Systems and methods for automated, artificial intelligence based monitoring of, and/or alerting for, digital out of home display units

1 . A system for automated, artificial intelligence (“AI”) based monitoring of, and alerting for, display units for digital out of home applications, said system comprising:

the display units, each installed at a respective geographic location and including a structural subassembly, a display subassembly connected to the structural subassembly, sensors for measuring conditions at the respective display unit, airflow pathways, fans for cooling the display units located along the airflow pathways, and electronics for operating the display units, including controlling the display subassembly, controlling the fans, and receiving data from the sensors; and

a monitoring subsystem in electronic communication with the display units, the monitoring subsystem comprising one or more non-transitory electronic storage devices comprising software instructions, which when executed, configure one or more processors of the monitoring subsystem to:

receive data from the display units, including sensor data and operational status data;

tag the received data, including with a respective unique identifier corresponding to the respective one of the display units from which the received data originated;

analyze the received, tagged data using an AI model trained using historical data from same or different ones of the display units to identify if the received, tagged data indicates that any of the display units are experiencing any of: abnormal conditions and maintenance needs within a predetermined time period, wherein the historical data includes the sensor data and the operational status data from the same or different ones of the display units tagged as one of normal and abnormal; and

generate an alert and electronic service request for each of the abnormal conditions and maintenance needs identified.

2 . The system of claim 1 wherein:

the one or more non-transitory electronic storage devices comprise additional software instructions, which when executed, configure the one or more processors to:

receive the historical data;

tag the received historical data, including with the respective unique identifier corresponding to the respective one of the display units from which the received data originated and one of the normal and the abnormal indicators; and

train the AI model using the historical data.

3 . The system of claim 1 wherein:

the one or more non-transitory electronic storage devices comprise additional software instructions, which when executed, configure the one or more processors to:

train the AI model using the historical data before receiving the data from the display units.

4 . The system of claim 1 wherein:

the one or more non-transitory electronic storage devices comprise additional software instructions, which when executed, configure the one or more processors to:

establish normal operating parameters for the display units; and

analyze the received data to determine if one or more of the normal operating parameters is violated, and if so:

identify a selection of a repository of display unit data, which includes the historical data and additional historical data from the same or different ones of the display units, said additional historical data including sensor data and operational status data from the same or different ones of the display units tagged as one of normal and abnormal; and

retrieve the selection of the repository of display unit data for use as the historical data for training the AI model.

5 . The system of claim 4 wherein:

the selection of the repository of display unit data includes the sensor data and the operational status data from the same or different ones of the display units with conditions matching or within a predetermined margin of the received, tagged data violating the one or more of the normal operating parameters.

6 . The system of claim 5 wherein:

the one or more non-transitory electronic storage devices comprise additional software instructions, which when executed, configure the one or more processors to:

train the AI model using the historical data after receiving the data from the display units and identifying the selection of the repository of display unit data.

7 . The system of claim 6 wherein:

the one or more non-transitory electronic storage devices comprise additional software instructions, which when executed, configure the one or more processors to:

normally sample data from the display units at a first rate;

upon determining that one or more of the normal operating parameters is violated, sample data from the display units at a second rate, which is higher than the first rate; and

analyze the data from the display units sampled at the second rate using the AI model.

8 . The system of claim 1 wherein:

the AI model comprises a neural network.

9 . The system of claim 1 wherein:

the one or more non-transitory electronic storage devices comprise additional software instructions, which when executed, configure the one or more processors to:

tag the received data with the normal tag where no abnormal conditions are detected.

10 . The system of claim 1 wherein:

the one or more non-transitory electronic storage devices comprise additional software instructions, which when executed, configure the one or more processors to:

receive service reports in response to the electronic service requests;

analyze the service reports for findings; and

tag the received data associated with the electronic service requests based on the findings in the service reports, including tagging the associated, received data with the normal tag where acceptable conditions were indicated, and the abnormal tag where abnormal conditions were indicated.

11 . The system of claim 10 wherein:

the one or more non-transitory electronic storage devices comprise additional software instructions, which when executed, configure the one or more processors to:

tag the received data associated with the electronic service requests based on the findings in the service reports, including tagging the associated, received data with one of a specific failure condition and maintenance need where specific failure conditions and maintenance needs were indicated, respectively.

12 . The system of claim 1 wherein:

the sensors of each of the display units comprise temperature sensors and light sensors;

the operational status data includes speed data for the fans and illumination levels for the display subassemblies of the display units; and

the electronics of each of the display units comprise controllers for the fans and the display subassemblies.

13 . The system of claim 1 wherein:

the sensors of each of the display units comprise a humidity sensor and temperature sensors, at least one of which is in contact with ambient air, and at least two of which are in contact with other portions of the display unit; and

the electronics of each of the display units comprise a controller for receiving humidity data from the humidity sensor and temperature data from the temperature sensors, identifying a lowest temperature reading from the temperature data from the at least two temperature sensors at a given time, and calculate a dewpoint spread (“DPS”) between a dew point derived from the humidity data and temperature data of the at least one temperature sensor and the lowest temperature reading, and report the DPS as part of the sensor data.

