of operating an apparatus for providing quality prediction information. The method of claim 4,
Further comprising the step of setting variable information for applying the quality prediction function
A method of operating an apparatus for providing quality prediction information. The method of claim 1,
Obtaining the quality prediction information,
Determining a model input variable of the wireless terminal device from the variable information; And
Comprising the step of applying the model input variable to a quality prediction learning model for each wireless network, and obtaining quality prediction information for each accessible network.
A method of operating an apparatus for providing quality prediction information. The method of claim 9,
Collecting a model setting variable and a basic variable for generating a quality model for each wireless network from the variable information;
Refining the basic variables to obtain model input variables; And
Generating a quality prediction learning model for each wireless network based on at least one of the model setting variable and the refined model input variable
A method of operating an apparatus for providing quality prediction information. The method of claim 10,
Generating the learning model,
Obtaining variable information for each communication section from the model input variable; And
The step of generating a quality prediction learning model for each wireless network according to a relation learning operation for each communication section based on the variable information for each communication section.
A method of operating an apparatus for providing quality prediction information. The method of claim 11,
The variable information for each communication section is
Including physical variable information corresponding to at least one communication section among a wired section between an access target device and an AP (Access Point) access point, an AP internal section, a wireless section between the AP and a wireless terminal device, and a wireless terminal device internal section
A method of operating an apparatus for providing quality prediction information. The method of claim 12,
The physical variable information,
Wired cable performance information corresponding to the wired section between the connection target device and the AP access point, including information on the difference between the IP of the connection target device and the IP of the AP
A method of operating an apparatus for providing quality prediction information. The method of claim 12,
The physical variable information,
Including AP hardware capability information and number of connected devices corresponding to the AP inner section
A method of operating an apparatus for providing quality prediction information. The method of claim 12,
The physical variable information,
Including at least one of protocol information, signal strength information, frequency band information, and channel/frequency congestion information corresponding to a radio section between the AP and the wireless terminal device
A method of operating an apparatus for providing quality prediction information. The method of claim 12,
The physical variable information,
Including at least one of wireless module performance information, wireless module characteristic information, and temperature information corresponding to the internal section of the wireless terminal device
A method of operating an apparatus for providing quality prediction information. The method of claim 10,
Generating the learning model,
Acquiring constant element information and variable element information from previously collected model input variables;
Generating a quality prediction learning model for each wireless network according to a relational learning operation based on the constant element information; And
Including the step of generating a relationship model between the variable element information and the quality prediction learning model,
The step of obtaining the quality prediction information for each accessible network,
Comprising the step of applying the model input variables collected in real time to the variable elements of the relationship model to obtain quality prediction information for each network
A method of operating an apparatus for providing quality prediction information. The method of claim 17,
The constant element includes at least one of performance information of an access point (AP) providing a wireless network, information on the number of neighboring APs, and communication protocol information,
The variable element includes at least one of information on the number of devices connected to the AP, information on the strength of an access signal, information on a TCP socket destination, information on a round trip time (RTT), information on a window size, and information on a transmission/reception data
A method of operating an apparatus for providing quality prediction information. The method of claim 9,
The plurality of wireless networks include one or more WIFI standard networks,
Obtaining the quality prediction information,
Obtaining hardware information of an AP providing the WIFI standard network and signal strength information with the wireless terminal as the model input variable; And
Comprising the step of obtaining, from the quality prediction learning model for each wireless network, quality prediction information when using the WIFI standard network of the wireless terminal corresponding to the hardware information and signal strength information
A method of operating an apparatus for providing quality prediction information. The method of claim 19,
The quality prediction learning model for each wireless network,
Learning operation, logistic regression operation, artificial neural network operation, unsupervised learning operation, using the hardware performance information calculated from the unique characteristic information of each AP and the unique characteristic information of each wireless terminal as the model input variable, and the communication quality information as an output variable, It characterized in that it is generated according to at least one of the supervised learning operations
A method of operating an apparatus for providing quality prediction information. The method of claim 20,
The unique characteristic information for each AP is calculated from the radiated power intensity information of the AP determined corresponding to the MCS (Modulation Coding Scheme) index of the AP.
