Abstract: Examples described herein generally relate to a system for monitoring workers in a retail environment. The system may include a plurality of cameras located in different regions of the retail location and configured to capture a video feed of a respective region. The system may include a computer system comprising a memory storing computer executable instructions. The system may provide a video feed of at least one region of the retail environment to a machine learning classifier, the machine learning classifier trained on labeled videos, to classify a sequence of images of a worker into a probability certainty of an activity being performed by the worker. The processor may determine, based on the probability certainties generated by the machine learning classifier over a period of time, an activity schedule of the worker. The system may determine labor productivity statistics based on the activity schedule.

Abstract: A controller for making initiating actions in a building management system (BMS) is shown. The controller includes a processing circuit configured to receive location data relating to the building occupant located at a first location outside of a building. The processing circuit is configured to, in response to determining the first location is within a first distance range of the building, provide control signals to a first subsystem of the BMS. The processing circuit is configured to receive location data relating to the building occupant located at a second location outside of the building. The processing circuit is configured to, in response to determining that the second location is within a second distance range of the building, provide control signals to a second subsystem of the BMS.

Abstract: Example implementations include a method, apparatus, and computer-readable medium comprising receiving visual data captured by cameras at a store; retrieving one or more pre-defined events related to shopper pose or location; applying data analytics to the visual data, including comparing the visual data with the pre-defined events to identify a sequence of events related to activities of a shopper in relation to an item in an aisle or zone of the store; generating a score based on the events to indicate a likelihood of the shopper completing a purchase transaction of the item at the store; determining, responsive to the score being above a threshold, whether the events indicate that the shopper completed the purchase transaction; identifying, responsive to the score being above the threshold, friction reasons that resulted in the shopper failing to complete the purchase transaction; and generating an alert corresponding to the score or the friction reasons.

Abstract: A controller for making initiating actions in a building management system (BMS) is shown. The controller includes a processing circuit configured to receive location data relating to the building occupant located at a first location outside of a building. The processing circuit is configured to, in response to determining the first location is within a first distance range of the building, provide control signals to a first subsystem of the BMS. The processing circuit is configured to receive location data relating to the building occupant located at a second location outside of the building. The processing circuit is configured to, in response to determining that the second location is within a second distance range of the building, provide control signals to a second subsystem of the BMS.

Abstract: Example implementations include a method, apparatus and computer-readable medium of controlling a security system by a computer device, comprising receiving device metadata associated with a device in communication with a wireless communication access point. The implementations further include determining that the device metadata comprises matched device metadata based on a match with one of a plurality of previously-identified device metadata in a historical database that stores the plurality of previously-identified device metadata in association with one or more of a plurality of security breach events and a corresponding one of a plurality of security breach probability values. Additionally, the implementations further include determining that the matched device metadata corresponds with a security breach probability value that exceeds a security breach probability threshold.

Abstract: A system may be configured to generate real-time analytics using machine learning and computer vision. In some aspects, the system may receive a storage structure video frame and an interaction video frame, determine a storage structure inference based on the storage structure video frame, and determine an interaction inference based on the interaction video frame. Further, the system may determine that the storage structure inference and the interaction inference correspond to a common time period and common location, and generate analytics information based on the storage structure inference and the interaction inference.

Abstract: Systems and methods for returning an item. The methods comprise: performing operations by a self-return station to capture an image of a first item that an individual is trying to return to an entity; performing machine learning operations by the self-return station using the image to determine whether the first item is damaged and to determine a degree of item damage; allowing, by the self-return station, a return of the first item to the entity when the first item is not damaged or when the degree of item damage does not exceed a threshold value; and preventing, by the self-return station, the return of the first item to the entity when the first item is damaged and the degree of item damage exceeds the threshold value.

Abstract: Examples described herein generally relate to a system for managing a retail environment. The system may collect data from a plurality of retail information systems including at least an inventory system, a loss prevention system, and a retail traffic system. The system may predict a condition based on a machine-learning model applied to a combination of the collected data from at least two systems of the plurality of retail information systems. The system may push an alert to a user identifying the condition and a recommended action, the user having a user persona matching a persona associated with the condition.

Abstract: Examples described herein generally relate to a system for monitoring workers in a retail environment. The system may include a plurality of cameras located in different regions of the retail location and configured to capture a video feed of a respective region. The system may include a computer system comprising a memory storing computer executable instructions. The system may provide a video feed of at least one region of the retail environment to a machine learning classifier, the machine learning classifier trained on labeled videos, to classify a sequence of images of a worker into a probability certainty of an activity being performed by the worker. The processor may determine, based on the probability certainties generated by the machine learning classifier over a period of time, an activity schedule of the worker. The system may determine labor productivity statistics based on the activity schedule.

Abstract: Systems and methods for returning an item. The methods comprise: performing item return operations by a computing device using at least one of machine learned information about a person who purchased the item, machine learned information about a person returning the item, and machined learned information about a condition of the item at the time of sale and at the time of return; and automatively sorting the item using a conveyer system to move the item from a counter to a respective storage area of a plurality of storage areas assigned to different product types.

Abstract: Example implementations include a method, apparatus and computer-readable medium of controlling a security system by a computer device, comprising receiving device metadata associated with a device in communication with a wireless communication access point. The implementations further include determining that the device metadata comprises matched device metadata based on a match with one of a plurality of previously-identified device metadata in a historical database that stores the plurality of previously-identified device metadata in association with one or more of a plurality of security breach events and a corresponding one of a plurality of security breach probability values. Additionally, the implementations further include determining that the matched device metadata corresponds with a security breach probability value that exceeds a security breach probability threshold.

Abstract: Systems and methods for operating a Point Of Sale (“POS”) system. The methods comprise: performing operations by the POS system to machine learn at least information about a condition of an article to be purchased using at least one of imaging, sensing, and short range communications; determining by the POS system if the article is accepted for purchase based at least on the machine learned information about the condition of the article; and completing a purchase transaction by the POS system if a determination is made that the article is accepted for purchase. The POS system may also perform operations to deactivate a security tag coupled to the article or actuate a detachment mechanism of the security tag, if the article was successfully purchased during the purchase transaction.

Abstract: Systems and methods for operating a Point Of Sale (“POS”) system. The methods comprise: performing operations by the POS system to machine learn at least information about a condition of an article to be purchased using at least one of imaging, sensing, and short range communications; determining by the POS system if the article is accepted for purchase based at least on the machine learned information about the condition of the article; and completing a purchase transaction by the POS system if a determination is made that the article is accepted for purchase. The POS system may also perform operations to deactivate a security tag coupled to the article or actuate a detachment mechanism of the security tag, if the article was successfully purchased during the purchase transaction.

Abstract: Systems and methods for returning an item. The methods comprise: performing item return operations by a computing device using at least one of machine learned information about a person who purchased the item, machine learned information about a person returning the item, and machined learned information about a condition of the item at the time of sale and at the time of return; and automatively sorting the item using a conveyer system to move the item from a counter to a respective storage area of a plurality of storage areas assigned to different product types.