KR102641710B1 - A method of providing travel product sales service through reverse auction - Google Patents

Abstract

According to an embodiment of the present invention, a method for providing a travel product sales service through a reverse auction performed by an apparatus is disclosed. In addition, the method includes receiving priority information including rankings for each of the places to be visited and accommodations from the user terminal; If the ranking for the place to visit is higher than the ranking for the accommodation, first user information including travel area, travel date, user tourist destination preference, age, gender, number of people, relationship between people, user food preference, and physical strength is stored in advance. Input the learned first artificial neural network as an input value, obtain a plurality of first recommended visiting places from the first artificial neural network, transmit the first recommended visiting places to the user terminal, and receive the user information from the user terminal. Receiving first preferred visit places that are the selected first recommended visit places; selecting an age weight, a gender weight, and a physical strength weight matched with the age, the gender, and physical strength from a database, and determining the product of the age weight, the gender weight, and the physical strength weight as an activity weight; determining an activity time corresponding to the travel date using the arrival time of the first date of arrival at the travel area, a preset schedule start time, a preset schedule end time, a return time leaving the travel area, and the activity weight; Select a first standard travel time matched with each of the airport and the first preferred visit locations from the database, and select a first travel time weight matched by visit time for each of the airport and the first preferred visit locations. and determining a first expected travel time corresponding to each of the airport and the first preferred visit locations using the first standard travel time and the first travel time weight; Select a first reference travel time matching each of a plurality of first routes connecting between the airport and the first preferred visit locations from the database, and select each of the first routes by means of transportation and travel time. selecting a first travel time weight matched with , and determining a first expected travel time corresponding to each of the first routes using the first reference travel time and the first travel time weight; Determine a plurality of first recommended recommended routes connecting the airport and at least two of the first preferred places to visit, and each of the first recommended places included in the first recommended places to visit correspond to each of the first preferred places to visit. Using the first expected travel time and the first expected travel time corresponding to each of the first routes included in the first expected recommended route, a first required time corresponding to each of the first expected recommended route is calculated. deciding step; determining the first expected recommended routes for which the first required time is smaller than the activity time as first recommended routes; Transmitting the first recommended routes to the user terminal and receiving first preferred routes, which are the first recommended routes selected by the user, from the user terminal; determining a starting location corresponding to each of the first preferred movement lines, and determining a plurality of first preliminary recommended lodgings where the distance from the starting location is less than or equal to a preset reference distance and the number of people available for reservation is greater than or equal to the number of people; selecting an accommodation preference matched with the first preliminary recommended accommodation, the age, the gender, and the relationship between people from the database; determining the first preliminary recommended accommodations whose accommodation preferences are equal to or higher than a preset standard as first recommended accommodations; transmitting the first recommended accommodations to the user terminal and receiving first preferred accommodations, which are the first recommended accommodations selected by the user, from the user terminal; generating a first user travel plan using the first preferred routes and the first preferred accommodations; If the ranking for the accommodation is higher than the ranking for the visiting place, the second user includes the travel area, the travel date, accommodation budget, preferred accommodation information, the age, the gender, the number of people, and the relationship between the people. Enter information as an input value into a pre-trained second artificial neural network, obtain a plurality of second recommended accommodations from the second artificial neural network, transmit the second recommended accommodations to the user terminal, and transmit the second recommended accommodations from the user terminal. Receiving second preferred accommodations, which are the second recommended accommodations selected by the user; setting areas located within a preset distance from each of the second preferred accommodations as activity areas corresponding to each of the second preferred accommodations; determining a plurality of second preliminary recommended visit locations using the activity area, the arrival time, and the return time; When the second preliminary recommended visit places are tourist destinations, a first matching diagram corresponding to each of the preliminary recommended visit places using the tourist destination preference, the age, the gender, and the relationship between people included in the first user information Calculating and determining second recommended visit places among the second preliminary recommended visit places using the first matching degree; When the second preliminary recommended visit places are restaurants, a second service corresponding to each of the second preliminary recommended visit places using the food preference, age, gender, and relationship between people included in the first user information calculating a matching degree and determining second recommended visit places among the second preliminary recommended visit places using the second matching degree; transmitting the second recommended visit places to the user terminal and receiving second preferred visit places, which are the second recommended visit places selected by the user, from the user terminal; Select a second standard travel time that matches each of the airport, the second preferred accommodations, and the second preferred visiting locations from the database, and select the airport, the second preferred accommodations, and the second preferred visiting locations from the database. For each of them, a second travel time weight is selected that matches each visit time, and a second travel time weight corresponding to each of the airport and the second preferred visit location is selected using the second standard travel time and the second travel time weight. Determining the expected time required; Select a second reference travel time matching each of a plurality of second routes connecting the airport, the second preferred accommodations, and the second preferred visit locations from the database, and select a second reference travel time for each of the second routes. For each means of transportation and travel time, a second travel time weight is selected, and a second expected travel time corresponding to each of the second routes is determined using the second reference travel time and the second travel time weight. deciding step; Determine a plurality of second recommended recommended routes connecting at least two of the airport, the second preferred accommodations, and the second preferred visit locations, and determine the second preferred route included in the second recommended route. Using the second expected travel time corresponding to each of the places and the second expected travel time corresponding to each of the second routes included in the second expected recommended route, each of the second expected recommended routes and determining a corresponding second required time; determining the second expected recommended routes for which the second necessary time is smaller than the activity time as second recommended routes; Transmitting the second recommended routes to the user terminal and receiving second preferred routes, which are the second recommended routes selected by the user, from the user terminal; generating a second user travel plan using the second preferred routes; determining at least one seller terminal whose business area matches the second user's travel plan; transmitting the second user travel plan to at least one matched merchant terminal; Receiving at least one travel product from at least one seller terminal; Transmitting at least one received travel product to the user terminal; And it may include receiving a preferred travel product selected from at least one of the travel products from the user terminal.

Description

{A METHOD OF PROVIDING TRAVEL PRODUCT SALES SERVICE THROUGH REVERSE AUCTION}

The present invention relates to a method of providing a travel product sales service through a reverse auction.

Unless otherwise indicated herein, the material described in this section is not prior art to the claims of this application, and is not admitted to be prior art by inclusion in this section.

Types of travel are largely classified into independent travel and package travel. Independent travel is a form in which an individual plans the entire travel itinerary, and package travel is a form in which an individual uses a travel product in which the entire travel itinerary is planned by a travel product planner.

In the case of independent travel, there is an advantage that the individual can enjoy the trip as he or she wants, but on the other hand, there is a disadvantage that the individual has to plan everything.

In the case of package travel, it has the advantage of being convenient because you can enjoy an already planned itinerary, but on the other hand, it has the disadvantage of not being able to experience things other than the planned itinerary.

As the demand for travel increases, the number of consumers who want travel products that combine the advantages of independent travel and package travel is increasing.

Korean Patent No. 10-2087543 (registered on March 4, 2020)

One purpose of the present invention is to recommend to the user a place to visit, accommodation and route that matches the user's information, and to determine the user's travel plan based on the place to visit, accommodation and route selected by the user, a travel product through reverse auction. The purpose is to provide a method of providing sales services.

Another object of the present invention is to provide a method of providing a travel product sales service through reverse auction, which matches the user's travel plan with a product seller and provides the user with a travel product that includes at least part of the user's travel plan. .

One aspect of the present invention for achieving the above object provides a method of providing a travel product sales service through a reverse auction performed by an apparatus.