A method of operating an apparatus for providing quality prediction information. The method of claim 20,
The unique characteristic information for each AP includes minimum signal strength information and maximum speed information calculated for each AP.
A method of operating an apparatus for providing quality prediction information. The method of claim 9,
The plurality of wireless networks includes one or more mobile communication networks,
Obtaining a moving average value by processing a Decay function based on velocity samples of the last n data obtained from the mobile communication network; And
And generating a quality prediction learning model corresponding to the mobile communication network by performing regression learning processing of transmission performance information corresponding to the moving average value.
A method of operating an apparatus for providing quality prediction information. The method of claim 9,
The quality prediction learning model for each wireless network is
Characterized in that it is formed to be shared according to exchange of learning data with other wireless terminal devices connected to the wireless terminal device
A method of operating an apparatus for providing quality prediction information. The method of claim 24,
Further comprising the step of sharing the variable data for exchanging the learning data to the other wireless terminal devices according to a predetermined period
A method of operating an apparatus for providing quality prediction information. The method of claim 1,
The wireless terminal device is a device that compares the quality prediction information for each network according to preset user preference information or mode setting information, and determines an optimal network according to the comparison result as the first wireless network.
A method of operating an apparatus for providing quality prediction information. In the apparatus for providing quality prediction information accessible to a plurality of wireless networks,
A variable information processing unit that collects variable information for quality prediction for each wireless network;
A quality prediction module that obtains quality prediction information for each accessible network according to a quality prediction process using the variable information; And
Including an information service providing unit for providing the quality prediction information for each wireless network to one or more wireless terminal devices,
The wireless terminal device is a device that determines a first wireless network to perform data transmission among the plurality of wireless networks based on the network-specific quality prediction information
A device for providing quality prediction information. The method of claim 27,
The quality prediction module is configured to calculate the quality prediction information for each network using a predetermined quality prediction function in response to the variable information.
A device for providing quality prediction information. The method of claim 28,
The quality prediction function includes at least one of a linear function, a log function, a sigmoid function, and an arctangent function capable of representing network quality information in comparison with a signal strength information (RSSI) variable.
A device for providing quality prediction information. The method of claim 29,
The quality prediction function includes at least one of a linear function based on frequency band information and variable information, a linear function based on link speed and variable information, a first frequency band based log function, and a second frequency band based linear function.
A device for providing quality prediction information. The method of claim 30,
The linear function based on the frequency band information and the variable information includes a linear function for forming a different slope for each frequency band by differently determining a variable limitation range according to the frequency band information for each network.
A device for providing quality prediction information. The method of claim 30,
The link speed and variable information-based linear function is a linear function that limits a maximum value range of a quality prediction result according to link speed information for each network.
A device for providing quality prediction information. The method of claim 30,
The quality prediction function includes a selective adaptive processing function for processing a logarithmic function corresponding to the first frequency band and a linear function corresponding to the second frequency band,
Characterized in that the first frequency band is higher than the second frequency band
A device for providing quality prediction information. The method of claim 30,
The quality prediction module sets variable information for applying the quality prediction function
A device for providing quality prediction information. The method of claim 27,
A model input variable processor for determining a model input variable of the wireless terminal device from the variable information; And
A learning-based quality prediction module for obtaining quality prediction information for each accessible network by applying the model input variable to a quality prediction learning model for each wireless network;
A device for providing quality prediction information. The method of claim 35,
Further comprising a model setting variable processing unit for collecting the quality model setting variable for each wireless network,
The learning-based quality prediction module
Generating the quality prediction learning model for each wireless network based on a learning operation using the model input variable corresponding to the quality prediction learning model determined according to the model setting variable
A device for providing quality prediction information. The method of claim 36,
The learning-based quality prediction module
Obtaining variable information for each communication section from the model input variable, and generating a quality prediction learning model for each wireless network according to a relationship learning operation for each communication section based on the variable information for each communication section.
