Question and answer matching method, training method of text matching model and related equipment
A matching model and matching method technology, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve problems such as inability to accurately understand the semantic relevance of sentences, low answer accuracy, and low sentence similarity.
Active Publication Date: 2021-09-03
MASHANG CONSUMER FINANCE CO LTD
View PDF10 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004]
However, since the same question may have many different text expressions, and the calculation of sentence similarity based on word embedding cannot accurately understand the semantic relevance between sentences, it may cause two sentences with the same semantics to differ due to different expressions. The word vectors corresponding to the text are completely different, which leads to a very low sentence similarity between the two sentences, and finally leads to a low accuracy rate of answers matched to user questions
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0043] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments It is only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.
[0044] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of this application and the above drawings are used to distinguish similar objects and not necessarily Describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circ...
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
Login to View More Abstract
The embodiment of the invention provides a question and answer matching method, a text matching model training method and related equipment, and the method comprises the steps: determining N candidate questions matched with a to-be-answered question in a question and answer knowledge base, N being an integer greater than 1; inputting the N sets of data into a text matching model, outputting N semantic similarities, wherein each set of data comprises the question to be answered and one candidate question, and the semantic similarities are used for representing the semantic similarities between the question to be answered and the candidate questions; according to the N semantic similarities, determining a target question in the N candidate questions, wherein the proximity of the target question and the question to be answered is larger than or equal to a first threshold value; and determining an answer to the to-be-answered question according to the target question. By adopting the method provided by the embodiment of the invention, the answer accuracy of the to-be-answered question can be improved.
Description
technical field [0001] The embodiments of the present application relate to the technical field of natural language processing, and in particular to a question-answer matching method, a text matching model training method, and related equipment. Background technique [0002] With the rapid development of computer science and artificial intelligence technology, more and more artificial intelligence products are applied to daily life to provide people with various convenient services. Among them, the intelligent question answering system based on Frequently Asked Questions (FAQ) is a typical application product, and it is widely used in real life. For example, it can be applied to various fields such as intelligent customer service and web search. When users ask customer service or use search engines to search for questions, the intelligent question answering system can find answers that match the user's questions in a large number of resources. [0003] In related technologi...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06F16/3329G06F40/30G06N3/08G06N3/045G06F18/22G06F18/2415
Inventor 罗通吴海英蒋宁王洪斌
Owner MASHANG CONSUMER FINANCE CO LTD