System and method for providing guidance or feedback to a user

Abstract

A device for providing guidance or feedback to a user. The device includes a camera configured to detect image data indicating a user performance of an activity. The system includes a guidance unit connected to the camera. The guidance unit is configured to identify the activity based on image processing of the image data or an identification of the activity from the user. The guidance unit is also configured to determine a criteria associated with the activity. The guidance unit is also configured to determine a user performance of the activity based on the image data. The guidance unit is also configured to determine feedback based on a comparison of the criteria and the user performance of the activity, the feedback indicating an improvement or suggestion for the user. The system also includes an output unit connected to the guidance unit, the output unit configured to output the feedback.

Description

BACKGROUND

1. Field

The present disclosure relates to providing information by a device, and more particularly to a system and a method for providing guidance or feedback to a user performing an activity.

2. Description of the Related Art

An individual performing an activity, such as cooking, repairing a vehicle, or playing a sport, may follow a set of instructions. For example, an individual who is cooking or baking may follow a recipe. In another example, an individual who is repairing a component of a vehicle may follow instructions for disassembling the component, repairing the component, and reassembling the component. However, following a set of instructions may not always be convenient. An individual following a recipe may print the recipe on a paper or may view the recipe on a mobile device, such as a tablet or a smartphone. However, the integrity of the paper may become compromised if subjected to water or foods spilling on the paper, and the mobile device may turn off or may dim the display, requiring periodic engagement with the screen. In addition, it is often the responsibility of the individual to ensure the instructions are being followed so that the activity is successfully completed with no other oversight.

Thus, there is a need for systems and methods for providing more convenient guidance and feedback to users.

SUMMARY

What is described is a system for providing guidance or feedback to a user. The system includes a camera configured to detect image data indicating a user performance of an activity. The system also includes a guidance unit connected to the camera. The guidance unit is configured to identify the activity based on image processing of the image data or an identification of the activity from the user. The guidance unit is also configured to determine a criteria associated with the activity. The guidance unit is also configured to determine a user performance of the activity based on the image data. The guidance unit is also configured to determine feedback based on a comparison of the criteria and the user performance of the activity, the feedback indicating an improvement or suggestion for the user. The system also includes an output unit connected to the guidance unit, the output unit configured to output the feedback.

Also described is a device for providing guidance or feedback to a user. The device includes a camera configured to detect image data indicating a user performance of an activity. The device also includes a guidance unit connected to the camera. The guidance unit is configured to identify the activity based on image processing of the image data or an identification of the activity from the user. The guidance unit is also configured to determine a set of instructions associated with the activity. The guidance unit is also configured to determine a current stage of the activity based on the image data. The guidance unit is also configured to determine a next instruction from the set of instructions to provide the user based on the current stage. The device also includes an output unit connected to the guidance unit, the output unit configured to output the next instruction.

Also described is a method for providing guidance or feedback to a user. The method includes detecting, by a camera, image data indicating a user performance of an activity. The method also includes identifying, by a guidance unit, the activity based on image processing of the image data or an identification of the activity from the user. The method also includes determining, by the guidance unit, a criteria or a set of instructions associated with the activity. The method also includes determining, by the guidance unit, a user performance of the activity based on the image data or a current stage of the activity based on the image data. The method also includes determining, by the guidance unit, feedback based on a comparison of the criteria and the user performance of the activity or a next instruction from the set of instructions to provide the user based on the current stage. The method also includes outputting, by an output unit, the feedback or the next instruction.

BRIEF DESCRIPTION OF THE DRAWINGS

Other systems, methods, features, and advantages of the present invention will be or will become apparent to one of ordinary skill in the art upon examination of the following figures and detailed description. It is intended that all such additional systems, methods, features, and advantages be included within this description, be within the scope of the present invention, and be protected by the accompanying claims. Component parts shown in the drawings are not necessarily to scale, and may be exaggerated to better illustrate the important features of the present invention. In the drawings, like reference numerals designate like parts throughout the different views, wherein:

FIG. 1A illustrates an exemplary use of a system for providing guidance or feedback to a user cooking food, according to an embodiment of the present invention;

FIG. 1B illustrates an exemplary use of a system for providing guidance or feedback to a user repairing a vehicle, according to an embodiment of the present invention;

FIG. 1C illustrates an exemplary use of a system for providing guidance or feedback to a user swinging a golf club, according to an embodiment of the present invention;

FIG. 1D illustrates an exemplary use of a system for providing guidance or feedback to a user administering first aid, according to an embodiment of the present invention;

FIG. 1E illustrates an exemplary use of a system for providing guidance or feedback to a user regarding food or drink consumption, according to an embodiment of the present invention;

FIG. 1F illustrates an exemplary use of a system for providing guidance or feedback to a user regarding a piece of art, according to an embodiment of the present invention;

