IP Library Granted Patent US 12,597,424
Granted Patent B2
US 12,597,424 · App. 17/912,112 · Granted Apr 7, 2026

Method and apparatus for determining skill field of dialogue text

Inventors: Chengya Zhu (Suzhou, CN); Shuai Fan (Suzhou, CN); Chun Li (Suzhou, CN); Weisi Shi (Suzhou, CN)
Assignee: AI SPEECH CO., LTD.
G10L15/22G10L15/1815
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 12,597,424
App. No.
17/912,112
Filed
Sep 16, 2022
Granted
Apr 7, 2026
Kind
B2
Art Unit
2653
USPC
704/231
Abstract

Disclosed is a method for determining a skill field of a dialogue text including determining a skill field hit by a dialogue text input by a user, and a name semantic slot and a character semantic slot in the skill field; when the dialogue text hits a first skill field, determining whether the name semantic slot and the character semantic slot match according to a knowledge base of the first skill field; determining, if not matched, whether the name semantic slot and the character semantic slot match according to a knowledge base of a second skill field; and determining, if matched, the second skill field as the skill field of the dialogue text. Also provided is an apparatus for determining a skill field of a dialogue text. The error rate of field classification is reduced, and the skill field can be hit by the user's voice dialogue more accurately.

Claims (12)

1 . A method for determining a skill field of a dialogue text, applied to an electronic device, the method comprising:

scheduling, by the electronic device, a task-based skill semantic service and a knowledge-based skill service in parallel to determine a skill field hit by a dialogue text input by a user, a name semantic slot and a character semantic slot in the skill field, wherein the skill field comprises a first skill field and a second skill field, and the first skill field and the second skill field have the same parsing confidence, wherein, when the electronic device is a TV, the first skill field is a film and television field, the second skill field is a music field, and when the electronic device is a smartphone, the first skill field is the music field, the second skill field is the film and television field;

determining, by the electronic device, whether the name semantic slot and the character semantic slot corresponding to the first skill field match according to a knowledge base of the first skill field;

further determining, by the electronic device, whether the name semantic slot and the character semantic slot corresponding to the second skill field match according to a knowledge base of a second skill field, if the name semantic slot and the character semantic slot corresponding to the first skill field do not match in the knowledge base of the first skill field; and

determining, by the electronic device, the second skill field as the skill field of the dialogue text, if the name semantic slot and the character semantic slot corresponding to the second skill field match in the knowledge base of the second skill field, and responding to the user using a skill of the determined skill field of the dialogue text,

the method further comprising:

establishing in advance a knowledge base in the film and television field and a knowledge base in the music field, wherein the knowledge base in the film and television field stores information of correlation between film and television titles and filmmakers, and the knowledge base in the music field stores information of correlation between music names and singer names.

2 . The method according to claim 1 , wherein if the name semantic slot and the character semantic slot corresponding to the first skill field match in the knowledge base of the first skill field, the first skill field is determined as the skill field of the dialogue text.

3 . The method according to claim 1 , wherein after determining the second skill field as the skill field of the dialogue text, the method further comprises:

preferentially determining the second skill field as the skill field of the dialogue text when the user inputs the dialogue text again.

4 . An electronic device comprising at least one processor, and a memory communicatively coupled to at least one processor, wherein the memory stores instructions readable and executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the method of claim 1 .

5 . A non-transitory computer-readable storage medium having stored therein a computer program, wherein the computer program, when executed by a processor, implements the steps of the method of claim 1 .

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 16, 2022
From: ZHU, CHENGYA; FAN, SHUAI; LI, CHUN; SHI, WEISI
To: AI SPEECH CO., LTD.
Reel/Frame 061116/0523 →
Priority Claims (1)
CN 202010193878.7 · Mar 18, 2020 · national
Continuity (1)
Related Publication 20230133146A1 · May 4, 2023
References Cited (21)
US 7143353B2 · McGee · 2006 [cited by examiner]
US 8234284B2 · Shao · 2012 [cited by examiner]
US 9466295B2 · Zhang · 2016 [cited by applicant]
US 10276170B2 · Gruber · 2019 [cited by examiner]
US 10453117B1 · Reavely · 2019 [cited by examiner]
US 20190147052A1 · Lu · 2019 [cited by examiner]
CN 108920497A · 2018 [cited by applicant]
CN 109783735A · 2019 [cited by examiner]
CN 109918673A · 2019 [cited by examiner]
CN 110008314A · 2019 [cited by applicant]
CN 110543633A · 2019 [cited by applicant]
CN 110808051A · 2020 [cited by applicant]
CN 111061908A · 2020 [cited by examiner]
CN 111414764A · 2020 [cited by applicant]
JP 2017224155A · 2017 [cited by applicant]
C. Xiao, D. Zheng, Y. Yang and G. Shao, “Automatic Domain-Ontology Relation Extraction from Semi-structured Texts,” 2009 International Conference on Asian Language Processing, Singapore, 2009, pp. 211-216 (Year: 2009). [cited by examiner]
International Search Report (English and Chinese) and Written Opinion of the International Searching Authority (Chinese) issued in PCT/CN2020/129342, mailed Feb. 19, 2021; ISA/CN. [cited by applicant]
First Notice of Reasons for Refusal of corresponding JP Application No. 2022-555166 with English translation. [cited by applicant]
Second Notice of Reasons for Refusal of corresponding JP Application No. 2022-555166 with English translation. [cited by applicant]
Communication Pursuant to Article 94(3) EPC issued by the EPO on Jul. 11, 2024 in corresponding EP Application No. 20925821.9-1203. [cited by applicant]
Extended European Search Report issued by the EPO on Jul. 12, 2023 in corresponding EP Application No. 20925821.9-1203. [cited by applicant]