IP Library › Granted Patent US 12,001,793
Granted Patent B2
US 12,001,793 · App. 17/042,605 · Granted Jun 4, 2024

Interaction server

Inventors: Hiroshi Fujimoto (Chiyoda-ku, JP); Takanori Hashimoto (Chiyoda-ku, JP); Yuriko Ozaki (Chiyoda-ku, JP)
Assignee: NTT DOCOMO, INC.
G06F40/279G06F16/2455G06F16/284G06F40/30
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,001,793
App. No.
17/042,605
Filed
Sep 28, 2020
Granted
Jun 4, 2024
Kind
B2
Art Unit
2657
USPC
704/9
Abstract

An object is to provide an interaction server in which inputs of an input keyword are reduced and the number of exchanges in interaction is reduced as a result. An interaction server 100 includes a truth table 104 configured to have question sentences including a sentence to be provided to a user and a plurality of searching keywords associated with, and a relational table 105 configured to have one main keyword and a plurality of related keywords related to the main keyword associated with each other. A search unit 102 acquires at least one of the one main keyword and any of the plurality of related keywords listed in the relational table 105 on the basis of an input keyword, further performs searching in the truth table 104 using the main keyword and/or the related keyword which has been acquired, and acquires a question sentence candidate which is response content corresponding to the main keyword or the related keyword.

Claims (39)

1. An interaction server that holds an interaction by responding to an input made by a user such that the user is urged to make an additional input and by providing response content according to the input of the user, the interaction server comprising:

processing circuitry; and

a memory configured to store

a truth table that associates response content including a sentence to be provided to the user with a plurality of searching keywords, and

a relational table that includes a plurality of related keywords associated with each other;

wherein the processing circuitry

receives an input of an input keyword from the user,

automatically refers to the relational table and acquires a related keyword of a word that matches the input keyword, from the relational table,

performs searching in the truth table, and acquires response content corresponding to the related keyword, and

transmits the response content to the user,

wherein the processing circuitry acquires the input keyword on the basis of an input sentence received from the user,

wherein the processing circuitry is configured to make a determination to perform searching based on determining whether searching including any of the plurality of related keywords or searching including none of the plurality of related keywords by performing natural language analysis on the input sentence, the natural language analysis being trained via machine learning based on sentence examples of affirmative sentences and negative sentences.

2. The interaction server according to claim 1 ,

wherein the truth table further associates related contents related to the response contents,

wherein when a plurality of response contents are acquired, in a case in which related contents mapped to the plurality of acquired response contents are the same, the processing circuitry acquires response content corresponding to at least one related keyword, and

wherein the processing circuitry transmits the response content.

3. The interaction server according to claim 2 ,

wherein when a plurality of response contents are acquired, in a case in which related contents mapped to the plurality of acquired response contents are different, the processing circuitry acquires one related keyword of the plurality of related keywords, and

wherein the processing circuitry transmits the one related keyword as a return question key for urging the user to make an additional input.

4. The interaction server according to claim 1 ,

wherein when the input keyword does not coincide with any searching keyword in the truth table and coincides with a related keyword in the relational table, the processing circuitry acquires response content corresponding to a different related keyword associated with the related keyword in the relational table from the truth table.

5. The interaction server according to claim 1 ,

wherein the relational table causes one main keyword to be associated with the plurality of related keywords related to each other.

6. The interaction server according to claim 2 ,

wherein the processing circuitry acquires the input keyword on the basis of an input sentence received from the user,

wherein the processing circuitry is configured to perform searching based on determining determine whether searching including any of the plurality of related keywords is performed or searching including none of the plurality of related keywords is performed by analyzing the input sentence.

7. The interaction server according to claim 3 ,

wherein the processing circuitry acquires the input keyword on the basis of an input sentence received from the user,

wherein the processing circuitry is configured to perform searching based on determining determine whether searching including any of the plurality of related keywords is performed or searching including none of the plurality of related keywords is performed by analyzing the input sentence.

8. A method, implemented by an interaction server that holds an interaction by responding to an input made by a user such that the user is urged to make an additional input and by providing response content according to the input of the user, the method comprising:

storing, in a memory, a truth table that associates response content including a sentence to be provided to the user with a plurality of searching keywords, and

storing, in the memory, a relational table that includes a plurality of related keywords associated with each other;

performing, by processing circuitry,

receiving an input of an input keyword from the user;

automatically referring to the relational table and acquires a related keyword of a word that matches the input keyword, from the relational table

performing searching in the truth table, and acquiring response content corresponding to the related keyword; and

transmitting the response content to the user,

wherein the method further includes acquiring the input keyword on the basis of an input sentence received from the user, and

making a determination to perform searching based on determining whether searching including any of the plurality of related keywords or searching including none of the plurality of related keywords by performing natural language analysis on the input sentence, the natural language analysis being trained via machine learning based on sentence examples of affirmative sentences and negative sentences.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 28, 2020
From: FUJIMOTO, HIROSHI; HASHIMOTO, TAKANORI; OZAKI, YURIKO
To: NTT DOCOMO, INC.
Reel/Frame 053904/0929 →
Priority Claims (1)
JP 2018-071835 · Apr 3, 2018 · national
Continuity (1)
Related Publication 20210097236A1 · Apr 1, 2021