KR20190139130A - Analysis method of fluidized population information capable of providing real-time fluidized population data by pcell algorithm - Google Patents

Abstract

The present invention relates to a method for analyzing floating population information, capable of providing floating population data in real time by using pCELL algorithm and, more specifically, to a method for analyzing floating population information, capable of providing floating population data in real time by using pCELL algorithm and also easily and rapidly obtaining the floating population data in real time by linkage of a correlation analysis, a regression analysis, and the pCELL algorithm. According to the present invention, the method for analyzing floating population information, capable of providing floating population data in real time by using pCELL algorithm can provide accurate information more than five times than an existing cell ID method of providing position information of a cell unit across several Km by applying the pCELL algorithm to the real-time floating population measurement and also can easily obtain the floating population data in real time. The method for analyzing floating population information, capable of providing floating population data in real time by using pCELL algorithm also can obtain active population by days, floating populations for sex/age by days, floating populations for time by days, unique population for cities and provinces by days, unique populations for cities, counties, and districts by days, foreigner data by days, and origin-destination matrix for time by days. The method for analyzing floating population information, capable of providing floating population data in real time by using pCELL algorithm synch creates a basic unit area and can build areas except for a downtown by a grid of a basic analysis unit. The method for analyzing floating population information, capable of providing floating population data in real time by using pCELL algorithm can also build a space unit area corresponding to development business. Moreover, the method for analyzing floating population information, capable of providing floating population data in real time by using pCELL algorithm can extract an independent variable for calculating the floating population by an analysis radius, the correlation analysis, and the regression analysis, which can explain classification of position type the best.

Description

ANALYSIS METHOD OF FLUIDIZED POPULATION INFORMATION CAPABLE OF PROVIDING REAL-TIME FLUIDIZED POPULATION DATA BY PCELL ALGORITHM}

The present invention is a flow population information analysis method that can provide real-time flow population data using the Picsel algorithm, more specifically, it is possible to easily and quickly obtain real-time flow population data through the correlation analysis, regression analysis, the Picelle algorithm The present invention relates to a method for analyzing floating population information that can provide real-time floating population data using the Fissel algorithm.

Recently, various services such as counterpart location service, traffic guidance service, and navigation service have been implemented using location-based mobile communication technology. In addition, as a part of the various services, by using a mobile communication terminal incorporating a location-based mobile communication technology, by implementing a service for identifying the current status of the flow of service subscribers possessing it, by measuring the congestion degree in a specific area Based on the collected data, there is a need to analyze the current state of the floating population, to analyze the commercial area of the region, or to determine the congestion level for a given destination in real time.

In order to investigate the floating population information, it is a situation to survey the floating population manually by investigating investigators, but it is impossible to make an accurate survey when a large number of passers pass, and despite the fact that age information is very important factor among floating population information, There is a problem in that it is insufficient to collect accurate age information because the age is estimated only by the appearance of the passenger.

In addition, in the existing location and business analysis method, in order to obtain such information, the information is obtained by visiting the site or by visiting the government offices individually. Could get

Among the information generated in this way, the floating population data is directly counted at important locations, which may be useful in determining the total number of floating populations at different time slots, but it was insufficient to utilize other information.

As such, the conventional floating population measurement method cannot be an accurate information collection method even if a person registers a place of residence, because it does not reflect real-time cases such as working or living in another area without living in an actual place of residence. . Accordingly, since the error rate of the population density value measured by the conventional flow population measurement method is not only large, but also it is difficult to accurately reflect accurate information, various estimation or prediction information based on this also have a lot of errors inherently. There is a problem of very low reliability.

In order to solve this problem, real-time floating population measurement technology has been developed using a method using a GPS satellite, a method using a mobile communication environment, a method using proximity to a fixed object such as a wireless LAN.

However, the GPS technique for measuring the position of the floating population (approximately 15m error rate) and the proximity method are more accurate than the mobile communication environment in terms of accuracy. If the attenuation is large, there is a disadvantage that can not be used.

Recently, various services such as counterpart location service, traffic guidance service, and navigation service have been implemented using location-based mobile communication technology. In addition, as a part of the various services, by using a mobile communication terminal incorporating a location-based mobile communication technology, by implementing a service for identifying the current status of the flow of service subscribers possessing it, by measuring the congestion degree in a specific area Based on the collected data, there is a need to analyze the current state of the floating population, to analyze the commercial area of the region, or to determine the congestion level for a given destination in real time.