FIG. 1G illustrates an exemplary use of a system for providing guidance or feedback to a user regarding speech behavior, according to an embodiment of the present invention;

FIG. 1H illustrates an exemplary use of a system for providing guidance or feedback to a user regarding reminders for when the user leaves the user's house, according to an embodiment of the present invention;

FIG. 2 is a block diagram of components of a system for providing guidance or feedback to a user, according to an embodiment of the present invention;

FIG. 3 is a block diagram of components of a system for providing guidance or feedback to a user, according to another embodiment of the present invention;

FIG. 4 illustrates an exemplary device, according to an embodiment of the present invention;

FIG. 5 illustrates a method for providing feedback to a user of a device, according to an embodiment of the present invention; and

FIG. 6 illustrates a method for providing guidance to a user of a device, according to an embodiment of the present invention.

DETAILED DESCRIPTION

Disclosed herein are systems and methods for providing guidance or feedback to a user. The systems and methods disclosed herein determine an activity the user is engaged in, and automatically provides guidance or feedback to the user. The activity may be detected by a camera on a device worn by the user, or may be provided to the wearable device by the user. The user receives the guidance or feedback from the wearable device, allowing the user to perform the activity without occupying the user's hands. The guidance or feedback may be suggestions for the user or may be instructions for the user to follow. The systems and methods provide several benefits and advantages, such as providing updated, accurate, and personalized guidance or feedback for the user. Additional benefits and advantages include the user not having to rely on memory to remember instructions for performing an activity. As such, the user may perform the activity at a higher level and may achieve more consistent and better results. Further, the user may be more capable while using the systems and methods disclosed herein, as the user can access instructions on how to perform activities the user may not have previously been capable of performing.

The systems and methods provide additional benefits and advantages such as allowing users to become less reliant on other human beings to teach the users how to do things and inform the users about suggestions or reminders.

An exemplary system includes a camera configured to detect image data indicating a user performance of an activity or a user about to begin an activity. The system also includes a guidance unit connected to the camera. The guidance unit is configured to identify the activity based on image processing of the image data or an identification of the activity from the user. The guidance unit is also configured to determine a criteria associated with the activity. The guidance unit is also configured to determine a user performance of the activity based on the image data. The guidance unit is also configured to determine feedback based on a comparison of the criteria and the user performance of the activity, the feedback indicating an improvement or suggestion for the user. The system also includes an output unit connected to the guidance unit, the output unit configured to output the feedback.

FIGS. 1A-1H illustrate various exemplary situations where the system for providing guidance or feedback to a user may be used. In each of the FIGS. 1A-1H, there is a user 102 of a device 100. The system for providing guidance or feedback to the user includes the device 100. The device 100 is illustrated as a wearable device resembling a necklace, but other devices, such as a wearable smart watch or a smartphone may be used.

The device 100 is configured to provide an output 104 via an output unit including a speaker 110, for example. The output 104 may be an audio output from a speaker 110 or a tactile output from a vibration unit. The output 104 may be guidance or feedback. When the output 104 is feedback, the output 104 may be a suggestion, a reminder, an improvement, or general information for the user 102. When the output 104 is guidance, the output 104 may be an instruction for the user 102 in performing an activity. The device 100 may automatically identify the activity being performed by the user 102 using a camera 106. The user 102 may provide an identification of the activity to the device 100 using an input unit 108. The input unit 108 may be a touchpad, a keyboard, or a microphone, for example.

FIG. 1A illustrates the user 102 making cookies. The device 100 may identify that the user 102 is making cookies. The device 100 may detect image data using a camera 106 and the device 100 may analyze the detected image data to determine that the user 102 is making cookies. For example, the camera 106 detects a cookie box or mix or ingredients to make cookies and determines that the user 102 wants to make cookies. The device 100 may compare the detected image data with a learned model to determine that the activity performed by the user 102 is making cookies. Part of the learned model may be recognition of objects 112 or actions associated with the activity. In FIG. 1A, the learned model may include a bowl, a hand mixer, ingredients such as flour, or the action of scooping flour with a measuring spoon or measuring cup. Alternatively, or in addition, the user 102 may speak into the input unit 108 an indication that the user 102 is making cookies, such as “Hey, I'm making chocolate chip cookies, can you help me?” or “Hey, teach me how to make chocolate chip cookies.” In addition, the user 102 may type into the input unit 108 an indication that the activity the user 102 is engaged in is making cookies.

The device 100 may output an output 104 that is feedback. The device 100 may determine, based on image data that the user 102 has not scooped enough flour, and the device 100 may output an output 104 such as “You might want to check how much flour you scooped.” The user 102 may prompt the device 100 for feedback using the input unit 108. For example, the user 102 may say “Hey, did I scoop enough flour?” and the device 100 may, based on detected image data, determine a response to the prompt provided by the user 102.

