KR102148349B1 - Context-aware route finding algorithm for self-driving tourists using ontology - Google Patents

Abstract

Disclosed is a context-aware route search algorithm for self-driving travelers using ontology. A travel route search method comprises the following steps: building a driver experience ontology including a route section according to a driver experience; and searching for a travel route corresponding to a request of the traveler using the driver experience ontology.

Description

Context-aware route search algorithm for self-driving travelers using ontology {CONTEXT-AWARE ROUTE FINDING ALGORITHM FOR SELF-DRIVING TOURISTS USING ONTOLOGY}

The description below relates to a route finding technique.

Various tours have been organized around the world to travel to different countries, providing travel plans for travelers. Independent travelers primarily tour destination cities by self-driving and rental car.

Using information on the Internet, travelers can learn about tourist destinations and destination cities, and select several cities to visit. Various travel applications are being developed for specific travel plans of travelers. A mobile agent called DTG (Dynamic Tour Guide) that plans a trip according to the user's requirements is provided, and this application is mainly focused on navigation in tourist destinations. For example, Korean Laid-Open Patent Publication No. 10-2014-0030463 (published on March 12, 2014) discloses a knowledge-based driving route search method and a navigation terminal.

Other applications present key elements for designing and implementing a virtual travel operating system. It includes a service that finds the most suitable hotel according to the needs of the traveler, selects the best flight according to some criteria, and a navigation service. Navigation provides routes based on the traveler's location, needs, and defined destinations.

Another study is investigating other business programs for travel planning by travelers, where programs offer regular tours. For example, you plan a general tour for Italy according to your needs. Provides where to start and which cities to visit.

For self-driving travelers, a context-aware path search algorithm based on an ontology model of driver experience is provided.

A travel route search method executed in a computer system, wherein the computer system comprises at least one processor configured to execute computer readable instructions contained in a memory, the travel route search method comprising: by the at least one processor Building a driver experience ontology including a route section according to the driver experience; And searching, by the at least one processor, a travel route corresponding to a request of a traveler using the driver experience ontology.

According to an aspect, in the step of constructing the driver experience ontology, experimental routes and non-experimental routes are configured as a main class, and a traffic route is a subclass of the main class. And non-traffic routes can be configured.

According to another aspect, the step of searching for the travel route may include finding a class corresponding to a section between the location and the destination in the driver experience ontology when the location and destination of the traveler are input.

According to another aspect, in the step of searching for the travel route, if a class corresponding to the section between the location and the destination in the driver experience ontology does not exist, the location and the location and the location are determined using a hierarchical experimental network. It may further include the step of finding a point closest to at least one of the destinations.

According to another aspect, the travel route search method further includes, by the at least one processor, building a service ontology including data collected by an OSM (Open Street Map) as a service item related to a trip. In addition, in the step of searching for the travel route, the travel route may be searched using the driver experience ontology and the service ontology.

According to another aspect, in the step of searching for the travel route, when the location and destination of the traveler, and at least one service item to be used before the destination are input, a facility corresponding to the service item is regarded as a station, and the driver In the experience ontology, it is possible to find a class corresponding to the section between the location and the station, the section between the station, and the section between the station and the destination.

According to another aspect, in the step of searching for the travel route, a class corresponding to the traveler's request may be found through filtering using context information related to the traveler in the service ontology.

A computer system comprising: at least one processor configured to execute computer readable instructions contained in a memory, the at least one processor comprising: building a driver experience ontology including a route section according to a driver experience; And a computer system that processes a process of searching for a travel route corresponding to a request of a traveler using the driver experience ontology.

1 shows an example of a driver experience ontology according to an embodiment of the present invention.
2 illustrates an example of a service ontology class according to an embodiment of the present invention.
3 shows an example of a service ontology according to an embodiment of the present invention.
4 illustrates an example of context-related information according to an embodiment of the present invention.
5 illustrates two types of ontology-based route search according to an embodiment of the present invention.
6 illustrates an example of a route search algorithm for a business trip according to an embodiment of the present invention.
7 is an exemplary diagram for explaining a route search process of a business trip according to an embodiment of the present invention.
8 is a diagram illustrating an example of a route search algorithm for a tourism trip according to an embodiment of the present invention.
9 is a block diagram illustrating an example of an internal configuration of a computer system according to an embodiment of the present invention.

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

Embodiments of the present invention relate to a route search technology for travel.

Embodiments including those specifically disclosed herein may provide a context-aware route search algorithm based on an ontology model of a driver's experience for a self-driving traveler.

