KR102349665B1 - Apparatus and method for providing user-customized destination information - Google Patents

Abstract

The present invention relates to an apparatus and method for providing user-customized destination information, wherein the providing apparatus is an information collecting unit that collects destination information in advance according to the type of destination action and user characteristics and collects user characteristic information in motion using transportation means , a destination request calculation unit that generates a destination request model by performing learning to implement mapping of user characteristic information and destination behavior information from the destination information collected in advance, a user by applying the user characteristic information in motion to the destination request model A destination information search unit that searches for customized destination information, and a destination information that provides the user-customized destination information searched for before the moving user arrives at the destination to a user terminal or a transportation terminal installed in the user's boarding space. includes wealth.

Description

Apparatus and method for providing user-customized destination information

The present invention relates to a user-customized destination information providing technology, and more particularly, a user capable of providing optimized destination information to the user before the user arrives at the destination by collecting user characteristic information while moving using transportation means. It relates to an apparatus and method for providing customized destination information.

With the recent development of transportation means (cars, trains, airplanes, ships, etc.), most users can conveniently move anywhere using transportation means and arrive at their destinations in time. In this case, information required at the destination may be different for each user. For example, the required information may vary according to the intention of visiting the destination, such as tourist attractions, lodgings, restaurants, special products, and weather around the destination, and according to the user's personal taste.

In the past, users searched for necessary information through the Internet, etc., but it was not easy to find information suitable for them from a large amount of information on the Internet.

On the other hand, although digital signage that can provide various information and advertisements to users in real time is installed in the transportation space, the efficiency of the user's information use is lowered due to the unilateral provision of information.

Recently, a service that provides information tailored to the user's personal taste has been proposed, but in this case, the process of collecting user information by explicitly asking the user's personal preference is required, which may cause inconvenience to users on the go. . Accordingly, there is a need for a technology for collecting user information without causing inconvenience to a moving user and providing necessary destination information to the user.

Korean Patent Laid-Open No. 10-2006-0024257 (2006.03.16.) relates to a location-based customized surrounding information providing system and method, and a surrounding information database for storing surrounding information, and user preference for storing user preference information Information database, information registration means for receiving the surrounding information or user preference information from the terminal to update the surrounding information database and the user preference information database, respectively, and the user stored in advance according to a request for customized surrounding information from the terminal Disclosed is a technology including a surrounding information providing means for searching for surrounding information corresponding to the preference information of the user and transmitting the information to the terminal.

Korean Patent Laid-Open Patent No. 10-2010-0123060 (2010.11.24.) relates to a system and method for providing real-time customized information for tourist destinations. Information related to the promotion of tourist destinations is converted into a database, and in response to advertisement requests, it is matched with tourist destination facilities. A tourism relay server that organizes advertisement information by doing this, organizes customized information consisting of tourist information promotion and advertisement information based on tourist information, and provides detailed information of advertisement information step by step in response to the location information of the tourist destination; and tourism relay A repeater that transmits tourist information and advertisement information transmitted from the server to the access point and transmits the request signal transmitted from the access point to the tourism relay server, is installed in a number of tourist destinations to form a network node, and accesses the tourist terminal The system is configured with an access point that detects and transmits a wireless communication signal, a tourism terminal that generates a request signal, and receives and executes tourist information and advertisement information transmitted in response to the request signal, providing customized information and tourist attractions Disclosed is a technology capable of effectively delivering advertisement information about a facility.

Korean Patent Laid-Open Patent No. 10-2006-0024257 (2006.03.16.) Korean Patent Publication No. 10-2010-0123060 (2010.11.24.)

An embodiment of the present invention is to provide a user-customized destination information providing apparatus and method capable of providing user-optimized destination information to the user before the user arrives at the destination by collecting user characteristic information on the move using transportation means .

An embodiment of the present invention collects destination information according to the type of destination action and user characteristics, creates a destination request model that maps user characteristic information and destination information, and applies the characteristics of a moving user to the destination request model to the user An object of the present invention is to provide an apparatus and method for providing user-customized destination information that can provide the required customized destination information.

An embodiment of the present invention is to provide an apparatus and method for providing user-customized destination information that can support the user to sufficiently respond to the information by selecting and providing user-customized destination information according to the remaining section of the user's movement to the destination.