A device for providing quality prediction information. The method of claim 37,
The variable information for each communication section is
Including physical variable information corresponding to at least one communication section among a wired section between a target device and an AP (Access Point) access point, an internal section of the AP, a section between the AP and a wireless terminal, and a section inside the wireless terminal device,
The physical variable information,
Wired cable performance information corresponding to the wired section between the connection target device and the AP access point, difference information between the IP of the connection target device and the IP of the AP, AP hardware performance information and the number of connected devices corresponding to the AP internal section, Protocol information, signal strength information, frequency band information, and channel/frequency congestion information corresponding to the wireless section between the AP and the wireless terminal device, and wireless module performance information, wireless module characteristic information and temperature corresponding to the internal section of the wireless terminal device Containing at least one of the information
A device for providing quality prediction information. The method of claim 35,
The learning-based quality prediction module
Acquires constant element information and variable element information from the model input variable, generates a quality prediction learning model for each wireless network according to a relationship learning operation based on the constant element information, and generates the variable element information and the quality prediction learning model A relationship model is generated, and the model application variable is applied to the variable element of the relationship model to obtain quality prediction information for each network,
The constant element includes at least one of performance information of an access point (AP) providing a wireless network, information on the number of neighboring APs, and communication protocol information,
The variable element includes at least one of information on the number of devices connected to the AP, information on the strength of an access signal, information on a TCP socket destination, information on a round trip time (RTT), information on a window size, and information on a transmission/reception data
A device for providing quality prediction information. The method of claim 35,
The plurality of wireless networks include one or more WIFI standard networks,
The learning-based quality prediction module acquires hardware information of an AP providing the WIFI standard network and signal strength information with the wireless terminal as the model input variable, and from the quality prediction learning model for each wireless network, the hardware information and Obtaining quality prediction information when using the WIFI standard network of the wireless terminal corresponding to signal strength information
A device for providing quality prediction information. The method of claim 35,
The plurality of wireless networks includes one or more mobile communication networks,
The learning-based quality prediction module obtains a moving average value by processing a Decay function based on the velocity samples of the last n data obtained from the mobile communication network, and regresses transmission performance information corresponding to the moving average value. By learning to generate a quality prediction learning model corresponding to the mobile communication network
A device for providing quality prediction information. The method of claim 35,
The quality prediction learning model for each wireless network is shared and formed according to exchange of learning data with other wireless terminal devices connected to the wireless terminal device,
The information service providing unit shares the learning model based on the shared learning data to wireless terminal devices according to a predetermined period.
A device for providing quality prediction information. The method of claim 27,
The wireless terminal device is a device that compares the quality prediction information for each network according to preset user preference information or mode setting information, and determines an optimal network according to the comparison result as the first wireless network.
A device for providing quality prediction information. The method of claim 27,
The wireless terminal device performs application-based network layer control to process a change or switch from an existing connected wireless network to the first wireless network.
A device for providing quality prediction information. The method of claim 44,
The wireless terminal device terminates the connection with the existing wireless network, collectively terminates the network sockets interworked with the existing wireless network, activates the connection with the first wireless network, and operates the application. The necessary sockets are regenerated and processed to be connected to the first wireless network.
A device for providing quality prediction information. The method of claim 44,
The wireless terminal device transmits reset (RST) flag data corresponding to the TCP socket linked to the existing connected wireless network to the TCP socket, and processes the socket reboot of the applications without waiting for the socket termination of the existing connected wireless network. Processing so that the connection to the first wireless network is immediately performed as is performed
A device for providing quality prediction information. The method of claim 44,
The wireless terminal device,
The data packet requested to be written before the switch to the first wireless network is temporarily stored from the socket interlocked with the existing wireless network, and the temporarily stored packet is retransmitted through a socket connected to the first wireless network. To control the communication department
A device for providing quality prediction information. A computer-readable nonvolatile recording medium in which a program for executing the method according to any one of claims 1 to 26 on a computer is recorded.

Images