In order to investigate the floating population information, it is a situation to survey the floating population manually by investigating investigators, but it is impossible to make an accurate survey when a large number of passers pass, and despite the fact that age information is very important factor among floating population information, There is a problem in that it is insufficient to collect accurate age information since the age is estimated only by the appearance of the passenger.

In addition, in the existing location and business analysis method, in order to obtain such information, the information is obtained by visiting the site or by visiting the government offices individually. Could get

Among the information generated in this way, the floating population data is directly counted at important locations, which may be useful in determining the total number of floating populations at different time slots, but it was insufficient to utilize other information.

As such, the conventional floating population measurement method cannot be an accurate information collection method even if a person registers a place of residence, because it does not reflect real-time cases such as working or living in another area without living in an actual place of residence. . Accordingly, since the error rate of the population density value measured by the conventional flow population measurement method is not only large, but also it is difficult to accurately reflect accurate information, various estimation or prediction information based on this also have a lot of errors inherently. There is a problem of very low reliability.

In order to solve this problem, real-time floating population measurement technology has been developed using a method using a GPS satellite, a method using a mobile communication environment, a method using proximity to a fixed object such as a wireless LAN.

However, the GPS technique for measuring the position of the floating population (approximately 15m error rate) and the proximity method are more accurate than the mobile communication environment in terms of accuracy. If the attenuation is large, there is a disadvantage that can not be used.

On the other hand, the positioning method that provides location information by using the signal strength information of the wireless LAN has the advantage of utilizing the existing wireless Internet infrastructure, but it cannot be used in the area where the wireless LAN is not installed. There are disadvantages. On the other hand, the method using the mobile communication environment (cell ID) can cover almost every part of life and does not require any additional equipment, but has a relatively inaccurate disadvantage in terms of accuracy.

Republic of Korea Patent Publication No. 10-1573190

In order to solve the above-mentioned problems, the present invention uses real-time flow population data using a Fissel algorithm, which can quickly and easily obtain real-time flow population data through correlation, regression analysis, and interoperation of the Fissel algorithm in an embodiment of the present invention. An object of the present invention is to provide a method for analyzing floating population information that can be provided.

However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

The floating population information analysis method, which can provide real-time floating population data using the PICSL algorithm, according to an embodiment of the present invention, analyzes the floating population performed by a population analysis server for providing a population analysis service using big data. A service providing method comprising the steps of: a) collecting pre-aggregated data including regional information, population movement information, commodity transaction information, demographic information, communication record information, and tourism information via a network; b) Based on the pre-aggregated data collected above, standardization work will be carried out on the basis of the number of businesses, residential population information and workplace population information for each basic unit area, and the housing type, commercial type, workplace type, complex type, tourism type, and other types. Categorizing into a location type comprising a; c) When a measurement point for calculating a floating population is input, the flow population of the measurement point is set as a dependent variable, a basic analysis area of a preset measurement range is set based on the measurement point, and the basic analysis area is Extracting a plurality of independent variables used for the prediction of the dependent variable while expanding an analysis region within a predetermined analysis unit within a measurement range; d) A regression coefficient is derived by applying a regression analysis based on the correlation between the location type, the day / weekday / weekend category, the correlation between the dependent variable and the independent variable, and the significant independent variable using the regression coefficient. Determining the location type, the area of analysis of each location type, respectively; And e) constructing a spatial unit area by applying an analysis area for each of the determined location types, and applying a pCELL algorithm to the spatial unit area to generate floating population data of time zone / region / sex / age / visitor population. It includes a step of predicting.

In addition, the floating population information analysis method that can provide real-time flow population data using the Picelle algorithm according to an embodiment of the present invention, a plurality of access to at least one base station respectively disposed in one or more areas in step a) User data related to the user terminal and traffic data including a call, a text generated in accordance with the session connection of the plurality of user terminal is characterized in that the real-time collection through the mobile communication network as communication record information.

In addition, the floating population information analysis method capable of providing real-time floating population data using the PICS algorithm according to an embodiment of the present invention, in step b) is 70% or more of the residential population based on the basic unit classification classification of the National Statistical Office Residential type, commercial type when the number of businesses is 50% or more, commercial type when the working population is 70% or more, complex type when the working type is 30% or more and less than 70%, and the working population is 30% or more and less than 70%. A primary type classification step of categorizing the independent variables of tourist attractions in the region and classifying the tourism type set according to the inclusion relations and other regions into other types; And the case where the number of standardized businesses by region is 0.1 or less and the business type and other types, when the standardized housing population by region is 0.05 or less and the housing type and other types, and the standardized work population by region is 0.05 or less and the workplace type and other types. In addition, the method includes a second type classification step in which the total number of standardized businesses by region and the total population by region is 0.05 or less, and classified into complex types and other types.

