Natural expression processing method, processing and response method, device, and system

• US 9,760,565 B2
• Filed: 06/16/2014
• Issued: 09/12/2017
• Est. Priority Date: 10/28/2013
• Status: Expired due to Fees

• Current Assignee: Icontek Corporation
• Original Assignee: Zili Yu
• Inventors: Yu, Zili
• Primary Examiner(s): Chawan, Vijay B
• Application Number:
  US15/032,603
• Publication Number:
  US 20160275075A1
• Time in Patent Office: 1,184 Days
• Field of Search: 704 9, 704 2, 704 4, 704 7, 704 10, 704231, 704251, 704254, 704257, 704270, 704275, 704 3
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/42 Data-driven translation
• CPC Class Codes: G06F 40/47 Machine-assisted translation, e.g. using translation memory
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/008 based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/24 the user being prompted to utter a password or a predefined phrase

Abstract

The present invention discloses a natural expression processing method, which includes: identifying a natural expression from a user, to obtain a certain form of language information which can be processed by a computer; and converting the obtained language information to a standard expression in an encoded form. In the natural expression processing method according to the embodiments of the present invention, the natural expression may be converted into an encoded standard expression; because the conversion to the standard expression is converting the semantics of the natural expression into codes and parameters, and precise verbatim translation is not required, the requirement of accuracy for machine translation can be reduced, and meanwhile the complexity of the database for expression conversion (machine translation) is reduced, increasing data query and updating speed, and thus improving the performance of intelligent processing. In addition, the relatively simple encoded expression reduces the workload of manually-assisted interventions, increasing the efficiency of the work of manually-assisted interventions.

Claims

1. A computing system comprising:

a dialogue gateway, a central controller, a manual aided understanding (MAU) workstation, a robot, an expression database, a response database, and a response generator, wherein,

wherein the dialogue gateway is configured to receive a natural expression, to transmit the natural expression to the central controller for subsequent processing, and to transmit a response to the natural expression;

wherein the central controller is configured to receives the natural expression from the dialogue gateway, to cooperate with the robot and the MAU workstation to convert the natural expression to a standard expression, and instruct the response generator according to the standard expression to generate a standard response corresponding to the standard expression;

wherein the robot is configured to convert the natural expression input to language information that can be processed by a computer, and to convert the language information to the standard expression using the expression database;

wherein the MAU workstation is configured to present the natural expression via a manual-agent interface, to receive the standard expression in input data received via manual-agent interface, and to transmit the standard expression to the central controller;

wherein the expression database is configured to store expression-related data, which includes;

language information data associated with the natural expression, standard expression data associated with the standard expression, and data associated with a relationship between the language information and the standard expression;

wherein the response database stores response-related data, including standard response data for invocation, data for generating the response, or both; and

wherein the response generator is configured to receives instructions of the central controller, and to generate the response for the natural expression using the data in the response database.

2. The computing system of claim 1, wherein, the central controller is further configured to update the expression database, the response database, or both.

3. The computing system of claim 1, further including a trainer configured to train the robot to convert the natural expression into the standard expression.

4. The computing system of claim 1, wherein, the dialogue gateway further comprises an identity authenticator, configured to identify and verify an identity before receiving the natural expression, wherein authentication methods for the identity at least include pass-phrase and voice-print identification.

6. The computing system of claim 2, wherein, the system further includes a trainer configured to train the robot to convert the natural expression input into the standard expression.

5. A computing system, comprising:

an intelligent response device comprising a dialogue gateway, a central controller, a manual aided understanding (MAU) workstation, a robot, an expression database, a response database, and a response generator,

wherein the dialogue gateway is configured to receive a natural expression input obtained via an interface of a client device and comprising a first form of language information, and to transmit the natural expression input to the central controller;

wherein the central controller is configured to instruct the robot to identify the natural expression by conversion of the natural language to a second form of language information that can be processed by a computer, to instruct the robot to convert the identified natural expression in the second form of language to a standard expression;

wherein the central controller is further configured to;

determine whether an understanding of the robot is sufficiently mature based at least in part on an accuracy rate of the understanding of the robot over a certain time interval;

when it is determined that the understanding of the robot is sufficiently mature, instruct the robot to perform machine conversion to determine the standard expression;

when it is determined that the understanding of the robot is not sufficiently mature to complete the conversion to a standard expression, coordinate with the MAU workstation to perform a manual conversion of the identified natural expression to a standard expression; and

based on the standard expression, instruct the response generator to generate a response to the natural expression input; and

wherein the dialogue gateway is configured to feed back the generated response to a calling device associated with the natural expression input.