KR102534726B1 - Method and apparatus for performing area based place search - Google Patents

Abstract

The present invention relates to a method and apparatus for searching a place based on an area. In the method according to an embodiment of the present invention, an input map used for a region-based place search is divided into input sub-maps, place search results are collected for each input sub-map, and a distance weight is applied to each input sub-map based on the collection result. , and an output map may be generated by performing a convolution operation between the input map and the weight matrix.
In the present invention, an output map is divided into output submaps, and a distance weight of an output submap may be determined based on distance weights of a plurality of input submaps.

Description

METHOD AND APPARATUS FOR PERFORMING AREA BASED PLACE SEARCH

The present invention relates to methods and apparatus for performing area based place searches.

Various methods for servicing electronic maps have been proposed. Recent electronic map services provide a variety of additional services, such as a Points Of Interest (POI) search and route search function, real-time public transportation information, and restaurant information, in addition to map display.

In region-based place search, a query entered by a user is analyzed to determine the user's intention, and based on the user's intention, a plurality of search results are prioritized, and search results are provided to the user according to the priority. .

Recently, it is necessary to develop a region-based place search technology capable of providing more accurate search results to users.

The foregoing background art is technical information that the inventor possessed for derivation of the present invention or acquired during the derivation process of the present invention, and cannot necessarily be said to be known art disclosed to the general public prior to filing the present invention.

SUMMARY OF THE INVENTION The present invention provides a method and apparatus for performing geographic location retrieval. The problem to be solved by the present invention is not limited to the above-mentioned problems, and other problems and advantages of the present invention that are not mentioned can be understood by the following description and more clearly understood by the embodiments of the present invention. It will be. In addition, it will be appreciated that the problems and advantages to be solved by the present invention can be realized by the means and combinations indicated in the claims.

As a technical means for achieving the above-described technical problem, a first aspect of the present disclosure is a method for generating a driving route, in which an input map used for a region-based place search is input as a submap. Dividing into; collecting place search results for each input sub-map; calculating a distance weight for each input sub-map based on the collection result; and generating an output map by performing a convolution operation between the input map and a weight matrix, wherein the output map is divided into output submaps, and the distance weights of the output submaps are a plurality of the output submaps. It is possible to provide a method that is determined based on the distance weight of the input submap.

A second aspect of the present disclosure provides an apparatus for searching for a place based on a region, comprising: a memory in which at least one program is stored; and a processor performing an operation by executing the at least one program, wherein the processor divides an input map used for local search into input sub-maps; collecting place search results for each input sub-map; calculating a distance weight for each input sub-map based on the collection result; and generating an output map by performing a convolution operation between the input map and a weight matrix, wherein the output map is divided into output submaps, and the distance weights of the output submaps are a plurality of the output submaps. It is determined based on the distance weight of the input submap.

A third aspect of the present disclosure may provide a computer-readable recording medium recording a program for executing the method according to the first aspect on a computer.

In addition to this, another method for implementing the present invention, another system, and a computer readable recording medium storing a computer program for executing the method may be further provided.

Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims and detailed description of the invention.

According to the above-described problem solving means of the present disclosure, when a user performs a place search, the priority of the search result is determined by considering not only the distance weight of the area where the user is located but also the distance weight of neighboring areas. It is possible to provide users with more accurate search results that are not concentrated only in regions.

In addition, according to the above-mentioned problem solving means of the present disclosure, it is possible to provide a user with an accurate search result considering the characteristics of a query by assigning a distance weight according to the regional characteristics of a query input by a user.

1 is a system diagram including a user terminal and a region-based place search server according to an embodiment.
2A to 2B are diagrams for explaining an example of providing a place search result from a region-based place search server according to an embodiment.
3A and 3B are diagrams for explaining an example of dividing an input map into input sub-maps according to an exemplary embodiment.
4 is an exemplary diagram for explaining a method of calculating a distance weight for each input sub-map according to an exemplary embodiment.
5A and 5B are exemplary diagrams for explaining a method of generating an output map according to an exemplary embodiment.
6 is a flowchart of a method for performing a region-based place search according to an exemplary embodiment.
7 is a block diagram of a region-based place search server according to an embodiment.

