Method and device for recognizing abrupt timeliness search term

Abstract

The invention provides a method and device for recognizing an abrupt timeliness search term. The method comprises the steps of calculating the variation tendency of the search quantity of a search item in a first period of time and the variation tendency of the search quantity of the search item in a second period of time, wherein the second period of time is part of the first period of time; comparing the variation tendency of the search quantity of the search item in the first period of time with the variation tendency of the search quantity of the search item in the second period of time to obtain the difference, and judging whether the search term is the abrupt timeliness search term according to the difference. According to the technical scheme, the variation tendency of the search quantity of the search item in the longer period of time is compared with the variation tendency of the search quantity of the search item in the shorter period of time, the abrupt increase condition of the search quantity can be obviously reflected in the difference between the variation tendencies of the search quantity even though the search quantity of the search item is kept in a small order of magnitudes, and therefore the abrupt timeliness search term can be easily recognized.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method and system for identifying query words with sudden timeliness. Background technique [0002] The sudden timeliness query is a query word whose query volume is significantly larger than before in a short period of time, so the sudden timeliness query often reflects the outbreak of a new event, causing users to pay attention to the event. It has strong timeliness. Therefore, identifying the sudden time-sensitive query words in time, and adjusting the ranking of news in the search engine according to the sudden time-sensitive query words can effectively improve the user's search experience for news and improve the quality of the search engine. [0003] The existing method for identifying sudden time-sensitive query words is based on comparing the query volume of the query word in the current time period with the query volume in the previous period. Time-sensitiv...

AI Technical Summary

Problems solved by technology

[0004] The disadvantage of the above technical solution is that if the query volume of the query words is maintained at a small level in the two periods of time, it may cause a sudden increase in the query volume of the query words but the difference is small, and the difference is too small Then cause the unexpected timeliness query word to be unrecognized, for example:

[0005] 1. Changes in the query volume of some query words with a large query volume will cover up sudden time-sensitive query words. For example, if the query volume of query word A changes from 10,000 to 11,000, the difference is 1,000, while sudden time-sensitive query words The number of queries changed from 100 to 200. Although the query volume has doubled, the difference is only 100. Compared with the difference of query word A, it is small, and it cannot reflect the sudden increase in query volume, making it difficult to identify the sudden timeliness query term

[0006] 2. Generally, the time period for statistical query volume is set relatively small (for example, set by hour). Since the query volume of query words is greatly affected by time, the overall query volume in the early morning period is small, and the query volume in the early morning is compared to get The difference is also small, so it is difficult to identify sudden time-sensitive query words; if in order to overcome this problem, the time period is set relatively large (for example, set by day), the time interval for comparing query volumes in different time periods is If it takes a long time, the sudden time-sensitive query words will be updated slowly

Images