14 . The system of claim 1 wherein:

the display subassemblies of the display units each comprise a cover, a liquid crystal layer, and a backlight.

15 . The system of claim 1 wherein:

the sensors of the display units include location sensors;

the data received from the display units includes location data from the location sensors; and

the one or more non-transitory electronic storage devices comprise additional software instructions, which when executed, configure the one or more processors to:

as part of, or before, generating the electronic service requests, and for each of the service requests, respectively:

identify a respective geographic location associated with the unique display identifier associated with the received, tagged data indicating the respective abnormal conditions or maintenance need;

identify a respective technician or service team associated with the respective geographic location; and

cause the electronic service request to be transmitted to a remote electronic device associated with the respective technician or service team, said electronic service request including information identifying the respective display unit and indicating the respective abnormal conditions or maintenance need.

16 . The system of claim 1 wherein:

the one or more non-transitory electronic storage devices comprise additional software instructions, which when executed, configure the one or more processors to:

for each at least certain of the abnormal conditions identified, identify a respective remedial action from a plurality of candidate remedial actions and cause the respective remedial action to be implemented at the respective display unit by electronic command.

17 . The system of claim 16 wherein:

the candidate remedial actions comprise altering operating speed of the fans, altering operating levels of the display subassembly, and initiating a recovery sequence.

18 . The system of claim 1 wherein:

the AI model is configured to identify the abnormal condition where the analyzed data indicates any one of: downward trends in peak to peak pressure cycles and downward trends in dew point spread.

19 . A method for automated, artificial intelligence (“AI”) based monitoring of, and alerting for, display units for digital out of home applications, said method comprising:

receiving data from display units at a monitoring subsystem, said data including sensor data and operational status data, each of the display units being installed at a respective geographic location and including a structural subassembly, a display subassembly connected to the structural subassembly, sensors for measuring conditions at the respective display unit, airflow pathways, fans for cooling the display units located along the airflow pathways, and electronics for operating the display units, including controlling the display subassembly, controlling the fans, and receiving data from the sensors, and the monitoring subsystem being in electronic communication with the display units and comprising one or more databases and one or more computing devices;

tagging the received data, including with a respective unique display unit identifier corresponding to the respective one of the display units from which the received data originated;

analyzing the received, tagged data using an AI model trained using historical data from same or different ones of the display units to identify if the received, tagged data indicates that any of the display units are experiencing any of: abnormal conditions and maintenance needs within a predetermined time period, wherein the historical data includes the sensor data and the operational status data from the same or different ones of the display units tagged as one of normal and abnormal; and

generating an alert and electronic service request for each of the abnormal conditions and maintenance needs identified.

20 . A system for automated, artificial intelligence (“AI”) based monitoring of, and alerting for, display units for digital out of home applications, said system comprising:

the display units, each installed at a respective geographic location and including a structural subassembly, a display subassembly connected to the structural subassembly and comprising a cover, a liquid crystal layer behind the cover, and a backlight behind the liquid crystal layer, sensors for measuring conditions at the respective display unit, airflow pathways, fans for cooling the display units located along the airflow pathways, and a controller for operating the display units, said controller configured to control at least certain operations of the display subassembly, including illumination levels of the backlight, and at least certain operations of the fans, including operating speed levels, and receive data from the sensors, including temperature readings from temperature sensors, humidity readings from a humidity sensor, location information from a location sensor, pressure readings from pressure sensors, ambient light levels from an ambient light sensor, and dew point spread (“DPS”) readings derived from the humidity readings and the temperature readings from at least one of the temperature sensors; and

a monitoring subsystem in electronic communication with the display units, the monitoring subsystem comprising one or more non-transitory electronic storage devices comprising software instructions, which when executed, configure one or more processors of the monitoring subsystem to:

establish a repository of historical data including sensor data from the sensors and operational status data from the controllers for the display units, each portion of said repository of said historical data being tagged as one of normal and abnormal operating conditions;

establish normal operating parameters for the display units;

receive further data from the display units, including the sensor data and the operational status data, sampled at a first rate;

analyze the received, tagged further data to determine if one or more of the normal operating parameters is violated, and if so:

begin sampling the further data from the respective display unit at a second rate, which is higher than the first rate;

identify a selection of the historical data of the repository having at least one of the sensor data and the operational status data within a predetermined margin of the sensor data and the operational status data, respectively, of the received, tagged further data determined to be violating the one or more of the normal operating parameters;

retrieve the selection of the historical data from the repository of the historical data;

utilize the selection of the historical data to train an AI model;

analyze the further data indicated as violating the normal operating parameters, including the further data sampled at the second rate, using the AI model to identify if the received data indicates that any of the display units are likely experiencing abnormal conditions, including based on the tags applied to the selection of the historical data;

generate an alert and electronic service request for each of the abnormal conditions identified;

tag the received data indicated as violating the normal operating parameters with the abnormal tag; and

add the received, tagged data to the repository of the historical data;

where any of: the analysis of the received data determines that none of the normal operating parameters is violated, and the analysis of the received data using the AI model indicates that no abnormal conditions are detected:

tag the received data with the normal tag; and

add the received, tagged data to the repository of the historical data.