Method and apparatus for energy efficient probabilistic context awareness of a mobile or wearable device user by switching between a single sensor and multiple sensors

{
  "publication_number": "US10748075B2",
  "country": "US",
  "kind": "B2",
  "title": "Method and apparatus for energy efficient probabilistic context awareness of a mobile or wearable device user by switching between a single sensor and multiple sensors",
  "abstract": "Disclosed herein is a method of operating an electronic device. The method includes activating a first sensing device, and determining a first probabilistic context of the electronic device relative to its surroundings. The method includes outputting the first probabilistic context, and determining a confidence measure of the first probabilistic context. Where the confidence measure of the first probabilistic context is below a threshold, the method includes activating a second sensing device, determining a second probabilistic context of the electronic device relative to its surroundings. outputting the second probabilistic context, and determining a confidence measure of the second probabilistic context. Where the confidence measure of the second probabilistic context is above the threshold, the second sensing device is deactivated and the method returns to determining the first probabilistic context.",
  "claims": [
    "1. A sensor chip mounted on a printed circuit board (PCB) and electrically coupled to a system on chip (SoC) mounted on the PCB via at least one conductive trace, the sensor chip comprising: first and second sensing devices; and a control circuit configured to: activate the first sensing device; determine a first probabilistic context of an electronic device into which the sensor chip is incorporated relative to its surroundings, wherein the first probabilistic context comprises probabilities that a mode of movement of a user carrying the electronic device is each of a plurality of modes of movement; output the first probabilistic context; determine a confidence measure of the first probabilistic context; where the confidence measure of the first probabilistic context is below a first threshold: activate the second sensing device; determine a second probabilistic context of the electronic device relative to its surroundings; output the second probabilistic context; and determine a confidence measure of the second probabilistic context; wherein the control circuit determines confidence measure of the first probabilistic context by: determining a difference between a highest of the probabilities and a second highest of the probabilities; and determining the confidence measure of the first probabilistic content as a function of the determined difference; and where the confidence measure of the second probabilistic context is above a second threshold, deactivate the second sensing device and return to determining the first probabilistic context.",
    "2. The sensor chip of claim 1, wherein the first threshold and second threshold are equal.",
    "3. The sensor chip of claim 1, wherein the first threshold and second threshold are unequal.",
    "4. The sensor chip of claim 1, further comprising a third sensing device; and wherein the control circuit is further configured to: where the confidence measure of the second probabilistic context is below the first threshold: activate the third sensing device; determine a third probabilistic context of the electronic device relative to its surroundings; output the third probabilistic context; and determine a confidence measure of the third probabilistic context; and where the confidence measure of the third probabilistic context is above the second threshold, deactivate the third sensing device and return to determining the second probabilistic context.",
    "5. The sensor chip of claim 1, wherein the control circuit is further configured to, where the confidence measure of the second probabilistic context is below the first threshold, return to determining the second probabilistic context.",
    "6. The sensor chip of claim 1, wherein the control circuit outputs the first probabilistic context to the SoC.",
    "7. The sensor chip of claim 1, wherein the control circuit is configured to deactivate the first sensing device when activating the second sensing device.",
    "8. The sensor chip of claim 1, wherein the control circuit is configured to maintain activation of the first sensing device when activating the second sensing device.",
    "9. The sensor chip of claim 1, wherein the second threshold is a level above which accuracy of the first or second probabilistic context is at least 80%.",
    "10. The sensor chip of claim 1, wherein first the threshold is approximately 60%.",
    "11. A sensor chip mounted on a printed circuit board (PCB) and electrically coupled to a system on chip (SoC) mounted on the PCB via at least one conductive trace, the sensor chip comprising: first and second sensing devices; and a control circuit configured to: activate the first sensing device; determine a first probabilistic context of an electronic device into which the sensor chip is incorporated relative to its surroundings; output the first probabilistic context; determine a confidence measure of the first probabilistic context; where the confidence measure of the first probabilistic context is below a first threshold: activate the second sensing device; determine a second probabilistic context of the electronic device relative to its surroundings; output the second probabilistic context; and determine a confidence measure of the second probabilistic context; and where the confidence measure of the second probabilistic context is above a second threshold, deactivate the second sensing device and return to determining the first probabilistic context; and wherein the second probabilistic context comprises probabilities that a mode of movement of a user carrying the electronic device is each of a plurality of modes of movement; and wherein the control circuit determines confidence measure of the second probabilistic context by: determining a difference between a highest of the probabilities and a second highest of the probabilities; and determining the confidence measure of the second probabilistic content as a function of the determined difference.",
    "12. The sensor chip of claim 11, wherein the control circuit also determines the confidence measure of the first probabilistic context as a function of conditional entropy of the first probabilistic context.",
    "13. The sensor chip of claim 11, wherein the control circuit also determines the confidence measure of the second probabilistic context as a function of conditional entropy of the second probabilistic context.",
    "14. The sensor chip of claim 11, wherein the first threshold is set based on a desired level of probabilistic context accuracy.",
    "15. The sensor chip of claim 1, wherein the control circuit also determines the confidence measure of the first probabilistic context as a function of conditional entropy of the first probabilistic context.",
    "16. The sensor chip of claim 1, wherein the control circuit determines the confidence measure of the second probabilistic context as a function of conditional entropy of the second probabilistic context.",
