Method for dynamically updating knowledge graph based on user log
A knowledge map and dynamic update technology, applied in the field of knowledge map, can solve the problems of large amount of data and frequent updates, and achieve the effect of taking into account real needs and reducing the amount of data
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0037] combined with figure 1 As shown, a method for dynamically updating knowledge graphs based on user logs, including:
[0038] Step A: Collection of user logs: Obtain the user's request log data in this update cycle from the smart TV semantic log;
[0039] Step B: Extract the entity name and entity type from the user's request statement based on the named entity recognition model. You can use the Bi-LSTM+CRF model (Bi-LSTM: Bi-directional Long Short-Term Memory, bidirectional long-term short-term memory network; CRF :Conditional Random Field, conditional random field) to mark the named entity; traverse the user's request log, and count the visits according to the request category and entity category, and record it as entity set E1,
[0040] E1={(e 1 ,t 1 ,n 11 ),(e 1 ,t 2 ,n 12 ),(e 2 ,t 3 ,n 23 ),..., (e i ,t j ,n ij ),..., (e n ,t m ,n nm )}, where the triplet (e i ,t j ,n ij ) indicates that the entity name is e i and the entity class is t j The num...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