Among the embodiments, the user-customized destination information providing device includes an information collection unit that pre-collects destination information according to the type of destination action and user characteristics and collects user characteristic information while moving using a transportation means, the pre-collected destination information A destination request calculation unit that generates a destination request model by performing learning to implement mapping of user characteristic information and destination behavior information from, and a destination that searches for user-customized destination information by applying the user characteristic information in motion to the destination request model It includes an information search unit, and a destination information providing unit for providing the user-customized destination information searched for before the moving user arrives at the destination to a user terminal or a transportation terminal installed in the user's boarding space.

The information collection unit collects destination information in advance by classifying destination actions and user characteristics, determines the appearance and character of the user based on the image and voice photographed of the user while moving, and determines the user's boarding from the transportation terminal. User characteristic information may be collected by receiving user context information including the type of transportation, boarding time and place, and getting off (destination) time and place.

The destination request calculator may create a destination request model that classifies information corresponding to goods, services, and actions required by the user at the destination and maps user characteristics according to the destination information classified through neural network learning.

The destination request calculator may perform neural network learning for generating a destination request model by using one or more convolutional neural networks (CNNs), long short term memory (LSTMs), and autoencoders simultaneously.

The destination request calculation unit may determine the destination request of the user by language analysis of the voice information of the moving user.

The destination request calculation unit may determine the destination request of the user through a correlation between the user characteristics and the request characteristics at the destination based on the moving user characteristic information.

The destination information search unit may search for destination information mapped to a user's appearance and destination information mapped to a user's character from the destination request model, respectively, and collect search results to determine destination information to recommend to the moving user.

The destination information providing unit may provide the searched user-customized destination information in an order according to the remaining distance to the destination.

Among the embodiments, the method for providing user-customized destination information is a method performed by an apparatus for providing user-customized destination information, comprising the steps of: pre-collecting destination information according to the type of destination action and user characteristics; Creating a destination request model by performing learning to implement mapping of characteristic information and destination behavior information, collecting user characteristic information on the move using transportation means, and applying the user characteristic information on the move to the destination request model Searching for user-customized destination information by applying, and providing the user-customized destination information searched for before the user on the move arrives at the destination to a user terminal or a means of transportation terminal installed in the user's boarding space do.

Among the embodiments, the method performed by the apparatus for providing user-customized destination information may further include analyzing the emotional state of the user while moving and calculating the destination requirements of the user according to the analysis result.

Among the embodiments, in the method performed by the user-customized destination information providing device, visual information is provided to the user on the move, and the user's interest is recognized based on AI to determine the user's field of interest, psychological state, and desire It may further include the step of calculating.

The disclosed technology may have the following effects. However, this does not mean that a specific embodiment should include all of the following effects or only the following effects, so the scope of the disclosed technology should not be construed as being limited thereby.

The apparatus and method for providing user-customized destination information according to an embodiment of the present invention may provide optimized destination information to the user before the user arrives at the destination by collecting user characteristic information while moving using transportation.

An apparatus and method for providing user-customized destination information according to an embodiment of the present invention collects destination information according to the type of destination action and user characteristics to create a destination request model that maps user characteristic information and destination information, and By applying the characteristics to the destination request model, it is possible to provide customized destination information required by the user.

The apparatus and method for providing user-customized destination information according to an embodiment of the present invention can support the user to sufficiently respond to the information by selecting and providing the user-customized destination information according to the remaining section of the user's movement to the destination.

Therefore, the apparatus and method for providing user-customized destination information according to an embodiment of the present invention can provide information to a user on the go by identifying user needs at a destination in advance, thereby reducing user discomfort at the destination and providing information can increase the effectiveness of

1 is a view for explaining the configuration of a user-customized destination information providing system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a physical configuration of the destination information providing apparatus shown in FIG. 1 .
3 is a block diagram illustrating a functional configuration of the destination information providing apparatus shown in FIG. 1 .
FIG. 4 is a flowchart illustrating a process of providing user-customized destination information performed by the destination information providing apparatus shown in FIG. 1 .
FIG. 5 is an exemplary diagram for explaining an embodiment of a destination request model generated by the destination information providing apparatus shown in FIG. 1 .

