Place attribute classification method, device, electronic equipment and storage medium

Abstract

Embodiments of the invention provide a place attribute classification method, a device, electronic equipment and a storage medium. The method comprises the steps of obtaining face spatio-temporal dataand sample label data; extracting a global place and personnel flow information corresponding to the global place according to the face spatio-temporal data and the personnel flow information of thesample place; performing label propagation on the target place according to the personnel flow information corresponding to the global place and the initialized sample label matrix to obtain a first label distribution matrix; performing label propagation on the target place based on the personnel flow information corresponding to the global place and the initialized sample label matrix to obtain afirst label distribution matrix; continuously updating to obtain a label distribution matrix corresponding to the current number of iterations by combining the label distribution matrix correspondingto the last number of iterations to obtain a final label distribution matrix; and performing attribute classification on the target place according to the final label distribution matrix. According to the invention, the overall calibration effect of each place can be improved.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a place attribute classification method, device, electronic equipment and storage medium. Background technique [0002] With the continuous improvement of living standards, various complex commercial or non-commercial places have been put into use, such as Internet cafes combining Internet cafes and cafes, reading stations combining water bars, cafes and bookstores, and multi-entertainment functions. clubs and other places, and because the functions of these places are more complex, the calibration of their place attributes is more difficult, which is not conducive to the management of the department in charge, resulting in high difficulty in management. The existing site attribute calibration is mostly based on the judgment and calibration of the attributes of various sites by managers based on the collected site intelligence data and experience, and the department...

AI Technical Summary

Problems solved by technology

[0002] With the continuous improvement of living standards, various complex commercial or non-commercial places have been put into use, such as Internet cafes combining Internet cafes and cafes, reading stations combining water bars, cafes and bookstores, and multi-entertainment functions. Clubs and other places, and because the functions of these places are more complex, the calibration of their place attributes is more difficult, which is not conducive to the management of the department in charge, resulting in high difficulty in management

The existing site attribute calibration is mostly based on the judgment and calibration of the attributes of various sites by managers based on the collected site intelligence data and experience, and the departments in charge manage according to these calibrations. The changes are fast and the changes are not obvious, so that the method of manual calibration not only has low attribute calibration efficiency and high delay in response to changes, but also has miscalibration due to insufficient objectivity of intelligence data.

Therefore, the existing methods of manual calibration of site attributes have low calibration efficiency, high delay in response to changes, and high mis-calibration rate, which makes the calibration of site attributes ineffective.

Images