    "17. The sensor chip of claim 1, wherein the first threshold is set based on a desired level of probabilistic context accuracy.",
    "18. The sensor chip of claim 17, wherein the control circuit receives the desired level of probabilistic context accuracy from the SoC.",
    "19. The sensor chip of claim 1, wherein the first threshold is set based as a function of minimum power consumption required to achieve a desired level of probabilistic context accuracy.",
    "20. The sensor chip of claim 1, wherein the control circuit is configured to place the first sensing device into a low power mode when activating the second sensing device; and wherein the control circuit is configured to place the second sensing device into a low power mode when activating the first sensing device.",
    "21. A method of operating an electronic device, comprising: activating a first sensing device; determining a first probabilistic context of the electronic device relative to its surroundings, wherein the first probabilistic context comprises probabilities that a mode of movement of a user carrying the electronic device is each of a plurality of modes of movement; outputting the first probabilistic context; determining a confidence measure of the first probabilistic context; wherein the confidence measure of the first probabilistic context is determined by: determining a difference between a highest of the probabilities and a second highest of the probabilities; and determining the confidence measure of the first probabilistic content as a function of the determined difference; where the confidence measure of the first probabilistic context is below a threshold: activating a second sensing device; determining a second probabilistic context of the electronic device relative to its surroundings, wherein the second probabilistic context comprises probabilities that a mode of movement of a user carrying the electronic device is each of a plurality of modes of movement; outputting the second probabilistic context; determining a confidence measure of the second probabilistic context; wherein the confidence measure of the second probabilistic context is determined by: determining a difference between a highest of the probabilities and a second highest of the probabilities; and determining the confidence measure of the second probabilistic content as a function of the determined difference; where the confidence measure of the second probabilistic context is above the threshold, deactivating the second sensing device and return to determining the first probabilistic context.",
    "22. The method of claim 21, further comprising, where the confidence measure of the second probabilistic context is below the threshold: activating a third sensing device; determining a third probabilistic context of the electronic device relative to its surroundings; outputting the third probabilistic context; determining a confidence measure of the third probabilistic context; and where the confidence measure of the third probabilistic context is above the threshold, deactivating the third sensing device and return to determining the second probabilistic context.",
    "23. The method of claim 21, further comprising deactivating the first sensing device when activating the second sensing device.",
    "24. The method of claim 21, further comprising maintaining activation of the first sensing device when activating the second sensing device.",
    "25. The method of claim 21, wherein the confidence measure of the first probabilistic context is also determined as a function of conditional entropy of the first probabilistic context; and wherein the confidence measure of the second probabilistic context is determined as a function of conditional entropy of the second probabilistic context.",
    "26. The method of claim 21, wherein the threshold is set based on a desired level of probabilistic context accuracy.",
    "27. The method of claim 21, wherein the threshold is set based as a function of minimum power consumption required to achieve a desired level of probabilistic context accuracy.",
    "28. The method of claim 21, wherein the first sensing device is placed into a low power mode when activating the second sensing device; and wherein the second sensing device is placed into a low power mode when activating the first sensing device.",
    "29. The method of claim 21, wherein the confidence measure of the first probabilistic context is an indicator of a likely correctness of the first probabilistic context; and wherein the confidence measure of the second probabilistic context is an indicator of likely correctness of the second probabilistic context."
  ],
  "description_excerpt": "This disclosure relates to the method and apparatus for determining a mobile or wearable device user's context in an energy efficient manner while providing a desired level of context classification accuracy.\n\nPortable electronic devices such as smartphones, smartwatches, other wearables, and tablets are ever more popular in the world today. Certain functions of these devices depend on the device having knowledge of the device's orientation, or of conditions of the environment in which the device currently resides. For example, a smartphone may rotate its user interface from a portrait view to a landscape view based upon the orientation in which the smartphone is held. As another example, a smartwatch may activate its display or alter the brightness of its display based upon the orientation in which the smartwatch is held, or based upon the ambient light in the environment in which the smartwatch resides, respectively. Such portable electronic devices may also log the physical activity of a user. For example, a smartphone or smartwatch may count the number of steps taken by a user.\n\nIn order to determine the orientation of the device or conditions of the environment in which the device resides, sensors such as accelerometers and gyroscopes are employed. Typically, the electronic device includes a system on chip (SOC) that receives raw data from the sensors, and then determines the device orientation or conditions of the environment.",
  "cpc": [
    "G06F 1/3287",
    "G01L 11/00",
    "G06F 1/163",
    "G06F 1/3296",
    "G06F 3/011",
    "G06F 3/0346",
    "G06F 3/16",
    "G06N 7/005",
    "G06N 7/01",
    "Y02D 10/00"
  ],
  "ipc": [
    "G06F 1/32",
    "G06N 7/00",
    "G06F 1/3287",
    "G06F 1/3296",
    "G06F 16/22",
    "G06F 16/90",
    "G06K 9/00",
    "G06Q 20/06",
    "H04L 12/24"
  ],
  "assignees": [
    "STMicroelectronics International NV",
    "STMicroelectronics lnc USA"
  ],
  "inventors": [
    "Mahesh Chowdhary",
    "Arun Kumar",
    "Ghanapriya Singh",
    "Kashif R. J. Meer",
    "Indra Narayan Kar",
    "Rajendar Bahl"
  ],
  "filing_date": "2016-10-21",
  "publication_date": "2020-08-18",
  "grant_date": "2020-08-18",
  "priority_date": "2016-10-21",
  "application_number": "US-201615299656-A",
  "family_id": "61971048",
  "cited_by_count": 60,
  "citations": [
    "US20050126274A1",
    "US8588871B1",
    "CN104460957A",
    "US20150199224A1",
    "CN104656898A",
    "CN105630197A",
    "US20180114133A1"
  ]
}