The device 100 may output an output 104 that is guidance. The device 100 may determine, based on image data, that the user has finished performing a step in a series of instructions. For example, the device 100 may detect that the user 102 has finished adding flour to the bowl, and that the user 102 should next add baking soda. The device 100 may provide an output 104 that is an instruction, such as “Next, after the flour, you should add 2 teaspoons of baking soda.”

The learned model may be stored locally on the device 100 or remotely. The learned model may be periodically updated. For example, the user 102 may identify a particular chocolate chip cookie recipe the user likes, or a most popular chocolate chip cookie recipe may be provided in the learned model.

Another example embodiment is illustrated in FIG. 1B. In FIG. 1B, the user 102 wearing the device 100 is repairing a vehicle. The device 100 may identify that the user 102 is repairing a vehicle. The device 100 may detect image data using a camera 106 and the device 100 may analyze the detected image data to determine that the user 102 is repairing the vehicle. The device 100 may compare the detected image data with a learned model to determine that the activity performed by the user 102 is repairing the vehicle. In FIG. 1B, the learned model may include objects 112, such as a vehicle, a vehicle part, tools, or the action of engaging the vehicle part with the tool. Alternatively, or in addition, the user 102 may speak into the input unit 108 an indication that the user 102 is repairing a vehicle, such as “Hey, I'm trying to repair this engine for a 1982 Car Make X, Car Model Y, can you help me?” or “Hey, teach me how to replace a gasket in an engine.” In addition, the user 102 may type into the input unit 108 an indication that the activity the user 102 is engaged in is repairing a vehicle. As described herein, the learned model may be updated to provide a most up-to-date and accurate guidance or feedback possible.

The device 100 may output an output 104 that is feedback. The device 100 may determine, based on image data that the user 102 has not forgotten to replace a removed engine component, and the device 100 may output an output 104 such as “You might want to check if you replaced all of the bolts.” The user 102 may prompt the device 100 for feedback using the input unit 108. For example, the user 102 may say “Hey, did I miss anything when putting this engine back together?” and the device 100 may, based on detected image data, determine a response to the prompt provided by the user 102.

The device 100 may output an output 104 that is guidance. The device 100 may determine, based on image data, that the user has finished performing a step in a series of instructions. For example, the device 100 may detect that the user 102 has finished removing the bolts, and that the user 102 should next remove the cover plate and clean the surface of debris. The device 100 may provide an output 104 that is an instruction, such as “Next, after you remove the bolts, remove the cover plate and clean the surface of any debris.”

FIG. 1C illustrates a user 102 wearing a device 100, a second user 132 wearing a second device 130, and a third device 134. The device 100 may also be used with other devices (e.g., second device 130 and third device 134) to provide guidance or feedback to the user 102. In some situations, the camera 106 of the device 100 may be unable to view the user 102 or the user's actions to properly assess the user's performance. In other situations, the device 100 may benefit from having additional image data of different angles of the activity being performed by the user 102 to provide more comprehensive feedback to the user 102.

As illustrated in FIG. 1C, the user 102 is performing an activity of playing golf. The device 100 may identify that the user 102 is playing golf. The device 100 may use location data to determine that the user 102 is playing golf, when the location data indicates that the device 100 and the user 102 are at a golf course.

The device 100 may detect image data using a camera 106 and the device 100 may analyze the detected image data to determine that the user 102 is playing golf. The detected image data may be the user 102 carrying a set of golf clubs. The device 100 may compare the detected image data with a learned model to determine that the activity performed by the user 102 is playing golf. The learned model may include objects 112 such as a golf club, wide areas of grass, or a golf ball. Alternatively, or in addition, the user 102 may speak into the input unit 108 an indication that the user 102 is playing golf, such as “Hey, I'm playing golf, how does my swing look?” or “Hey, teach me how to swing a 5 iron properly.” In addition, the user 102 may type into the input unit 108 an indication that the activity the user 102 is engaged in is playing golf.

The device 100 may not be able to view the user's swing and form from the perspective of the user 102. The device 100 may communicate with other devices, such as second device 130 or third device 134, to evaluate the user's actions, to provide feedback. The device 100 may communicate directly with the other devices using a device-to-device protocol such as Bluetooth or Wi-Fi Direct. The device 100 may communicate with the other devices via a remote server, such as a cloud based server, whereby the other devices (e.g., the second device 130 and the third device 134) communicate image data to the cloud based server, and the device 100 retrieves the image data from the cloud based server.

The other devices, such as the second device 130 and the third device 134 may be wearable devices with cameras or may be other devices, such as a tablet, a smartphone, or a camera. In FIG. 1C, the second device 130 is another wearable device similar to the device 100 of the user 102, and the third device is a tablet mounted to a stand. The second device 130 has a camera 136 and the third device has a camera 138.