The route search algorithm according to the present invention considers two types of travel including business trips and sightseeing. In the route search algorithm according to the present invention, when the location and the destination are within the ontology of the driver experience, the route section can be searched from the ontology without any processing, and when the location or destination does not exist in the driver experience ontology, it is optimal for the user. You can present a route between your location and your destination. The path is calculated based on the ontology and other parts based on Dijkstra's algorithm.

In the route search algorithm according to the present invention, two ontology may be used according to tourism requirements. The ontology used in the present invention includes an ontology of driver experience and an ontology of essential services for travelers (hereinafter referred to as'service ontology'). By collecting necessary data for each ontology, both ontology are built. Data necessary for the ontology of the driver's experience is collected through an application that provides a travel route. The data required for service ontology is collected by OSM (Open Street Map) and placed in a related class. The route search algorithm according to the present invention is designed according to two ontologies.

Hereinafter, a specific embodiment of a context-aware route search method for a self-driving traveler using an ontology will be described.

In order to propose a route search algorithm for self-driving travelers, the ontology model is used to find a route in real time according to user requirements under all conditions. Because the path search algorithm takes a long time to find the optimal path between two points due to the large amount of data, the spatial experience of the modeling driver using the ontology promotes the timeliness of the service and provides the function to utilize the initial information without reprocessing. do. Also, the advantage of using Ontology to store data in OWL (Ontology Web Language) files is to improve the sharing, reuse and processing of domain knowledge.

Two ontologies (the driver's experience ontology and the essential service for travelers) are used for city route search. The driver experience ontology is modeled on the driver experience, and the service ontology is composed of service items related to travel, and provides the services that travelers need through the ontology. In general, travelers can request two routes. In other words, it is a business trip from the place of departure and destination, and tourism to visit a tourist destination on the way. When a traveler requests a route search for a business trip, only the driver experience ontology is used, whereas in the case of a tourism trip, both ontology are used.

Drivers' Experiences Ontology

1 shows an example of a driver experience ontology.

There are two main classes of driver experience ontology: experimental routes and non-experimental routes, which are classified by route type. Each of these classes contains two subclasses: the'traffic' route and the'non-traffic' route. Subclasses related to the experimental route class are routes that the driver traveled during peak transit times (7-10 am, 4-8 pm) and during off-peak hours. Each driver's route is defined as a separate class. Depending on the departure time, it is also defined as having no traffic subclass or traffic test route class. If the route is ubiquitous of the'non-traffic' class, the class name is location_destination, and if it is a subclass of the'traffic' class, the class name is location_destination_t representing traffic t. Individual of this class is a route section, and the ID of each route section is the name of the individual. X and Y coordinates are individual data properties. For example, if the driver's route between Poonak and Tajrish is considered in transit time, a class named Poonak_Tajrish_t and an OWL file are created as a subclass of the traffic class in the driver experience ontology. In this class, we define as an individual each segment of the route that must be taken to reach Tajrish from Poonak during peak traffic times. Table 1 shows the individual in the first section of the Poonak_Tajrish_t class.

The non-experimental route includes the route obtained through the route search algorithm. Depending on the departure time, each new route generated by the route search algorithm is defined with or without a'traffic' or'non-traffic' subclass of the non-experimental route class. If the route is a subclass of the'non-traffic' class, the class name is location_destination_n representing non-experimental n, and if the route is a subclass of the'traffic' class, the class name is location_destination_n_t. The individual of each route is defined in a separate file as a class with a name similar to the route class in the driver experience ontology. The reason for this work can prevent the ontology from becoming complicated.

Service Ontology (Ontology of Required Tourist Services)

Service Ontology deals with various classes that may be needed during travel, including shopping (bakeries, advertisements, shopping malls, supermarkets, etc.) and food (bars, cafes, fast food, food courts, restaurants, etc.).

FIG. 2 illustrates examples of a service ontology class and a subclass, and FIG. 3 illustrates an example of a service ontology.

Because travelers are not familiar with the new environment, they may face some accidents, for example, services that travelers usually need during their trip, such as food and accommodation, as well as the services they need after accidents such as vehicle breakdown, fire, theft, etc. Several services are also considered. All other facilities generally provided in the gym (body building, aerobics, etc.) are classified in the sports center class. Sports that require a field, such as golf, are classified separately.

Context Context-Related Information

Either user or data-centric approach can be considered in any system. In a data-centric approach, GIS (Geographic Information System) is designed according to the data after the expert collects service data, and the result is displayed to the user as an output. Therefore, since the user's preference is not considered in the system design, the output may not be optimal from the user's point of view. However, in the user-centered approach, the system design considers the user's preference and provides services according to the interests of travelers. Here, the results will vary according to users with different preferences.

