NLP-based listed company financial fast message automatic generation method and system

An automatic generation and financial technology, applied in neural learning methods, biological neural network models, natural language data processing, etc., can solve problems such as poor diversity, high quality requirements, and difficulty in training sets, achieving simple maintenance and use, The effect of rich text styles and increasing diversity

Pending Publication Date: 2021-06-15
JIANGSU SECURITIES
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Defects in the method based on rule templates: the generated text style is too single and rigid, and the diversity is poor; the maintenance and expansion of rule templates require high labor costs and domain knowledge
Defects in the end-to-end text generation method based on deep neural networks: training an available neural network requires a certain amount of training corpus, but in actual business scenarios, it is difficult to build a training set with sufficient data; The generation of financial numbers and terminology requires high quality. Directly using seq2seq for text generation is prone to produce wrong digital descriptions, which often have a great impact

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
  • NLP-based listed company financial fast message automatic generation method and system
  • NLP-based listed company financial fast message automatic generation method and system
  • NLP-based listed company financial fast message automatic generation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] The problem of automatic generation of financial newsletters is to automatically identify elements such as financial indicator descriptions, transactional financial and operating indicators, etc. from the periodic reports of listed companies, and generate a streamlined and concise financial newsletter based on these elements. Suppose a PDF document D is given, the set of financial indicators A={a 1 , a 2 ,...,a m}. The model needs to convert the document into structured data S D ={T text ,T table}, where T text stands for text data, T table Represents tabular data. Next, the model needs to extract the key indicator information R according to the set of financial indicators index and key text information R text . Finally, the model is based on the extracted key information R index and R text Generate the final financial alert text Y.

[0033] like Figure 1-7 As shown, this embodiment provides a method for automatically generating financial alerts, includin...

Embodiment 2

[0088] Based on the method for automatically generating financial newsletters described in Embodiment 1, this embodiment provides a system for automatically generating financial newsletter, including: an announcement file analysis module, which is used to structure the announcement file to obtain text analysis information; an information extraction module , which is used to extract financial data and text data from text analysis information to obtain key financial information; the text generation module is used to input key financial information into the trained improved seq2seq model to generate financial alerts.

Embodiment 3

[0090] Based on the method for automatically generating financial alerts described in Embodiment 1 and the system for automatically generating financial alerts described in Embodiment 2, this embodiment provides a computer-readable storage medium, the computer-readable storage medium includes stored computer programs, Wherein, when the computer program is run by the processor, the device where the storage medium is located is controlled to execute the method for automatically generating financial alerts in Embodiment 1.

[0091] Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more compute...

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 an NLP-based listed company financial fast message automatic generation method and system in the technical field of natural language processing, and the method comprises the steps: carrying out the structural processing of an announcement file, and obtaining text analysis information; extracting financial data and text data from the text analysis information to obtain key financial information; and inputting the key financial information into the trained improved seq2seq model to generate a financial message. The method has the characteristics that the generated financial message text is rich in style, simple to maintain and use, good in text matching effect and the like.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to a method and system for automatically generating financial alerts of listed companies based on NLP. Background technique [0002] Through research, we found that financial news reports usually include basic elements such as the description of basic financial indicators, the description of the main business, and the abnormal financial and operating indicators and their reasons. These basic financial elements can be automatically parsed from the announcement documents of listed companies by using natural language processing technology. On the other hand, most of these financial news reports are objective statements, and generally do not involve complex in-depth viewpoint analysis. [0003] There are two main methods for automatic generation of financial alerts, one is based on rule templates; the other is end-to-end text generation based on deep neu...

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): G06F16/34G06F16/35G06F40/186G06F40/205G06F40/289G06N3/04G06N3/08
CPCG06F16/345G06F16/35G06F40/205G06F40/186G06F40/289G06N3/08G06N3/045
Inventor 邱震宇王玲孔亚洲朱德伟张弛
Owner JIANGSU SECURITIES
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