In addition, the floating population information analysis method capable of providing real-time floating population data using the PICS algorithm according to an embodiment of the present invention, the primary classification step is the residential population ratio to the residential population / (resident population + work population) Calculate the workforce ratio as the workforce / (resident population + working population), and calculate the business ratio as the standardized number of businesses / (standardized number of businesses + standardized total population (resident population + working population)) It is characterized by.

In addition, the floating population information analysis method capable of providing real-time flow population data using the Picelle algorithm according to an embodiment of the present invention, in step b) using the standard normal distribution, the mean of the independent variables 'variance', '0' The standardized value is '1', and the independent variables are converted into values between 0 and 1 by excluding negative values.

In addition, the floating population information analysis method capable of providing real-time flow population data using the Picelle algorithm according to an embodiment of the present invention, characterized in that the circular analysis method using a buffer function in step c) is applied. do.

In addition, the flow population information analysis method that can provide real-time flow population data using the Picelle algorithm according to another embodiment of the present invention, in step c) the location type and independent variables in the analysis region for each analysis unit And the aggregated result is provided in the regression analysis.

In addition, the floating population information analysis method that can provide real-time flow population data using the Picelle algorithm according to an embodiment of the present invention, for the daily average, weekly average, weekend average for each location type determined in step d) The regression coefficients of the determined independent variable are recorded and stored in an analysis table.

In addition, in the method for analyzing flow population information capable of providing real-time flow population data using the PICSell algorithm according to an embodiment of the present invention, step e) includes the communication record information and the PICS data based on the base station traffic data. Using join key as base station ID and generating ratio data for each cell and weighting each cell to extract floating population for time zone / region / sex / age / visitor population based on the measured point The flow population extraction value of the analysis region is calculated.

In addition, the floating population information analysis method capable of providing real-time flow population data using the Picelle algorithm according to an embodiment of the present invention, the weight is characterized by applying a standardized regression coefficient through the regression analysis.

In addition, the floating population information analysis method capable of providing real-time floating population data using the Picelle algorithm according to another embodiment of the present invention, is performed by a population analysis server for providing a population analysis service using big data A method of providing a floating population analysis service, the method comprising: a) user data associated with a plurality of user terminals connected to at least one base station respectively disposed in one or more regions, and traffic data generated according to session connection of the plurality of user terminals; Collecting in real time through the mobile communication network as pre-aggregated data; b) Generate refined data having a grid form of a first analysis unit based on a predetermined analysis area, remove duplicate data in monthly units except one unit, and coordinate of the removed duplicate data. Generating spatial data using the information; c) generating index map data having a grid form of a second analysis unit; d) spatially joining the refine data to the index map data to generate basic picel data, and adding weights for extracting a floating population for a time zone / region / sex / age / visitor population to the basic picel data. Granting to generate the picel data; And e) dividing the analysis region into at least one subregion block, and calculating population flow data by mapping a subregion code in the subregion block based on the picel data.

In addition, the floating population information analysis method capable of providing real-time flow population data using the Picelle algorithm according to another embodiment of the present invention, characterized in that the refined data and the index map data is converted into YXDB format to improve the processing speed It is done.

In addition, the floating population information analysis method that can provide real-time flow population data using the PICSL algorithm according to another embodiment of the present invention, using the base station ID as the join key (KEY) during the spatial join in step d) It features.

In addition, the floating population information analysis method capable of providing real-time flow population data using the Picelle algorithm according to another embodiment of the present invention, characterized in that for generating the spatial data based on the TUM-K coordinate system in step b) It is done.

In addition, the floating population information analysis method capable of providing real-time flow population data using the Picelle algorithm according to another embodiment of the present invention, the refined data is a base station ID, pixel ID in the base station, X coordinate, Y coordinate, spatial information Wherein the index map data includes a record ID and spatial information, and the basic picel data includes a record ID, a base station ID, a pixel ID in a base station, an X coordinate, a Y coordinate, and spatial information. Point ID, population number, X coordinate, Y coordinate, and spatial information, the subregion block is characterized in that it comprises a subregion code and spatial information.