In this respect, user-related information can be considered part of the context. Context-related information is assigned to personal and environmental contexts. 4 shows an example of context-related information.

Referring to FIG. 4, information such as user preference and user location is included in a personal context section. User preferences may include history or interests. If a traveler is interested in history, a class corresponding to user preference in the service ontology, that is, a class related to history in the Attractive Places class, can be navigated. Conversely, if the traveler is not interested in a historical place, they navigate to other subclasses not related to Attractive Places. In the Interests section, travelers can engage in their interests in terms of accommodation, food and sports. On the other hand, when requesting food, a place related to food is provided in consideration of the traveler's preference. This information is performed by filtering. In addition to speeding up, the system output is guaranteed to meet the needs and interests of the user. In the user location section, traveler's location information is stored using GPS. Also, the user's location can be regarded as a starting point of a trip.

In addition, the environmental context section may include information related to traffic volume, opening and closing times of museums and tourist attractions, amount of fuel, type of fuel, and departure time. Since the route of an experienced driver is used and data is collected at peak and off-peak transit times, the navigation route contains traffic information. Other information is used while navigating the user's requirements in the service ontology. For example, when the vehicle's fuel is low and the required fuel is gas, the system considers only the fuel center with gaseous fuel. When requesting an entertainment center, only centers open according to the departure time will be considered.

Based on driver experience ontology and service ontology Context Recognition path search algorithm

In the present invention, a network is first created and then a route search is performed accordingly. Each path section in each graph is regarded as an edge. The weight of the edge is determined based on the driving frequency by the drivers. The driving frequency passing through the edge may be defined as in Equation 1.

[Equation 1]

는 에지

의 정상적인 통과 횟수,

는 에지

의 통과 횟수,

과

는 에지로부터의 최소 및 최대 통과 횟수를 의미한다.here,

The edge

The normal number of passes of,

The edge

The number of passes of,

and

Means the minimum and maximum number of passes from the edge.

는 0이다. 따라서

은 0이다. 일반적으로 네트워크 그래프의 가중치는 수학식 2와 같이 결정되어 값을 반전시킨다.Equation 1 is based on the Min-Max normalization method of adding 1 to both the numerator and denominator to avoid negative results. For sections that are not experimental

Is 0. therefore

Is 0. In general, the weight of the network graph is determined as in Equation 2 to invert the value.

[Equation 2]

는 네트워크의 i번째 에지의 가중치이고, 길이

는 i번째 에지의 길이이고,

는 에지 통과 횟수를 에지 길이로 나눈 최대 통과 횟수를 의미한다.here,

Is the weight of the i-th edge of the network, and the length

Is the length of the i-th edge,

Denotes the maximum number of passes divided by the number of passes of the edge by the length of the edge.

In the Dijkstra algorithm, each edge with less weight is preferred, so a specific value is subtracted from the maximum value to invert the value. Experimental network 1 includes a route that drivers travel during low traffic times. Experimental network 2 includes the route that drivers travel during heavy traffic hours. The main network is the main layer of the city network. Typical experimental networks are included in experimental networks 1 and 2. In general, two types of route navigation are considered: tourism and business trip. 5 is a diagram illustrating an example of a route search for a tourism trip and a route search for a business trip.

(1) Business trip

If the traveler only needs a route between location and destination, the trip is considered a business trip. 6, a business trip uses a driver experience ontology. After receiving context, location and destination information, it is essential to review whether there are subclasses with locations and destinations entered in the ontology. In this case, the saved route is displayed to the user without route search. Otherwise, it is necessary to examine whether the location and destination exist in the experimental network. Consider either the experimental network (1 or 2) depending on the departure time. If both the location and the destination are located in the experimental network, then a graph is created and a route is found using the experimental network. If there is no location or destination in the experimental network, the closest point to one or both is found in the network.

7 is an exemplary diagram for explaining a route search process of a business trip according to an embodiment of the present invention. (a) shows the hierarchical experimental network, and (b) shows the square definition of the main network.

이다. 마지막으로, 더 큰 직사각형을 경로 탐색하여 출발지 또는 목적지와 가장 가까운 지점을 찾는다.Referring to FIG. 7, the distance between the starting point S and the destination D is first regarded as a rectangular diagonal d1 known as R1. Then add d1 to each side of the rectangle with the h value to make a large rectangle of R2. In fact, the h value is used to define a rectangular dimension (R2) route search to find the closest point to the origin and destination in the experimental network. If the value of h is large, the number of sections increases and the throughput increases, and if the value of h is small, it may not be possible to find the nearest point to the origin or destination. In this embodiment, the value of h is regarded as 0.01 d1 determined on the basis of trial and error. Thus, the diagonal (h) of the final rectangle is

to be. Finally, it navigates through a larger rectangle to find the point closest to the origin or destination.