Since the description of the present invention is merely an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiment described in the text. That is, since the embodiment may have various changes and may have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, it should not be understood that the scope of the present invention is limited thereby.

On the other hand, the meaning of the terms described in the present application should be understood as follows.

Terms such as “first” and “second” are for distinguishing one component from another, and the scope of rights should not be limited by these terms. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected to” another component, it may be directly connected to the other component, but it should be understood that other components may exist in between. On the other hand, when it is mentioned that a certain element is "directly connected" to another element, it should be understood that the other element does not exist in the middle. On the other hand, other expressions describing the relationship between elements, that is, "between" and "between" or "neighboring to" and "directly adjacent to", etc., should be interpreted similarly.

The singular expression is to be understood to include the plural expression unless the context clearly dictates otherwise, and terms such as "comprises" or "have" refer to the embodied feature, number, step, action, component, part or these It is intended to indicate that a combination exists, and it should be understood that it does not preclude the possibility of the existence or addition of one or more other features or numbers, steps, operations, components, parts, or combinations thereof.

In each step, identification numbers (eg, a, b, c, etc.) are used for convenience of description, and identification numbers do not describe the order of each step, and each step clearly indicates a specific order in context. Unless otherwise specified, it may occur in a different order from the specified order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs, unless otherwise defined. Terms defined in general used in the dictionary should be interpreted as having the meaning consistent with the context of the related art, and cannot be interpreted as having an ideal or excessively formal meaning unless explicitly defined in the present application.

1 is a view for explaining the configuration of a user-customized destination information providing system according to an embodiment of the present invention.

Referring to FIG. 1 , the user-customized destination information providing system 100 may include a user terminal 110 , a transportation terminal 120 , a destination information providing device 130 , and a database 140 .

The user terminal 110 may correspond to a computing device that can check information about a destination, and may be implemented as a smartphone, tablet PC, or notebook computer, but is not necessarily limited thereto, and various devices that the user can hold while moving. can be implemented as The user terminal 110 may be connected to the destination information providing apparatus 130 through a network, and a plurality of user terminals 110 may be simultaneously connected to the destination information providing apparatus 130 .

The transportation terminal 120 may correspond to a computing device that can provide user characteristic information on the move using transportation, may be implemented as a digital signage, and is not necessarily limited thereto, and may be installed in the user's boarding space. It can be implemented in various devices that can be used. Here, the means of transportation may refer to all automobiles, trains, airplanes, ships, and the like. In an embodiment, the transportation terminal 120 may be connected to the destination information providing device 130 through a network and may provide user context information to the destination information providing device 130 . The user context information may include at least a user destination, and may further include a boarding location and time of the user and an estimated arrival time.

In an embodiment, the means of transportation terminal 120 may be installed for each seat and may include a camera and a microphone for acquiring information of a user riding on the seat, and may include a display for displaying information.

The destination information providing device 130 may generate a destination request model by pre-collecting destination information according to the type of destination action and user characteristics, and automatically collects user characteristic information in motion using transportation means and applies it to the destination request model. Thus, it can be implemented as a server corresponding to a computer or program that can provide optimized destination information to the user. The destination information providing device 130 may be wirelessly connected to the user terminal 110 and the transportation terminal 120 through Bluetooth, WiFi, a communication network, etc., and the user terminal 110 and the transportation terminal 120 through the network. data can be exchanged with

The destination information providing device 130 may be connected through a network with facilities operating devices around the destination in order to collect destination information.

In an embodiment, the destination information providing apparatus 130 may store information necessary to provide user-customized destination information in conjunction with the database 140 . Meanwhile, the destination information providing apparatus 130 may be implemented by including the database 140 therein, unlike FIG. 1 . In addition, the destination information providing apparatus 130 may be implemented including a processor, a memory, a user input/output unit, and a network input/output unit, which will be described in more detail with reference to FIG. 2 .

The database 140 may correspond to a storage device for storing various types of information required in the process of providing the destination information required by the user to the user on the move. The database 140 may store the collected user characteristic information, destination request model information, and destination-related information (eg, tourist destination, accommodation, special product, event, etc.), and is not necessarily limited thereto, and the destination information providing device 130 is Information collected or processed in various forms can be stored in the process of receiving a user's request on the move and generating and providing a related response.