In addition, the method includes receiving priority information including rankings for each of the places to be visited and accommodations from the user terminal; If the ranking for the place to visit is higher than the ranking for the accommodation, first user information including travel area, travel date, user tourist destination preference, age, gender, number of people, relationship between people, user food preference, and physical strength is stored in advance. Input the learned first artificial neural network as an input value, obtain a plurality of first recommended visiting places from the first artificial neural network, transmit the first recommended visiting places to the user terminal, and receive the user information from the user terminal. Receiving first preferred visit places that are the selected first recommended visit places; selecting an age weight, a gender weight, and a physical strength weight matched with the age, the gender, and physical strength from a database, and determining the product of the age weight, the gender weight, and the physical strength weight as an activity weight; determining an activity time corresponding to the travel date using the arrival time of the first date of arrival at the travel area, a preset schedule start time, a preset schedule end time, a return time leaving the travel area, and the activity weight; Select a first standard travel time matched with each of the airport and the first preferred visit locations from the database, and select a first travel time weight matched by visit time for each of the airport and the first preferred visit locations. and determining a first expected travel time corresponding to each of the airport and the first preferred visit locations using the first standard travel time and the first travel time weight; Select a first reference travel time matching each of a plurality of first routes connecting between the airport and the first preferred visit locations from the database, and select each of the first routes by means of transportation and travel time. selecting a first travel time weight matched with , and determining a first expected travel time corresponding to each of the first routes using the first reference travel time and the first travel time weight; Determine a plurality of first recommended recommended routes connecting the airport and at least two of the first preferred places to visit, and each of the first recommended places included in the first recommended places to visit correspond to each of the first preferred places to visit. Using the first expected travel time and the first expected travel time corresponding to each of the first routes included in the first expected recommended route, a first required time corresponding to each of the first expected recommended route is calculated. deciding step; determining the first expected recommended routes for which the first required time is smaller than the activity time as first recommended routes; Transmitting the first recommended routes to the user terminal and receiving first preferred routes, which are the first recommended routes selected by the user, from the user terminal; determining a starting location corresponding to each of the first preferred movement lines, and determining a plurality of first preliminary recommended lodgings where the distance from the starting location is less than or equal to a preset reference distance and the number of people available for reservation is greater than or equal to the number of people; selecting an accommodation preference matched with the first preliminary recommended accommodation, the age, the gender, and the relationship between people from the database; determining the first preliminary recommended accommodations whose accommodation preferences are equal to or higher than a preset standard as first recommended accommodations; transmitting the first recommended accommodations to the user terminal and receiving first preferred accommodations, which are the first recommended accommodations selected by the user, from the user terminal; generating a first user travel plan using the first preferred routes and the first preferred accommodations; If the ranking for the accommodation is higher than the ranking for the visiting place, the second user includes the travel area, the travel date, accommodation budget, preferred accommodation information, the age, the gender, the number of people, and the relationship between the people. Enter information as an input value into a pre-trained second artificial neural network, obtain a plurality of second recommended accommodations from the second artificial neural network, transmit the second recommended accommodations to the user terminal, and transmit the second recommended accommodations from the user terminal. Receiving second preferred accommodations, which are the second recommended accommodations selected by the user; setting areas located within a preset distance from each of the second preferred accommodations as activity areas corresponding to each of the second preferred accommodations; determining a plurality of second preliminary recommended visit locations using the activity area, the arrival time, and the return time; When the second preliminary recommended visit places are tourist destinations, a first matching diagram corresponding to each of the preliminary recommended visit places using the tourist destination preference, the age, the gender, and the relationship between people included in the first user information Calculating and determining second recommended visit places among the second preliminary recommended visit places using the first matching degree; When the second preliminary recommended visit places are restaurants, a second service corresponding to each of the second preliminary recommended visit places using the food preference, age, gender, and relationship between people included in the first user information calculating a matching degree and determining second recommended visit places among the second preliminary recommended visit places using the second matching degree; transmitting the second recommended visit places to the user terminal and receiving second preferred visit places, which are the second recommended visit places selected by the user, from the user terminal; Select a second standard travel time that matches each of the airport, the second preferred accommodations, and the second preferred visiting locations from the database, and select the airport, the second preferred accommodations, and the second preferred visiting locations from the database. For each of them, a second travel time weight is selected that matches each visit time, and a second travel time weight corresponding to each of the airport and the second preferred visit location is selected using the second standard travel time and the second travel time weight. Determining the expected time required; Select a second reference travel time matching each of a plurality of second routes connecting the airport, the second preferred accommodations, and the second preferred visit locations from the database, and select a second reference travel time for each of the second routes. For each means of transportation and travel time, a second travel time weight is selected, and a second expected travel time corresponding to each of the second routes is determined using the second reference travel time and the second travel time weight. deciding step; Determine a plurality of second recommended recommended routes connecting at least two of the airport, the second preferred accommodations, and the second preferred visit locations, and determine the second preferred route included in the second recommended route. Using the second expected travel time corresponding to each of the places and the second expected travel time corresponding to each of the second routes included in the second expected recommended route, each of the second expected recommended routes and determining a corresponding second required time; determining the second expected recommended routes for which the second necessary time is smaller than the activity time as second recommended routes; Transmitting the second recommended routes to the user terminal and receiving second preferred routes, which are the second recommended routes selected by the user, from the user terminal; generating a second user travel plan using the second preferred routes; determining at least one seller terminal whose business area matches the second user's travel plan; transmitting the second user travel plan to at least one matched merchant terminal; Receiving at least one travel product from at least one seller terminal; Transmitting at least one received travel product to the user terminal; And it may include receiving a preferred travel product selected from at least one of the travel products from the user terminal.

According to one embodiment of the present invention, options that match the user's information regarding places to visit, accommodations, and routes are provided to the user, and the user can directly select a place, accommodations, and routes of visit that he or she likes from the provided options. . Through this, users can establish a highly satisfying travel plan without spending excessive time or money.

Additionally, according to another embodiment of the present invention, a travel product including at least part of the user's travel plan is provided to the user. Through this, users can establish a highly satisfying travel plan that combines only the advantages of independent travel and package travel.

1 is a schematic diagram of a travel product sales service provision system according to an embodiment.
FIG. 2 is a block diagram illustrating functional modules of the travel product sales service device according to FIG. 1.
Figure 3 is a diagram conceptually showing the process by which the priority determination unit determines user priority.
Figure 4 is a flowchart showing the process of a method for providing a travel product sales service according to an embodiment.
Figure 5 is a diagram conceptually showing the process by which the visit place determination module determines a recommended visit place.
Figure 6 is a diagram conceptually showing the process by which the visit place determination module determines the preferred visit place.
Figure 7 is a diagram conceptually showing the process by which the movement route decision module calculates business hours, expected travel time, and expected travel time.
Figure 8 is a diagram conceptually showing the process by which the route decision module determines the recommended route.
Figure 9 is a diagram conceptually showing the process by which the route decision module determines the preferred route.
Figure 10 is a diagram conceptually showing the process by which the accommodation decision module determines recommended accommodation.
Figure 11 is a diagram conceptually showing the process by which the accommodation decision module determines preferred accommodation.
Figure 12 is a diagram conceptually showing the process of a method for providing travel product sales services according to another embodiment.
Figure 13 is a diagram conceptually showing the process by which the accommodation decision module determines recommended accommodation.
Figure 14 is a diagram conceptually showing the process by which the accommodation decision module determines preferred accommodation.
Figure 15 is a diagram conceptually showing the process by which the visit place determination module determines a recommended visit place.
Figure 16 is a diagram conceptually showing the process by which the visit place determination module determines the preferred visit place.
Figure 17 is a diagram conceptually showing the process by which the movement route decision module calculates business hours, distance, and expected travel time.
Figure 18 is a diagram conceptually showing the process by which the route decision module determines the recommended route.
Figure 19 is a diagram conceptually showing the process by which the accommodation decision module determines the preferred route.
Figure 20 is a flowchart showing the process of a method for providing a travel product sales service according to another embodiment.
Figure 21 is a flowchart showing the process by which the product review unit determines user priorities.
Figure 22 is a diagram conceptually showing seller information and travel product information provided to the user terminal.
Figure 23 is a flowchart showing a process in which a travel information provider provides travel information to a user terminal.
Figure 24 is a flowchart showing a process in which an accommodation reservation department provides an accommodation reservation service.
Figure 25 is a flowchart showing a process in which a restaurant reservation department provides a restaurant reservation service.
FIG. 26 is a diagram illustrating an exemplary hardware configuration of the device according to FIG. 1.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention. While describing each drawing, similar reference numerals are used for similar components.

Terms such as first, second, A, and B may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be named a second component, and similarly, the second component may also be named a first component without departing from the scope of the present invention. The term and/or includes any of a plurality of related stated items or a combination of a plurality of related stated items.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the technical field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

In this specification, “place to visit” may comprehensively include various places that tourists generally visit, such as art galleries, historical sites, restaurants, and activity service providers.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings.

1 is a schematic diagram of a travel product sales service provision system according to an embodiment.

Referring to FIG. 1 , a travel product sales service providing system may include a device 100, a user terminal 200, and a seller terminal 300.

The user terminal 200 is a terminal of a user who wants to use a travel product sales service, registers user information in the device 100, transmits the user information to the device 100, and sells travel products through the device 100. Several features of the sales service are available. At this time, travel product sales services may be provided in the form of a platform.

The seller terminal 300 is a terminal of a travel product seller that proposes a travel product to a user, registers seller information in the device 100, and can be matched with a user who wants to use the travel product through the device 100. .

