Movie and television entity identification method based on IDCNN-crf and knowledge graph

A technology of entity recognition and knowledge graph, which is applied in the field of film and television entity recognition based on IDCNN-crf and knowledge graph, can solve the problems of recognition impact, non-standard Mandarin of users, and inconsistent entity naming methods, so as to improve accuracy and increase user The effect of experience

Inactive Publication Date: 2020-02-18
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Moreover, compared with other fields, the film and television field involves complex types of entities, and the types of entities involved are also very different. "Sweeping Drugs" and the movie "Sweeping Drugs" seem to be the same entity but belong to different entity types, and the naming methods of entities cannot be unified. The user's Mandarin is not standard, the flat tongue is indistinguishable, and the same entity is expressed in different ways, etc., all of which have a great impact on the named entity recognition after speech recognition

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
  • Movie and television entity identification method based on IDCNN-crf and knowledge graph
  • Movie and television entity identification method based on IDCNN-crf and knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Many existing entity recognition methods are based on biLSTM. biLSTM is essentially a sequence model, but it is not as powerful as CNN in the use of GPU parallel computing, and when applied to online systems, as the number of users increases, the model The training and prediction time requirements are relatively high, and the performance and processing time of the model are particularly important under high concurrency. This embodiment provides a method for video and television entity recognition based on IDCNN-crf and knowledge graphs. The IDCNN-crf model is trained And the prediction time is better than bilstm+crf, which can solve the entity recognition problem of video text data with less labeled data, short text and colloquial language.

[0039] Specifically, such as figure 1 Shown, the film and television entity recognition method based on IDCNN-crf and knowledge map of the present embodiment comprises the following steps:

[0040] Step 1. Collect film and ...

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 movie and television entity identification method based on IDCNN-crf and a knowledge graph. The method comprises the following steps: A, collecting movie and television datainformation; B, collecting a large amount of user search film and television data converted into texts through voice, and performing data analysis to obtain training data for model training; C, training the entity recognition model; D, collecting prediction data needing to be predicted, and inputting the prediction data into the entity identification model for prediction after data preprocessing;and E, carrying out verification processing on the model prediction result and outputting the result. The method provided by the invention can solve the entity identification problems of few annotation data, short text and spoken movie and television text data.

Description

technical field [0001] The present invention relates to the technical field of deep learning natural language processing, in particular to a video and television entity recognition method based on IDCNN-crf and knowledge graph. Background technique [0002] Smart TV has entered into rapid development, and the video field has also accumulated a large amount of unstructured user data such as movies and actors. The original semantic recognition system is to perform simple data processing on the text after speech recognition, and then go to the media database for fuzzy search. Due to the large amount of data in the media database, the search is time-consuming and the accuracy is not high, and some noise data may also be recognized It is output as a movie title, and it cannot meet the needs of users for multiple rounds of requests, and the user experience is very poor. The recognition of the semantics of the text after speech recognition, that is, naming recognition, is one of t...

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): G06F40/289G06F40/295G06F40/30G06F16/35G06F16/36G06K9/62G06N3/04G06N3/08
CPCG06F16/35G06F16/367G06N3/08G06N3/045G06F18/23213
Inventor 孙云云刘楚雄唐军
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
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