Advantages and features of the present invention, and methods for achieving them will become clear with reference to the detailed description of embodiments in conjunction with the accompanying drawings. However, it should be understood that the present invention is not limited to the embodiments presented below, but may be implemented in a variety of different forms, and includes all conversions, equivalents, and substitutes included in the spirit and scope of the present invention. . The embodiments presented below are provided to complete the disclosure of the present invention and to fully inform those skilled in the art of the scope of the invention to which the present invention belongs. In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Some embodiments of the present disclosure may be represented as functional block structures and various processing steps. Some or all of these functional blocks may be implemented as a varying number of hardware and/or software components that perform specific functions. For example, functional blocks of the present disclosure may be implemented by one or more microprocessors or circuit configurations for a predetermined function. Also, for example, the functional blocks of this disclosure may be implemented in various programming or scripting languages. Functional blocks may be implemented as an algorithm running on one or more processors. In addition, the present disclosure may employ prior art for electronic environment setup, signal processing, and/or data processing, etc. Terms such as “mechanism,” “element,” “means,” and “composition” will be used broadly. It can be, and is not limited to mechanical and physical configurations.

In addition, connecting lines or connecting members between components shown in the drawings are only examples of functional connections and/or physical or circuit connections. In an actual device, connections between components may be represented by various functional connections, physical connections, or circuit connections that can be replaced or added.

Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings.

1 is a system diagram including a user terminal and a region-based place search server according to an embodiment.

A system according to an embodiment may include a user terminal 1000 and a region-based place search server 2000 (hereinafter, a search server).

The user terminal 1000 includes a smart phone, a tablet PC, a PC, a smart TV, a mobile phone, a personal digital assistant (PDA), a laptop, a media player, a micro server, a global positioning system (GPS) device, an e-book reader, and a digital broadcasting terminal. , navigation, kiosks, MP3 players, digital cameras, consumer electronics, devices with cameras, and other mobile or non-mobile computing devices. Also, the user terminal 1000 may be a wearable device having a communication function and a data processing function, such as a watch, glasses, a hair band, and a ring. However, it is not limited thereto.

The search server 2000 may be implemented as a computer device or a plurality of computer devices that communicate over a network to provide commands, codes, files, contents, services, and the like.

The search server 2000 may generate an output map by performing a convolution operation between the input map and the weight matrix. The input map is divided into a plurality of input submaps, and the search server 2000 may calculate a distance weight for each input submap based on the place search result collected for each input submap. The output map is divided into a plurality of output submaps, and the search server 2000 may determine the distance weight of the output submap based on the distance weights of the plurality of input submaps.

The user terminal 1000 and the search server 2000 may perform communication using the network 3000 . In one embodiment, an application is installed in the user terminal 1000, and the search server 2000 may be a server that manages the application. The search server 2000 may exchange data with the user terminal 1000 through an application installed in the user terminal 1000 .

The network 3000 includes a local area network (LAN), a wide area network (WAN), a value added network (VAN), a mobile radio communication network, a satellite communication network, and their mutual It is a data communication network in a comprehensive sense that includes a combination and enables each network constituent entity shown in FIG. 1 to communicate smoothly with each other, and may include wired Internet, wireless Internet, and mobile wireless communication network. In addition, wireless communication, for example, wireless LAN (Wi-Fi), Bluetooth, Bluetooth low energy (Bluetooth low energy), Zigbee, WFD (Wi-Fi Direct), UWB (ultra wideband), infrared communication (IrDA, infrared Data Association), NFC (Near Field Communication), etc. may be present, but are not limited thereto.

Meanwhile, in FIG. 1, the search server 2000 is illustrated as performing communication with one user terminal 1000 using a network, but this is only an example. Communication may be performed using a network.

2A to 2B are diagrams for explaining an example of providing a place search result from a region-based place search server according to an embodiment.

The user terminal 1000 may transmit data required for place search to the search server 2000 . For example, the user terminal 1000 may transmit a source query, a destination query, a source latitude and longitude, and a destination latitude and longitude to the search server 2000, but the type of transmitted data is not limited thereto.

