WO2021021035A1

WO2021021035A1 - Data modeling and analysis system for geographic information systems

Info

Publication number: WO2021021035A1
Application number: PCT/TR2019/050630
Authority: WO
Inventors: Pinar ERASLAN
Original assignee: Maptriks Bilisim Teknolojileri Sanayi Ve Ticaret A.S
Priority date: 2019-07-29
Filing date: 2019-07-29
Publication date: 2021-02-04

Abstract

The invention is a data modeling and analysis system in which meaningful classifications are formed by grouping demographic data and industry-specific geographic data, shortening processes that take a long time to organize and analyze data; comprising, source database (2), where data sources (1) containing demographic and industry-specific geographic data consisting of various sources from geographic data sets, statistical institutions, are stored, polygons (7) created by dividing the geographical regions desired to be analyzed into areas of certain sizes via mapping engine (3), the unit of analysis (4), which allows the calculation of the source data (1) by integrating it into polygons (7) and the raw data generated on polygons (7) after calculations, to be organized, clustered and interpreted using statistical and geographic information system tools (5).

Description

Data Modeling And Analysis System For Geographic Information Systems Technical Field

The invention relates to a system that offers solutions in the fields of geographic information systems, geographic marketing, and data analysis, and that can be used in sectors such as retail sector, rapid consumption, real estate, consulting, media, etc.

Prior Art

Today, demographic and geographic results made through map software are associated with customer data and then various statistical and geographic information systems (GIS) tools are used to obtain analysis results and inferences. All data are gathered together to form the lower and upper segments for the target audience.

In existing systems, it takes a lot of time to collect and assemble data from different sources and to make queries. In addition, similar queries / methods are repeated for each customer, resulting in loss of time / cost and labor.

In the existing systems, there is no micro - scale database that includes both demographic data and sectoral geographic data throughout the country and that groups these data to create meaningful classifications. Therefore, companies cannot include geographical values in their studies while making various estimations and analyses related to store or customer data.

The technical survey revealed an application with number KR20140132795 (A) which relates to a system and method for estimating of the spatial development patterns based on urban form determination factors, more specifically, a system and a method for estimating the spatial development model and density of a future urban area through splitting the area. Using a geographic information system, the hexagonal polygon aims to utilize the physical urban form determination factors (physiographic characteristics, traffic facility accessibility, and use of district status) of a total urban area and divided area. To achieve this goal, an embodiment of the current invention comprises the system for estimating a spatial development model based on an urban form determination factor, a split area information collection part, a computation part, and a prediction part.

As is seen, the system is related to monitoring the development of the physical characteristics of the regions by dividing the regions into small areas, yet does not mention a structure that can provide solutions to the above-mentioned disadvantages and a system that provides demographic and geographical information to be analyzed in micro-scale.

As a result, due to the above-mentioned drawbacks and the inadequacy of the existing solutions, an improvement in the technical field has been required.

The Purpose Of Invention

The invention is intended to provide a structure with different technical features which, unlike the structures used in the present technique, brings a new development to this area.

The main purpose of the invention is to establish micro-scale databases that include both demographic and industry-specific geographic data throughout the country and where meaningful classifications are formed by grouping these data.

Another purpose of the invention is to enable companies to incorporate geographic values into their work while making various predictions and analyses about store or customer data so that they can observe what values sales relate to in a short period of time.

Another purpose of the invention is to enable future- oriented turnover / sales etc. estimations by combining statistical methods, artificial intelligence, and machine learning algorithms in this system, which was created together with a mapping infrastructure.

In the system of the invention, demographics released annually by TUIK (or similar institutions in different countries) throughout Turkey have been reduced to smaller scales than the neighborhood detail (consisting of approximately 600m by 700m hexagons). In this method of reduction, map/GIS engine and algorithms have been used to calculate the population of the neighborhood in smaller areas developed with the invention (these algorithms can compute and reflect a much more accurate ratio - with a much lower error margin - by using the road network and road track information instead of the polygon in the polygon process).

The hexagonal shape has been specially selected. A hexagonal form has the most effective form of storage. Maximum data can be used within the minimum space. Hexagons are easily added to each other and can easily be used to visualize various classifications or groupings. With the special indexing method created over hexagons, queries can be made in the shortest way throughout Turkey or another country by associating many geographic, numerical and verbal data with hexagons. For each hexagon, besides data sets of institutions such as TUIK, many data sets that are taken from various institutions were reduced from region-province-county scale to micro-scales (hexagons) with statistical models.

