TERMINAL, SERVER AND EVENT SUGGESTING METHODS THEREOF

• US 20170161393A1
• Filed: 12/05/2016
• Published: 06/08/2017
• Est. Priority Date: 12/08/2015
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: OH, Hyung-rai, CHOI, Ho-jin, KIM, Zae-myung, OH, Kyo-joong, LIM, Chae-gyun
• Granted Patent: US 10,353,975 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 50/14 Travel agencies
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
• CPC Class Codes: H04L 51/42 Mailbox-related aspects, e.g. synchronisation of mailboxes
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/023 using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
• CPC Class Codes: H04W 4/14 Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

Disclosed are a terminal, a server and event suggesting methods thereof, the event suggesting method using word embedding, the method including: determining user preference information about a predetermined object by assigning values to a plurality of reference items with respect to user input data corresponding to the object; generating user intent information, which includes values based on the plurality of reference items, based on at least one piece of review data corresponding to a plurality of events for recommendation objects, and accessing a database built up by adding the generated user intent information to the plurality of events; and suggesting an event following the object among the plurality of events based on a similarity between the user preference information about the object and the user intent information of each event included in the database. Thus, the event based on to a user'"'"'s preference is suggested, thereby providing the event-recommendation service to make a user'"'"'s satisfaction higher.

Claims

1. An event suggesting method using word embedding, the method comprising:

determining user preference information about a predetermined object by assigning values to a plurality of reference items based on user input data corresponding to the object;

generating user intent information, comprising values of the plurality of reference items, based on at least one piece of review data corresponding to a plurality of events for recommendation objects, and accessing a database built up by adding the generated user intent information to the plurality of events; and

suggesting an event following the object among the plurality of events based on a similarity between the user preference information about the object and the user intent information of each event involved in the database.

2. The method according to claim 1, further comprising:

sensing a trigger event comprising a terminal receiving the user input data.

3. The method according to claim 2, wherein the user input data comprises at least one of:

a text, a picture, a moving picture and a voice uttered by a user, and the user input data is input by at least one of;

a review input to a website, a short message service (SMS), a social network service (SNS) and E-mail.

4. The method according to claim 1, wherein the user input data comprises a plurality of user reviews input at a predetermined time difference and corresponding to the plurality of objects, respectively,

the method further comprising sensing a trigger event comprising updating history information including the plurality of user reviews.

5. The method according to claim 1, further comprising:

sensing a user'"'"'s context information as a trigger event;

changing the user preference information by increasing or decreasing a value of at least one among the plurality of reference items in the user preference information based on the sensed context information.

6. The method according to claim 1, wherein the object comprises a travel destination previously visited by a user, and the event comprises a next travel destination recommendable based on a user'"'"'s intent about the visited travel destination.

7. The method according to claim 6, further comprising:

building up the database by collecting at least one piece of review data of the plurality of events from at least one accessible website.

8. The method according to claim 7, wherein the building up the database comprises:

creating a visit intent vector based on a user'"'"'s visit intent with respect to the collected review data; and

adding a travel-destination visit intent vector, created by averaging and normalizing the created visit intent vector based on the plurality of events, as the user intent information to the plurality of events.

9. The method according to claim 8, wherein the creating the visit intent vector comprises:

crawling the collected review data;

preprocessing at least one word to be filtered out of the crawled review data; and

transforming the preprocessed review data into a review vector by word embedding.

10. The method according to claim 9, further comprising:

creating intent vectors respectively corresponding to the plurality of reference items from a set of words based on intents respectively created with respect to the plurality of events; and

determining a similarity between the transformed review vector and each of the plural intent vectors corresponding to the plurality of reference items and assigning the similarity to the visit intent vector.

11. The method according to claim 10, wherein the building up the database comprises

determining a correlation distance between the plurality of events by the travel-destination visit intent vector;

and

establishing a travel-destination network model in the database so that the events can be linked to form a network if the correlation distance is not greater than a predetermined reference value.

12. A terminal comprising:

a display;

input circuitry configured to receive a user'"'"'s input;

communication circuitry configured to access a database including a user intent information, which is generated based on at least one piece of review data corresponding to a plurality of events for recommendation objects and comprises values based on a plurality of reference items, to the plurality of events;

at least one processor configured to determine user preference information about a predetermined object by assigning values to the plurality of reference items with respect to user input data corresponding to the object, and to control the display to display information for suggesting an event following the object among the plurality of events based on a similarity between the user preference information about the object and the user intent information of each event included in the database.

13. The terminal according to claim 12, wherein the processor is configured to sense a trigger event, the trigger event comprising the terminal receiving the user input data.

14. The terminal according to claim 12, wherein

the user input data comprises a plurality of user reviews input at a predetermined time difference and respectively corresponding to the plurality of objects, and

the processor configured to sense a trigger event, the trigger event comprising updating history information comprising the plurality of user reviews.

15. The terminal according to claim 12, wherein the processor is configured to sense a user'"'"'s context information as a trigger event, and to change the user preference information by increasing or decreasing the value of at least one among the plurality of reference items in the user preference information based on the sensed context information.

16. A server to be accessed by at least one terminal, the server comprising:

communication circuitry configured to receive information of user input data about a predetermined object from the terminal;

a database configured to be built up by generating user intent information, which comprises values based on a plurality of reference items, based on at least one piece of review data corresponding to a plurality of events for recommendation objects, and adding the generated user intent information to the plurality of events;

at least one processor configured to determine a recommendation event following the object among the plurality of events based on a similarity between user preference information about the object determined by assigning values to the plurality of reference items with respect to the user input data and the user intent information of each event involved in the database, and to control the communication circuitry to send information about the determined recommendation event to the terminal.

17. The server according to claim 16, wherein the object comprises a travel destination previously visited by a user, and the event comprises a next travel destination recommendable based on a user'"'"'s intent about the visited travel destination.

18. The server according to claim 17, wherein the processor is configured to build up the database by collecting at least one piece of review data based on the plurality of events from at least one accessible website, creating a visit intent vector based on a user'"'"'s visit intent with respect to the collected review data, and adding a travel-destination visit intent vector, which is created by averaging and normalizing the created visit intent vector based on the plurality of events, as the user intent information to the plurality of events.

19. The server according to claim 18, wherein the processor is configured to determine a correlation distance between the plurality of events by the travel-destination visit intent vector, and to establish a travel-destination network model in the database so that the events can be linked to form a network if the correlation distance is not greater than a predetermined reference value.