ITEM RECOMMENDATION DEVICE, ITEM RECOMMENDATION METHOD, AND COMPUTER PROGRAM PRODUCT

• US 20160125048A1
• Filed: 10/29/2015
• Published: 05/05/2016
• Est. Priority Date: 10/31/2014
• Status: Active Grant

• Current Assignee: Toshiba Digital Solutions Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Solutions Corporation (Toshiba Corporation)
• Inventors: Hamada, Shinichiro
• Granted Patent: US 10,089,364 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking

Abstract

An item recommendation device includes a context information generator and a ranker. The context information generator generates and outputs context information including user intention by performing semantic analysis on a natural language request which is input. The ranker ranks candidates of items to be presented to a user based on the context information, user information representing an attribute of the user, and history information representing item usage history of the user.

Claims

1. An item recommendation device comprising:

a context information generator that generates and outputs context information including user intention by performing semantic analysis on a natural language request which is input; and

a ranker that ranks candidates of items to be presented to a user based on the context information, user information representing an attribute of the user, and history information representing item usage history of the user.

2. The device according to claim 1, further comprising a context tag dictionary that stores therein a context tag, which straightforwardly represents a context, in association with a phrase which is semantically similar to the context tag, wherein

when a phrase extracted from the natural language request which is input matches with the context tag stored in the context tag dictionary, the context information generator outputs the context tag as the context information, and

when a phrase extracted from the natural language request which is input matches with a phrase stored in the context tag dictionary, the context information generator outputs the context tag, which is stored in association with the phrase in the context tag dictionary, as the context information.

3. The device according to claim 1, wherein the context information generator generates a feature vector that represents meaning of entire text of the natural language request by performing statistical semantic analysis on the natural language request which is input, and outputs the feature vector as the context information.

4. The device according to claim 1, further comprising:

a search information generator that generates search information which is used in searching a storing unit storing therein item information by performing semantic analysis on the natural language request which is input; and

a candidate extractor that searches the storing unit using the search information, and extracts candidates of items to be presented to the user.

5. The device according to claim 4, further comprising a search tag dictionary that stores therein a search tag, which serves as a search keyword, in association with a phrase semantically similar to the search tag and an application destination attribute representing an attribute to which the search tag is applied, wherein

when a phrase extracted from the natural language request which is input matches with the search tag stored in the search tag dictionary, the search information generator outputs the search tag and the application destination attribute, which is stored in association with the search tag in the search tag dictionary, as the search information, and

when a phrase extracted from the natural language request which is input matches with a phrase stored in the search tag dictionary, the search information generator outputs the search tag, which is stored in association with the phrase in the search tag dictionary, and the application destination attribute, which is stored in association with the search tag in the search tag dictionary, as the search information.

6. The device according to claim 1, further comprising:

a human relationship information generator that analyzes an image which is input, and generates and outputs human relationship information which represents human relationship in a group of persons included in the image; and

an integrating unit that integrates the human relationship information into the context information, wherein

the ranker ranks candidates of items to be presented to user based on the context information into which the human relationship information has been integrated, the user information, and the history information.

7. The device according to claim 6, wherein the human relationship information generator

detects persons from the image and estimates attribute of each of the persons, and

collates a set of attributes of the persons detected from the image with a predetermined rule and generates the human relationship information.

8. The device according to claim 7, wherein

from among persons detected from the image, the human relationship information generator selects a person having largest size in the image, or selects a person detected to be closest to center of the image, or selects a person whose lip area is moving, and

the ranker uses attribute of the person, who is selected by the human relationship information generator, as the user information.

9. An item recommendation method implemented in an item recommendation device, comprising:

generating and outputting context information including user intention by performing semantic analysis on a natural language request which is input; and

ranking candidates of items to be presented to a user based on the context information, user information representing an attribute of the user, and history information representing item usage history of the user.

10. A computer program product comprising a computer readable medium including programmed instructions for enabling item recommendation, wherein the instructions, when executed by a computer, cause the computer to perform:

generating and outputting context information including user intention by performing semantic analysis on a natural language request which is input; and

ranking candidates of items to be presented to a user based on the context information, user information representing an attribute of the user, and history information representing item usage history of the user.