In addition, the floating population information analysis method capable of providing real-time flow population data using the PICSL algorithm according to another embodiment of the present invention, in step e) the population by reference time, time zone code, base station ID, sector, gender / age A step of aggregating population by gender / age by base station unit after removing a time zone column from the pre-aggregation data using the pre-aggregation data in the form of a table; Calculating a daily average value by dividing a time zone code into a day of the week code and dividing the number of days per month from the total gender / age population; Calculating weekday_floating population data corresponding to the weekend among the day codes and weekday_floating population data not corresponding to the weekend among the day codes; Joining the weekday_floating population data and the weekend_floating population data to generate unified floating population data, and applying a carrier correction ratio and a 3G user ratio to the unifying floating population data; And deleting the row having the total value of the row `` 0 '' and grouping it by month / small region / pissel to generate gender / age floating population data.

In addition, the floating population information analysis method capable of providing real-time flow population data using the PICSL algorithm according to another embodiment of the present invention, in step e) the population by reference time, time zone code, base station ID, sector, gender / age A step of eliminating gender / age column from the pre-aggregation data using the pre-aggregation data in the form of a table, and then counting population data by time zone; Calculating a daily average value by dividing a time zone code into a day of the week code in the aggregated time zone population data and dividing the number of days per month; Calculating weekday_floating population data corresponding to the weekend among the day codes and weekday_floating population data not corresponding to the weekend among the day codes; The integrated floating population data is generated by joining the weekday_floating population data and the weekend_floating population data, applying the carrier correction rate and the 3G user ratio to the integrated floating population data, and time zones according to a preset time period (TMST). Creating a column; And deleting the row having the total value of the row '0' and then grouping by month / subregion / pistel to generate the floating population data for each time zone.

In addition, the floating population information analysis method capable of providing real-time flow population data using the PICSL algorithm according to another embodiment of the present invention, in step e) the population by reference time, time zone code, base station ID, sector, gender / age A step of removing a time zone column from the pre-aggregation data using the pre-aggregation data in the form of a table, and then aggregating gross population values by gender / age; Dividing a time zone code into a day of the week code in the aggregated population total value, counting the number of days for each day of the day of the week data, and counting the number of days for each day of the population; Calculating weekday_floating population data corresponding to the weekend among the day codes and weekday_floating population data not corresponding to the weekend among the day codes; Generating the integrated floating population data by joining the weekday_floating population data and the weekend_floating population data, applying a carrier correction ratio and a 3G user ratio to the integrated floating population data, and generating a day column with a day code column; And deleting the row having the total value of the row `` 0 '' and then grouping by month / subregion / pistel to generate the floating population data for each day of the week.

On the other hand, the present invention is not limited to the embodiments disclosed below, but may be implemented in a variety of different forms, only the embodiments of the present invention by completing the disclosure of the present invention to the general knowledge in the art to which the present invention belongs It is provided to fully convey the scope of the invention to those skilled in the art, and the present invention is defined only by the scope of the claims. Like reference numerals refer to like elements throughout.

As described above, the floating population information analysis method capable of providing real-time floating population data using the Fissel algorithm according to the present invention provides a cell unit location information of several Km by applying the Fissel algorithm to real-time floating population measurement. In addition to providing more than five times more accurate information than conventional cell ID methods, it is easy to obtain floating population data in real time.

In addition, the present invention is a daily active population, daily inflow population by gender / age, daily inflow population by day, unique attempt population by day trial, unique population by daily city and district, daily foreign data, daily OD (Origin) -Destination) matrix can be obtained.

In addition, the present invention can implement the basic unit area, the area outside the city center can be constructed with a grid of basic analysis units, and not only can build a spatial unit area in accordance with the modernization project, but also classify location type best Descriptive radius and correlation analysis and regression analysis can be used to extract independent variables that can best predict the dependent variables for the estimation of the floating population.