The second device 130 may detect image data of the user 102 swinging the golf club from an angle that the device 100 is unable to capture using the camera 106 of the device 100. Likewise, the third device 134 may further detect image data of the user 102 swinging the golf club from another angle that neither the device 100 nor the second device 130 are able to capture using their respective cameras.

The device 100, based on the image data from the device 100, the second device 130, and the third device 134, may evaluate the user's performance of the activity based on the image data to provide feedback. The learned model may further include criteria by which the user's actions should be compared and the device 100 may determine the feedback based on a comparison of the user's performance and the criteria.

The device 100 may output an output 104 that is feedback. The feedback may be critiques of the user's performance, such as “You should keep your back straight.” The user 102 may prompt the device 100 for feedback using the input unit 108. For example, the user 102 may say “Hey, was my left aim straight?” and the device 100 may, based on detected image data, determine a response to the prompt provided by the user 102.

The device 100 may output an output 104 that is guidance. The device 100 may determine, based on image data, that the user has finished performing a step in a series of instructions. For example, the device 100 may detect that the user 102 has finished gripping the club and getting ready to swing, and that the user 102 should next bring the club back for the backswing. The device 100 may provide an output 104 that is an instruction, such as “Next, after you address the ball, begin your backswing, making sure to keep your left arm straight, your hips turned, your back straight, and your front heel on the ground.” The guidance provided by the device 100 may be particularly useful when there are many things to remember at once, and doing so may be challenging for a human being.

The guidance provided by the device 100 may also be particularly useful when the user 102 has never performed a particular activity or when a situation is an emergency. For example, as illustrated in FIG. 1D, the user 102 is administering first aid to a victim 142. The user 102 may be performing cardiopulmonary resuscitation (CPR) on the victim 142.

The device 100 may identify that the user 102 is performing CPR. The device 100 may detect image data using a camera 106 and the device 100 may analyze the detected image data to determine that the user 102 is performing CPR. The device 100 may compare the detected image data with a learned model to determine that the activity performed by the user 102 is performing CPR. Alternatively, or in addition, the user 102 may speak into the input unit 108 an indication that the user 102 is performing CPR, such as “Hey, my friend was drowning, but we got him out of the water and he's not breathing, can you help me?” or “Hey, teach me how to perform CPR.” In addition, the user 102 may type into the input unit 108 an indication that the activity the user 102 is engaged in is performing CPR.

The device 100 may output an output 104 that is feedback. The device 100 may determine, based on image data that the user 102 has not performed enough chest compressions, and the device 100 may output an output 104 such as “You are not pumping rapidly enough in your chest compressions—the target is 100-120 times per minute, or more than one per second.” The user 102 may prompt the device 100 for feedback using the input unit 108. For example, the user 102 may say “Hey, is this location the right one for chest compressions?” and the device 100 may, based on detected image data, determine a response to the prompt provided by the user 102.

The device 100 may output an output 104 that is guidance. The device 100 may determine, based on image data, that the user has finished performing a step in a series of instructions. For example, the device 100 may detect that the user 102 has finished performing chest compressions, and that the user 102 should next blow into the victim's mouth. The device 100 may provide an output 104 that is an instruction, such as “Next, after chest compressions, you should tilt the victim's head back, lift the chin, pinch the nose, cover the mouth with yours and blow until you can see the victim's chest rise.”

As described herein, the learned model and/or other data used by the device 100 to provide guidance or feedback may be stored locally on the device 100 or stored on a remote memory and accessed by the device 100. The learned model and/or other data may be updated periodically so that the feedback and/or guidance provided is up-to-date and current. For example, when general first aid guidelines change, the device 100 is able to provide the updated instructions. In this way, use of the device 100 may be superior to relying on human knowledge, which may become outdated and/or inaccurate.

The device 100 may provide situationally appropriate guidance or feedback without being prompted by the user 102 based on the detected activity. For example, when the device 100 detects an individual in distress, the device 100 may automatically provide CPR instructions to the user 102.

The output 104 provided by the device may be feedback or a reminder associated with a behavior identified by the user 102. The behavior may be a limitation of an undesirable behavior. For example, as shown in FIG. 1E, the user 102 may indicate to the device 100 that the user would like to limit consumption of a particular beverage, such as soda or coffee. The device 100 may detect, based on image data detected from the camera 106 that the user 102 is consuming the beverage and may provide an output 104 reminding the user 102 of the restriction. The output 104 may be an audio output of “Remember to watch your consumption of coffee.” The device 100 may detect an object 112 associated with the particular beverage. The output 104 may be a tactile output of a series of vibrations when the device 100 determines the user 102 is participating in the undesirable behavior.