The pickup terminal 400 is a driver's terminal that picks up the user and transports the user to the user's desired destination. It registers the driver information in the device 100 and matches with the user who wants to use the transportation service through the device 100. You can.

Examples of the user terminal 200, seller terminal 300, and pickup terminal 400 include a desktop computer, a laptop computer, a laptop, a smart phone, Tablet PC, mobile phone, smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital Digital camera, DMB (digital multimedia broadcasting) player, digital audio recorder, digital audio player, digital video recorder, digital video player, It may be a PDA (Personal Digital Assistant), etc.

The device 100 may be a server for providing a travel product sales service to at least one of the user terminal 200 and the seller terminal 300. The device 100 may operate a travel product sales service and provide various services to the user terminal 200 and the seller terminal 300.

Specifically, the device 100 may request the user terminal 200 to select priorities for accommodations and places to visit, and receive the priorities for the accommodations and places to visit from the user terminal 200.

Additionally, if the visit place has priority, the device 100 may sequentially determine the visit place, route, and accommodation based on user information.

Additionally, if the accommodation has priority, the device 100 may sequentially determine the accommodation, place to visit, and route based on user information.

Additionally, the device 100 may determine the user's travel plan based on the determined visit location, route, and accommodation.

In addition, the device 100 provides the user's travel plan to a seller terminal 300 whose business area overlaps the user's travel plan among the plurality of seller terminals 300, and provides the user's travel plan to the seller terminal that has received the user's travel plan. At least one travel product related to the user's travel plan may be received from (300). The device 100 may provide payment and reservation services based on the user's travel plan and at least one travel product.

FIG. 2 is a block diagram illustrating functional modules of the device according to FIG. 1 by way of example.

Referring to FIG. 2, the device 100 includes a priority determination unit 101 that requests the user terminal 200 to input priorities for places to visit and accommodations, and receives the priorities from the user terminal 300. Includes.

In addition, the device 100 includes a travel plan decision unit 102 that determines the place to visit, route and accommodation based on priority and user information, and establishes a travel plan for the user based on the determined Gwanggwang attractions, route and accommodation. Includes. The travel plan decision unit 102 includes a visit location decision module 102a, a movement route decision module 102b, and an accommodation decision module 102c.

In addition, the device 100 matches the user's travel plan with the seller terminal 300, receives travel products from the matched seller terminal 300, and makes payments and reservations based on the user's travel plan and travel products. It includes a seller matching unit 103 that conducts the process.

In addition, the device 100 compares the travel product information received from the seller terminal 300 with preset registration criteria, determines whether to register the travel product information based on the comparison result, and compares the registered travel product information and travel product information. It includes a product screening unit 104 that provides product information and corresponding seller information to the user terminal 300.

In addition, the device 100 includes a travel information provider 105 that receives an information request from the user terminal 300 and provides travel information and travel product information matching the received information request to the user terminal 300. Includes.

Additionally, the device 100 includes an accommodation reservation unit 106 that specifies reservable accommodations based on the location information of the user terminal 300 and makes reservations for the specified accommodations.

Additionally, the device 100 includes a restaurant reservation unit 107 that specifies a restaurant that can be reserved based on the location information of the user terminal 300 and makes a reservation for the specified restaurant.

Figure 3 is a diagram conceptually showing the process by which the priority determination unit determines user priority.

The priority determination unit 101 may request the user terminal 200 to input priorities for places to visit and accommodations, and when the priorities are entered by the user, it receives the priorities from the user terminal 200. .

The priority determination unit 101 determines whether to establish a travel plan by prioritizing a place to visit or establishing a travel plan by prioritizing an accommodation based on the received priority.

Figure 4 is a flowchart showing the process of a method for providing a travel product sales service according to an embodiment.

When the priority for the visit place is high among the accommodation and the visit place, the travel plan decision unit 102 sequentially determines the visit place, route, and accommodation, and plans the user's travel based on the determined visit place, route, and accommodation. Establish.

First, the travel plan decision unit 102 calculates a plurality of recommended places to visit based on user information and transmits them to the user terminal 200 (S110).

Figure 5 is a diagram conceptually showing the process by which the visit place determination module 102a determines a recommended visit place.

The visit place determination module 102a determines a plurality of recommended visit places based on user information. User information may include travel area, travel date, user tourist destination preference, age, gender, relationship between people, and user food preference. User tourist destination preferences may be preferences corresponding to activities, nature, culture, and shopping, respectively, and may be calculated based on the user's answers to a preset tourist destination preference questionnaire. The user's food preference may be a preference corresponding to each of the representative foods sold by restaurants in the travel area selected by the user, and may be calculated based on the user's answer to a preset food preference questionnaire.

In one embodiment, the visit place determination module 102a may match user information with a plurality of recommended visit places through a first artificial neural network supervised by learning data. The first artificial neural network is a prediction model implemented in software or hardware that imitates the computational ability of a biological system using a large number of artificial neurons (or nodes). According to one embodiment, the artificial neural network may be an artificial neural network based on a Convolution Neural Network (CNN), Recurrent Neural Network (RNN), Long Short Term Memory models (LSTM), or Gated Recurrent Unit (GRU).

The learning data used for learning the first artificial neural network is the first feature vector (input value) that transforms the travel area, travel date, user tourist attraction preference, age, gender, and relationship between people included in the user information, and the visit place information. It consists of a second feature vector (output value) that converts the location of the included tourist attraction, the business date of the tourist attraction, the services provided by the tourist attraction, the preference according to the age of the tourist attraction, the preference according to the gender of the tourist attraction, and the preference according to the relationship between people at the tourist attraction. do. In addition, the learning data used for learning the first artificial neural network includes the first feature vector (input value) and visit location that converted the travel area, travel date, user food preference, age, gender, and relationship between people included in the user information. A second feature vector (output value) that converts the location of the restaurant included in the information, the business date of the restaurant, the food provided by the restaurant, the preference based on the age of the restaurant, the preference based on gender of the restaurant, and the preference based on the relationship between people in the restaurant. It consists of Since supervised learning is learning done with the correct answer known, the first feature vector (input value) and the second feature vector (output value) that are related to the correct answer are labeled and used for learning.

The first artificial neural network may calculate the similarity between a first feature vector converted from user information and a second feature vector converted from visit place information, and determine a plurality of recommended visit places based on the calculated similarity. In one embodiment, the first artificial neural network may determine visit places whose calculated similarity is greater than or equal to a preset standard as recommended visit places.

In another embodiment, the visit location determination module 102a receives reservable airline ticket information from an external server (not shown), and matches the received airline ticket information with the travel area and travel date included in the user information to obtain a reservable departure airline ticket. And a return flight ticket list is provided to the user terminal 200.

In addition, the visit location determination module 102a receives information about the departure flight ticket and return flight ticket selected by the user from the user terminal 200, and determines the arrival time and return time based on the information about the received departure flight ticket and return flight ticket. Calculate . Arrival time refers to the time at which the plane corresponding to the departure ticket arrives at the travel area airport, and return time refers to the time at which the plane corresponding to the return ticket leaves the travel area airport.

Additionally, the visit location determination module 102a determines a plurality of preliminary recommended visit locations based on the travel area, travel date, arrival time, and return time. The location, business date, and business hours corresponding to each of the plurality of business places are already stored in the database of the device 100, and the visit place determination module 102a determines the location, business date, and business hours of the user's travel area, Search the database for business locations that match the travel date, arrival time, and return time, and determine the searched business locations as preliminary recommended places to visit. For example, business places whose business hours end before the arrival time and business places whose business hours begin after the return time may be excluded from the preliminary recommended visit locations.

In addition, when the preliminary recommended visit place is a tourist destination, the visit place determination module 102a determines the connection between a plurality of preliminary recommended visit places and the user based on the user tourist destination preference, age, gender, and relationship between people included in the user information. The matching degree can be calculated, and the final recommended visiting place among the plurality of preliminary recommended visiting places can be determined based on the calculated matching degree.

In the database of the device 100, preferences for each of a plurality of preliminary recommended visit places are preset and stored by age, gender, and relationship between people (family, lover, friend, etc.). Additionally, user tourist destination preference includes preference for each type of service provided by the preliminary recommended visit location. For example, if the services provided by a preliminary recommended visit location are classified into activities, nature, culture, and shopping, user tourist destination preference may include preferences for each of the classifications (e.g., activity 1, nature 0.9 , culture 0.5, shopping 0.3).

