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

Information processing method and electronic device

An information processing method and technology of electronic equipment, applied in the field of information, can solve problems such as difficulty in user understanding, inconsistency with user understanding, and poor user experience, so as to reduce misunderstandings, improve user experience and equipment performance, reduce Understanding the effect of difficulty

Active Publication Date: 2018-09-07
LENOVO (BEIJING) CO LTD
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing intelligent question answering systems generally focus on the accuracy of question answers, but sometimes the answer text or answer voice provided by the intelligent question answering system is not provided in the way of natural speech, for example, the answer text is composed of several isolated words or words , on the one hand, it does not conform to the user's understanding, which makes it difficult for the user to understand; on the other hand, even if the user understands it, it will lead to poor user experience

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
  • Information processing method and electronic device
  • Information processing method and electronic device
  • Information processing method and electronic device

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0137] Such as Figure 4 As shown, this example proposes a method and device for text generation based on SPO constrained self-encoding neural network, which mainly includes the following steps:

[0138] Step 1: Training Corpus Preparation

[0139] Step 1.1: Collect text corpus, the text corpus can be the aforementioned sample sentences, and the corresponding text corpus can be collected according to application scenarios. For example, for scenarios in the pharmaceutical industry, relevant question-and-answer texts can be crawled on some medical question-and-answer websites as text corpus. The text collected in this example is expected to consist of one or more natural sentences satisfying grammatical rules.

[0140] Step 1.2: Preprocessing the text corpus, the preprocessing of the text corpus may include:

[0141] Split the text corpus into individual natural sentences;

[0142] Preprocessing natural sentences mainly includes: performing word segmentation operations on na...

example 2

[0150] Based on example 1, this example provides a training corpus preparation for further detailed description, which may include:

[0151] In step 1.2, the natural sentence is preprocessed, such as Figure 5 shown, may include:

[0152] corpus collection;

[0153] Sentence splitting, splitting large sections of corpus into natural sentences;

[0154] participle of natural sentences,

[0155] Encoding of words, for example, using one-hot encoding, converting the vector formed by one-hot encoding into a word vector corresponding to the aforementioned first vector through vector conversion;

[0156] Extraction of SPO.

[0157] The word segmentation of the natural sentence may include:

[0158] Segment each natural sentence through statistical learning or dictionary matching and other word segmentation algorithms to obtain the word sequence corresponding to each natural sentence, and then deduplicate and summarize the words in all word sequences to obtain the word corpus se...

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

Embodiments of the invention disclose an information processing method and an electronic device. The method comprises the steps of obtaining a first text; based on the first text, determining a firstkeyword; and inputting a first keyword vector corresponding to the first keyword to a conversion model, thereby generating a second text based on the first keyword vector, wherein the second text comprises the first keyword and words except the first keyword.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to an information processing method and electronic equipment. Background technique [0002] Along with the development of technology, intelligent question answering system has already been arranged in the prior art. The intelligent question answering system can obtain a question through voice or text reception; based on the question, the intelligent system can provide an answer to the question through operations such as search. Existing intelligent question answering systems generally focus on the accuracy of question answers, but sometimes the answer text or answer voice provided by the intelligent question answering system is not provided in the way of natural speech, for example, the answer text is composed of several isolated words or words , On the one hand, it does not conform to the user's understanding, resulting in difficulties for users to understand; on 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): G06F17/30G06F17/27
CPCG06F40/289
Inventor 杨帆匡启帆金宝宝张成松
Owner LENOVO (BEIJING) 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