The database 140 may be composed of at least one partial database independently implemented according to the type of data to be stored. For example, the database 140 may establish a database by collecting in advance information on places to be visited, information on consumption, and services requested by a user at a destination based on universal user characteristics that are not specific to each user. Here, the user characteristics include information about the user's appearance, which can be defined as the user's age, gender, attire, face shape, behavior pattern, possessions, etc., and the user's voice, language usage, nationality, etc., which can be defined as user characteristics. It may include character information, and is not necessarily limited thereto, and various information that may be related to user characteristics may be included.

FIG. 2 is a block diagram illustrating a physical configuration of the destination information providing apparatus shown in FIG. 1 .

Referring to FIG. 2 , the destination information providing apparatus 130 may be implemented including a processor 210 , a memory 220 , a user input/output unit 230 , and a network input/output unit 240 .

The processor 210 may execute a process of processing each operation in the process of providing customized destination information to the user on the go regardless of the user's request, and manage the memory 220 read or written throughout the process. Also, a synchronization time between the volatile memory and the non-volatile memory in the memory 220 may be scheduled. The processor 210 may control the overall operation of the destination information providing device 130 , and is electrically connected to the memory 220 , the user input/output unit 230 , and the network input/output unit 240 to control the flow of data therebetween. can do. The processor 210 may be implemented as a central processing unit (CPU) of the destination information providing apparatus 130 .

The memory 220 is implemented as a non-volatile memory, such as a solid state disk (SSD) or a hard disk drive (HDD), and may include an auxiliary storage device used to store overall data required for the destination information providing device 130, and , may include a main memory implemented as a volatile memory such as RAM (Random Access Memory),

The user input/output unit 230 may include an environment for receiving a user input and an environment for outputting specific information to the user. For example, the user input/output unit 230 may include an input device including an adapter such as a touch pad, a touch screen, an on-screen keyboard, or a pointing device, and an output device including an adapter such as a monitor or a touch screen. In an embodiment, the user input/output unit 230 may correspond to a computing device accessed through remote access, and in such a case, the destination information providing device 130 may be performed as a server.

The network input/output unit 240 includes an environment for connecting to an external device or system through a network, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a VAN ( It may include an adapter for communication such as Value Added Network).

3 is a block diagram illustrating a functional configuration of the destination information providing apparatus shown in FIG. 1 .

Referring to FIG. 3 , the destination information providing device 130 includes an information collection unit 310 , a destination request calculation unit 320 , a destination information search unit 330 , a destination information providing unit 340 , and a control unit 350 . may include

The information collection unit 310 may collect user characteristic information and user behavior information at a destination. In one embodiment, the information collection unit 310 can automatically collect user characteristic information, classify the behavior patterns of behaviors required by the moving user when they arrive at the destination, and collect information on these behaviors at each destination. can be collected Here, the user characteristic information may include appearance information, character information, and situation information of the user. The user behavior information at the destination may include visiting a restaurant, shopping, participating in an event, visiting a point of interest (POI), or visiting a specific place.

In an embodiment, the information collection unit 310 may collect user context information from the transportation terminal 120 . Here, the user context information may include the user's boarding and disembarking location, each time, and the like. That is, when the user wants to move by using public transportation such as train, airplane, or ship, he can select boarding and disembarking (destination) locations, respective times, etc. in the ticket reservation step through the user terminal 110, which It may be stored in the transportation terminal 120 . Accordingly, the information collection unit 310 can easily collect user context information from the transportation terminal 120 . Even when the user wants to move by using personal transportation such as a car, the user in the information collection unit 310 executes a navigation service app through the user terminal 110 or sets a destination through a navigation device mounted on the vehicle. We can collect situational information.

