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

Method and device for judging document sentiment

A document and emotion technology, applied in unstructured text data retrieval, text database clustering/classification, instruments, etc., can solve the problem of low accuracy of emotion judgment and achieve the effect of improving the accuracy of emotion judgment

Active Publication Date: 2022-03-01
BEIJING GRIDSUM TECH CO LTD
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a method and device for judging the emotion of a document, so as to at least solve the technical problem that the emotion judging method in the prior art has low accuracy of emotion judging for documents containing multiple evaluation objects

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
  • Method and device for judging document sentiment
  • Method and device for judging document sentiment
  • Method and device for judging document sentiment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] According to an embodiment of the present invention, an embodiment of a method for judging the sentiment of a document is provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and , although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0033] figure 1 is a flow chart of a method for judging the sentiment of a document according to an embodiment of the present invention, such as figure 1 As shown, the method includes the following steps:

[0034] Step S102, performing sentence recognition on the document to obtain multiple sentences.

[0035] Specifically, the above-mentioned documents may be comment information about users’ thoughts, experiences and opinions on commodities, services, news and other fields. When users are...

Embodiment 2

[0081] According to an embodiment of the present invention, an embodiment of an apparatus for judging a document sentiment is provided, figure 2 is a schematic diagram of a device for judging the sentiment of a document according to an embodiment of the present invention, such as figure 2 As shown, the device includes:

[0082] The recognition unit 21 is configured to perform sentence recognition on the document to obtain multiple sentences.

[0083] Specifically, the above-mentioned documents may be comment information about users’ thoughts, experiences and opinions on commodities, services, news and other fields. When users are satisfied with products, services, news, etc., they will express positive emotions; when users are dissatisfied with products, services, news, etc., they will express derogatory emotions; when users are neutral about products, services, news, etc., they will express neutrality emotion.

[0084] In an optional solution, when it is necessary to ana...

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 discloses a method and a device for judging the emotion of a document. Among them, the method includes: performing sentence recognition on the document to obtain multiple sentences; extracting all evaluation objects included in the multiple sentences; Words, get the score corresponding to each evaluation object included in the sentence; get the emotion type of the document corresponding to each evaluation object based on the score of each sentence corresponding to each evaluation object included, where emotion Types include one of the following: Positive Sentiment, Neutral Sentiment, Negative Sentiment. The invention solves the technical problem that the emotion judgment method in the prior art has low accuracy of emotion judgment for documents containing multiple evaluation objects.

Description

technical field [0001] 本发明涉及自然语言处理领域,具体而言,涉及一种文档情感的判断方法和装置。 Background technique [0002] 情感判断是自然语言处理的关键任务之一,目前,无论是基于词汇还是基于语料,处理文档的情感分析方法很多,但受限于实际问题的复杂程序和文档较复杂的特征情感判断的限制,没有一个万能的算法可以在各种具体问题中都能够具有较好的情感判断准确率。而技术选型尤其是评价对象与情感的匹配过程需要大量人为主观性的参与。因此,如何能够更好的进行情感判断仍然是领域内一大难题。 [0003] 现有的情感判断方法中并不存在一个万能的算法,能够帮助解决各式各样的情感分析问题,因此,有人提出Frequent phrase+rules(常用词汇+语法)等一系列方法,旨在词汇和语料的基础上对不同评价对象且不同倾向的文档进行分析,然后再对分析结果聚合得出结论。 这种方法在很大程度上弥补了同一篇文档存在不同评价对象的不足,但是这种方法对于评价对象缺失的文档不能有效解决,从而会造成情感与语料或词汇不匹配而导致情感判断缺失的 Condition. [0004] 针对现有技术中的情感判断方法对于包含多个评价对象的文档,情感判断准确度低的问题,目前尚未提出有效的解决方案。 Contents of the invention [0005] 本发明实施例提供了一种文档情感的判断方法和装置,以至少解决现有技术中的情感判断方法对于包含多个评价对象的文档,情感判断准确度低的技术问题。 [0006] 根据本发明实施例的一个方面,提供了一种文档情感的判断方法,包括:对文档进行语句识别,得到多条语句;提取出多条语句中包括的所有评价对象;基于每条语句包括的所有评价对象以及该条语句中每个评价对象对应的情感词,得到该条语句对应于其包括的每个评价对象的分值;基于每条语句对应于其包括的每个评价对象的分值得到文档对应于每个评价对象的情感类型,其中,情感类型至少包括如下之一:正面情感、中立情感,负面情感。 [0007] 进一步地,基于每条语句包括的所有评价对象以及该条语句中每个评价对象对应的情感词,得到该条语句对应于其包括的每个评价对象的分值包括:判断每条语句是否包含至少一个评价对象;若包含,则提取该条语句中每个评价对...

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 Patents(China)
IPC IPC(8): G06F40/284G06F40/216G06F16/35
CPCG06F40/30
Inventor 赵钰
Owner BEIJING GRIDSUM TECH 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