1 is a view showing the configuration of a population analysis server for performing a floating population information analysis method capable of providing real-time flow population data using the Picelle algorithm according to an embodiment of the present invention.
Figure 2 is a flow chart illustrating a flow population information analysis method capable of providing real-time flow population data using the Fissel algorithm according to an embodiment of the present invention.
3 is a view for explaining a standardized work process for the location type classification of FIG.
4 is a view for explaining a location type classification result of FIG. 2.
FIG. 5 is a diagram illustrating a buffer operation status for the analysis region of FIG. 2. FIG.
FIG. 6 is a diagram illustrating a correlation result through the correlation analysis of FIG. 2. FIG.
FIG. 7 is a diagram for explaining a regression coefficient derived through the regression analysis of FIG. 2. FIG.
FIG. 8 is a flowchart illustrating a method for analyzing flow population information capable of providing real-time flow population data using the PICSL algorithm according to another embodiment of the present invention. FIG.
9 illustrates pre-aggregation data according to an embodiment of the present invention.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention.

As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and like reference numerals designate like parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, which means that it may further include other components, except to exclude other components unless specifically stated otherwise, one or more other It is to be understood that the present invention does not exclude the possibility of the presence or the addition of features, numbers, steps, operations, components, parts, or combinations thereof.

The following examples are detailed description to aid in understanding the present invention, and do not limit the scope of the present invention. Therefore, the same range of inventions that perform the same functions as the present invention will also fall within the scope of the invention.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram showing the configuration of a population analysis server for performing a floating population information analysis method capable of providing real-time floating population data using the PICSL algorithm according to an embodiment of the present invention.

Referring to FIG. 1, a population analysis server 100 that provides a population analysis service using big data includes a communication module 110, a memory 120, a processor 130, and a database 140.

In detail, the communication module 110 provides a communication interface required to provide a transmission / reception signal between the population analysis server 100 and the user terminal in the form of packet data in cooperation with the communication network 300. In addition, the communication module 110 may receive a data request from a user terminal and transmit data as a response thereto.

Here, the communication module 110 may be a device including hardware and software necessary for transmitting and receiving a signal such as a control signal or a data signal through a wired or wireless connection with another network device.

The memory 120 records a program for performing a floating population information analysis method capable of providing real-time floating population data using the Picelle algorithm. In addition, the processor 130 performs a function of temporarily or permanently storing data processed. Here, the memory 120 may include a volatile storage media or a non-volatile storage media, but the scope of the present invention is not limited thereto.

The processor 130 controls the entire process of providing a floating population information analysis method capable of providing real-time floating population data using the PICSL algorithm. Each step performed by the processor 130 will be described later with reference to FIGS. 2 and 8.

Here, the processor 130 may include all kinds of devices capable of processing data, such as a processor. Here, the 'processor' may refer to a data processing apparatus embedded in hardware having, for example, a circuit physically structured to perform a function represented by code or instructions included in a program. As an example of a data processing device embedded in hardware, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, and an application-specific integrated device (ASIC) It may include a processing device such as a circuit, a field programmable gate array (FPGA), etc., but the scope of the present invention is not limited thereto.

The database 140 stores data accumulated while performing a floating population information analysis method capable of providing real-time floating population data using the PICSL algorithm. For example, the database 140 may store pre-aggregated data, floating population data, refined data, index map data, basic data, data, and the like in a table form.

Meanwhile, the user terminal may be a wireless communication device with guaranteed portability and mobility, for example, a personal communication system (PCS), a global system for mobile communications (GSM), a personal digital cellular (PDC), and a personal handyphone system (PHS). ), Personal Digital Assistant (PDA), International Mobile Telecommunication (IMT) -2000, Code Division Multiple Access (CDMA) -2000, W-Code Division Multiple Access (W-CDMA), Wireless Broadband Internet (WBro) terminal, Tablet PC It may be a handheld based wireless communication device of any kind. In addition, the terminal may be a wired communication device such as a PC that can be connected to another terminal or server through a network.

FIG. 2 is a flowchart illustrating a method for analyzing flow population information capable of providing real-time flow population data using the PICSL algorithm according to an embodiment of the present invention, and FIG. 3 illustrates a standardization process for classifying location types of FIG. 2. FIG. 4 is a diagram for explaining the location type classification result of FIG. 2, and FIG. 5 is a diagram for explaining the current status of buffer operations for the analysis region of FIG. 2.

2 to 5, the floating population information analysis method capable of providing real-time floating population data using the PICSL algorithm, the area information, population movement information, commodity transaction information, demographic information, communication record information through a network Collect the pre-aggregated data including tourism information (S110). Population analysis server 100 collects pre-aggregated data through the National Statistical Office, provincial offices / city halls / county offices, card companies, telecommunications companies, tourism corporations, big data companies. In particular, the demographic analysis server 100 includes user data related to a plurality of user terminals connected to at least one base station respectively disposed in one or more regions, and traffic including a call and a text generated according to a session connection of the plurality of user terminals. The data is collected in real time through a mobile communication network as communication record data.