The behavior may also be a limitation of calories consumed throughout the day. The camera 106 may detect image data of food as the user 102 is eating the food. The device 100 may identify the food being eaten based on the image data, and may determine nutritional data associated with the identified food. The nutritional data may be stored in a local or remote memory or may be provided by the user 102. The user 102 may provide the nutritional data by identifying values of categories, such as calories, fat, sugar, or ingredients. The user 102 may also provide the nutritional data by holding up a nutritional label associated with the food so the camera 106 may capture an image of the nutritional label.

The device 100 may determine nutritional feedback for the user 102, such as “You have consumed your daily allotment of sugar and it is only 11 AM. You may consider limiting your sugar intake for the rest of the day or exercising.” The device 100 may include an inertial measurement unit (IMU) for detecting user activity to determine an approximate calories burned by the user 102. The nutritional feedback provided by the device 100 may vary based on the user's activity, as detected by the IMU.

In addition to the image data detected by the camera 106, the device 100 may use a microphone to detect audio data. The device 100 may use the audio data to assist in determining the user 102 is participating in an activity. For example, as shown in FIG. 1F, the user 102 may instruct the device 100 to notify the user when the user says the word “umm.” The device 100 may detect audio data using the microphone, and when the device 100 detects the user 102 has said “umm,” the device 100 may output an output 104 that is an audio output or a tactile output to indicate to the user 102 that the user 102 has said “umm.”

The output 104 may be information associated with a detected object. For example, as shown in FIG. 1G, the device 100 may determine, using image data detected by the camera 106, that the user 102 is looking at an object 112, such as a painting 170. The device 100 may identify the painting 170 by comparing the image data associated with the painting with a database of paintings. In addition, the device 100 may determine a location of the user 102 based on the location data and may identify a painting associated with the location, as the location may be a museum or other landmark.

In the example embodiment of FIG. 1G, the output 104 may be information regarding the painting 170, such as the artist, the year it was painted, the style of painting, the circumstances surrounding the painting, and a history of owners of the painting. The user 102 may provide an input to the device 100 inquiring about the object 112 (e.g., painting 170), or the device 100 may automatically provide the output 104 based on identifying the object 112 based on the image data.

The output 104 may be a location-based reminder to the user 102. For example, the user 102 may indicate to the device 100 that the user 102 would like to be reminded when the user 102 leaves his house, that the user 102 should make sure he has his wallet, keys, and cell phone. The device 100 may detect, based on location data detected by a GPS unit, the location of the user 102. When the user 102 is in a first location within the user's home and then goes to a second location outside of the user's home (as detected by the location data), the device 100 may provide the output 104 reminding the user 102. The output 104 may be an audio output such as “Don't forget your keys, wallet, and phone,” or may be a tactile output of a series of vibrations.

In one implementation, and with reference to FIG. 2, a device 100 includes a guidance unit 202, connected to a memory 204, a sensor array 206, an output unit 208, a transceiver 210, an activity detection unit 212, and an input unit 108.

The guidance unit 202 may be one or more computer processors such as an ARM processor, DSP processor, distributed processor, microprocessor, controller, or other processing device. The guidance unit 202 may be located in the device 100, may be a remote processor or it may be a pairing of a local and a remote processor.

The memory 204 may be one or any combination of the following: a RAM or other volatile or nonvolatile memory, a non-transitory memory or a data storage device, such as a hard disk drive, a solid state disk drive, a hybrid disk drive or other appropriate data storage. The memory 204 may further store machine-readable instructions which may be loaded into or stored in the memory 204 and executed by the guidance unit 202. As with the guidance unit 202, the memory 204 may be positioned on the device 100, may be positioned remote from the device 100 or may be a pairing of a local and a remote memory. The memory 204 may also store learned model data, such that the activity detection unit 212 may compare the image data to the learned model data to determine an activity and/or the guidance unit 202 may compare the image data to the learned model data to determine guidance or feedback. The memory 204 may also store past performance data associated with the user performing the activity. The output 104 may be determined based on the past performance data. For example, in FIG. 1A when the user 102 is making cookies, the output may include a reminder that the last time the user made cookies, the user 102 forgot to take them out of the oven in time. In another example, in FIG. 1C when the user is playing golf, the output may include a reminder that the user's average score for this particular course is 82, that the user 102 typically shoots par on this particular hole, or that the user should use a particular club for that particular hole.

