Multi-model fusion question answering method, system and medium for urban brain
A multi-model, brain technology, applied in special data processing applications, instruments, unstructured text data retrieval, etc., can solve problems such as non-optimization, single question answering system, etc., to achieve the effect of improving accuracy
Active Publication Date: 2022-02-15
BEIJING ZHONGHAIJIYUAN DIGITAL TECH DEV CO LTD
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] The technical problem to be solved by the present invention is that the question-answering system is single and the non-optimization caused by choosing a manually set threshold with great 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 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
[0054] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.
[0055] In the description of the present invention, it should be noted that unless otherwise specified and limited, the terms "installation", "connection" and "connection" should be understood in a broad sense, for example, it can be a fixed connection or a detachable connection. Connected, or integrally connected; it may be mechanically connected or electrically connected; it may be directly connected or indirectly connected through an intermediary, and it may be the internal communication of two components. Those of ordinary skill in the art can understand the specific meanings of the above terms in the present invention in specific situations.
[0056] In the embodimen...
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 invention discloses a multi-model fusion question answering method for urban brains, comprising: obtaining the first answer of a question input by a user according to a knowledge map database, and determining the first confidence level; matching the user input question according to the question answer database, and determining The second answer and the second degree of confidence; obtain the predicted answer of the question input by the user according to the generative pre-training; match the predicted answer according to the question-and-answer database to determine the third answer and the third degree of confidence; the first degree of confidence, the second degree of confidence degree and the third confidence degree for fusion classification to obtain the target answer. The invention also discloses a multi-model fusion question answering system and a computer storage medium for the city brain. The purpose of this multi-model fusion question answering method for urban brain is to solve the problem of non-optimization caused by the selection of artificially set thresholds with great experience in question answering methods.
Description
technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a multi-model fusion question answering method, system and medium for urban brains. Background technique [0002] At present, most of the algorithms of question answering systems in professional fields match user questions directly with questions in the question answer database. Question-to-question matching is calculated using the similarity ranking between questions. This type of model does not make effective use of the answers in the question answering database, resulting in the effective information in the answers not being considered. At the same time, due to the difficulty of controlling generative answers, the professional field question answering system does not use this model, although some question answering systems Generative models are used, but only in the domain of small talk. [0003] At present, deep semantic matching is widely used i...
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 Patents(China)
IPC IPC(8): G06F16/332G06F16/36G06F16/35
CPCG06F16/3329G06F16/367G06F16/353
Inventor 张宏志李浩浩马亚中何彬梅一多张聪聪
Owner BEIJING ZHONGHAIJIYUAN DIGITAL TECH DEV CO LTD