The visit place determination module 102a matches the user's tourist attraction preference with the services of the preliminary recommended visit place, searches for the first preference for the service provided by the preliminary recommended visit place, and determines the user's age, gender, and relationship between people. Search for the second preference of the matched preliminary recommended visit location.

The visit place determination module 102a may use the value obtained by multiplying the first preference and the second preference as the matching degree between the preliminary recommended visit place and the user. When the number of users is two or more, the average value of the matching degree for each user can be used as the overall matching degree.

When the preliminary recommended visit place is a restaurant, the visit place determination module 102a matches a plurality of preliminary recommended visit places and the user based on the user's food preference, age, gender, and relationship between people included in the user information. The degree can be calculated, and the final recommended visit place among the plurality of preliminary recommended visit places can be determined based on the calculated matching degree.

In the database of the device 100, preferences for each of a plurality of preliminary recommended visit places are preset and stored by age, gender, and relationship between people (family, lover, friend, etc.). Additionally, the user's food preference includes preference for each type of food provided by the preliminary recommended visit location. For example, if the food provided by a preliminary recommended visit location is classified as pizza, pasta, rosotto, and lasagna, the user's tourist attraction preference may include preference for each of the categories (e.g., pizza 0.3, pasta 0.3) 1, Rossotto 0.2, Lasagna 0.5).

The visit place determination module 102a matches the user's food preference with the food provided by the preliminary recommended visit place and searches for the first preference for the food provided by the preliminary recommended visit place. In one embodiment, the first preference may be determined as a preference for the most preferred food among the foods provided by the preliminary recommended visit location. In addition, the visit place determination module 102a searches for a second preference of a preliminary recommended visit place that matches the user's age, gender, and relationship between people.

The visit place determination module 102a may use the value obtained by multiplying the first preference and the second preference as the matching degree between the preliminary recommended visit place and the user. When the number of users is two or more, the average value of the matching degree for each user can be used as the overall matching degree.

Figure 6 is a diagram conceptually showing the process by which the visit place determination module 102a determines a preferred visit place.

The visiting place determination module 102a provides the determined plurality of recommended visiting places to the user terminal 200, and receives a preferred visiting place selected from the plurality of recommended visiting places from the user terminal 200 (FIG. 4, S120 ).

Referring again to FIG. 4, the travel plan decision unit 102 determines the business hours for each of the plurality of preferred visiting places, the expected travel time by time zone, and the expected travel time by time zone between the airport and the plurality of preferred visiting places. Calculate (S130).

The travel plan decision unit 102 calculates the activity time corresponding to each date, and calculates the activity time for each date, arrival time, return time, business hours for each preferred visit location, time required for each time zone, airport and multiple destinations. A recommended route for each day is determined based on the expected travel time for each time zone between the preferred visit locations (S140).

Figure 7 is a diagram conceptually showing the process by which the movement route determination module 102b calculates business hours, expected travel time, and expected travel time.

Figure 8 is a diagram conceptually showing the process by which the route decision module determines the recommended route.

The movement route determination module 102b calculates the activity time for each day based on the travel date, activity weight, arrival time, and return time.

The movement line determination module 102b calculates the activity weight based on age, gender, and physical strength included in the user information. If the number of people is two or more, the average value of each person's activist weight can be used as the overall activist weight.

Physical strength may be set based on responses to a preset questionnaire regarding physical strength received from the user, and may be divided into a plurality of different levels. In one embodiment, physical strength may be classified as strong, moderate, or weak. Strong, medium, and weak are each assigned different physical strength weights, and the weights can be sequentially set lower from strong to weak.

In the database of the device 100, preset age weights for each age group and preset gender weights for each gender are stored. In one embodiment, the highest age weight may be set in the teens, and the age weight may be set to sequentially decrease from the 20s to the 90s. In one embodiment, a relatively higher gender weight may be set for men compared to women.

The movement determination module 102b may search user information for a physical strength weight, age weight, and gender weight that match age, gender, and physical strength, and calculate an activity weight by multiplying the searched physical strength weight, age weight, and gender weight.

In addition, the movement route determination module 102b may determine the activity time on the first date as the difference between the arrival time on the first date of arrival at the travel area and the preset schedule deadline multiplied by the activity weight. For example, if the arrival time is 10 o'clock, the schedule deadline is 21 o'clock, and the activity weight is 1.2, the movement route determination module 102b may determine the activity time of the first day as 13.2.

Additionally, the movement route determination module 102b may determine the activity time of the intermediate date as the difference between the preset schedule start time and the schedule end time multiplied by the activity weight. For example, if the schedule start time is 11 o'clock, the schedule end time is 21 o'clock, and the activity weight is 1.2, the movement route determination module 102b may determine the activity time of the middle day to be 12.

Additionally, the movement route determination module 102b may determine the difference between the preset schedule start time and the return time leaving the travel area multiplied by the activity weight as the activity time on the return date. For example, if the schedule start time is 11:00, the return time is 16:00, and the activity weight is 1.2, the route determination module 102b may determine the activity time on the return date to be 6.

Once the activity time is determined, the movement route decision module 102b determines the activity time by day, arrival time, return time, business hours by day for the preferred visit location, time required by time zone, and time zone between the airport and a plurality of preferred visit locations. Based on the expected travel time, the recommended route for each day is determined.

The movement line determination module 102b can correct the daily activity time based on the daily weight. The weight for each day is a preset value and can be set in consideration of the user's fatigue that accumulates as the travel date passes. For example, the weight for each day may be set to decrease sequentially from the first date to the return date. For example, if the activity time from the first date to the return date is sequentially 13.2, 12, and 6, and the weight for each day from the first date to the return date is 1, 0.9, 0.8, the activity time from the first date to the return date can be corrected to 13.2, 10.8, 4.8.

The movement route determination module 102b creates a plurality of nodes, each corresponding to an airport and a plurality of preferred visit locations, and assigns a label to each of the created nodes. Additionally, the moving line determination module 102b creates an edge connecting one of the plurality of nodes to another node, and assigns a weight to the created edge.

The route determination module 102b may set the label of the node based on the expected travel time corresponding to the airport or preferred visit location.

The database of the device 100 stores a preset standard time required for each of the airport and a plurality of preferred visit locations, and the movement route determination module 102b searches the database for the standard time required corresponding to the node.

The database of the device 100 stores preset time required weights for each visit time for each of the airport and a plurality of preferred visit locations, and the movement route determination module 102b determines the node and the time required corresponding to the node's visit time in the database. Search for weights. The time required weight can be set based on the expected number of visitors by visit time for the airport or preferred visit location corresponding to the node.

The movement route determination module 102b calculates the expected travel time by multiplying the searched standard travel time by the travel time weight. The movement route determination module 102b may correct the expected travel time by multiplying the calculated expected travel time by a preset activity fatigue level for each of the airport and a plurality of preferred visit locations. Activity fatigue can be set based on activities performed by the user at the airport and a plurality of preferred visiting locations. For example, when a user visits an art museum and goes on a bicycle tour, a relatively higher level of activity fatigue may be set for the bicycle tour compared to visiting the art museum.

The movement line determination module 102b determines the label of the node based on the corrected expected time required. For example, if the corrected expected time required for one node is 3 hours, the route determination module 102b may set the label of the corresponding node to 3. That is, the label can be set for each visit time based on the standard time required and the time required weight retrieved from the database.

The route determination module 102b sets a weight for the edge that matches the path between one of the plurality of nodes corresponding to the airport or preferred visit location and the other.

The database of the device 100 stores a preset reference movement time corresponding to an edge connecting one of the plurality of nodes to another, and the movement line determination module 102b determines the reference movement time corresponding to the edge from the database. Search.

The database of the device 100 stores preset travel time weights for each transportation method and travel time for the edge, and the movement route determination module 102b calculates the edge, the travel time of the edge, and the travel time weight corresponding to the transportation method from the database. Search for. The travel time weight can be set based on the degree of delay by travel time of the transportation means traveling the route corresponding to the edge. For example, if the means of transportation is a bus and the travel time is 12 o'clock, the travel time weight can be set based on the traffic traffic on the route at 12 o'clock and the frequency of the bus at 12 o'clock.

The movement route determination module 102b calculates the expected movement time by multiplying the reference movement time by the movement time weight. The movement route determination module 102b may correct the expected travel time by multiplying the calculated expected travel time by a preset travel fatigue level for each means of transportation. For example, a relatively higher level of travel fatigue may be set for traveling by taxi compared to traveling by bus.