For example, if both the origin (S) and the destination (D) are not within the experimental network (Fig. 7), the distance between S and D is considered to be d1, which is the diagonal of R1. Then a larger rectangle of R2 is formed by the diagonal of d2, which is created by adding h to each side of R1. The points closest to S and D within the larger rectangle are found in the experimental network. After finding this point, the distance between SS' using the main network and S'D' using the experimental network and D'D using the main network is calculated. These three routes are connected and the full route is displayed to the user. After route search, the name of the route is saved as one of the non-experimental class traffic subclasses in the driver experience ontology according to the departure time, and if the user requests this route in the future, the saved route is immediately displayed to the user without route search. .

(2) tourism

If a traveler must stop in order to use a particular facility, it is considered a tourist. In this case, both the driver experience ontology and the service ontology are used for route search. For example, if a traveler needs food before arriving at their destination and then a gas station, food sub-categories, context data, and Euclidean distances can be used to find a food center close to the origin. Then, for these three centers, the network distance to the origin is calculated, and according to the network distance, the center closest to the origin is determined as the first stop. Therefore, the algorithm calculates the route between the origin and this center using an ontology-based route search algorithm.

The ontology-based route search problem in tourism travel is based on the concept of segmentation and conquest approach. The path search problem is divided into several small subproblems, and then each subproblem is solved. After that, the results of the subproblems are linked together to create a full path. The first stop is considered the new starting point, and the gas station is considered the second. Euclidean Street is used to find gas stations near the first stop. Then, the network distance to the first station is calculated and the gas station with the shortest network distance to the first station is selected as the second station. The distance between the first and second stops is calculated using an algorithm. Finally, the route between the gas station and the destination (second stop) is calculated. All three routes (departure-first stop, first stop-second stop, second stop-destination) are connected and displayed to the user as routes.

Note that each of the three routes is considered a separate trip. Depending on the example above, the number of services may vary and is not limited to two. Tourist trips usually take time, so travelers may stay at each location for several hours. Therefore, if a traveler finds a route during a heavy traffic time and enters during a low traffic time in the middle, a warning may be issued that the period of use of the route is ended and a re-route is necessary. 8 shows an example of a sightseeing tour algorithm.

9 is a block diagram showing an example of a computer system according to an embodiment of the present invention. For example, the travel route search system according to embodiments of the present invention may be implemented by the computer system 900 shown through FIG. 9.

As shown in FIG. 9, the computer system 900 is a component for executing the travel route search method according to embodiments of the present invention, and includes a memory 910, a processor 920, a communication interface 930, and An input/output interface 940 may be included.

The memory 910 is a computer-readable recording medium and may include a permanent mass storage device such as a random access memory (RAM), read only memory (ROM), and a disk drive. Here, a non-destructive large-capacity recording device such as a ROM and a disk drive may be included in the computer system 900 as a separate permanent storage device separated from the memory 910. In addition, the memory 910 may store an operating system and at least one program code. These software components may be loaded into the memory 910 from a computer-readable recording medium separate from the memory 910. Such a separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, disk, tape, DVD/CD-ROM drive, and memory card. In another embodiment, software components may be loaded into the memory 910 through the communication interface 930 rather than a computer-readable recording medium. For example, software components may be loaded into the memory 910 of the computer system 900 based on a computer program installed by files received over the network 960.

The processor 920 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. Instructions may be provided to the processor 920 by the memory 910 or the communication interface 930. For example, the processor 920 may be configured to execute a command received according to a program code stored in a recording device such as the memory 910.

The communication interface 930 may provide a function for the computer system 900 to communicate with other devices through the network 960. For example, a request, command, data, file, etc., generated by the processor 920 of the computer system 900 according to a program code stored in a recording device such as the memory 910, can be transmitted to the network according to the control of the communication interface 930. 960) can be transferred to other devices. Conversely, signals, commands, data, files, etc. from other devices may be received by the computer system 900 through the communication interface 930 of the computer system 900 via the network 960. Signals, commands, data, etc. received through the communication interface 930 may be transmitted to the processor 920 or the memory 910, and the file, etc. may be a storage medium (described above) that the computer system 900 may further include. Permanent storage).