A clustering method has been developed for the target groups of firms by combining raw demographic data sets on hexagons. Accordingly, it is possible to observe at a glance which people profile live in a hexagon. Within each hexagon, the profiles of people living in can be observed as a percentage, not only according to the target audience but also according to the neighborhood relations around them.

When combined with the customer's coordinates and sales information, this data set, designed in conjunction with the map base developed by the invention, can show where the customer can be geographically successful and where new opportunities are likely to be. The dominant sectors are grouped within every hexagon. For example, it can be observed at a glance whether the industry-specific theme of a hexagon is food and drink or furniture.

A demographic indexing method has been developed so that raw demographic data on hexagons can be perceived and read more easily. The indexing system consists of numbers on a scale of 0-400. For example, Index 50 represents the half of the Turkey average, 100 represents Turkey average, 200 represents 2 times higher than Turkey average, and index figures between 200 and 400 represent well above the upper values show. According to this, geographically distant regions throughout Turkey can be compared with each other and evaluated. Similar indexing standards can also be developed at different ranges and specific to different countries.

In order to fulfill the purposes described above, the invention is a data modeling and analysis system in which meaningful classifications are formed by grouping demographic data and industry-specific geographic data, shortening processes that take a long time to organize and analyze data; comprising,

• Source database, where data sources containing demographic and industry- specific geographic data consisting of various sources from geographic data sets, statistical institutions, are stored,

• Polygons created by dividing the geographical regions desired to be analyzed into areas of certain sizes via mapping engine,

• The unit of analysis, which allows the calculation of the source data by integrating it into hexagons and the raw data generated on hexagons after calculations, to be organized, clustered and interpreted using statistical and geographic information system tools,

• Polygon database in which the hexagons that have completed the calculation and analysis process in the said unit of analysis are recorded,

• The software unit that enables the interpretation of the data obtained from the customer database containing the customer's data and the arranged / analyzed data contained in the said hexagons received from the hexagonal database,

• Reporting, analysis and visualization unit with machine learning algorithms, artificial intelligence support, and sector-specific query and analysis tools, which enables reports to be received.

The structural and characteristic features and all advantages of the invention outlined in the drawings below and in the detailed description made by referring these figures will be understood clearly, therefore the evaluation should be made by taking these figures and detailed explanation into consideration.

Brief Description of the Figures

Figure 1 is the general representation of the system of the invention.

Figure 2 is a schematic representation of the hexagon and its parts, preferably meter lengths.

The drawings do not necessarily have to be scaled, and the details that are not necessary to understand the invention may be neglected. Other than that, elements that are substantially identical, or at least have substantially identical functions, are denoted by the same number.

Reference Numbers

1. Data sources

2. Source database

3. Mapping engine

4. Analysis unit

4.1 Geographical area analysis unit

5. Statistical and geographic information system tools

6. Polygon database

7. Polygon

8. Software unit

9. Customer database

10. Reporting, analysis, and visualization unit

11. Point Processing Unit (point of interest = POI)

Detailed Description Of The Invention

In this detailed description, preferred structures of the invention are explained only for a better understanding of the subject matter and without any restrictive effect.

The invention relates to minimizing the processes that take a long time to organize and analyze the data as mentioned above, bringing together existing data to produce meaningful results, and developing a new approach to the market in this context.

The structures that form the data modeling system of the invention are as follows. The data sources (1 ) containing demographic and industry-specific geographic data consisting of various sources from geographic data sets, statistical institutions, etc. are stored within a source database (2).

Data sources (1 ) that are collected on a single platform within the source database (2) are then subjected to the editing and data processing operations. The regions to be analyzed employing the mapping engine (3) are divided into polygonal (7) areas of certain sizes. The circumferential circles of the said polygons (7) preferentially have a radius of 600-700 meters. Polygons preferably have a hexagonal structure.