The processor 130 performs standardization based on the pre-aggregated data and classifies the location type based on the number of businesses, residential population information, and workplace population information for each basic unit area (S120).

In other words, the processor 130 is based on the basic unit classification classification of the National Statistical Office, the housing type in the case of more than 70% of the housing population, the commercial type in the case of more than 50% of the number of businesses, the workplace type, 70% or more of the workplace population 30 Complex type, if the working population is more than 70% and less than 70% and less than 30% to 70% Perform primary type classification. The processor calculates the ratio of residential population to residential population / (resident population + working population) in the primary type classification, the working population ratio to workplace population / (resident population + working population), and the proportion of businesses is standardized. Calculate the number / (standardized number of businesses + standardized total population (residential population + workplace population)).

Subsequently, based on the primary type classification, the process 130 again calculates the number of standardized businesses by region and the location type (Table 3) is the business type and other types, when the standardized residential population by region is 0.05. If the location type (Table 3) is less than the residential type and other types, the standardized work population by region is 0.05 or less, and the location type is the work type and other types, and the total number of standardized businesses by region and total population by region is 0.05. In the following, the location type (Table 3) is a complex type and other types, and the secondary type classification is performed by subdividing the conditions.

As shown in FIG. 2, the processor 130 performs a standardization operation to equally match different distributions and sizes of the total population and the business variables. Standardization uses a standard normal distribution to ensure that the independent variables are normalized to a mean of '0' and a variance of '1'. In this case, a negative value is generated, but the regression coefficient is affected by the actual positive value, but it may be negatively affected, so the independent variable is excluded by excluding the negative value. Convert all of them to values between 0 and 1.

After the standardization process, the processor contains 3.09σ99.8% of data by standard normal distribution table, and 99.74% of data for 3.0σ. That is, since 3σ contains data close to 100%, all data are normalized by fixing the point of 3σ value to 1 based on the mean of each independent variable.

When the standardization of the independent variables is completed, all data are changed into the form as shown in Table 1 and FIG.

TABLE 1

Looking at the average in Table 1 has a value smaller than 0.5, as shown in Figure 3 (b) it can be seen that there are a lot of ideal values larger than 3σ, which is the ratio of the values distributed in the upper This is why 3σ is used instead of the maximum value for proper use.

 On the other hand, when the measured point for calculating the floating population is Seoul City, as shown in (a) of FIG. 4, the processor may classify the location type by dividing the urban area by the base unit zone, and display the location type. As shown in (b) of, the urban area may be divided into basic unit areas, and the area outside the city may be divided into grids to classify and display location types.

Referring back to FIG. 2, when the measured point for calculating the floating population is input through the user terminal, the processor 130 sets the floating population of the measured point as a dependent variable and based on the measured range preset based on the measured point. An analysis area is set and a plurality of independent variables used for the prediction of the dependent variable are extracted while the analysis area is expanded to a predetermined analysis unit within the measurement range (S130).

In this case, as shown in FIG. 5, the processor sets an analysis area by applying a circular analysis method through a buffer function, and sets a basic analysis area having a radius of 50m to 200m based on the measured point. In addition, while increasing the radius by 10m analysis unit, the analysis area is expanded to collect the independent variables expected for each radius. The processor aggregates the location type and independent variables in the analysis area whose radius is expanded by the analysis unit, and assigns the aggregated result to the regression equation in the regression analysis.

The processor derives the regression coefficient by applying the regression analysis based on the location type, the category of the day / weekend / weekend, the correlation analysis between the dependent variable and the independent variable, and uses the regression coefficient to identify the significant independent variables and the location. The type and analysis area of each location type are respectively determined (S140). Here, regression analysis is used to statistically estimate the causal effects of the independent variable on the dependent variable.

6 is a diagram illustrating a correlation result through the correlation analysis of FIG. 2, and FIG. 7 is a diagram illustrating a regression coefficient derived through the regression analysis of FIG. 2.

As shown in FIG. 6 and FIG. 7, the processor compares multiple correlation coefficients R2 representing correlations among three or more variables through correlation analysis of location types, categories, and independent variables. As shown in FIG. 4, the radius that can best describe the location type classification, that is, the analysis area is determined, and the independent variable that can most predict the dependent variable is determined.