The movement line determination module 102b sets the weight of the edge based on the corrected expected travel time. That is, the weight may be set for each means of transportation and for each travel time based on the standard travel time and expected travel time determined in the database.

The moving route determination module 102b sets a plurality of recommended recommended moving routes and calculates the required time for each of the set plurality of recommended recommended moving routes.

The expected recommended movement line includes some nodes selected from a plurality of nodes and edges that can connect all selected nodes. Then, the movement decision module 102b calculates the sum of the labels of the selected nodes and the sum of the weights of the selected edges. The labels of nodes and the weights of edges can be selected over time. For example, if the arrival time on the first day is 13:00, the first node is the airport, and the label given to the airport at 13:00 is selected. Then, the moving line determination module 102b selects the weight of the first edge connecting the first node and the second node. If the label of the first node is 1, any one of the weights set for each means of transportation for 14 o'clock is selected as the weight of the first edge. The first node of the first date may be set as a node corresponding to the airport. The last node of the return date can be set to the node corresponding to the airport.

The movement route determination module 102b calculates the required time for the expected recommended movement route by adding the sum of the labels of the selected nodes and the sum of the weights of the selected edges. The required time is calculated for each of the plurality of recommended recommended routes.

The route determination module 102b compares the required time for each of the plurality of recommended recommended routes with the user's daily activity time, and determines the expected recommended routes whose required time is less than or equal to the activity time as recommended routes. For example, if the activity time on the first day is 13.2, the expected recommended routes with a required time of 13.2 or less may be selected as the recommended routes on the first date.

Figure 9 is a diagram conceptually showing the process by which the route determination module 102b determines the preferred route.

When the recommended route for each day is determined, the route determination module 102b transmits the recommended route for each day to the user terminal 200, and receives the preferred route for each day selected from the recommended route for each day in the user terminal 200 (FIG. 4, S150 ).

Referring again to FIG. 4, the travel plan decision unit 102 determines recommended accommodations for each day based on the preferred movement route for each day and transmits the determined recommended accommodations for each date to the user terminal (S160).

In addition, the travel plan decision unit 102 receives preferred accommodations for each day selected from recommended accommodations for each day at the user terminal 200, and generates a user travel plan based on the preferred accommodations for each date and the preferred route for each date (S170).

Figure 10 is a diagram conceptually showing the process by which the accommodation decision module 102c determines recommended accommodation.

The accommodation decision module 102c determines the starting location for each day based on the preferred movement route for each day. For example, if the preferred route for the first date starts from the airport, the accommodation decision module 102c may determine the airport as the starting location for the first date.

The accommodation decision module 102c determines preliminary recommended accommodations for each date whose distance from the starting location for each date is less than or equal to a preset standard distance and where reservations for the number of people included in the user information are possible.

The accommodation decision module 102c may determine the final recommended accommodation among the preliminary recommended accommodations for each date based on the accommodation budget, age, gender, and relationship between people included in the user information.

In the database of the device 100, preferences for each of a plurality of preliminary recommended accommodations are preset and stored by age, gender, and relationship between people (family, lover, friend, etc.).

The visit location determination module 102a can search for accommodation preferences of preliminary recommended accommodations that match the user's age, gender, and relationship between people.

The accommodation decision module 102c classifies preliminary recommended accommodations whose prices are below the user's accommodation budget among the preliminary recommended accommodations by date, and selects the preliminary recommended accommodations whose prices are higher than the preset standard among the classified preliminary recommended accommodations into the final recommended accommodations. can be decided.

Figure 11 is a diagram conceptually showing the process by which the accommodation decision module 102c determines preferred accommodation.

Once the recommended route for each day is determined, the accommodation decision module 102c transmits the recommended accommodations for each day to the user terminal 200 and receives the preferred accommodation for each day selected from the recommended accommodations for each day from the user terminal 200 (FIG. 4, S170 ).

When the preferred lodging by date is received, the lodging decision module 102c determines the user's travel plan based on the preferred route by date and the preferred lodging by date. The preferred accommodation for the first date can be placed right behind the airport, and the preferred accommodation for the remaining days can be placed right in front of the starting location.

Figure 12 is a diagram conceptually showing the process of a method for providing travel product sales services according to another embodiment.

If accommodation has a high priority among accommodations and places to visit, the travel plan decision unit 102 sequentially determines the accommodation, place to visit, and route, and makes the user's travel plan based on the determined accommodation, place to visit, and route. establish.

First, the travel plan decision unit 102 calculates a plurality of recommended accommodations based on user information and transmits them to the user terminal 200 (S210).

Figure 13 is a diagram conceptually showing the process by which the accommodation decision module 102c determines recommended accommodation.

The accommodation decision module 102c determines a plurality of recommended accommodations based on user information. User information may include travel area, travel date, accommodation budget, preferred accommodation information, age, gender, number of people, and relationship between people. Preferred accommodation information may include information on whether breakfast is provided, size, whether food is allowed, whether swimming facilities are available, whether fitness facilities are available, and whether spa facilities are available.

In one embodiment, the accommodation decision module 102c may match user information with a plurality of recommended places to visit through a second artificial neural network supervised by learning data. The second artificial neural network is a prediction model implemented in software or hardware that imitates the computational ability of a biological system using a large number of artificial neurons (or nodes). According to one embodiment, the artificial neural network may be an artificial neural network based on a Convolution Neural Network (CNN), Recurrent Neural Network (RNN), Long Short Term Memory models (LSTM), or Gated Recurrent Unit (GRU).

The learning data used for learning the second artificial neural network is the first feature vector (input value) converted from the travel area, travel date, accommodation budget, preferred accommodation information, age, gender, number of people, and relationships between people included in the user information. and the location of the accommodation included in the accommodation information, the reservation date of the accommodation, the price of the accommodation, the preference according to the age of the accommodation, the preference according to the gender of the accommodation, the preference according to the relationship between the number of people in the accommodation, the size of the accommodation, and the provision of accommodation. It consists of a second feature vector (output value) converted from facilities (breakfast, meals, swimming facilities, fitness facilities, spa facilities, etc.).

The second artificial neural network may calculate the similarity between the first feature vector converted from user information and the second feature vector converted from accommodation information, and determine a plurality of recommended accommodations based on the calculated similarity. In one embodiment, the first artificial neural network may determine accommodations whose calculated similarity is greater than or equal to a preset standard as recommended accommodations.

In another embodiment, the accommodation decision module 102c receives reservable airline ticket information from an external server (not shown), matches the received airline ticket information with the travel area and travel date included in the user information, and provides reservable departure airline tickets and A return flight ticket list is provided to the user terminal 200.

In addition, the accommodation decision module 102c receives information about the departure flight ticket and return flight ticket selected by the user from the user terminal 200, and determines the arrival time and return time based on the information about the received departure flight ticket and return flight ticket. Calculate Arrival time refers to the time at which the plane corresponding to the departure ticket arrives at the travel area airport, and return time refers to the time at which the plane corresponding to the return ticket leaves the travel area airport.

Additionally, the accommodation decision module 102c determines a plurality of preliminary recommended visit locations based on the travel area, travel date, and number of people. The database of the device 100 stores the location corresponding to each of the plurality of accommodations and the number of people available for reservation by date, and the accommodation decision module 102c calculates the number of people available for reservation by location and date according to the user's travel area, travel date, and number of people. Accommodations that match are searched in the database, and the searched accommodations are determined as preliminary recommended places to visit. The database can receive and store the number of people available for reservation by date for each of a plurality of accommodations from an external server (not shown). The number of people available for reservation per day can be received at preset time intervals.

In addition, the accommodation decision module 102c may determine the final recommended accommodation among a plurality of preliminary recommended accommodations based on the accommodation budget, preferred accommodation information, age, gender, number of people, and relationships between people included in the user information. .

In the database of the device 100, preferences for each of a plurality of preliminary recommended accommodations are preset and stored by age, gender, and relationship between people (family, lover, friend, etc.).

The visit location determination module 102a can search for accommodation preferences of preliminary recommended accommodations that match the user's age, gender, and relationship between people.

The accommodation decision module 102c classifies the preliminary recommended accommodations whose prices are below the user's accommodation budget among a plurality of preliminary recommended accommodations, and selects the preliminary recommended accommodations whose prices are higher than the preset standard among the classified preliminary recommended accommodations into the final recommended accommodations. You can decide by

Figure 14 is a diagram conceptually showing the process by which the accommodation decision module 102c determines preferred accommodation.