To search for a desired point of interest (POI), the user may input a name, industry, region, menu, product, etc. into the user terminal 1000 as a query 210 . The user terminal 1000 may transmit the query 210 input by the user to the search server 2000 .

The search server 2000 may determine the intention of the query 210 received from the user terminal 1000 . The search server 2000 may determine the intent of the query 210 based on which category of words the query 210 is composed of. For example, the query 210 may include business type, business name, region + business type, area + business name, business type + business name, business name near a landmark, industry type near a landmark, and the like.

The search server 2000 may determine weights of evaluation factors based on the intent of the query 210 . The ranking factor is used to prioritize search results. For example, the evaluation factors may include the distance between the user's location and the search result, the name match between the query 210 and the search result, the industry match between the query 210 and the search result, and the search frequency for each search result. Not limited.

Depending on the intent of the query 210, the weight assigned to each evaluation factor may vary. For example, if the intention of the query 210 is to search for a point closest to the user's location as a point of interest, the search server 2000 assigns a high weight to the distance between the user's location and the search result among evaluation factors. can be granted On the other hand, if the intention of the query 210 is to search for a point whose name matches as a point of interest regardless of distance, the search server 2000 has a high degree of name matching between the query 210 and the search result among the evaluation factors. weight can be assigned.

The search server 2000 may assign an appropriate weight to each of the evaluation factors based on the intent of the query 210 . Also, the search server 2000 may prioritize search results based on weighted evaluation factors. For example, when a high weight is given to a distance between a user's location and a search result, a search result closer to the user's location may have a higher priority. On the other hand, when a high weight is assigned to the name matching between the query 210 and the search result, a search result having a high name matching with the query 210 may have a higher priority.

The search server 2000 transmits search results with priorities reflected to the user terminal 1000, and the user terminal 1000 may provide them to the user. For example, search results may be displayed on the user terminal 1000 in the order of search results having a high priority to a search result having a low priority.

Referring to FIG. 2A , the user terminal 1000 may receive an input for inputting a departure point and a destination from the user. For example, the user may input 'Seolleung Station' as the starting point and 'hardware store' as the destination through the input interface of the user terminal 1000 . Meanwhile, the starting point may be determined based on the location of the user terminal 1000 instead of directly input by the user.

The user terminal 1000 may transmit 'hardware store' as a query to the search server 2000 .

Since the 'hardware store' is composed of only business types, the search server 2000 may assign a high weight to the distance between the user's location and the search result and the degree of business matching. The search server 2000 may assign high priority to search results close to the user's location and transmit search results reflecting the priority to the user terminal 1000 . The user terminal 1000 may display the place search results 220 in the order of a search result close to the user's location to a search result distant from the user's location.

When the user selects a predetermined search result 221, the user terminal 1000 may determine the selected search result 221 as a destination, generate a movement route between the starting point and the destination, and provide the selected search result 221 to the user.

Referring to FIG. 2B , the user terminal 1000 may receive an input for inputting a departure point and a destination from the user. For example, the user may input 'Seolleung Station' as the starting point and 'Haeundae Raw Fish Restaurant' as the destination through the input interface of the user terminal 1000 . Meanwhile, the starting point may be determined based on the location of the user terminal 1000 instead of directly input by the user.

The user terminal 1000 may transmit 'Haeundae raw fish restaurant' to the search server 2000 .

Since 'Haeundae Sashimi Restaurant' is composed of region + industry, the search server 2000 can assign a high weight to the name matching between the query 210 and the search result and the industry matching between the query 230 and the search result. The search server 2000 may assign a high priority to a search result having a name matching the query 230 and a business category matching the same, and transmit the search result reflecting the priority to the user terminal 1000 . The user terminal 1000 may display the place search results 240 in the order of search results having a high name matching degree and a low industry matching degree.

When the user selects a predetermined search result 241, the user terminal 1000 may determine the selected search result 241 as a destination, generate a travel route between the starting point and the destination, and provide the selected search result 241 to the user.

