Unknown intent identification method, device, device and storage medium
A recognition method and intention technology, applied in the field of artificial intelligence, can solve the problem of low accuracy of unknown intentions, and achieve the effect of improving the recognition accuracy.
Active Publication Date: 2022-06-03
北京钱袋宝支付技术有限公司 +1
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, such methods have a great possibility of identifying noise samples as unknown intentions, resulting in a low accuracy rate for determining unknown intentions.
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
[0026] In order to make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.
[0027] First of all, some terms involved in this application are introduced:
[0028] Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines,...
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 application discloses an unknown intent recognition method, device, equipment and storage medium, belonging to the technical field of artificial intelligence. The method includes: calling the intention recognition model to obtain the intention unknown sample when the intention recognition of the sample to be identified fails; performing anomaly detection on the semantic representation vector of the intention unknown sample to obtain the local outlier factor density of the sample; in response to the density being greater than the density threshold, determining There are unknown intentions in the samples with unknown intentions, and the samples with unknown intentions are used to retrain the intention recognition model after manually labeling new intentions. This method reconfirms samples with unknown intentions through abnormal detection of local outlier factors, and screens out samples with real unknown intentions, so as to expand the intention recognition type of the intention recognition model; especially for intelligent customer service scenarios, it can meet its new requirements. User intentions emerge in an endless stream, and it is necessary to continuously mine new user intentions and increase the demand for the types of user intentions that intelligent customer service robots can identify.
Description
technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, to a method, apparatus, device and storage medium for identifying unknown intentions. Background technique [0002] With the development of deep learning, classic learning tasks such as image classification and intent recognition have achieved breakthrough progress in performance and accuracy. [0003] As one of the most basic supervised learning tasks in deep learning, classification task often relies on a large amount of training data. Firstly, the training data set is manually labeled, that is, the data set is labeled according to the given intention, and the intention of each training sample is marked. However, in the initial stage of the intent recognition model, it is difficult to provide a relatively comprehensive set of intent-labeled samples, which inevitably leads to some intent labels being ignored. Therefore, an unknown intent discovery m...
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): G06F16/332G06F16/33G06F16/35G06N3/04G06N3/08
CPCG06F16/3329G06F16/3344G06F16/35G06N3/084G06N3/045
Inventor 包梦蛟
Owner 北京钱袋宝支付技术有限公司