The information collection unit 310 may install the information acquisition device in the user boarding space in the means of transportation, and may collect user appearance information and character information from the information acquisition device. Here, the information acquisition device may be implemented as a camera, a microphone, a display, or the like. In an embodiment, when the means of transportation terminal 120 is installed in each boarding seat, an information acquisition device implemented as a camera, a microphone, and a display may be included in the means of transportation terminal 120 . In one embodiment, the information collection unit 310 may receive image data photographed by the user from the camera when the camera is installed in the user's boarding space of the means of transportation, and may collect user appearance information from the received image data. . Here, the information collection unit 310 may collect the user's appearance information by analyzing the user's age, gender, possessions, attire, face shape, and behavior pattern from the user image data. The information collection unit 310 may analyze the consumption tendency of the user from the user appearance information. In an embodiment, the information collection unit 310 may extract the emotional state of the user from the received image data. Here, the information collection unit 310 may extract the user's emotional state by analyzing the user's facial expression from the user image data. In one embodiment, when the microphone is installed in the user boarding space of the transportation means, the information collection unit 310 may receive user voice data from the microphone and collect user character information from the received voice data. Here, the information collection unit 310 may analyze the user's region of origin, age, gender, etc. from the user voice data, and may collect user character information therefrom. In one embodiment, when the display is installed in the user's boarding space of the means of transportation, the information collection unit 310 may provide the user with some visual information in the form of pictures or images and recognize the user's interest accordingly. Here, the user's level of interest can be recognized using AI technology, and the user's field of interest, psychological state, desires, etc. can be calculated therefrom.

The destination request calculation unit 320 may perform learning to implement mapping of user characteristic information and destination behavior information from the collected user characteristic information and destination behavior information, and may calculate the destination request through learning. The destination request may refer to goods, services, or other actions required by the user at the destination. In an embodiment, the destination request calculation unit 320 may learn by dividing the user characteristic information into a model for mapping appearance information and a destination request, and a model for mapping character information and a destination request. Here, the destination request calculation unit 320 may use a rule-based, statistical, or machine learning method, and may focus on learning using a neural network technology, but is not limited thereto, and various technologies such as a database technology and a recommendation technology are utilized. can be

A neural network is a statistical learning algorithm, and one or more of a Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), and an autoencoder may be used simultaneously.

CNN is an algorithm that has been optimized so that the neural network can acquire 2D images well by applying the filtering technique to the neural network.

LSTM is a type of RNN, and is an algorithm mainly used when applying time-series data.

An autoencoder is a neural network that is trained by unsupervised learning so that the output computed from the input resembles the input.

The destination request calculation unit 320 may convert the collected user characteristic information into a reduced-dimensional vector form through a neural network algorithm of at least one of CNN, LSTM, and auto-encoder, and the reduced-dimensional vector value and the user at the destination By creating a data set that connects actions, the user's consumption pattern values are learned, and the destination demand can be calculated and judged using the learned model.

The destination request calculation unit 320 may additionally determine the desire that the user needs now or at the destination through language analysis of the collected user's voice information. In an embodiment, the destination request calculation unit 320 may analyze the user's conversation content to convert it to text, and extract the user's intention by analyzing the text in a natural language. The destination request calculation unit 320 may calculate the destination request through a correlation between the user characteristics and the request characteristics at the destination based on the collected user characteristic information. In this case, the destination request calculation unit 320 may use a neural network for correlation calculation.

When the user's emotional state is extracted, the destination request calculation unit 320 can calculate the destination requirements by analyzing the user's emotional state. to determine the destination needs.

When the characteristic information of the moving user is collected, the destination information search unit 330 may apply the collected user characteristic information to the destination request model to search for destination information optimized for the user. In an embodiment, the destination information search unit 330 may determine the final destination information to be recommended to the user by searching for destination information mapped to the user's appearance and destination information mapped to the user's character from the destination request model, respectively, and then collecting them. . That is, since different results can be given according to the user's appearance and character, more accurate information can be provided by collecting them.

The destination information providing unit 340 may provide information and services on a customized destination to a user who is moving by means of transportation in advance before arriving at the destination. In an embodiment, the destination information providing unit 340 may provide customized destination information optimized to the user riding in the seat on the display screen of the transportation terminal 120 installed in each seat. Here, the transportation terminal 120 may correspond to digital signage in the case of public transportation, and may correspond to a navigation device in the case of personal transportation. In an embodiment, the destination information providing unit 340 may provide the same destination information to the user terminal 110 by interworking the transportation terminal 120 and the user terminal 110 . In this case, the user may download information or discount coupons required for the user terminal 110 .