The sensor array 206 includes a camera 106, stereo cameras 216, a GPS unit 218, an inertial measurement unit (IMU) 220, and a sensor 222. The stereo cameras 216 may be a stereo camera pair including two cameras offset by a known distance. In that regard, the guidance unit 202 may receive image data from the stereo cameras 216 and may determine depth information corresponding to objects in the environment based on the received image data and the known distance between the cameras of the stereo cameras 216. The stereo cameras 216 may be used instead of or in conjunction with the camera 106 to detect image data. The sensor 222 may be one or more sensors which provide further information about the environment in conjunction with the rest of the sensor array 206 such as one or more of a temperature sensor, an air pressure sensor, a moisture or humidity sensor, a gas detector or other chemical sensor, a sound sensor, a pH sensor, a smoke detector, an altimeter, a depth gauge, a compass, a motion detector, a light sensor, or other sensor. The GPS unit 218 may detect location data and may be used to determine a geographical location. The map data stored in the memory 204 may also be used to determine the geographical location.

The output unit 208 includes a speaker 110 and a vibration unit 224. The speaker 110 may be one or more speakers or other devices capable of producing sounds and/or vibrations. The vibration unit 224 may be one or more vibration motors or actuators capable of providing haptic and tactile output.

The transceiver 210 can be a receiver and/or a transmitter configured to receive and transmit data from a remote data storage or other device. The transceiver 210 may include an antenna capable of transmitting and receiving wireless communications. For example, the antenna may be a Bluetooth or Wi-Fi antenna, a cellular radio antenna, a radio frequency identification (RFID) antenna or reader and/or a near field communication (NFC) unit.

In another implementation and with reference to FIG. 3, the system 300 may include a device 100 and a secondary device 302. The device 100 is a wearable device, as described herein and includes the sensor array 206, the input unit 108, the output unit 208, and the device transceiver 304. The secondary device 302 may be a device communicatively coupled with the device 100 and configured to perform the processing of the detected data.

The secondary device 302 may be a smartphone or tablet and includes the guidance unit 202, memory 204, a secondary device transceiver 306, and an activity detection unit 212. In the system 300 of FIG. 3, the device 100 may not be responsible for the processing of the detected data, such as the image data and the location data. The device 100 may communicate the detected data to the secondary device 302 via the respective transceivers (device transceiver 304 and secondary device transceiver 306).

Turning to FIG. 4, the device 100 may be a wearable device, which has an outer casing, or body 402 having a shape designed to be worn by a user. In particular, the body 402 has a neck portion 404 designed to rest against a back of a neck of the user. The body 402 also includes a first side portion 406 and a second side portion 408 each configured to extend across a shoulder of the user and to rest on a front of the user. In that regard, the wearable device 100 may be worn in a similar manner as a necklace. Although the disclosure is directed to the wearable device 100 having the U-shape, one skilled in the art will realize that the features described herein can be implemented in a wearable computing device having another shape such as eyeglasses or earpieces.

The wearable device 100 includes multiple components capable of receiving or detecting data. For example, the wearable device 100 may include an input unit 108, a microphone 418, and a camera 106 and/or a stereo pair of cameras (e.g., stereo cameras 216), each as described herein. The input unit 108 may include one or more buttons and/or a touchpad. Each of the input unit 108, the camera 106, and the microphone 418 may be physically attached to the body 402.

In some embodiments, the microphone 418 is part of the input unit 108. The microphone 418 may be capable of detecting audio data corresponding to the environment of the wearable device 100. For example, the microphone 418 may be capable of detecting speech data corresponding to speech of the user or of another person. In some embodiments, the user may provide input data to the guidance unit 202 by speaking commands that are received by the microphone 418. The microphone 418 may also be capable of detecting other sounds in the environment such as a scream, a siren from an emergency vehicle, or the like.

The wearable device 100 includes one or more output devices including speakers 110. The speakers 110 are physically attached to the body 402. Each of the speakers 110 is configured to output an audio output based on an instruction from the guidance unit 202. The speakers 110 may be part of the output unit 208, as described herein.

In some embodiments, as shown in FIG. 2, the wearable device 100 also includes the guidance unit 202, the memory 204, and the activity detection unit 212 physically within the wearable device 100.

In other embodiments, as shown in FIG. 3, the wearable device 100 only includes the camera 106, the input unit 108, and the speakers 110 physically within the wearable device 100. In these embodiments, the guidance unit 202, the memory 204 and the activity detection unit 212 are physically located in a secondary device 302, such as a smartphone or a tablet computer. As described herein, the components located in the wearable device 100 and the components located in the secondary device 302 are communicatively coupled and may communicate via respective transceivers configured to transmit and receive data (e.g., device transceiver 304 and secondary device transceiver 306).

With reference now to FIG. 5, a method 500 may be used by a device (e.g., device 100) or a system (e.g., system 300) for providing feedback to a user.

The image data is detected by the camera 106 and/or the stereo cameras 216 of the device 100 (step 502). The image data may indicate a user performance of an activity. The guidance unit 202 identifies the activity (step 504). The activity detection unit 212 connected to the guidance unit 202 may detect the activity based on the image data, and the activity detection unit 212 may communicate the identified activity to the guidance unit 202 (step 506). Alternatively, or in addition, the input unit 108 may detect input data from the user indicating the activity and the input unit 108 may communicate the identified activity to the guidance unit 202 (step 508).