[Table 2] Independent variable confirmation

[Table 3] Location Type Confirmation

[Table 4] Confirmation of radius by location type

Referring back to FIG. 2, the processor constructs a spatial unit region by applying an analysis region for each determined location type, and applies a pCELL algorithm to the spatial unit region to apply time zone / region / sex / age / visitor population. Predict the floating population data (S150, S160). At this time, the processor uses the join key (KEY) of the communication record information and the picel data as the base station ID based on the traffic data for each base station unit, generates ratio data for each picel, and assigns weight to each picel to time zone / region / After extracting the floating population for the sex / age / visitor population, the floating population data of the analysis area is calculated based on the measured points. Here, the weight is applied to the standardized regression coefficient through the regression analysis as shown in FIG.

FIG. 8 is a flowchart illustrating a method for analyzing flow population information capable of providing real-time flow population data using the PICSL algorithm according to another embodiment of the present invention, and FIG. 9 is pre-aggregated data according to an embodiment of the present invention. It is a figure explaining.

Referring to FIG. 8, the floating population information analysis method capable of providing real-time floating population data using the PICSell algorithm according to another embodiment of the present invention is a method of generating PICS data having a weight to generate floating population data. Explain the center.

First, the population analysis server collects pre-aggregation data in real time through a mobile communication network based on a base station (S210). In this case, the pre-aggregation data may be a floating population parameter estimation data for gender, age, time zone, and day of the week, which is aggregated daily by 50m × 50m units such as currency text.

The demographic analysis server generates refined data having a grid form of a first analysis unit (20m × 20m) based on a predetermined analysis area, removes duplicate data by monthly unit except daily unit, and then removes it. Spatial data is generated based on the TUM-K coordinate system using the coordinate information of the duplicated data (S220). The demographic server sets the date refinement data as input data as shown in Table 5 below, and removes duplicate data on a monthly basis except for the date from the input data.

[Table 5] Input data

The population analysis server generates index map data having a grid form of a second analysis unit (50m × 50m) as shown in Table 6 below (S230). If the analysis area is a national unit, the demographic server converts it to YXDB format, which is an ALTERYX supported extension, to speed up processing of refine data and index map data.

TABLE 6

In addition, the demographic server spatially joins the refined data to the index map data to generate basic picel data as shown in Table 7 (S240), and flows for the time zone / region / sex / age / visitor population to the basic picel data. By assigning a weight to extract the population to generate the data shown in Table 8 (S250). In this case, the base station ID is used as a join key during spatial joining, and the picel data represents an average flow population based on pCell (50m × 50m), and the picel coordinates are point data in 50m × 50m units.

TABLE 7

TABLE 8

The population analysis server divides the analysis area into at least one subregion block as shown in Table 9, and calculates real-time population flow data by mapping a subregion code in the subregion block based on the PICS data (S260).

TABLE 9

Meanwhile, the population analysis server may spatially join the weighted weekly weights to the PICS data and spatially join the small region codes based on the data in which the weights are reflected to calculate the weekly_floating population data as shown in Table 10. In addition, the population analysis server may spatially join the weekend weights and the small region code to the data to sequentially calculate the weekend_floating population data as shown in Table 11.

TABLE 10

The demographic analysis server removes the time zone column from the pre-aggregation data by using tabular pre-aggregation data including the reference time, time zone code, base station ID, sector, and sex / age population, and then aggregates the sex / age population by base station. . The time zone code is divided into weekday codes and the daily average value is calculated by dividing the number of days per month.

Thereafter, the demographic server calculates the weekday_floating population data corresponding to the weekend among the day codes and weekday_floating population data not corresponding to the weekend among the day codes, and then joins the weekday_floating population data and the weekend_floating population data. Generate aggregate floating population data, apply a carrier calibration ratio (eg 0.442) and 3G user ratio (eg 0.82) to the aggregate floating population data, and have a total value of ROW equal to '0'. By deleting the rows and grouping them by month, subregion, and / or cell, the floating population data by gender and age can be generated as shown in Table 11. On the other hand, the carrier correction rate can be calculated as the base station data rate by calculating the ratio value of the daily and hourly analysis area based on the floating population by time zone when the other areas are duplicated.

