Operation target data determination method and device, storage medium and equipment

Abstract

The invention discloses an operation target data determination method and device, a storage medium and equipment. The method comprises the steps of obtaining effective crowdsourcing trajectory data; carrying out character recognition on the picture of each first data object in the effective crowdsourcing trajectory data to obtain trajectory data to be processed, wherein each second data object inthe trajectory data to be processed comprises a recognition result, and the recognition result comprises at least one recognition target; filtering invalid identification targets in the identificationresults of the second data objects in the to-be-processed track data to obtain first track data; clustering the first trajectory data according to a recognition target to obtain an object sequence corresponding to the recognition target; obtaining reference data corresponding to each object sequence, and filtering the object sequence according to the reference data to obtain a filtering result; and determining operation target data according to a filtering result. The efficiency of the operation target data is improved.

Description

technical field [0001] This specification relates to the field of digital maps, and in particular to a method, device, storage medium and equipment for determining operation target data. Background technique [0002] Batch update is one of the most important technical means to enable the map master database to draw the physical world and its changes at any time. Specifically, according to the collected crowdsourced trajectory data, the physical world expressed in the crowdsourced trajectory data is found by manual operation. The difference points of the physical world expressed by the map mother database, and correspondingly updated in the map mother database in a timely manner. In order to ensure the accuracy of the map mother database update, batch updates are highly dependent on manual work. [0003] However, the huge amount of crowdsourced trajectory data leads to high manual labor costs. In order to reduce costs, the existing technology can rely on machine learning to ...

AI Technical Summary

Problems solved by technology

However, the recognition accuracy of machine learning is limited, so that there is still a high redundancy in the data that actually enters manual work, and the pressure of manual work has not been effectively relieved

Images