The guidance unit 202 determines a criteria associated with the activity (step 510). The criteria associated with the activity may be determined based on the learned model stored in the memory 204. The guidance unit 202 may analyze the learned model to determine a criteria to identify in order to determine whether the user 102 is properly performing the activity.

The guidance unit 202 determines a user performance of the activity based on the image data (step 512). The guidance unit 202 may perform image processing on the image data to construct a model of the user performance.

The guidance unit 202 determines feedback based on a comparison of the criteria and the user performance of the activity (step 514). The feedback indicates an improvement or suggestion for the user, such as a suggestion to check an amount of an ingredient in a recipe (as shown in FIG. 1A), an improvement to the user's form in a sports activity (as shown in FIG. 1C), a suggestion to the user 102 in the form of relevant information regarding an object near the user 102 (as shown in FIG. 1G), or a suggestion to the user 102 to make sure the user has certain items in the user's possession (as shown in FIG. 1H).

The guidance unit 202 communicates the feedback to the output unit 208 and the output unit 208 outputs the feedback to the user 102 (step 516). For example, the output unit 208 includes a speaker 110 and the speaker outputs an audio output of the feedback.

With reference now to FIG. 6, a method 600 may be used by a device (e.g., the device 100) or a system (e.g., the system 300) for providing guidance to a user.

The image data is detected by the camera 106 and/or the stereo cameras 216 of the device 100 (step 602). The image data may indicate a user performance of an activity. The guidance unit 202 identifies the activity (step 604). An activity detection unit 212 connected to the guidance unit 202 may detect the activity based on the image data, and the activity detection unit 212 may communicate the identified activity to the guidance unit 202 (step 606). Alternatively, or in addition, the input unit 108 may detect input data from the user indicating the activity and the input unit 108 may communicate the identified activity to the guidance unit 202 (step 608).

The guidance unit 202 determines a set of instructions associated with the activity (step 610). The set of instructions associated with the activity may be determined based on the learned model stored in the memory 204. The guidance unit 202 may analyze the learned model to determine a set of instructions to provide to the user 102 or the guidance unit 202 may retrieve the set of instructions from the memory 204. The set of instructions in the memory 204 may be indexed by activity, allowing the guidance unit 202 to retrieve a set of instructions corresponding to a given activity.

The guidance unit 202 determines a current stage of the activity based on the image data (step 612). The guidance unit 202 may perform image processing on the image data to determine an action being performed, and the determined action being performed may be associated with a corresponding current stage of the activity.

The guidance unit 202 determines a next instruction from the set of instructions to provide the user based on the current stage (step 614). The set of instructions may be an ordered list of instructions such that for each instruction there is a next instruction, unless the current instruction is the final stage of the activity. For example, the current stage of the activity may be adding flour to a bowl and the next instruction may be to add chocolate chips (as shown in FIG. 1A).

The guidance unit 202 communicates the next instruction to the output unit 208 and the output unit 208 outputs the next instruction to the user 102 (step 616). For example, the output unit 208 includes a speaker 110 and the speaker 110 outputs an audio output of the next instruction.

Exemplary embodiments of the methods/systems have been disclosed in an illustrative style. Accordingly, the terminology employed throughout should be read in a non-limiting manner. Although minor modifications to the teachings herein will occur to those well versed in the art, it shall be understood that what is intended to be circumscribed within the scope of the patent warranted hereon are all such embodiments that reasonably fall within the scope of the advancement to the art hereby contributed, and that that scope shall not be restricted, except in light of the appended claims and their equivalents.

Claims

1. A wearable neck device for providing guidance or feedback to a user, the wearable neck device comprising: a body having a neck portion configured to rest against a back of a neck of the user, a first side portion connected to the neck portion, and a second side portion connected to the neck portion, the first side portion configured to extend across a first shoulder of the user and rest on a front body portion of the user and the second side portion configured to extend across a second shoulder of the user and rest on the front body portion of the user;a camera located on the first side portion or the second side portion and configured to detect image data of a first angle of a user performance of an activity;a GPS unit located within the body and configured to detect location data;a memory located within the body and configured to store a learned model associated with the activity;an activity detection unit located in the body, connected to the camera and the GPS unit, and configured to automatically analyze the image data to identify a presence of one or more objects associated with the activity, compare the one or more objects associated with the activity to the learned model and identify the activity based on the location data and the comparison of the one or more objects associated with the activity to the learned model;a guidance unit located in the body, connected to the camera and the IMU, and configured to: obtain, from a second camera of another device, additional image data of a second angle of the user performance of the activity,determine a series of instructions associated with the activity and including a plurality of steps to be performed by the user based on the learned model,determine an action being performed within the detected image data,determine a current step of the plurality of steps of the series of instructions associated with the activity that is being performed based on the action,determine that the current step of the activity has been completed based on the image data of the first angle of the user performance of the activity and the additional image data of the second angle of the user performance of the activity, anddetermine an instruction associated with a next step within the series of instructions in response to determining that the current step has been completed; andan output unit located on the body, connected to the guidance unit, and configured to output the instruction to the user.

