System and method for measuring semantic relevance of keywords

摘要

The server can receive the seed keyword and generate additional keywords associated with the seed keyword. The server can identify keyword categories using the semantic relationship graph. Each keyword can have a semantic distance from the seed keyword that is less than the threshold. The server can generate a keyword seed affinity score for each keyword in the keyword category based on the frequency of keywords that appear with the seed keyword on the information resource. The server can determine a category seed affinity score for each keyword category based on the keyword seed affinity score for each of the keywords in the keyword category. The server can compare each category seed affinity score to a threshold. The server can transmit keywords for display. Based on the comparison result, one keyword category may be shown as a selected state, and the other keyword category may be shown as a non-selected state.