When providing destination information, the destination information providing unit 340 may provide a function for the user to purchase a service of the destination in advance.

The destination information providing unit 340 may also control the order of providing the destination information searched for by the destination information search unit 330 to provide the user with a sufficient response to the information. In an embodiment, the destination information providing unit 340 may provide different types of information and specific service contents in proportion to the remaining distance to the destination. Here, when the remaining distance to the destination is greater than or equal to a specific distance, the destination information providing unit 340 may provide destination information, which requires important decisions of the user, in preference to other information. For example, if the distance remaining to the destination of the user on the move is 30 km or more, destination information that requires review time, such as hotel reservations and museum information, is given priority. It is possible to provide destination information necessary for the user to act immediately upon getting off the destination, such as location, procedure, and restaurant information in the terminal.

The control unit 350 may control the overall operation of the user-customized destination information providing device 130, and the information collecting unit 310, the destination request calculation unit 320, the destination information search unit 330, and the destination information providing ( 340) can control the control flow or data flow between them.

FIG. 4 is a flowchart illustrating a process of providing user-customized destination information performed by the destination information providing apparatus shown in FIG. 1 .

In FIG. 4 , the destination information providing apparatus 130 may collect destination information according to the type of destination action and user characteristics (step S410 ). In an embodiment, the destination information providing apparatus 130 may classify destination actions by type and user characteristics through the information collection unit 310 , and collect destination information according to destination action classification and user characteristics classification. Here, the information collection unit 310 may define user characteristic information composed of a user's appearance, character, and user context information as universally collectable information that is not specialized for each user, and a user using a means of transportation. Information on visited places, consumption information, requested services, etc. performed at the destination can be collected in advance according to user characteristics.

The destination information providing device 130 may generate a destination request model by performing modeling to implement mapping of user characteristic information and destination action information from the collected information (step S420). In one embodiment, the destination information providing device 130 classifies the information required at the destination through the destination request calculation unit 320, and simultaneously utilizes one or more neural network algorithms such as CNN, LSTM, and autoencoder. A destination request model that maps user characteristics according to destination information can be created.

The destination information providing apparatus 130 may search for user-customized destination information by applying the characteristic information of the user who is moving using a transportation means to the destination request model (step S430). The destination information providing device 130 performs learning by inputting user characteristic information including at least one of the user's appearance, character, and situation through the destination information search unit 330 into the destination request model learned as pre-collection information. Thus, it is possible to search for information and services for each type of destination behavior optimized for the characteristics of the moving user.

The destination information providing apparatus 130 may provide the searched user-customized destination information to the user terminal 110 or the means of transportation terminal 120 in an order according to the remaining distance to the destination (step S440). In an embodiment, the destination information providing device 130 may display the destination information on the display screen of the transportation terminal 120 installed in the seat in which the moving user is seated through the destination information providing unit 340 .

FIG. 5 is an exemplary diagram for explaining an embodiment of a destination request model generated by the destination information providing apparatus shown in FIG. 1 .

In Figure 5, the destination information providing device 130, in order to generate a destination request model, first, as shown in (a), obtained by photographing the user through the camera of the transportation terminal 120 used by the user on the move. Learning can be performed by taking image data as input, reducing the dimensionality in the middle through the encoder, expressing it as a vector, and completing the original again through the decoder. For example, by reducing the dimension of image data, the reduced vector value can be expressed as a feature of appearance. By training a neural network, a destination request model can be created.

Although the above has been described with reference to preferred embodiments of the present application, those skilled in the art can variously modify the present application within the scope without departing from the spirit and scope of the present invention as described in the claims below. and may be changed.