2. The wearable neck device of claim 1, further comprising an input unit configured to detect input data from the user identifying the activity.

3. The wearable neck device of claim 1, wherein the learned model stored in the memory is periodically updated.

4. The wearable neck device of claim 1, wherein the output unit includes a speaker configured to provide an audio output or a vibration unit configured to provide a tactile output.

5. The wearable neck device of claim 1, wherein the one or more objects identified by the activity detection unit are one or more stationary objects unconnected to the user.

6. A wearable neck device for providing guidance or feedback to a user, the wearable neck device comprising: a body having a neck portion configured to rest against a back of a neck of the user, a first side portion connected to the neck portion, and a second side portion connected to the neck portion, the first side portion and the second side portion configured to extend across a shoulder of the user and rest on a front body portion of the user;a camera located on the first side portion or the second side portion and configured to detect image data of a first angle of a user performance of an activity;an inertial measurement unit (IMU) located within the body and configured to detect movement data associated with the user during the user performance of the activity;a GPS unit located within the body and configured to detect location data;an activity detection unit connected to the camera and the GPS unit, and configured to: automatically analyze the image data to identify the activity based on a presence of one or more objects associated with the activity, andidentify the activity based on the presence of the one or more objects associated with the activity and the location data;a guidance unit connected to the camera and the IMU, and configured to: obtain, from a second camera of another device, additional image data of a second angle of the user performance of the activity,determine a series of instructions associated with the activity and including a plurality of steps to be performed by the user,determine an action being performed within the image data,determine a current step of the plurality of steps of the series of instructions associated with the activity that is being performed based on the image data, the additional image data and the movement data,determine that the current step of the activity has been completed based on the image data of the first angle of the user performance of the activity and the additional image data of the second angle of the user performance of the activity, anddetermine a instruction associated with a next step within the series of instructions; andan output unit connected to the guidance unit, the output unit configured to output the instruction.

7. The wearable neck device of claim 6, further comprising an input unit configured to detect input data from the user indicating the activity.

8. The wearable neck device of claim 6, further comprising: a memory configured to store a learned model;wherein the guidance unit is configured to determine that the current step of the activity has been completed by comparing the image data to the learned model stored in the memory.

9. The wearable neck device of claim 6, wherein the output unit includes a speaker configured to provide an audio output or a vibration unit configured to provide a tactile output.

10. A method of providing guidance or feedback to a user of a wearable neck device, the method comprising: providing, by the wearable neck device, a body having a neck portion configured to rest against a back of a neck of the user, a first side portion connected to the neck portion, and a second side portion connected to the neck portion, the first side portion configured to extend across a first shoulder of the user and rest on a front body portion of the user and the second side portion configured to extend across a second shoulder of the user and rest on the front body portion of the user;detecting, by a camera located on the first side portion or the second side portion of the body of the wearable neck device, image data of a first angle of a user performance of an activity;detecting, by a GPS unit, location data associated with the wearable neck device;storing, by a memory located within the body, a learned model associated with the activity;automatically analyzing, by an activity detection unit, the image data to identify a presence of one or more objects;identifying, by the activity detection unit, the presence of the one or more objects associated with the activity;comparing, by the activity detection unit, the one or more objects associated with the activity to the learned model;identifying, by the activity detection unit, the activity based on the location data and the comparison of the one or more objects associated with the activity to the learned model;obtaining, by a guidance unit and from a second camera of another device, additional image data of a second angle of the user performance of the activity;determining, by the guidance unit, a series of instructions associated with the activity and including a plurality of steps to be performed by the user based on the learned model;determining, by the guidance unit, an action being performed within the image data;determining, by the guidance unit, a current step of the plurality of steps of the series of instructions associated with the activity that is being performed based on the action;determining, by the guidance unit, that the current step of the activity has been completed based on the image data of the first angle of the user performance of the activity and the additional image data of the second angle of the user performance of the activity;determining, by the guidance unit, an instruction associated with a next step within the series of instructions; andoutputting, by an output unit located on the body, the instruction.

11. The method of claim 10, wherein identifying the activity includes receiving, by an input unit, input data from the user indicating the activity.

12. The method of claim 10, wherein the method further comprises periodically updating the learned model stored in the memory.