The accommodation decision module 102c provides the determined plurality of recommended accommodations to the user terminal 200, and receives preferred accommodations for each date selected from the plurality of recommended visit locations in the user terminal 200 (FIG. 12, S220).

Referring again to FIG. 12, the travel plan decision unit 102 determines recommended visit locations for each date based on user information and preferred accommodations for each date, and transmits the determined recommended visit locations for each date to the user terminal (S230).

Additionally, the travel plan decision unit 102 receives preferred visit places by date selected from the recommended visit places by date from the user terminal 200 (S240).

Figure 15 is a diagram conceptually showing the process by which the visit place determination module 102a determines recommended visit places by date.

The visit location determination module 102a calculates the activity area for each day based on the location of each preferred accommodation for each day. Areas located within a preset distance from each location can be set as activity areas.

Additionally, the visit location determination module 102a determines a plurality of preliminary recommended visit locations based on the daily activity area, arrival time, and return time. In the database of the device 100, the location, business date, and business hours corresponding to each of the plurality of business places are already stored, and the visit place determination module 102a stores the location, business date, and business hours according to the activity area and arrival time by date. Search the database for business locations that match the time and return time, and determine the searched business locations as preliminary recommended places to visit. For example, business places whose business hours end before the arrival time and business places whose business hours begin after the return time may be excluded from the preliminary recommended visit locations. Since preliminary recommended visit places are searched based on activity areas by date, preliminary recommended visit places can be searched by date. That is, the visit place determination module 102a searches for preliminary recommended visit places by date.

In addition, when the preliminary recommended visit place is a tourist destination, the visit place determination module 102a determines the connection between a plurality of preliminary recommended visit places and the user based on the user tourist destination preference, age, gender, and relationship between people included in the user information. The matching degree can be calculated, and the final recommended visiting place among the plurality of preliminary recommended visiting places can be determined based on the calculated matching degree.

When the preliminary recommended visit place is a restaurant, the visit place determination module 102a matches a plurality of preliminary recommended visit places and the user based on the user's food preference, age, gender, and relationship between people included in the user information. The degree can be calculated, and the final recommended visit place among the plurality of preliminary recommended visit places can be determined based on the calculated matching degree.

Figure 16 is a diagram conceptually showing the process by which the visit location determination module 102a determines a preferred visit location.

The visit place determination module 102a provides recommended visit places for each determined date to the user terminal 200, and receives preferred visit places for each date selected from the recommended visit places for each date from the user terminal 200 (FIG. 12, S240). .

Referring again to FIG. 12, the travel plan decision unit 102 calculates the business hours and time required for each preferred visit location by date, and predicts the preferred visit location by date and each time zone between the plurality of preferred visit locations. Calculate the travel time (S250).

The travel plan decision unit 102 calculates the activity time corresponding to each date, and calculates the activity time for each date, arrival time, return time, business hours for each preferred visit location, time required for each time zone, and preferred accommodation for each date. A recommended route for each day is determined based on the expected travel time for each time zone between the fields and preferred visit locations for each day (S260).

Figure 17 is a diagram conceptually showing the process by which the route determination module 102b calculates business hours, expected travel time, and expected travel time.

Figure 18 is a diagram conceptually showing the process by which the route determination module 102b determines the recommended route.

The movement route determination module 102b calculates the activity time for each day based on the travel date, activity weight, arrival time, and return time.

The movement line determination module 102b calculates the activity weight based on age, gender, and physical strength included in the user information.

Physical strength may be set based on responses to a preset questionnaire regarding physical strength received from the user, and may be divided into a plurality of different levels. For example, physical strength can be classified as strong, average, or weak.

In addition, the movement route determination module 102b may determine the activity time on the first date as the difference between the arrival time on the first date of arrival at the travel area and the preset schedule deadline multiplied by the activity weight. For example, if the arrival time is 10 o'clock, the schedule deadline is 21 o'clock, and the activity weight is 1.2, the movement route determination module 102b may determine the activity time of the first day as 13.2.

Additionally, the movement route determination module 102b may determine the activity time of the intermediate date as the difference between the preset schedule start time and the schedule end time multiplied by the activity weight. For example, if the schedule start time is 11 o'clock, the schedule end time is 21 o'clock, and the activity weight is 1.2, the movement route determination module 102b may determine the activity time of the middle day to be 12.

Additionally, the movement route determination module 102b may determine the difference between the preset schedule start time and the return time leaving the travel area multiplied by the activity weight as the activity time on the return date. For example, if the schedule start time is 11:00, the return time is 16:00, and the activity weight is 1.2, the route determination module 102b may determine the activity time on the return date to be 6.

Once the activity time is determined, the movement route decision module 102b determines the activity time by day, arrival time, return time, business hours by day for the preferred visit location, time required by time zone, and time zone between the airport and a plurality of preferred visit locations. Based on the expected travel time, the recommended route for each day is determined.

The movement line determination module 102b can correct the daily activity time based on the daily weight. The weight for each day is a preset value and can be set in consideration of the user's fatigue that accumulates as the travel date passes. For example, the weight for each day may be set to decrease sequentially from the first date to the return date. For example, if the activity time from the first date to the return date is sequentially 13.2, 12, and 6, and the weight for each day from the first date to the return date is 1, 0.9, 0.8, the activity time from the first date to the return date can be corrected to 13.2, 10.8, 4.8.

The movement route determination module 102b creates a plurality of nodes, each of which corresponds to an airport, preferred accommodations by date, and preferred visit places by date, and assigns a label to each of the created nodes. Additionally, the movement line determination module 102b generates an edge connecting one of the plurality of nodes to another node, and assigns a weight to the generated edge.

The route determination module 102b may set the label of the node based on the expected travel time corresponding to the airport, preferred accommodation, or preferred visit location.

The database of the device 100 stores a preset standard time required for each of the airport, preferred accommodations by date, and a plurality of preferred visit locations, and the movement route determination module 102b determines the standard time required corresponding to the node in the database. Search.

The database of the device 100 stores preset time required weights for each visit time for each of the airport, preferred accommodations by date, and a plurality of preferred visit locations, and the movement route determination module 102b determines the node and the visit time of the node in the database. Search for the time required weight corresponding to . The time required weight can be set based on the expected number of visitors by visit time for the airport or preferred visit location corresponding to the node.

The movement route determination module 102b calculates the expected travel time by multiplying the searched standard travel time by the travel time weight. The movement route determination module 102b may correct the expected travel time by multiplying the calculated expected travel time by the preset activity fatigue level for the airport, preferred accommodations by date, and preferred visit places by day. Activity fatigue can be set based on activities performed by the user at the airport, preferred accommodations by day, and preferred visit places by day. For example, when a user visits an art museum and goes on a bicycle tour, a relatively higher level of activity fatigue may be set for the bicycle tour compared to visiting the art museum.

The movement line determination module 102b determines the label of the node based on the corrected expected time required. For example, if the corrected expected time required for one node is 3 hours, the route determination module 102b may set the label of the corresponding node to 3. That is, the label can be set for each visit time based on the standard time required and the time required weight retrieved from the database.

The route determination module 102b sets a weight for the edge that matches the path between one of the plurality of nodes corresponding to the airport, preferred accommodations by date, and preferred visit place by date.

The database of the device 100 stores a preset reference movement time corresponding to an edge connecting one of the plurality of nodes to another, and the movement line determination module 102b determines the reference movement time corresponding to the edge from the database. Search.

The database of the device 100 stores preset travel time weights for each transportation method and travel time for the edge, and the movement route determination module 102b calculates the edge, the travel time of the edge, and the travel time weight corresponding to the transportation method from the database. Search for. The travel time weight can be set based on the degree of delay by travel time of the transportation means traveling the route corresponding to the edge. For example, if the means of transportation is a bus and the travel time is 12 o'clock, the travel time weight can be set based on the traffic traffic on the route at 12 o'clock and the frequency of the bus at 12 o'clock.

The movement route determination module 102b calculates the expected movement time by multiplying the reference movement time by the movement time weight. The movement route determination module 102b may correct the expected travel time by multiplying the calculated expected travel time by a preset travel fatigue level for each means of transportation. For example, a relatively higher level of travel fatigue may be set for traveling by taxi compared to traveling by bus.

The movement line determination module 102b sets the weight of the edge based on the corrected expected travel time. That is, the weight may be set for each means of transportation and for each travel time based on the standard travel time and expected travel time determined in the database.

The route determination module 102b sets expected recommended routes for each day based on preferred accommodations for each date and recommended recommended places to visit for each date, and calculates the required time for each of the recommended routes for each set date.