100: user-customized destination information providing system
110: user terminal 120: transportation terminal
130: destination information providing device 140: database
210: processor 220: memory
230: user input/output unit 240: network input/output unit
310: information collection unit 320: destination request calculation unit
330: destination information search unit 340: destination information providing unit
350: control unit

Claims (11)

an information collection unit that collects destination information in advance according to the type of destination action and user characteristics, and collects user characteristic information including appearance information, character information, and situation information of a user who is moving using a means of transportation;
a destination request calculation unit for generating a destination request model by performing learning to implement mapping of user characteristic information and destination action information from the pre-collected destination information;
a destination information search unit that searches for user-customized destination information by applying the moving user characteristic information to the destination request model; and
A destination information providing unit for providing the user-customized destination information found before the moving user arrives at the destination according to the remaining distance to the destination to the user terminal or a transportation terminal installed in the user's boarding space but,
The information collection unit
The destination information is collected in advance by classifying the destination behavior and user characteristics, and the age, gender, belongings, attire, face shape, The user's appearance information is collected by analyzing the behavior pattern, and user character information is collected by analyzing the user's region of origin, age, and gender based on the user's voice in movement received through the microphone of the transportation terminal, and User situation information, including the type of transportation selected by the user and stored in the transportation terminal, boarded by the user, boarding time and place, and getting off (destination) time and place, from the transportation terminal collect,
The destination request calculation unit
Classifies information corresponding to goods, services, and behaviors required by the user at the destination, and transforms the collected user characteristic information into a reduced-dimensional vector form through neural network learning. Create a data set connecting
The destination information providing unit
When the remaining distance to the destination is greater than or equal to the first specific distance, destination information required for important decisions of the user is given priority, and when the remaining distance to the destination is less than or equal to a second specific distance shorter than the first specific distance, the user can A user-customized destination information providing device, characterized in that it provides destination information necessary for immediate action.
delete delete The method of claim 1, wherein the destination request calculation unit
A device for providing user-customized destination information, characterized in that it performs neural network learning to generate a destination request model using one or more convolutional neural networks (CNNs), long short term memory (LSTM), and autoencoders at the same time.
According to claim 1, wherein the destination request calculation unit
The user-customized destination information providing device, characterized in that the user's destination request is determined by language analysis of the user's voice information while moving.
According to claim 1, wherein the destination request calculation unit
The user-customized destination information providing apparatus, characterized in that the user's destination request is determined through a correlation between user characteristics and desired characteristics at the destination on the basis of the moving user characteristic information.
According to claim 1, wherein the destination information search unit
User-customized destination information, characterized in that the destination information mapped to the user's appearance and the destination information mapped to the user character are searched from the destination request model, respectively, and the destination information to be recommended to the moving user is determined by collecting the search results Device.
delete In the method performed by the user-customized destination information providing device,
pre-collecting destination information according to the type of destination action and user characteristics;
generating a destination request model by performing learning to implement mapping of user characteristic information and destination behavior information from the pre-collected destination information;
collecting user characteristic information including appearance information, character information, and situation information of a user who is moving using a transportation means;
searching for user-customized destination information by applying the moving user characteristic information to the destination request model; and
Comprising the steps of providing the user-customized destination information found before the moving user arrives at the destination to the user terminal or a means of transportation terminal installed in the user's boarding space by arranging the order according to the remaining distance to the destination,
The step of generating the destination request model is
Transform user characteristic information into a reduced-dimensional vector form through neural network learning, create a data set that connects the reduced-dimensional vector value and user behavior at the destination, and learns the user’s consumption pattern value to create a destination demand model do,
The step of collecting the user characteristic information is
Destination information is collected in advance by classifying destination behavior and user characteristics, and based on the image captured by the user while moving through the camera of the transportation terminal, the user's age, gender, belongings, attire, face shape, The user's appearance information is collected by analyzing the behavior pattern, and user character information is collected by analyzing the user's region of origin, age, and gender based on the user's voice on the move received through the microphone of the transportation terminal, and User situation information, including the type of transportation selected by the user and stored in the transportation terminal, boarded by the user, boarding time and place, and getting off (destination) time and place from the transportation terminal collect,
The step of providing the destination information
When the remaining distance to the destination is greater than or equal to the first specific distance, destination information required for important decisions of the user is given priority, and when the remaining distance to the destination is less than or equal to a second specific distance that is shorter than the first specific distance, the user can A method for providing user-customized destination information, characterized in that it provides destination information necessary to act immediately.
10. The method of claim 9,
Analyzing the emotional state of the user on the move, and calculating the user's destination requirements according to the analysis result, the user-customized destination information providing method further comprising the step of.
10. The method of claim 9,
Providing visual information to the moving user and recognizing the user's level of interest based on AI, and calculating the user's field of interest, psychological state, and desire.

Images