3A and 3B are diagrams for explaining an example of dividing an input map into input sub-maps according to an exemplary embodiment.

Referring to FIGS. 3A and 3B , an input map 310 used for a region-based place search may be divided into a plurality of input sub-maps 311 .

The search server 2000 may collect place search results for each input sub map 311 . For example, when a specific user searches for a place in an area corresponding to the A6 input submap, the search server 2000 may store the search result by matching it to the A6 input submap. The place search result may include, but is not limited to, a query input by a user, location information of a starting point, location information of a destination, and a distance between a starting point and a destination.

In one embodiment, the input map 310 may be divided into equally sized input sub-maps 311 . In another embodiment, the input map 310 may be divided into input sub-maps 311 based on user density. For example, the input map 310 may be divided so that user densities are similar for each input sub map 311 .

4 is an exemplary diagram for explaining a method of calculating a distance weight for each input sub-map according to an exemplary embodiment.

Referring to FIG. 4 , an input map 410 used for a region-based place search may be divided into a plurality of input sub-maps 411 .

When a user performs a place search through the user terminal 1000, the search server 2000 may receive an input sub map ID, a query, and data about a distance between a departure point and a destination from the user terminal 1000. The input sub map ID is information representing the location of the user terminal 1000 and may be determined based on GPS information. That is, the search server 2000 may collect place search results for each input sub map.

Referring to FIG. 4, 'Haeundae', 'Haeundae restaurant', and 'Haeundae raw fish restaurant' are searched as queries in the A14 input submap, and the user's current location (ie, starting point) and the search result selected by the user (ie, destination) may be 3.5 km on average.

On the other hand, 'Haeundae', 'Haeundae parking lot', and 'Haeundae Beach' are searched as queries in the A15 input submap, and the distance between the user's current location (i.e., departure point) and the user's selected search result (i.e., destination) may be 380 km on average.

The search server 2000 may calculate a distance weight for each input submap 411 for a specific query based on the reference distance and the average distance between the starting point and the destination. If the query is changed, the distance weight for each input sub map 411 may also be changed.

The distance weight may be calculated using Equation 1 below or Equation 2 below.

The reference distance may be set differently according to the input map 410 . The input map 410 may correspond to the entire range of Korea, to a range of a specific administrative district such as a province, city, or county, or to an arbitrary regional range. Based on the area of the region corresponding to the input map 410, the search server 2000 may set a reference distance. For example, the reference distance may be set to the diagonal distance of Korea, but is not limited thereto. In FIG. 4 , it is assumed that the reference distance is 400 km.

According to Equation 2 above, the distance weight of the A14 input submap for the query related to 'Haeundae' can be calculated as '1 - log(3.5)/log(400) = 0.801'. Also, according to Equation 2 above, the distance weight of the A15 input submap for the query related to 'Haeundae' can be calculated as '1 - log(380)/log(400) = 0.009'.

In the A14 input submap, a high distance weight for a query related to 'Haeundae' can be calculated. That is, when a user is located on the A14 input submap and searches for a query related to 'Haeundae', the search server 2000 may give a high priority to a search result close to the user's location and provide it to the user.

On the other hand, in the A15 input submap, a low distance weight for a query related to 'Haeundae' can be calculated. That is, when a user is located on the A15 input submap and searches for a query related to 'Haeundae', the search server 2000 gives higher priority to search results with high popularity or name matching rather than search results close to the user's location. It can be granted and provided to the user.

In this way, after calculating the distance weight for each input submap, when the user performs a region-based place search later, different distance weights are applied depending on where the user is located to determine the priority of the search result differently. , it is possible to provide more optimized search results to users.

However, when the search result is prioritized based only on the distance weight of the input submap where the user is located, the accuracy of the search result may be lowered because the distance weight of the neighboring input submap is not considered at all. For example, when the user is located on the input submap A1, the user may be located close to the boundary of the input submap A1 and the input submap A2 within the input submap A1. In this case, when determining the priority of search results, not only the distance weight of the input submap A1 but also the distance weight of the input submap A2 are considered, and thus more optimized search results can be provided to the user.

5A and 5B are exemplary diagrams for explaining a method of generating an output map according to an exemplary embodiment.