The polygon (7) field information received via the mapping engine (3) and the data sources (1 ) received from the source database (2) are integrated into the analysis unit (4). In the analysis process, all the source data (1 ) is calculated together with the mapping engine (3) and the analysis unit (4) in the polygons (7) that have been created. After calculations, raw data generated on polygons (7) is organized, clustered, and interpreted using various statistical and geographic information system tools (5). The raw data stored in polygons (7) is indexed utilizing a special indexing method developed and then classified with using various statistical methods. Thus, data from areas divided into polygons (7) throughout Turkey or different countries/regions as preferred are calculated and analyzed in each polygon (7) particularly. The demographic data in polygons (7) is a collection of many various demographic data across Turkey, creating socio-economic clusters.

The polygons (7) in which the calculation and analysis process have been completed are recorded in the polygon database (6). The formed polygons (7) are specifically named for creating a common language within the system of the invention and customers. Each polygon (7) has been called“Quark”. The patterns formed by the polygons (7) coming together in line with the common features are called“Atom”. Polygons (7) and polygon database (6) have a particular hexagonal form. The hexagonal form reveals the most ideal and appropriate structure.

Reduced, clustered, classified, and interpreted polygons (7) recorded in the polygon database (6) are used by a software unit (8). Following the transfer of the data received from the customer database (9) containing the customer data to the software unit (8), the organized/analyzed data in said polygons (7) can be interpreted together with the customer data. In the reporting, analysis and visualization unit (10), special reports can be obtained along with machine learning algorithms, artificial intelligence support, and industry-specific interpretation and analysis tools.

The analysis unit (4) comprises a geographical area analysis unit (4.1 ), which produces a realistic result and reduces the margin of error by using the result of other geographical information layers. In addition, it comprises a point processing unit (11 ) that interacts with the bidirectional interaction, sees the millions of points the client has seen and accesses all the detailed information of that point while displaying millions of points (multiple points that the client cannot remove) depending on the unit. When creating a server-side view, image fragments (for example, millions of images in 16 image fragments) are sent to the client, where millions of points (images, logos, etc.) are depicted, then, when the client clicks on the point it has seen, this click information is processed on the server and the information to which point it clicked (with pixel sensitivity) is transmitted to the client. Then, the client can send requests to the analysis unit of the server to use all kinds of information visualization and different analyses related to this point. Thus, data transfer is low and also speed is increased. Except for showing the points in their bare forms, the point processing unit (11 ) can also show their relationship to each other on a model. While giving importance to each point category, heat maps of the proximity and distance of this point are obtained on the map. And different refractions can be obtained according to the desired standards and the desired preferences can be made according to the color of the pallet to be given. It is possible to see where these are clustered according to points of interest or the locations you prioritize.

Claims

1. The invention is a data modeling and analysis system in which meaningful classifications are formed by grouping demographic data and industry-specific geographic data, shortening processes that take a long time to organize and analyze data; comprising,

• source database (2), where data sources (1 ) containing demographic and industry-specific geographic data consisting of various sources from geographic data sets, statistical institutions, are stored,

• polygons (7) created by dividing the geographical regions desired to be analyzed into areas of certain sizes via mapping engine (3),

• the unit of analysis (4), which allows the calculation of the source data (1 ) by integrating it into polygons (7) and the raw data generated on polygons (7) after calculations, to be organized, clustered and interpreted using statistical and geographic information system tools (5),

• a geographical area analysis unit (4.1 ), which produces a realistic result and reduces the margin of error by using the result of analysis unit (4) and other geographical information layers,

• polygon database (6) in which the polygons (7) that have completed the calculation and analysis process in the said unit of analysis (4) are recorded,

• the software unit (8) that enables the interpretation of the data obtained from the customer database (9) containing the customer's data and the arranged/analyzed data contained in the said polygons (7) received from the polygon database (6),

• reporting, analysis and visualization unit (10) with machine learning algorithms, artificial intelligence support, and sector-specific query and analysis tools, which enables reports to be received.

2. The invention is a data modeling and analysis system according to Claim 1 , wherein; comprising polygons (7) with a hexagonal structure, preferably 600- 700 meters of circumference radius.

3. The invention is a data modeling and analysis system according to Claim 1 , wherein; comprising a polygon database (6) preferably hexagonal, in which the said polygons (7) are recorded.

4. The invention is a data modeling and analysis system according to Claim 1 , wherein; comprising a point processing unit (11 ) that interacts with the bidirectional interaction, sees the millions of points the client has seen and accesses all the detailed information of that point while displaying millions of points (multiple points that the client cannot remove) depending on the unit.