The recommended recommended route for each day includes some nodes selected from a plurality of nodes and edges that can connect all of the selected nodes. Then, the movement decision module 102b calculates the sum of the labels of the selected nodes and the sum of the weights of the selected edges. The labels of nodes and the weights of edges can be selected over time. For example, if the arrival time on the first day is 13:00, the first node is the airport, and the label given to the airport at 13:00 is selected. Then, the moving line determination module 102b selects the weight of the first edge connecting the first node and the second node. If the label of the first node is 1, any one of the weights set for each means of transportation for 14 o'clock is selected as the weight of the first edge. The first node of the first date may be set as a node corresponding to the airport. The last node of the return date can be set to the node corresponding to the airport.

The movement route determination module 102b calculates the required time for the expected recommended movement route by adding the sum of the labels of the selected nodes and the sum of the weights of the selected edges. The required time is calculated for each of the recommended recommended routes for each day.

The movement route determination module 102b compares the required time for each of the recommended recommended routes for each day with the user's daily activity time, and determines the expected recommended routes whose required time is less than the activity time as recommended routes. For example, if the activity time on the first day is 13.2, the expected recommended routes with a required time of 13.2 or less may be selected as the recommended routes on the first date.

Figure 19 is a diagram conceptually showing the process by which the route determination module 102b determines the preferred route.

Once the recommended routes for each day are determined, the route determination module 102b transmits the recommended routes for each day to the user terminal 200 (FIG. 12, S260).

In addition, the route determination module 102b receives a preferred route for each day selected from the recommended routes for each day from the user terminal 200, and generates a user travel plan based on the preferred route for each day (FIG. 12, S270).

Figure 20 is a flowchart showing the process of a method for providing a travel product sales service according to another embodiment.

The seller matching unit 103 determines at least one matching seller terminal whose business area matches the user's travel plan among the plurality of seller terminals 300 (S310). The business area is a preset area for each of the plurality of seller terminals 300 and is stored in the database of the device 100.

Additionally, the seller matching unit 103 transmits the user travel plan to at least one matched seller terminal (S320).

Additionally, the seller matching unit 103 receives at least one travel product from at least one matching seller terminal (S330). At least one travel product includes at least one of a departure flight ticket, a return flight ticket, a plurality of preferred accommodations, and a plurality of preferred visit locations included in the user's travel plan.

In addition, the seller matching unit 103 transmits at least one received travel product to the user terminal 200 (S340) and receives a preferred travel product selected from the at least one travel product from the user terminal 200 (S340) S350).

Additionally, the seller matching unit 103 performs payment and reservation based on the user's travel plan and preferred travel products (S360).

Figure 21 is a flowchart showing the process by which the product review unit 104 determines user priorities.

First, the product review unit 104 receives travel product information from the seller terminal 300 (410). Travel product information refers to information about travel products sold by a seller corresponding to the seller terminal 300. Travel product information may include the travel product name, price, schedule, number of people, related keywords, description of the travel product, etc.

Additionally, the product review unit 104 compares the received travel product information with preset registration criteria and determines whether to register the travel product result based on the comparison result (S420). In one embodiment, the preset registration criteria may include whether the price is included in a preset price range corresponding to the travel product, whether the travel product information includes all of a plurality of preset essential information, etc. If the received travel product information satisfies the preset registration criteria, the product review unit 104 registers the travel product information as a sellable travel product.

Additionally, the product screening unit 104 provides registered travel product information and seller information corresponding to the travel product information to the user terminal 200 (S430).

The device 100 provides registered travel product information to the user terminal 200, and when an information provision request for specific travel product information is received from the user terminal 200, the travel product specified by the user terminal 200 is provided. Seller information corresponding to the travel product information is provided to the user terminal 200 along with the information.

Figure 22 is a diagram conceptually showing seller information and travel product information provided to the user terminal 200. Seller information may include the seller's unique identifier (ID), seller introduction, image designated by the seller, and travel product information for each travel product sold by the seller. Travel product information may include the travel product name, price, schedule, number of people, rating, and keywords related to the travel product.

Additionally, the product screening unit 104 may provide a search service for travel product information to the user terminal 200. When a search term is received from the user terminal 200, the product screening unit 104 may provide the user terminal 200 with travel product information matching the search term.

FIG. 23 is a flowchart showing a process in which the travel information provider 105 provides travel information to the user terminal 200.

First, the travel information provider 105 receives an information request from the user terminal 200 (S510). In one embodiment, the information request may include transportation methods to reach the tourist destination, entrance fees to the tourist destination, a description of the tourist destination, travel products associated with the tourist destination, prices of travel products associated with the tourist destination, etc.

When an information request is received, the travel information provider 105 searches the database for travel information matching the information request (S520). In the database of the device 100, information related to tourist attractions, restaurants, and accommodations may be previously stored.

Additionally, the travel information provider 105 searches for travel product information that matches the information request among the travel product information provided by the seller terminal 300 (S530). The database of the device 100 stores travel product information provided by the seller terminal 300, and the device 100 searches for travel product information that matches the information request.

Additionally, the travel information provider 105 transmits the searched travel information and travel product information to the user terminal 200 (S540).

Figure 24 is a flowchart showing a process in which the accommodation reservation unit 106 provides an accommodation reservation service.

First, the accommodation reservation unit 106 specifies an accommodation whose distance from the user terminal 200 is less than or equal to a preset reference distance based on the location information of the user terminal 200 and the location information of the accommodation (S610). The accommodation reservation unit 106 calculates the distance between each of the plurality of accommodations and the user terminal 200 based on the location information for each of the plurality of accommodations stored in the database and the location information of the user terminal 200. And, an accommodation whose distance from the user terminal 200 is less than or equal to a preset reference distance is specified.

Additionally, the accommodation reservation unit 106 determines whether the specified accommodation can be reserved based on the reservation information of the specified accommodation (S620). The accommodation reservation unit 106 may receive reservation information about the reservation status of the accommodation at preset time intervals. Information on the reservation status of the received accommodation is stored in the database.

Additionally, if the specified accommodation is available for reservation, the accommodation reservation unit 106 transmits accommodation information about the specified accommodation to the user terminal 200 (S630). Accommodation information may include the name of the accommodation, description of the accommodation, rating, price, number of people who can make a reservation, services provided, facilities provided, etc.

Additionally, when a reservation request is received from the user terminal 200, the accommodation reservation unit 106 makes a reservation for the specified accommodation (S640).

When the reservation for the accommodation is confirmed, the accommodation reservation unit 106 may transmit article information about the plurality of pickup terminals 400 to the user terminal 200. When a reservation request for a specific pickup terminal 400 is received from the user terminal 200, the accommodation reservation unit 106 performs a reservation for the pickup terminal 400.

Figure 25 is a flowchart showing the process by which the restaurant reservation unit 107 provides a restaurant reservation service.

First, the restaurant reservation unit 107 specifies a restaurant whose distance from the user terminal 200 is less than or equal to a preset reference distance based on the location information of the user terminal 200 and the location information of the restaurant (S710). The restaurant reservation unit 107 calculates the distance between each of the plurality of restaurants and the user terminal 200 based on the location information for each of the plurality of restaurants stored in the database and the location information of the user terminal 200. And, a restaurant whose distance from the user terminal 200 is less than or equal to a preset reference distance is specified.

Additionally, the restaurant reservation unit 107 determines whether a reservation at a specified restaurant is possible based on the reservation information of the specified restaurant (S720). The restaurant reservation unit 107 may receive reservation information about the reservation status of the restaurant at preset time intervals. Information about the received restaurant reservation status is stored in the database.

Additionally, if the specified restaurant is available for reservation, the restaurant reservation unit 107 transmits restaurant information about the specified restaurant to the user terminal 200 (S730). Restaurant information may include the name of the restaurant, a description of the restaurant, ratings, prices, number of people who can make reservations, menus provided, etc.

Additionally, when a reservation request is received from the user terminal 200, the restaurant reservation unit 107 makes a reservation for the specified restaurant (S740).

When a reservation for a restaurant is confirmed, the restaurant reservation unit 107 may transmit article information about a plurality of pickup terminals 400 to the user terminal 200. When a reservation request for a specific pickup terminal 400 is received from the user terminal 200, the restaurant reservation unit 107 makes a reservation for the pickup terminal 400.

FIG. 26 is a diagram illustrating an exemplary hardware configuration of the device according to FIG. 1.

Referring to FIG. 26, the device 100 includes at least one processor 110 and a memory that stores instructions that instruct the at least one processor 110 to perform at least one operation. (memory) may be included.

