Information processing method, information processing device, and recording medium

Abstract

An information processing method according to an aspect of the present disclosure includes: acquiring, from a video, flow line information of a customer; detecting that the customer acquires an item; and storing, in a storage, flow line information of the customer and information on a number of items acquired by the customer, in association with each other.

1 . An information processing method, comprising:
 acquiring, from a video, a plurality of time-series positions of at least one customer;   detecting a number of items taken by each of the at least one customer at each of the plurality of time-series positions;   identifying the plurality of time-series positions associated with one of the at least one customer paying for items; and   detecting a discordance between a number of items associated with the identified plurality of time-series positions and a number of items paid for by the customer at a register as an anomaly.   
     
     
         2 . The information processing method according to  claim 1 , further comprising:
 notifying, based on a detection of the discordance, that an anomaly is detected.   
     
     
         3 . The information processing method according to  claim 2 ,
 wherein the notifying is executed in a case where a difference between the number of items exceeds a threshold value.   
     
     
         4 . The information processing method according to  claim 2 ,
 wherein the notifying includes transmitting an alert to a portable terminal possessed by a security guard or to a terminal in an office of a store.   
     
     
         5 . The information processing method according to  claim 1 ,
 wherein the customer paying for items is at a head of a line among customers lining up to pay.   
     
     
         6 . The information processing method according to  claim 1 ,
 wherein the detecting the number of items taken includes detecting an action of each of the at least one customer taking an item from a shelf or returning an item to a shelf.   
     
     
         7 . The information processing method according to  claim 1 , further comprising:
 storing, in a storage device, flow line information including the plurality of time-series positions and the number of items corresponding to each of the plurality of time-series positions.   
     
     
         8 . The information processing method according to  claim 7 ,
 wherein the comparing the number of items associated with the identified plurality of time-series positions includes comparing the number of items included in the flow line information stored in the storage device.   
     
     
         9 . The information processing method according to  claim 7 , further comprising:
 determining, by referring to the storage device, the number of items associated with the identified plurality of time-series positions.   
     
     
         10 . An information processing device, comprising:
 at least one memory configured to store instructions; and   at least one processor configured to execute the instructions to:   acquire, from a video, a plurality of time-series positions of at least one customer;   detect a number of items taken by each of the at least one customer at each of the plurality of time-series positions;   identify the plurality of time-series positions associated with one of the at least one customer paying for items; and   detect a discordance between a number of items associated with the identified plurality of time-series positions and a number of items paid for by the customer at a register as an anomaly.   
     
     
         11 . A non-transitory recording medium storing a program for causing a computer to execute:
 acquiring, from a video, a plurality of time-series positions of at least one customer;   detecting a number of items taken by each of the at least one customer at each of the plurality of time-series positions;   identifying the plurality of time-series positions associated with a customer paying for items; and   detecting a discordance between a number of items associated with the identified plurality of time-series positions and a number of items paid for by the customer at a register as an anomaly.