Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Man-machine interaction method and system and electronic equipment thereof

A human-computer interaction and machine translation technology, applied in digital data processing, instruments, natural language translation, etc., can solve problems such as robot work efficiency and single dialogue content that affect user experience

Pending Publication Date: 2019-07-16
ECOVACS COMML ROBOTICS CO LTD
View PDF8 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing man-machine dialogue system puts more emphasis on meeting the needs of users, and does not consider from the perspective of merchants at the same time. With the help of man-machine dialogue systems, how to satisfy merchants’ requirements for product recommendation on the basis that users do not have sufficient understanding of all product information demand, and then achieve the purpose of marketing recommendation
In addition, the existing human-computer dialogue system can achieve relatively single dialogue content. When there is a change in the user's intention, conflicts in content before and after the intention, or ambiguity in the intention, the human-computer interaction may no longer be able to continue normally, seriously affecting the user's experience. User experience and robot productivity

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
  • Man-machine interaction method and system and electronic equipment thereof
  • Man-machine interaction method and system and electronic equipment thereof
  • Man-machine interaction method and system and electronic equipment thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] Figure 4 It is a schematic diagram of a pre-customized logic tree model according to Embodiment 1 of the present invention. Such as Figure 4 As shown, for the logic tree customized according to the information provided by the merchant, only part of the information is shown but not all, and the amount of information in the customized logic tree in actual operation far exceeds Figure 4 Indicated range of , but based on Figure 4 The logical hierarchy shown is unchanged. Specifically, Figure 4 The logic tree in the first-level slot under the root node is divided into two intents, "eating" and "shopping", and the contents of these two intents are mutually exclusive; the same level also includes "price", and "price" is the above The soft node is not mutually exclusive with "dining" and "shopping". Under the node "shopping", it is divided into nodes "home appliances", "digital" and "food". The same level also includes "import", which is also a soft node. And "househ...

Embodiment 2

[0098] Figure 5 It is a schematic diagram of the search tree in Embodiment 2 of the present invention. Such as Figure 5 Shown is the normal human-computer interaction process, the main human-computer dialogue can include the following content:

[0099] Person (1) Hello!

[0100] Machine (2) Hello! Do you need to shop or eat?

[0101] Person (3) is shopping, which is more expensive.

[0102] Machine (4) What do you want to buy?

[0103] Person (5) mobile phone.

[0104] Machine (6) What brand do you want?

[0105] Person (7) Apple's mobile phone.

[0106] Machine (8) How much memory do you need?

[0107] People (9) 4G.

[0108] The output product recommendation information: Apple iphone TP is recommended for you.

[0109] It can be seen from the above that the difference between this embodiment and the first embodiment is that in the first embodiment, the user directly stated the purchase intention, but in this embodiment, the user is confirmed through a man-machin...

Embodiment 3

[0111] Figure 6 It is a schematic diagram of a search tree in Embodiment 3 of the present invention. Such as Figure 6 Shown is the human-computer interaction process in the case of intention switching. When the user's commodity demand is switched from one situation to another, the main human-computer dialogue can include the following content:

[0112] Person (1) Hello!

[0113] Machine (2) Hello! Do you need to shop or eat?

[0114] Person (3) I want to buy a mobile phone, which is expensive.

[0115] Machine (4) OK, what brand do you want?

[0116] Person (5) forget it, I'd better look at the tablet.

[0117] Machine (6) What brand do you want?

[0118] People (7) take a look at Samsung's tablet.

[0119] Machine (8) How much memory do you need?

[0120] Person (9) actually wants to buy an air conditioner.

[0121] Engine (10) How many horses do you want?

[0122] People (11) 1.5P, Midea.

[0123] Output product recommendation information: Midea 1.5P air conditio...

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 provides a man-machine interaction method and system and electronic equipment thereof. The method comprises the following steps: identifying voice input information of a user as text information, outputting intention labels from the text information through a machine translation multi-label intention classifier, dyeing the intention labels on a logic tree to form intention nodes, andfinding corresponding intention label sequences of the intention nodes under the control of the logic tree; searching a database according to the intention label sequence, and outputting commodity recommendation information; and after the man-machine interaction is finished, waiting for the next voice input of the user. According to the method, the intention label sequence under the control of the logic tree is found based on the machine translation multi-label intention classifier, user requirements are rapidly cleared, recommendation information is provided, topic switching is free, and efficient man-machine communication is achieved.

Description

technical field [0001] The invention relates to a human-computer interaction method, system and electronic equipment thereof, and belongs to the technical field of automatic response systems. Background technique [0002] In the existing technology, the human-computer dialogue in the vertical field usually needs to be completed through the following process: first, the received language is generally converted into text vectorization; then, the answer corresponding to the pre-established knowledge base or database is searched; finally, The corresponding answer is sent to the user in the form of voice, so as to realize a complete man-machine dialogue process. The existing man-machine dialogue system puts more emphasis on meeting the needs of users, and does not consider from the perspective of merchants at the same time. With the help of man-machine dialogue systems, how to satisfy merchants’ requirements for product recommendation on the basis that users do not have sufficien...

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
IPC IPC(8): G06F16/332G06F16/35G06F16/36G06F17/27G06F17/28G10L15/22G10L15/26G06F40/20
CPCG10L15/22G10L15/26G06F40/20G06F40/58G06F40/289G06F16/3329G06F16/35G06F16/367G06F16/332G06F16/36G06F40/40
Inventor 许建伟秦昌博
Owner ECOVACS COMML ROBOTICS CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com