Self-adaptive single-round dialogue and task type multi-round dialogue decision-making method

A decision-making method and self-adaptive technology, applied in data processing applications, natural language data processing, special data processing applications, etc., can solve problems such as switching topics, unable to form dialogue information, etc., and achieve the effect of ensuring fluency

Pending Publication Date: 2022-05-10
元保数科(北京)科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the dialogue process, artificial intelligence is also introduced. In many cases, some travel methods or commodity purchase processes use different forms of dialogue to complete the acquisition of user demand information, thereby improving work efficiency. However, there are various forms of dialogue , in the same communication process, multiple dialogue forms may be combined. If there is no decision-making method, the information obtained through communication cannot form a complete dialogue information;
[0005] In addition, the current automatic dialogue can only solve one task topic at a time, and open another after completing one task; it is impossible to switch topics during the dialogue; when users want to solve multiple forms of tasks, they can only wait for this dialogue to be resolved or timeout After that, the topic is reopened, and there are a lot of repeated dialogues and operations. In view of this, a decision-making method for adaptive single-round dialogue and task-based multi-round dialogue is proposed.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Self-adaptive single-round dialogue and task type multi-round dialogue decision-making method
  • Self-adaptive single-round dialogue and task type multi-round dialogue decision-making method
  • Self-adaptive single-round dialogue and task type multi-round dialogue decision-making method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] see figure 1 As shown, the purpose of this embodiment is to provide a decision-making method for adaptive single-round dialogue and task-type multi-round dialogue, including the following method steps:

[0042] First, dialogue is carried out in the user communication unit; then the dialogue state memory unit memorizes the dialogue form, slot information and dialogue state in the user communication unit, forms memory data, and outputs to the dialogue input unit; then the dialogue input unit communicates to the user The dialogue form different from the output memory form of the dialogue state memory unit is input in the unit, and the corresponding memory data is input at the same time.

[0043] Wherein, the dialogue form specifically includes a single-round dialogue form and a task-based dialogue form.

[0044] Assume that at this time, the user communicates with the human-computer through a single-round dialogue. At this time, the dialogue state memory unit memorizes th...

Embodiment 2

[0047] This embodiment specifically discloses the single-round dialog form, please refer to figure 2 As shown, the single-round dialogue form includes the following method steps:

[0048] First, identify the user's dialogue intention, and then match the corresponding slot information template according to the user's dialogue intention; after the information template is obtained, the user communication unit obtains the slot value through the dialogue with the user, and then fills the slot value acquired by the user dialogue into the corresponding slot, get a complete dialogue message.

[0049] This embodiment uses an example to illustrate the dialogue scene of buying insurance:

[0050] First, the user communication unit sends "I want to buy insurance", and then matches the slot information template: "age-insurance type-whether there is social security";

[0051] Continue to send out through the user communication unit: "What is your age, do you have social insurance, and wh...

Embodiment 3

[0057] This embodiment specifically discloses the task-based dialog form, please refer to image 3 As shown, the task-based dialogue form includes the following method steps:

[0058] First, identify the user's dialogue intention, and generate a finite state tree corresponding to the intention according to the user's dialogue intention, then the user communication unit conducts a dialogue according to the finite state tree, and determines the dialogue state node according to the finite state tree during the dialogue, and then matches the dialogue state node Reply message to get a complete dialog message.

[0059] The same example is given by buying insurance. The specific principles are as follows:

[0060] First obtain the dialogue intent, for example: the user asks "Can I buy A insurance if I have high blood pressure?", first obtains the intent "health notification when purchasing consultation", the first step is to determine the following diseases or symptoms: high blood pre...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the technical field of automatic dialogues, in particular to a decision-making method for adaptive single-round dialogues and task-type multi-round dialogues. The method comprises the following steps: carrying out conversation in a user communication unit; the dialogue state memory unit memorizes the dialogue form, the slot position information and the dialogue state in the user communication unit to form memory data, and outputs the memory data to the dialogue typing unit; and the dialogue input unit inputs a dialogue form different from the output memory form of the dialogue state memory unit into the user communication unit. According to the invention, the current dialogue form is memorized through the dialogue state memory unit, so that different dialogue forms can be typed in conveniently, the switching of a plurality of different dialogue forms in the dialogue process is ensured, and the fluency of the whole dialogue is ensured.

Description

technical field [0001] The invention relates to the technical field of automatic dialog, in particular to a decision-making method for an adaptive single-round dialog and a task-type multi-round dialog. Background technique [0002] With the improvement of intelligent technology, more and more artificial intelligence has replaced the way people work; [0003] Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems, etc. [0004] In the dialogue process, artificial intelligence is also introduced. In many cases, some travel methods or commodity purchase processes use different forms of dialogue to complete the acquisition of user demand information, thereby improving work efficiency. However, the...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G06F16/33G06F40/279G06Q40/08
CPCG06F16/3329G06F16/3344G06F40/279G06Q40/08
Inventor 马坤刘广通金雯王波
Owner 元保数科(北京)科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap