GB2617562A

GB2617562A - Apparatus to monitor mental attention

Info

Publication number: GB2617562A
Application number: GB2205268.2A
Authority: GB
Inventors: Norbury Mathew; Moore Dave
Original assignee: Fc Laboratories Ltd
Current assignee: Fc Laboratories Ltd
Priority date: 2022-04-11
Filing date: 2022-04-11
Publication date: 2023-10-18
Also published as: WO2023199046A1; GB202205268D0

Abstract

A system 10 comprises a wearable device 20 having a sensor array (210, fig.2) to collect biometric data by functional near-infrared spectroscopy (fNIRS) and apparatus 30 with processing circuitry (320, fig.3) to analyse the biometric data to obtain a mental attention metric, which may include haemodynamic information of a pre-frontal cortex for comparison to a threshold defining a predetermined mental attention level. Analysis may be based on a modified Beer-Lambert law and may include classification using a trained classifier. Based on the comparison, a signal indicative of the mental attention level of the user is output. The signal may indicate that mental attention of the user is low and perhaps unsafe and may be a visual, haptic or audio indication. The system 20 may comprise a motion sensor to obtain motion data, which may be used to compensate for poor quality light absorption data. The apparatus 30 may be integrated with the wearable device 20. Biometric data may be encrypted and may be stored in a database (330, fig.3) to be retrieved and analysed to determine a trend of the mental attention of the user.

Description

Apparatus to Monitor Mental Attention [0001] The present disclosure relates to an apparatus to monitor mental attention, and a corresponding system, method and machine readable instructions.

BACKGROUND

[0002] Many industrial jobs involve manual operation, where a high level of alertness is desirable by the operator at all times during operation in often high-risk and fatigue-prone environments. Such jobs may include for example truck drivers, for whom staying alert whilst they are behind the wheel is important to promote safety for both the driver and any surrounding drivers. In particular, any fall in the mental attention of the driver may increase the risk of accidents occurring. Construction workers or operators of industrial machinery provide further examples of where user attention is important to maintain safety.

[0003] It is therefore an object of the present disclosure to overcome at least one of the problems in the prior art.

BRIEF SUMMARY OF THE DISCLOSURE

[0004] In accordance with a first aspect of the present disclosure, there is provided an apparatus to monitor mental attention. The apparatus comprises processing circuitry. The processing circuitry is arranged to obtain biometric data comprising light absorption data obtained by performing functional near-infrared spectroscopy (fNIRS). The processing circuitry is arranged to analyse the biometric data. The processing circuitry is arranged to obtain information corresponding to a mental attention metric based on the analysed biometric data. The processing circuitry is arranged to compare the obtained information to a threshold to determine if the user has attained at least a predetermined mental attention level. The processing circuitry is arranged to output a signal indicative of the mental attention level of the user based on the comparison.

[0005] By analysing the fNIRS biometric data to obtain the mental attention metric, the apparatus ascertains whether a mental attention level of a user is effectively at a safe level or not. In doing so, this efficiently improves safety by facilitating regular monitoring of mental attention levels and signalling alerts in real-time when the mental attentiveness drops. Any interested person, such as the user, the employer, etc. can therefore be notified of the user's attention level, such as when the user's attention drops below the threshold and/or when the user's attention is above the threshold. This is beneficial in high risk environments and jobs, where consistent high levels of mental attentiveness are paramount, since the risk of accidents may be reduced. Even in a lower risk environment such as a desk job, a reduced focus level of a person may result in poorer work output as compared to when they have a high level of alertness, and may therefore also benefit from the present disclosure. For example an individual user may use the mental attention monitoring to track, understand and improve their own productivity.

[0006] The threshold may be predetermined. This may be beneficial by allowing a user to set the threshold, for example via the first and/or second electronic device. In doing so, the wearer and/or employer may set the threshold, thereby facilitating tailored mental attentiveness monitoring and alerts according to the wearer's environment. Alternatively, the threshold may be adaptable by a user or dynamically changed based, for example, on a change to a user's environment.

[0007] The signal indicative of the mental attention of the user may be output if the predetermined attention level has not been attained based on the comparison. The signal may be indicative that the mental attention level of the user is low. The signal indicative of the mental attention of the user may be output if the predetermined attention level has been attained based on the comparison. The signal may be indicative that the mental attention level of the user is high. When such a high attention level signal is absent, it can be deduced that a mental attention level of the user is low.

[0008] The light absorption data may comprise fNIRS short channel data and fNIRS long channel data. The processing circuitry may be arranged to analyse the biometric data by subtracting the short channel data from the long channel data for modelling light absorption from a user's pre-frontal cortex. The short channel data may be for modelling light transmission through a user's skin. By subtracting the short channel data from the long channel data, the light absorption data may be processed to reduce the effects of light transmission through the skin for accurately obtaining the mental attention level of the user.

[0009] The apparatus may comprise a sensor arrangement to perform fNIRS to obtain the light absorption data, rather than to receive the fNIRS data from a separate sensing device. The apparatus may comprise a wearable device arranged to perform fNIRS for determining a mental attention level of a user. The wearable device may be arranged to be head mountable. The wearable device may further comprise a frame for mounting the at least two sensors on a forehead of a user.

[0010] The biometric data may further comprise motion data associated with the light absorption data. The processing circuitry may be further arranged to analyse the light absorption data in dependence of the motion data, wherein the motion data is used to compensate for poor quality light absorption data. The processing circuitry may identify light absorption data deemed to be corrupted by a motion artifact, based on the motion data. The processing circuitry may be arranged to exclude from light absorption data, data deemed to be corrupted by motion artifact from the biometric data that is analysed. Therefore, the accuracy of the analysis may be further improved.

[0011] The apparatus may comprise a motion sensor arranged to detect the motion data. The motion sensor may include an accelerometer. The accelerometer may be a three-axis accelerometer.

[0012] Prior to analysing the biometric data, the processing circuitry may be further arranged to receive, from a first electronic device, the biometric data. The apparatus to monitor mental attention may comprise a server. The apparatus may comprise communication circuitry. The apparatus may be in wireless communication with a first electronic device. The first electronic device may be a portable device. The first electronic device may be a wearable device, such as a watch. The first electronic device may be a device having a display, such as a mobile phone, which may be associated with the wearer of the wearable device. The first electronic device may be in communication with an fNIRS device. In doing so, the first electronic device may act as a conduit between the fNIRS device and the apparatus to monitor mental attention, whilst also facilitating alerting the user when the attention level has not been attained. The second electronic device may be a portable device, such as a mobile phone. The second electronic device may belong to an employer or other person of interest to facilitate alerts when the wearer's attentiveness drops.

[0013] The light absorption data may include wavelength data from in a range from 700 nm to 900 nm or spanning the full range or a portion of the range. The fNIRS sensor may detect light absorption of wavelengths from 735 nm to 850 nm.

[0014] The information corresponding to the mental attention metric may include haemodynamic information of a pre-frontal cortex of the brain of a user of the apparatus to monitor mental attention.

[0015] The processing circuitry may be arranged to analyse the biometric data based on a modified Beer-Lambert law.

[0016] The processing circuitry may be arranged to classify the analysed biometric data to obtain the information, wherein the analysed biometric data is classified using a trained classifier. The apparatus may comprise storage circuitry for storing the trained classifier.

The trained classifier may use a rule-based algorithm, or machine-learning.

[0017] The signal may be for indicating that the user is unsafe. This is beneficial, for example, for monitoring focus levels in high risk jobs, such as truck drivers.

[0018] The apparatus may be arranged to encrypt the biometric data. In doing so, the user's biometric data may be securely obtained and perhaps stored.

[0019] The processing circuitry may be further arranged to store, in a database, the biometric data, the time of detection and the obtained information corresponding to the mental attention metric. The stored biometric data may be labelled such that it may be attributed to a given user or user group.

[0020] The processing circuitry may be further arranged to retrieve, from the database, stored biometric data detected at a plurality of times and corresponding information of a mental attention metric associated with the stored biometric data. The processing circuitry may be arranged to analyse the retrieved data and corresponding information and the obtained information. The processing circuitry may be arranged to determine a trend of the mental attention of the user based on the analysed retrieved data and corresponding information and the obtained information. The trend may be determined using machine learning. For example, a neural network based machine learning model may be used. The trend may be determined using a model, such as a rules-based algorithm. The apparatus may comprise storage circuitry for storing the model. Biometric data of a plurality of users may be stored on the database. The processing circuitry may be arranged to analyse the retrieved data and corresponding information by comparing one from among the stored biometric data and the corresponding information with another from among the stored biometric data and the corresponding information. By comparing the analysed biometric data with historical data at different times, the trend may indicate when the mental attentiveness of a given user or a user group comprising two or more users changes over time, for example over the course of a day/week.

[0021] The processing circuitry may be arranged to output information corresponding to the analysed trend.

[0022] In accordance with a second aspect of the present disclosure, there is provided a system for monitoring mental attention. The system comprises the apparatus as described hereinbefore, and a first electronic device arranged to receive the signal. In response to receiving the signal, the first electronic device is arranged to output an indication associated with the mental attention level of the user. Accordingly, a user may be notified with immediate effect that the mental attentiveness of the wearer is low. Alternatively, an indication that the mental attention level of a user is high or at least above a desired threshold may be output. When such a high attention level signal is absent it can be deduced that a mental attention level of the user or user group is low.

[0023] The first electronic device may be arranged to display the indication. The first electronic device may be arranged to haptically output the indication. The first electronic device may be arranged to audibly output the indication. The indication may be an alert or notification. Haptic and/or audio indications may be beneficial for alerting the user in scenarios where the first electronic device is not a mobile device, but rather a wearable watch device or the like.

[0024] The first electronic device may be arranged to display information corresponding to the analysed trend. Accordingly, the user is provided with visual feedback of their attentiveness over time.

[0025] The system may further comprise a second electronic device. If the obtained information is below the threshold, the apparatus may be further arranged to output, to the second electronic device, the signal, and in response to receiving the signal, the second electronic device is arranged to output an indication that the mental attention level of the user is low. The second electronic device may be arranged to at least one of visually, haptically and audibly output the indication. By notifying a second electronic device of the wearer's mental attentiveness dropping, a further person such as an employer may be beneficially notified when the mental attentiveness of the user drops below the threshold. Alternatively, an indication that the mental attention level of a user is high or at least above a desired threshold may be output. When such a high attention level signal is absent it can be deduced that a mental attention level of the user or user group is low.

[0026] The system may further comprise a wearable device arranged to perform functional near-infrared spectroscopy, fNIRS, for determining a mental attention level of a user and arranged to output biometric data including light absorption data. The wearable device may be arranged to be head mountable. The wearable device may further comprise a frame for mounting the at least two sensors on a forehead of a user.

[0027] The wearable device may be arranged to output the biometric data to the first electronic device. In doing so, the first electronic device may act as a conduit between the wearable device and the apparatus. The wearable device may comprise a wireless communication circuit for wirelessly communicating with the first electronic device. The wearable device may comprise one or more processors arranged to control the wireless communication circuit to output, to the first electronic device, the light absorption data.

[0028] The wearable device may comprise a multichannel array of light sources and detectors. The multichannel array may include at least one short channel and at least one long channel. The detectors may comprise photodiodes. The wearable device may comprise at least two light sources associated with each photodiode. The at least one short channel may be arranged to detect light at a distance of 10 mm from the detectors. The at least one long channel may be arranged to detect light at a distance of 30 mm from the detectors. The wearable device may be arranged to process raw biometric data to obtain and output haemodynamic information.

[0029] The wearable device may comprise a motion sensor such as an accelerometer arranged to detect motion, wherein the wearable device is arranged to output motion data. The accelerometer may be a three-axis accelerometer. The wearable device may be arranged to output the motion data to the first electronic device.

[0030] The wearable device may be arranged to perform fNIRS repetitively such as at regular intervals or at irregular intervals. In doing so, consistent monitoring may be performed, thereby improving the accuracy of the determined trend.

[0031] The wearable device may be arranged to perform fNIRS over a predetermined window of time. This beneficially facilitates in taking data over a more continuous window of time rather than as snapshots. The duration of the time window over which the fNIRS is performed may be adapted based on a user environment or based on feedback from results of the analysis such as an accuracy estimate of the determined mental attention level.

[0032] In accordance with a third aspect of the present disclosure, there is provided a method for monitoring mental attention. The method comprises obtaining biometric data comprising light absorption data, the light absorption data obtained by performing functional near-infrared spectroscopy, fNIRS. The method comprises analysing the biometric data. The method comprises obtaining information corresponding to a mental attention metric based on the analysed biometric data. The method comprises comparing the obtained information to a threshold to determine if the user has attained at least a predetermined mental attention level. The method comprises outputting a signal indicative of the mental attention level of the user based on the comparison.

[0033] The obtaining the biometric data may comprise performing functional near-infrared spectroscopy, fNIRS. The obtaining the biometric data may comprise obtaining motion data. The method may further comprise outputting the biometric data.

[0034] The method may further comprise, in response to receiving the signal, outputting at least one of a visual, haptic and audio indication associated with the mental attention level of the user.

[0035] In accordance with a fourth aspect of the present disclosure, there is provided machine readable instructions which, when executed by processing circuitry, cause the processing circuitry to carry out a method as described herein.

[0036] In accordance with a fifth aspect of the present disclosure, a computer readable data storage medium having tangibly stored thereon the machine readable instructions as described herein.

BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Embodiments of the disclosure are further described hereinafter with reference to the accompanying drawings, in which: Fig. 1 is a schematic illustration of a system according to a first example of the present disclosure; Fig. 2 is a schematic illustration of a wearable device according to the first

example of the present disclosure;

Fig. 3 is a schematic illustration of an apparatus according to the first example of the present disclosure; Fig. 4 is a schematic illustration of a first electronic device according to the first

example of the present disclosure;

Fig. 5 is a flow chart of a first method according to the present disclosure; Fig. 6 is a flow chart of a second method according to the present disclosure; and Fig. 7 is a flow chart of a third method according to the present disclosure. DETAILED DESCRIPTION [0038] Fig. 1 shows a system 10 according to a first example of the present disclosure.

The system 10 is for monitoring the mental attention of a user, and particularly for notifying in real time when the attention level of the user drops below a target attention level or acceptable attention range. According to the first example of the disclosure, the system 10 comprises a wearable device 20, an apparatus to monitor mental attention 30, a first electronic device 40 and a second electronic device 50.

[0039] The wearable device 20 is arranged to be worn by a user and perform functional near-infrared spectroscopy (fNIRS), which is a non-invasive optical brain monitoring technique for use in functional neuroimaging. In particular, fNIRS may measure brain activity by using near-infrared light to estimate haemodynamic activity in the pre-frontal cortex of the brain, which in turn may be an indicator of the mental attention of the user wearing the wearable device 20. The wearable device 20 will be discussed in more detail below in relation to Fig. 2.

[0040] In the first example of the disclosure, the wearable device 20 outputs biometric fNIRS data 60 to the apparatus 30 via the first electronic device 40. The apparatus 30 is arranged to process the biometric data 60 to obtain information corresponding to a mental attention metric and determine whether the user's attention has dropped below a threshold by comparing the obtained information to the threshold. If the predetermined attention level has not been attained, the apparatus 30 is arranged to output a signal 70 to at least one of the first electronic device 40 and the second electronic device 50. In response to receiving the signal 70, the first electronic device 40 and the second electronic device 50 are arranged to output an indication that the mental attention level of the user is low.

[0041] It will be understood that the disclosure is not limited to this however. In some examples of the disclosure, the apparatus is arranged to output a signal if the predetermined attention level has been attained, rather than when it has not been attained.

In such cases, it can be deduced that the attention level of the user is low by an absence of any indication being output. In further examples of the disclosure, if the attention level has not been attained, then a first signal indicative of the attention level being low may be output, whilst a second signal indicative of the attention level being high may be output when the attention level has been attained.

[0042] In some examples of the disclosure, the system 10 may however not include the second electronic device 50 shown in Fig. 1, but rather only include the first electronic device 40. In other examples of the disclosure, the system 10 may include further electronic devices (not shown), which are signalled by the apparatus 30 to notify when the attention level has dropped below the threshold. The electronic devices signalled by the apparatus 30 may be user devices belonging to persons of interest, who wish to be notified when the mental attention of the user has dropped. For example, whilst the first electronic device 40 may belong to the user whose mental attention is being monitored by the wearable device 20, the second electronic device 50 and any further electronic devices (not shown) that are signalled by the apparatus 30 may instead belong to an employer of the user, such as a manager. In doing so, the first electronic device 40 may act as both a conduit for transmitting biometric data 60 between the wearable device 20 and apparatus 30, whilst also facilitating alerts to the user when their attention level drops below the threshold. The second electronic device 50 and any further electronic devices signalled by the apparatus when the attention level drops allows for further people to be notified when the user's mental attention level drops. In further examples of the disclosure, the wearable device 20 may communicate directly with the apparatus to monitor mental attention 30, rather than indirectly via the first electronic device 40.

[0043] Fig. 2 shows the wearable device 20 of Fig. 1 in more detail. As discussed above, the wearable device 20 is arranged to perform fNIRS. In the first example of the disclosure, the wearable device 20 includes a sensor array 210, an accelerometer 220, a set of processing circuitry 230 and a set of communication circuitry 240.

[0044] The sensor array 210 is arranged to obtain light absorption data from a pre-frontal cortex of the user by performing fNIRS. In the first example of the disclosure, the sensor array 210 is arranged to detect light absorption of wavelengths in a range from 700 nm to 900 nm as a voltage. In some examples of the disclosure, the sensor array may detect light absorption of wavelengths from 735 nm to 850 nm. The wearable device 20 is arranged to be worn on the forehead of the user by any suitable means for obtaining light absorption data from the pre-frontal cortex. For example, the wearable device may include a frame (not shown) to mount the sensor array 210 on the user's forehead. It will be understood how to position the sensor array against the forehead of the user to obtain the light absorption data from the pre-frontal cortex.

[0045] In the first example of the disclosure, the sensor array 210 includes a multichannel array of light sources and light detectors. The light sources include pairs of LEDs, whilst the light detectors include photodiodes. In particular, the multichannel array includes two channels of fNIRS data being collected, namely a short channel and a long channel. Both channels use the same photodiode as a detector, whilst the light sources are arranged at different distances: the short channel is arranged with the light sources at a distance of 10 mm from the corresponding detectors, and the long channel is arranged with the light sources at a distance of 30 mm from the corresponding detectors. In the first example of the disclosure, the short channel wavelength is approximately 735 nm, and the long channel wavelength is 850 nm. By providing this arrangement, the short channel data is for modelling light transmission through the user's skin, whilst the long channel data is for modelling light transmission through the user's skin and pre-frontal cortex. In the first example of the disclosure, the wearable device 20 is arranged to perform fNIRS at regular intervals or alternatively repetitively but at irregular or dynamically changing time intervals, such that regular monitoring may be performed, thereby improving the accuracy of the determined trend. The fNIRS is also performed over a predetermined window of time, such that each interval at which fNIRS is performed is not merely a snapshot, but rather biometric data that is collected consistently and more continuously for a predetermined period of time. It will be understood that the disclosure is not limited by the above-described arrangement of the sensor array, and other suitable sensor arrays including the distances of the light sources and detectors for performing fNIRS may be implemented.

[0046] Turning now to the accelerometer 220 of Fig. 2, the accelerometer 220 is arranged to obtain motion data of the user wearing the wearable device 20. The motion data is associated with the light absorption data obtained by the sensor array 210. The accelerometer 220 may be of any suitable type, and in the first example of the disclosure includes a three-axis accelerometer so as to obtain three-dimensional motion data. An example is the Bosch® BMA400 acceleration sensor. The disclosure is not limited to this, and in other examples of the disclosure, the wearable device may obtain light absorption data without motion data.

[0047] The processing circuitry 230 may be of any suitable type. In the first example of the disclosure, the processing circuitry serves as both a microprocessor and a receiver, arranged to control the communication circuitry 240 to output the light absorption data from the sensor array 210 and the motion data from the accelerometer 220 to the first electronic device 40. An example is the Nordic® Semiconductor nRF52840. In doing so, the biometric data 60 includes both the light absorption data and the motion data. The communication circuitry 240 may be of any suitable type. In the first example of the disclosure, the communication circuitry 240 includes a wireless module to output the biometric data 60 wirelessly to the first electronic device 40. For example, the communication circuitry 240 may include a Bluetooth® module.

[0048] Fig. 3 shows the apparatus 30 of Fig. 1 in more detail. As discussed above in Fig. 1, the wearable device 20 is arranged to output the biometric data to the apparatus to monitor mental attention 30 via the first electronic device 40. The apparatus 30 includes communication circuitry 310 and processing circuitry 320. In the first example of the disclosure, the apparatus 30 includes a server in a cloud networking environment.

However, the apparatus is not limited to this and may be any suitable computing device.

[0049] In the first example of the disclosure, the communication circuitry 310 includes a wireless module for communicating remotely with the first electronic device by Wi-Fi and/or network data. However, the disclosure is not limited to this, and may include any suitable communication circuitry arranged to receive the biometric data from the first electronic device 40. The communication circuitry 310 may comprise a receiver in addition to a transmitter or may comprise a transceiver adapted to both transmit information to and receive information from the processing circuitry 320.

[0050] In the first example of the disclosure, the processing circuitry 320 of the apparatus 30 is arranged to analyse the received biometric data 60 to obtain information corresponding to a mental attention metric. As discussed above, the biometric data 60 includes the light absorption data and optionally the motion data obtained by the wearable device 20. The light absorption data and motion data may be time correlated to allow motion of a user when particular light absorption data is captured to be determined.

[0051] Considering firstly the light absorption data, as discussed above the light absorption data includes the fNIRS short channel data and the fNIRS long channel data, whereby the short channel data is for modelling light transmission through the user's skin, whilst the long channel data is for modelling light transmission through the user's skin and pre-frontal cortex. Since the biometric data 60 is effectively raw data in the first example of the disclosure, the processing circuitry 320 is arranged to process the raw biometric data by subtracting the short channel data from the long channel data. In doing so, this may help to reduce the effects of light transmission through the skin and therefore allow for the mental attention level of the user to be more accurately determined. However, the disclosure is not limited to using both the long and short wavelength channels, and in some examples of the disclosure, only a single channel may be used. In other examples, more than two channels may be used.

[0052] Furthermore, as discussed above, motion data is obtained alongside the light absorption data in the first example of the disclosure. The processing circuitry 320 is arranged to process the light absorption data in dependence on the motion data. In particular, the processing circuitry 320 is arranged to determine light absorption data corrupted by motion artifacts based on the motion data, and exclude the deemed corrupted light absorption data from further analysis. In doing so, the biometric data may be accurately processed, since the motion data may compensate for poor quality light absorption data.

[0053] Hence, the processed biometric data may be analysed by the processing circuitry 320 to obtain information corresponding to the mental attention metric that accurately corresponds to the light absorption data through the pre-frontal cortex, with reduced effects of light transmission through the skin, as well as compensating for any motion artefacts.

[0054] In some examples of the disclosure, since the motion data can highlight the presence of motion artefacts in the light absorption data, the resulting biometric data may be analysed by machine learning in the event it has been deemed to be corrupted. The corrupted data may be processed in dependence on the motion data to effectively remove the motion artefact, which may be particularly useful in allowing light absorption data to be used for determining the mental attention metric whilst the user is on the move.

[0055] However, the biometric data in some embodiments may be analysed by a rules-based algorithm rather than machine learning. Furthermore, although the processing of the biometric data is described as being performed at the apparatus in the first example of the disclosure, the disclosure is not limited to this. In some examples of the disclosure, the processing of the raw biometric data may be performed locally at the wearable device rather than the apparatus, such that the wearable device is arranged to output the biometric data as useful biometric data. However, by performing the processing of the biometric data at the apparatus 30, such that the wearable device is arranged to output the biometric data as raw biometric data, this means the processing circuitry 230 of the wearable device 20 may be reduced in size and complexity and in turn, cost.

[0056] In the first example of the disclosure, the processing circuitry 320 is arranged to analyse the biometric data to determine haemodynamic information of the pre-frontal cortex. The processing circuitry 320 is arranged to use a model to derive the haemodynamic information from the light absorption data based on the modified Beer-Lambert Law (MBLL), which may be represented by: [0057] [0058] [0059] [0060] where: [0061] Hb Haemoglobin [0062] A1 Short channel wavelength [0063] A2 Long channel wavelength [0064] Hb02 Oxyhaemoglobin [0065] -Hb & -Hb02 Extinction Coefficients of Oxy & Deoxy haemoglobin [0066] Ab Baseline light amplitude [0067] At Transient light amplitude (measured) [0068] L Optical path length between source and detector [0069] The processing circuitry 320 is arranged to obtain information corresponding to the mental attention metric based on the analysed biometric data. In the first example of the disclosure, the processing circuitry 320 is arranged to determine the mental attention metric based on the obtained haemodynamic information, using a trained classifier for classifying the haemodynamic information. In the first example of the disclosure, the trained classifier is a predetermined model, such as a rules-based algorithm.

[0070] In the first example of the disclosure, the apparatus to monitor mental attention 30 includes a storage unit (not shown) for storing the MBLL model and the trained classifier, which the processing circuitry 320 can access to determine the haemodynamic information and corresponding mental attention metric. It will be understood however that the MBLL model and trained classifier may instead by stored on one or more other servers in communication with the apparatus 30 that the processing circuitry 320 may access. In such cases, the apparatus 30 may include a cloud network of servers.

[0071] Once the mental attention metric has been obtained, the processing circuitry 320 is arranged to compare the mental attention metric to a threshold to determine if the user has attained at least a predetermined mental attention level. If the predetermined attention level has not been attained, the processing circuitry 320 is arranged to generate and output a signal to the first electronic device 40 and/or second electronic device 50 via the communication circuitry 310, as discussed above in relation to Fig. 1. The signal is for indicating that the mental attention level of the user is low.

[0072] By analysing the fNIRS biometric data to obtain the mental attention metric, the apparatus 30 ascertains whether a mental attention level of a user is effectively at a safe level or not. If the predetermined attention level has not been attained, then the user may be deemed as being unsafe, and the processing circuitry signals to the first and/or second electronic device that the mental attentiveness is low. In doing so, this efficiently improves safety by facilitating regular monitoring of mental attention levels and signalling user devices in real-time when the mental attentiveness drops. This is beneficial in high risk environments and jobs, where consistent high levels of mental attentiveness are paramount, since the risk of accidents may be reduced. In particular, not only can it be immediately identified when the attention of wearer of the wearable device has fallen, but the user and any surrounding interested persons, such as an employer, may be notified.