The communication method is not limited, and not only a communication method using a communication network (for example, a mobile communication network, wired Internet, wireless Internet, broadcasting network) that the network 960 may include, but also short-range wired/wireless communication between devices may be included. have. For example, the network 960 is a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), and a broadband network (BBN). , Internet, and the like. In addition, the network 960 may include any one or more of a network topology including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or a hierarchical network, etc. Not limited.

The input/output interface 940 may be a means for an interface with the input/output device 950. For example, the input device may include a device such as a microphone, keyboard, camera, or mouse, and the output device may include a device such as a display and a speaker. As another example, the input/output interface 940 may be a means for interface with a device in which input and output functions are integrated into one, such as a touch screen. The input/output device 950 may be configured with the computer system 900 and one device.

The embodiment of FIG. 9 is only an example of the computer system 900, and the computer system 900 further includes additional components not shown in FIG. 9, or may have a configuration or arrangement that combines two or more components. I can. Components that may be included in the computer system 900 may be implemented in hardware, software, or a combination of both hardware and software, including one or more signal processing or application-specific integrated circuits.

The apparatus described above may be implemented as a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the devices and components described in the embodiments include a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable gate array (PLU). It may be implemented using one or more general purpose computers or special purpose computers, such as a logic unit, a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications executed on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of software. For the convenience of understanding, although it is sometimes described that one processing device is used, one of ordinary skill in the art, the processing device is a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as a parallel processor.

The software may include a computer program, code, instructions, or a combination of one or more of these, configuring the processing unit to behave as desired or processed independently or collectively. You can command the device. Software and/or data may be embodyed in any type of machine, component, physical device, computer storage medium or device to be interpreted by the processing device or to provide instructions or data to the processing device. have. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. In this case, the medium may be one that continuously stores a program executable by a computer, or temporarily stores a program for execution or download. In addition, the medium may be a variety of recording means or storage means in a form in which a single or several pieces of hardware are combined, but is not limited to a medium directly connected to a computer system, but may be distributed on a network. Examples of media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magnetic-optical media such as floptical disks, and And a ROM, RAM, flash memory, and the like, and may be configured to store program instructions. In addition, examples of other media include an app store that distributes applications, a site that supplies or distributes various software, and a recording medium or a storage medium managed by a server.

As described above, although the embodiments have been described by the limited embodiments and drawings, various modifications and variations are possible from the above description by those of ordinary skill in the art. For example, the described techniques are performed in a different order from the described method, and/or components such as a system, structure, device, circuit, etc. described are combined or combined in a form different from the described method, or other components Alternatively, even if substituted or substituted by an equivalent, an appropriate result can be achieved.

Therefore, other implementations, other embodiments, and claims and equivalents fall within the scope of the claims to be described later.

Claims (8)

In the travel route search method executed in a computer system,
The computer system includes at least one processor configured to execute computer readable instructions contained in a memory,
The travel route search method,
Constructing, by the at least one processor, a driver experience ontology including a route section according to the driver experience;
Building, by the at least one processor, a service ontology including data collected by an OSM (Open Street Map) as a service item related to travel; And
Searching, by the at least one processor, a travel route corresponding to the request of a traveler using the driver experience ontology and the service ontology
Travel route search method comprising a. The method of claim 1,
The step of building the driver experience ontology,
The main class consists of experimental routes and non-experimental routes,
Constructing a traffic route and a non-traffic route as subclasses to the main class
Travel route search method, characterized in that. The method of claim 1,
The step of searching for the travel route,
When the location and destination of the traveler are input, finding a class corresponding to the section between the location and the destination in the driver experience ontology
Travel route search method comprising a. The method of claim 3,
The step of searching for the travel route,
If there is no class corresponding to the section between the location and the destination in the driver experience ontology, finding a point closest to at least one of the location and the destination using a hierarchical experimental network
Travel route search method further comprising a. delete The method of claim 1,
The step of searching for the travel route,
When the location and destination of the traveler and at least one service item to be used before the destination are input, the facility corresponding to the service item is regarded as a station, and the section between the location and the station in the driver experience ontology, and the section between the stops , Finding the class corresponding to the section between the stop and the destination
Travel route search method, characterized in that. The method of claim 1,
The step of searching for the travel route,
Finding a class corresponding to the traveler's request through filtering using context information related to the traveler in the service ontology
Travel route search method, characterized in that. In a computer system,
At least one processor configured to execute computer readable instructions contained in memory
Including,
The at least one processor,
Building a driver experience ontology including a route section according to the driver experience;
Building a service ontology including data collected by OSM (Open Street Map) as a service item related to travel; And
The process of searching for a travel route corresponding to a traveler's request using the driver experience ontology and the service ontology
The computer system that handles it.

Images