Referring to FIG. 5A , the search server 2000 may apply padding 512 to the input map 511 before performing a convolution operation between the input map 511 and the weight matrix 520 . The padding 512 refers to filling the periphery of the input map 511 with a specific value and increasing it. Padding is mainly used to adjust the spatial size of the output map 530 . For example, the input map 510 may be generated after padding by applying zero-padding to the input map 511 .

Specifically, when performing a convolution operation between the input map 511 before padding is applied and the weight matrix 520, the size of the input map 511 before padding is applied is 4 x 4, and the size of the weight matrix 520 is Since is 3 x 3, the size of the output map 530 becomes 2 x 2. In the present invention, padding 512 may be applied to the input map 511 so that the sizes of the input map 511 and the output map 530 are the same.

Referring to FIG. 5B, when performing a convolution operation between the input map 510 and the weight matrix 520 after padding, the size of the input map 510 after padding is 6 x 6 and the size of the weight matrix 520 is 3 x 6. 3, the size of the output map 530 becomes 4 x 4. That is, the sizes of the input map 511 and the output map 530 become the same.

Just as the input map 511 is divided into a plurality of input sub-maps, the output map 530 may also be divided into a plurality of output sub-maps. A distance weight for each query may be stored in each output submap. A distance weight for each query stored in each output submap may be determined based on distance weights of a plurality of input submaps.

In an embodiment, a distance weight of a reference input submap corresponding to the specific output submap and a distance weight of neighboring input submaps around the reference input submap may be reflected in the distance weight of the specific output submap.

For example, referring to FIG. 5B , the distance weight of the reference input submap A1 and the distance weights of the neighboring input submaps A2, A5, and A6 are reflected in the distance weight of the output submap B1, and the distance weight of the output submap B4 is reflected. The distance weight of the reference input submap A4 and the distance weights of the neighboring input submaps A3, A7 and A8 are reflected in B14, and the distance weight of the reference input submap A14 and the neighboring input submaps A9 and A10 are reflected in the distance weight of the output submap B14. , distance weights of A11, A13, and A15 may be reflected.

Meanwhile, the distance weights of the reference input submap and the distance weights of neighboring input submaps, which are reflected in the distance weights of the output submap, may be determined by element values of the weight matrix 520 . For example, the sum of element values of the weight matrix 520 may be 1, but is not limited thereto.

In an embodiment, the search server 2000 sets the weight matrix 520 so that the distance weight reflection ratio of the reference input submap, which is reflected in the distance weight of the output submap, is higher than the distance weight reflection ratio of the neighboring input submap. element values can be set. In addition, the reflection ratio of the neighboring input submap in contact with the surface of the reference input submap, which is reflected in the distance weight of the output submap, is higher than the reflection ratio of the neighboring input submap in contact with the vertex of the reference input submap. (2000) may set an element value of the weight matrix 520.

For example, referring to FIG. 5B , the distance weight ratio of A1, which is the reference input submap, is most highly reflected in the distance weight of the output submap B1, as 0.3, and then A2, which is a neighboring input submap adjacent to the surface of the reference input submap. and A5 are reflected as 0.15, and the lowest distance weight ratio of A6, which is a neighboring input submap adjacent to the vertex of the reference input submap, may be reflected as 0.025.

That is, if the distance weight of input submap A1 for a particular query is 0.8, the distance weight of input submap A2 is 0.7, the distance weight of input submap A5 is 0.75, and the distance weight of input submap A6 is 0.1. , the distance weight of the B1 output submap can be 0.46 (=0.8 X 0.3 + (0.7 + 0.75) X 0.15 + 0.1 X 0.025). Meanwhile, in order to prevent the distance weight of the output submap from being calculated to be small by the padding 512, the distance weight of the output submap is divided by the element value of the weight matrix used to calculate the distance weight of the output submap. The distance weight of the sub map can be corrected. In this case, the distance weight of the B1 output submap according to the above example may be 0.736 (=0.46/(0.3+0.15+0.15+0.025)).