TABLE 11

On the other hand, the population analysis server removes the gender / age column from the pre-aggregation data and then aggregates it with the time zone population data, divides it by the day code from the aggregated time zone population data, and calculates the daily average value by dividing the number of days per month. The demographic server calculates the weekday_floating population data corresponding to the weekend among the day codes and weekday_floating population data not corresponding to the weekend among the day codes, and then joins the weekday_floating population data with the weekend_floating population data. Generate integrated floating population data, apply telecommunications correction rate (eg 0.442) and 3G user rate (eg 0.82) to the integrated floating population data, and time zones with a preset time period (TMST) You can create a column, delete rows with a total value of ROW '0', and group them by month / subregion / picel to generate floating population data as shown in Table 12.

TABLE 12

The demographic analysis server removes the time zone column from the pre-aggregation data using table-type pre-aggregation data including reference time, time zone code, base station ID, sector, and gender / age population, and then aggregates the gross population value by gender / age, In the aggregated population, the time zone code is divided into the day code, the day of the week is counted in the day of the week data, and the day of the week is counted as the population / day of the month.

Thereafter, the demographic server calculates the weekday_floating population data corresponding to the weekend among the day codes and weekday_floating population data not corresponding to the weekend among the day codes, and joins the weekday_floating population data and the weekend_floating population data. Generates the integrated floating population data, and applies the carrier correction rate and the 3G user ratio to the integrated floating population data, and then generates the day column with the day code column. In addition, the demographic server may generate the floating population data by day as shown in Table 13 by deleting the row having the total value of the row as '0' and grouping it by month / subregion / picel.

TABLE 13

The floating population information analysis method capable of providing real-time flow population data using the PICSell algorithm according to the embodiment of the present invention described above, includes a recording medium including instructions executable by a computer, such as a program module executed by a computer. It can also be implemented in the form of. Such recording media includes computer readable media, and computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer readable media includes computer storage media, which are volatile and nonvolatile implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Both removable and non-removable media.

The foregoing description of the present invention is intended for illustration, and it will be understood by those skilled in the art that the present invention may be easily modified in other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is shown by the following claims rather than the above description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention. do.

As described above, although the present invention has been described by way of limited embodiments and drawings, the present invention is not limited to the above-described embodiments, which can be variously modified and modified by those skilled in the art to which the present invention pertains. Modifications are possible. Accordingly, the invention idea should be understood only by the claims set forth below, and all equivalent or equivalent modifications thereof will fall within the scope of the invention idea.

100: demographic server
110: communication module 120: memory
130: Processor 140: Database
300: network

Claims (2)

In the analysis service providing method of the floating population performed by the population analysis server for providing a population analysis service using big data,
a) user data associated with a plurality of user terminals connected to at least one base station respectively disposed in one or more regions, and traffic data generated according to session connection of the plurality of user terminals as pre-aggregated data in real time through a mobile communication network; Collecting;
b) Generate refined data having a grid form of a first analysis unit based on a predetermined analysis region, remove duplicate data in monthly units except one day, and coordinate of the removed duplicate data. Generating spatial data using the information;
c) generating index map data having a grid form of a second analysis unit;
d) spatially joining the refined data to the index map data to generate basic picel data, and adding weights for extracting a floating population for a time zone / region / sex / age / visitor population to the basic picel data. Granting to generate the picel data; And
e) dividing the analysis region into at least one subregion block, and calculating population flow data by mapping a subregion code in the subregion block based on the picel data;
In step d), the floating population information analysis method capable of providing real-time floating population data using the PICS algorithm, wherein the base station ID is used as a join key during a spatial join.
The method of claim 1,
Step e),
Removing the time zone column from the pre-aggregation data using table-type pre-aggregation data including a reference time, a time zone code, a base station ID, a sector, and a sex / age population;
Dividing a time zone code into a day of the week code in the aggregated population total value, counting the number of days for each day of the day of the week data, and counting the number of days for each day of the population;
Calculating weekday_floating population data corresponding to the weekend among the day codes and weekday_floating population data not corresponding to the weekend among the day codes;
Generating unified floating population data by joining the weekday_floating population data and the weekend_floating population data, applying a carrier correction ratio and a 3G user ratio to the unifying floating population data, and generating a day column with a day code column; And
Real-time floating population data using the Fiscel algorithm, characterized in that it further comprises the step of deleting the row of the total value of the row ('0'), and then grouping by month / subregion / by cell to generate the floating population data by day Method for analyzing floating population information.

Images