Artificial intelligence model training method and device, knowledge point pushing method and device and medium
An artificial intelligence and model training technology, applied in the field of knowledge push, can solve the problems of difficult users to provide knowledge points, low hit rate, etc., to reduce the possibility and improve the accuracy and hit rate.
Pending Publication Date: 2021-01-01
天讯瑞达通信技术有限公司
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in fields such as telecommunications, there are usually a large number of knowledge points with the same entity name in the inquiries made by users. Therefore, the existing technology tends to generate a large number of knowledge points that can be pushed at one time, and the hit rate is low, making it difficult to efficiently provide accurate knowledge to users. point
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
[0037] In this embodiment, a trained artificial intelligence model is used to push knowledge points. The artificial intelligence model used may be a convolutional neural network or the like.
[0038] In this embodiment, before executing the knowledge point pushing method, the artificial intelligence model training method is executed to obtain the artificial intelligence model to be used through training.
[0039] In this embodiment, an artificial intelligence model training method and a knowledge point pushing method are described by taking customer service in the telecommunications industry as an example. The customer service can be manual customer service or machine customer service. Customer service can be provided to the user by phone or text chat in a dialog box. In this embodiment, the manual customer service is sometimes referred to as an agent.
[0040] In this example, refer to figure 1 , the artificial intelligence model training method comprises the following ste...
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 an artificial intelligence model training method and device, a knowledge point pushing method and device and a medium, and the method comprises the steps: obtaining a click log, obtaining the access weight of a customer service knowledge point, crawling a knowledge point body, determining the demand weight of the knowledge point body, and obtaining content feature information and customer feature information; training an artificial intelligence model and the like. By executing the artificial intelligence model training method, proper artificial intelligence can be obtained through training, and as the basis of executing the knowledge point pushing method, the artificial intelligence model obtained through training can output customer service knowledge points according to content feature information, customer feature information and other information in customer service dialogues. The feature that a large number of knowledge points with the same entity name existin consultation proposed by users in the customer service field can be effectively responded, the possibility of generating a large number of pushable knowledge points at a time is reduced, and the accuracy and hit rate of customer service knowledge point query are improved. The invention is widely applied to the technical field of knowledge pushing.
Description
technical field [0001] The present invention relates to the technical field of knowledge push, in particular to an artificial intelligence model training method, a knowledge point push method, a device and a medium. Background technique [0002] In the fields of telecommunications, e-commerce, ticketing, and online games, customer service is usually set up to provide services to users. Whether it is human customer service or machine customer service, they usually communicate with users through voice calls or text chats. In the process of providing customer service, users may ask questions related to knowledge points. If the service is provided by machine customer service, the computer system can query the knowledge points consulted by the user and push them to the user. If the service is provided by human customer service, the customer service personnel will also The knowledge points consulted by the user can be queried with the help of the computer system and then pushed 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
Login to View More IPC IPC(8): G06F16/33G06F16/332G06F16/35G06N5/02G06Q30/06G06Q50/32
CPCG06F16/3329G06F16/3344G06F16/35G06N5/02G06Q30/0601G06Q50/60Y02D10/00
Inventor 李杰明陈伟斌匡胜贵沈泳龙
Owner 天讯瑞达通信技术有限公司