After the output map 530 is generated through a convolution operation between the input map 510 and the weight matrix 520 after padding, the search server 2000 may receive a place search request from the user terminal 1000 . The search server 2000 may determine an output submap corresponding to the location of the user terminal 1000 based on location information of the user terminal 1000 and obtain a distance weight of the determined output submap. As described above, the distance weight obtained from the output submap by the search server 2000 may be a value in which not only the distance weight of the input submap where the user terminal 1000 is located, but also the distance weight of neighboring input submaps are reflected. The search server 2000 may perform a place search based on the distance weight of the output map 530 and transmit a place search result to the user terminal 1000 .

In the present invention, the priority of search results is determined by considering not only the distance weight of the input submap where the user is located but also the distance weight of neighboring input submaps, so that more accurate search results that are not biased to the input submap where the user is located are provided to the user. can provide

6 is a flowchart of a method for performing a region-based place search according to an exemplary embodiment.

Referring to FIG. 6 , in step 610, the search server may classify an input map used for a region-based place search into input sub-maps.

In one embodiment, the search server may divide the input map into equally sized input sub-maps. In another embodiment, the input map may be divided into input sub-maps based on user density. For example, input maps may be divided so that user densities are similar for each input sub-map.

In step 620, the search server may collect place search results for each input sub-map.

The search server may collect a query input by a user, location information of a starting point, location information of a destination, and a distance between a starting point and a destination.

Specifically, when a user performs a place search through a user terminal, the search server may receive data about an input sub map ID, a query, and a distance between a departure point and a destination from the user terminal. The input sub map ID is information indicating the location of the user terminal and may be determined based on GPS information. That is, the search server may collect place search results for each input sub-map.

In step 630, the search server may calculate a distance weight for each input sub-map based on the collection result.

The search server may calculate an average distance between an origin and a destination for a predetermined query in the input submap. The search server may calculate a distance weight based on the reference distance and the average distance between the starting point and the destination.

In one embodiment, the search server may differently set the reference distance according to the input sub-map.

In step 640, the search server may generate an output map by performing a convolution operation between the input map and the weight matrix.

An output map is divided into output submaps, and a distance weight of the output submap may be determined based on distance weights of a plurality of input submaps. Specifically, the distance weight of the reference input submap corresponding to the specific output submap and the distance weight of neighboring input submaps around the reference input submap may be reflected in the distance weight of the specific output submap.

After the output map is generated, the search server may receive a search request from the user. The search server may identify an output submap corresponding to the location of the user in response to receiving the search request. The search server may obtain a distance weight of the identified output sub-map for a query input by a user, and provide a search result based on the acquired distance weight.

7 is a block diagram of a region-based place search server according to an embodiment.

Referring to FIG. 7 , a region-based place search server 700 may include a communication unit 710, a processor 720, and a DB 730. In the application operating server 1000 of FIG. 7 , only components related to the embodiment are shown. Accordingly, those skilled in the art can understand that other general-purpose components may be further included in addition to the components shown in FIG. 7 .

The communication unit 710 may include one or more components that enable wired/wireless communication between user terminals and payment standard data providing servers. For example, the communication unit 710 may include at least one of a short-range communication unit (not shown), a mobile communication unit (not shown), and a broadcast reception unit (not shown).

The DB 730 is hardware for storing various data processed in the search server 700, and may store programs for processing and controlling the processor 720. The DB 730 may store payment information, user information, and the like.

The DB 730 includes random access memory (RAM) such as dynamic random access memory (DRAM) and static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and CD-ROM. ROM, Blu-ray or other optical disk storage, hard disk drive (HDD), solid state drive (SSD), or flash memory.

The processor 720 controls overall operations of the search server 700 . For example, the processor 720 may generally control an input unit (not shown), a display (not shown), a communication unit 710, and the DB 730 by executing programs stored in the DB 730. The processor 720 may control the operation of the search server 1000 by executing programs stored in the DB 730 .

The processor 720 may control at least some of the operations of the applications described above with reference to FIGS. 1 to 8 .

The processor 720 includes application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, and microcontrollers. It may be implemented using at least one of micro-controllers, microprocessors, and electrical units for performing other functions.

