Personalized recommendation method based on automobile domain label
A recommendation method and labeling technology, which is applied in the direction of instruments, calculations, electrical digital data processing, etc., can solve the problems that personnel in the automotive field cannot obtain professional knowledge in a timely manner, professional knowledge is complicated, and label information cannot be effectively and reasonably applied. The effect of the cold start problem
Pending Publication Date: 2022-07-01
同方知网数字出版技术股份有限公司 +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The traditional label-based recommendation algorithm only judges whether the user has selected the item, but does not pay attention to the user's research on behavior information, resulting in the ineffective and reasonable application of label information.
[0003] At present, there are few studies on personalized recommendation methods based on tags in the automotive field, and in actual production practice, due to the complexity of professional knowledge, personnel in the automotive field cannot obtain the required professional knowledge in a timely manner. Therefore, this paper proposes an application A method for personalized recommendation based on tags in the automotive field
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
[0019] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail below with reference to the embodiments and accompanying drawings.
[0020] like figure 1 As shown, it is the process of personalized recommendation method based on automotive domain labels, including the following steps:
[0021] Step 10 According to the business, formulate five dimensions of knowledge classification, department, task, parts and molding in the automotive field, and use the information of the five dimensions as labels to establish a set of automotive field labels.
[0022] Step 20 The user can customize the selection label as the user's custom label; at the same time, the behavior information of the user in the recent period of time (according to the behavior of the user in the current system) can be obtained from the database, according to the user's click, download, and collection of knowledge....
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 personalized recommendation method based on automobile field labels, which comprises the following steps of: establishing a relationship between a user and knowledge through the labels, namely obtaining user behavior information from a database, filtering according to time, selecting the user behavior information in a recent period of time, and performing data processing on the user behavior information; removing the abnormal behavior information; counting behaviors of browsing, downloading, collecting and the like of the knowledge by the user in combination with time decay to obtain a statistical score of the knowledge by the user; then, according to the behavior statistical score of the user on the knowledge, adding a behavior tag for the user; and in combination with self-defined tags independently selected by the user and behavior tags obtained according to user behaviors, recommending related knowledge under the tags to the user, sorting the knowledge according to time and statistical scores, and selecting a plurality of pieces of data for recommendation.
Description
technical field [0001] The invention relates to the technical field of personalized recommendation, in particular to a personalized recommendation method based on tags in the automotive field. Background technique [0002] With the advancement of science and technology, the related requirements in the field of recommendation systems are becoming more and more complex, the tasks to be completed are also more difficult, and the effects to be satisfied are also increasing day by day. Among them, the recommendation method based on the automotive field label is one of the representatives. The automotive field tag is an abstract representation of the dimensions of professional terms such as processing technology, part model, model name, task type, department type, etc. in automotive design and manufacturing. It contains a collection of proper nouns in the field of automotive design and production, as well as pilot processing. The traditional tag-based recommendation algorithm onl...
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): G06F16/9535G06F16/9536G06F16/9537
CPCG06F16/9535G06F16/9536G06F16/9537
Inventor 滕康段飞虎印东敏吕强马宇柔乐斌顾君张宏伟
Owner 同方知网数字出版技术股份有限公司