The at least one operation may include the components 101 to 107 of the above-described device 100 or other functions or operating methods.

Here, the at least one processor 110 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed. You can. Each of the memory 120 and the storage device 160 may be comprised of at least one of a volatile storage medium and a non-volatile storage medium.

For example, the memory 120 may be one of read only memory (ROM) and random access memory (RAM), and the storage device 160 may be flash memory. , a hard disk drive (HDD), a solid state drive (SSD), or various memory cards (eg, micro SD card).

Additionally, the device 100 may include a transceiver 130 that performs communication through a wireless network. Additionally, the device 100 may further include an input interface device 140, an output interface device 150, a storage device 160, etc. Each component included in the device 100 is connected by a bus 170 and can communicate with each other.

Examples of the device 100 include a desktop computer, a laptop computer, a laptop, a smart phone, a tablet PC, and a mobile phone capable of communicating. , smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player. , a digital audio recorder, a digital audio player, a digital video recorder, a digital video player, a PDA (Personal Digital Assistant), etc.

The first artificial neural network and the second artificial neural network may be composed of an artificial neural network 10 communicatively connected to the device 100, and the artificial neural network 10 may include an input layer, a hidden layer, and an output layer.

In one embodiment, the first artificial neural network and the second artificial neural network receive input values, and each of the input layer 10 has nodes corresponding to the number of components of the first feature vector, and the output value of the input layer 10. One or more hidden layers that multiply the connection strengths (or weights) and add a bias to output; And it may include an output layer that multiplies each output value of the hidden layer by a connection strength (or weight) and outputs the result using an activation function. For example, the activation function may be a LeRU function or a Softmax function, but is not limited thereto. Connection strength and bias can be continuously updated through supervised learning.

Specifically, the first artificial neural network and the second artificial neural network may be supervised so that the output value of the loss function according to the given input value (first feature vector) and output value (second feature vector) is minimized. For example, the loss function (H(Y,Y')) can be defined as Equation 1 below.

In Equation 1, Y _m is the mth component of the second feature vector, and may be the mth component of the output vector output by receiving the first feature vector from the first artificial neural network and the second artificial neural network.

Methods according to the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. Computer-readable media may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on a computer-readable medium may be specially designed and constructed for the present invention or may be known and usable by those skilled in the computer software art.

Examples of computer-readable media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions may include machine language code such as that created by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The above-described hardware device may be configured to operate with at least one software module to perform the operations of the present invention, and vice versa.

Additionally, the above-described method or device may be implemented by combining all or part of its components or functions, or may be implemented separately.

Although the present invention has been described above with reference to preferred embodiments, those skilled in the art may make various modifications and changes to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that you can do it.

Claims (1)

A method of providing a travel product sales service through a reverse auction performed by a device, comprising:
Receiving priority information including rankings for each place to visit and accommodation from the user terminal;
If the ranking for the place to visit is higher than the ranking for the accommodation, first user information including travel area, travel date, user tourist destination preference, age, gender, number of people, relationship between people, user food preference, and physical strength is stored in advance. Input the learned first artificial neural network as an input value, obtain a plurality of first recommended visiting places from the first artificial neural network, transmit the first recommended visiting places to the user terminal, and receive the user information from the user terminal. Receiving first preferred visit places that are the selected first recommended visit places;
selecting an age weight, a gender weight, and a physical strength weight matched with the age, the gender, and physical strength from a database, and determining the product of the age weight, the gender weight, and the physical strength weight as an activity weight;
determining an activity time corresponding to the travel date using the arrival time of the first date of arrival at the travel area, a preset schedule start time, a preset schedule end time, a return time leaving the travel area, and the activity weight;
Select a first standard travel time matched with each of the airport and the first preferred visit locations from the database, and select a first travel time weight matched by visit time for each of the airport and the first preferred visit locations. and determining a first expected travel time corresponding to each of the airport and the first preferred visit locations using the first standard travel time and the first travel time weight;
Select a first reference travel time matching each of a plurality of first routes connecting between the airport and the first preferred visit locations from the database, and select each of the first routes by means of transportation and travel time. selecting a first travel time weight matched with , and determining a first expected travel time corresponding to each of the first routes using the first reference travel time and the first travel time weight;
Determine a plurality of first recommended recommended routes connecting the airport and at least two of the first preferred places to visit, and each of the first recommended places included in the first recommended places to visit correspond to each of the first preferred places to visit. Using the first expected travel time and the first expected travel time corresponding to each of the first routes included in the first expected recommended route, a first required time corresponding to each of the first expected recommended route is calculated. deciding step;
determining the first expected recommended routes for which the first required time is smaller than the activity time as first recommended routes;
Transmitting the first recommended routes to the user terminal and receiving first preferred routes, which are the first recommended routes selected by the user, from the user terminal;
determining a starting location corresponding to each of the first preferred movement lines, and determining a plurality of first preliminary recommended lodgings where the distance from the starting location is less than or equal to a preset reference distance and the number of people available for reservation is greater than or equal to the number of people;
selecting an accommodation preference matched with the first preliminary recommended accommodation, the age, the gender, and the relationship between people from the database;
determining the first preliminary recommended accommodations whose accommodation preferences are equal to or higher than a preset standard as first recommended accommodations;
transmitting the first recommended accommodations to the user terminal and receiving first preferred accommodations, which are the first recommended accommodations selected by the user, from the user terminal;
generating a first user travel plan using the first preferred routes and the first preferred accommodations;
If the ranking for the accommodation is higher than the ranking for the visiting place, the second user includes the travel area, the travel date, accommodation budget, preferred accommodation information, the age, the gender, the number of people, and the relationship between the people. Enter information as an input value into a pre-trained second artificial neural network, obtain a plurality of second recommended accommodations from the second artificial neural network, transmit the second recommended accommodations to the user terminal, and transmit the second recommended accommodations from the user terminal. Receiving second preferred accommodations, which are the second recommended accommodations selected by the user;
setting areas located within a preset distance from each of the second preferred accommodations as activity areas corresponding to each of the second preferred accommodations;
determining a plurality of second preliminary recommended visit locations using the activity area, the arrival time, and the return time;
When the second preliminary recommended visit places are tourist destinations, a first matching diagram corresponding to each of the preliminary recommended visit places using the tourist destination preference, the age, the gender, and the relationship between people included in the first user information Calculating and determining second recommended visit places among the second preliminary recommended visit places using the first matching degree;
When the second preliminary recommended visit places are restaurants, a second service corresponding to each of the second preliminary recommended visit places using the food preference, age, gender, and relationship between people included in the first user information calculating a matching degree and determining second recommended visit places among the second preliminary recommended visit places using the second matching degree;
transmitting the second recommended visit places to the user terminal and receiving second preferred visit places, which are the second recommended visit places selected by the user, from the user terminal;
Select a second standard travel time that matches each of the airport, the second preferred accommodations, and the second preferred visiting locations from the database, and select the airport, the second preferred accommodations, and the second preferred visiting locations from the database. For each of them, a second travel time weight is selected that matches each visit time, and a second travel time weight corresponding to each of the airport and the second preferred visit location is selected using the second standard travel time and the second travel time weight. Determining the expected time required;
Select a second reference travel time matching each of a plurality of second routes connecting the airport, the second preferred accommodations, and the second preferred visit locations from the database, and select a second reference travel time for each of the second routes. For each means of transportation and travel time, a second travel time weight is selected, and a second expected travel time corresponding to each of the second routes is determined using the second reference travel time and the second travel time weight. deciding step;
Determine a plurality of second recommended recommended routes connecting at least two of the airport, the second preferred accommodations, and the second preferred visit locations, and determine the second preferred route included in the second recommended route. Using the second expected travel time corresponding to each of the places and the second expected travel time corresponding to each of the second routes included in the second expected recommended route, each of the second expected recommended routes and determining a corresponding second required time;
determining the second expected recommended routes for which the second necessary time is smaller than the activity time as second recommended routes;
Transmitting the second recommended routes to the user terminal and receiving second preferred routes, which are the second recommended routes selected by the user, from the user terminal;
generating a second user travel plan using the second preferred routes;
determining at least one seller terminal whose business area matches the second user's travel plan;
transmitting the second user travel plan to at least one matched merchant terminal;
Receiving at least one travel product from at least one seller terminal;
Transmitting at least one received travel product to the user terminal; and
Comprising the step of receiving a preferred travel product selected from the at least one travel product from the user terminal,
How to provide travel product sales services.