Embodiments according to the present invention may be implemented in the form of a computer program that can be executed on a computer through various components, and such a computer program may be recorded on a computer-readable medium. At this time, the medium is a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a ROM hardware devices specially configured to store and execute program instructions, such as RAM, flash memory, and the like.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and usable to those skilled in the art of computer software. An example of a computer program may include not only machine language code generated by a compiler but also high-level language code that can be executed by a computer using an interpreter or the like.

According to one embodiment, the method according to various embodiments of the present disclosure may be included and provided in a computer program product. Computer program products may be traded between sellers and buyers as commodities. A computer program product is distributed in the form of a device-readable storage medium (eg compact disc read only memory (CD-ROM)), or through an application store (eg Play Store™) or between two user devices. It can be distributed (e.g., downloaded or uploaded) directly or online. In the case of online distribution, at least part of the computer program product may be temporarily stored or temporarily created in a device-readable storage medium such as a manufacturer's server, an application store server, or a relay server's memory.

The steps constituting the method according to the present invention may be performed in any suitable order unless an order is explicitly stated or stated to the contrary. The present invention is not necessarily limited according to the order of description of the steps. The use of all examples or exemplary terms (eg, etc.) in the present invention is simply to explain the present invention in detail, and the scope of the present invention is limited due to the examples or exemplary terms unless limited by the claims. it is not going to be In addition, those skilled in the art can appreciate that various modifications, combinations and changes can be made according to design conditions and factors within the scope of the appended claims or equivalents thereof.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments and should not be determined, and all scopes equivalent to or equivalently changed from the claims as well as the claims described below are within the scope of the spirit of the present invention. will be said to belong to

Claims (10)

In the area-based place search method,
classifying an input map used for region-based place search into input sub-maps;
collecting place search results for each input sub-map;
calculating a distance weight for each input sub-map based on the collection result; and
generating an output map by performing a convolution operation between the input map and a weight matrix;
including,
wherein the output map is divided into output submaps, and a distance weight of the output submap is determined based on distance weights of a plurality of input submaps. According to claim 1,
a distance weight of a reference input submap corresponding to the specific output submap and distance weights of neighboring input submaps around the reference input submap are reflected in the distance weight of the specific output submap. . According to claim 1,
The step of collecting the place search results,
collecting a query input by a user, location information of a starting point, location information of a destination, and a distance between a starting point and a destination;
A region-based place retrieval method comprising a. According to claim 3,
In the step of calculating the distance weight,
calculating an average distance between an origin and a destination for a predetermined query in the input submap;
calculating the distance weight based on a reference distance and the average distance between the source and destination;
A region-based place retrieval method comprising a. According to claim 4,
In the step of calculating the distance weight,
setting a reference distance based on the size of the input map;
Further comprising a, area-based place search method. According to claim 1,
The method,
identifying an output sub-map corresponding to the user's location;
obtaining a distance weight of the identified output sub-map for the query input by the user; and
providing a search result based on the obtained distance weight;
Further comprising a, area-based place search method. According to claim 1,
Generating the output map,
applying padding to the input map so that the sizes of the input map and the output map are the same; and
generating the output map by performing a convolution operation between the padded input map and the weight matrix;
A region-based place retrieval method comprising a. An apparatus for searching for a region-based place,
a memory in which at least one program is stored; and
a processor that performs calculations by executing the at least one program;
the processor,
Dividing an input map used for local search into input sub-maps;
collecting place search results for each input sub-map;
calculating a distance weight for each input sub-map based on the collection result; and
Generating an output map by performing a convolution operation between the input map and a weight matrix;
wherein the output map is divided into output submaps, and a distance weight of the output submap is determined based on distance weights of a plurality of input submaps. In the area-based place search method,
obtaining a query input by a user;
determining a reference input submap and a neighboring input submap around the reference input submap based on the location information of the user; and
providing a search result based on a distance weight of the reference input submap for the query and a distance weight of the neighboring input submap for the query;
A region-based place retrieval method comprising a. A computer-readable recording medium recording a program for executing the method of claim 1 on a computer.

Images