Even in a lower risk environment such as a desk job, a reduced focus level of a person may result in poorer work output as compared to when they have a high level of alertness, and may therefore also benefit from the present disclosure for the purposes of productivity tracking and enhancement.

[0073] Although the processing of the biometric data is described as being performed at the apparatus in the first example of the disclosure, the disclosure is not limited to this. In some examples of the disclosure, the steps performed by the apparatus 30 are rather performed locally at the wearable device. In doing so, the biometric data is analysed to obtain information corresponding to the mental attention metric and it is determined if the user has attained at least a predetermined mental attention level locally at the wearable device. It will be appreciated that in such examples, the biometric data may not be output to an apparatus, since the processing and analysis of the biometric data occurs locally at the wearable device.

[0074] Fig. 4 shows the first electronic device 40 of Fig. 1 in more detail. In the first example of the disclosure, the first electronic device 40 includes communication circuitry 410, processing circuitry 420, an input unit 430 and a display 440. If the first electronic device 40 is signalled by the apparatus 30 that the mental attentiveness of the user has dropped, the first electronic device 40 is arranged to output an indication that the mental attention of the user is low. In the first example of the disclosure, the processing circuitry 420 is arranged to control the display 440 to display the indication visually, for example as an alert such as a message or the like. However, in other examples of the disclosure, the indication may be output at least one of haptically, audibly and visually. In such examples, the first electronic device includes a vibration unit and a speaker (not shown) to output the indication haptically and audibly, respectively. The second electronic device 50 may include the same components as the first electronic device of Fig. 4.

[0075] The first electronic device 40 and the second electronic device 50 may be of any suitable type. For example, both devices 40 and 50 may be portable devices, such as mobile phones, tablets, laptops, or the like. However, the disclosure is not limited to this and the first electronic device in other examples of the disclosure may differ from the second electronic device. For example, whilst the second electronic device may still be provided as a mobile phone, tablet, laptop, or the like, the first electronic device may be provided as a gateway portable device such as a wearable watch arranged to transmit the biometric data from the wearable device to the apparatus.

[0076] In the first example of the disclosure, the threshold is predetermined. In particular, the threshold may be set according to an industry safety standard, which may be particularly beneficial in high risk environments, where a minimum attention level is required to perform a job safely, such as when the user is driving. In the first example of the disclosure, the threshold is set via a setting menu displayed on the first electronic device 40 and/or second electronic device 50. In particular, the first electronic device 40 may receive a user input via the input unit 430 to set the threshold. The input unit 430 may be of any suitable type, such as a touchscreen device.

[0077] Turning back to Fig. 3, the apparatus to monitor mental attention 30 in the first example of the disclosure is in communication with a database 330, which is arranged on another cloud server remote from the apparatus 30. The apparatus 30 is arranged to store information on the database 330 and also retrieve information from the database 330.

However, it will be understood that the disclosure is not limited to this, and the database may in other examples be stored on the apparatus 30 itself.

[0078] In the first example of the disclosure, the database 330 is arranged to store biometric data, including the raw biometric data 60 that is transmitted from the wearable device 20 to the apparatus 30 and the processed biometric data including the haemoglobin information, which are mapped against the corresponding mental attention metric derived from the biometric data and the corresponding time at which the biometric data was obtained. In doing so, the database 330 includes historically obtained biometric data, together with the corresponding mental attention metric and time points at which the biometric data was obtained. The processing circuitry 320 of the apparatus 30 is also arranged to transmit further biometric data and corresponding attention metrics, which the database 330 stores thereon. In doing so, the biometric data and corresponding attention metrics at various times may be collated for building a profile of the user's mental attention over time. Alternatively, the analysis can be performed with respect to a group comprising two or more users such as a given type or category or worker or a group of users working in a particular location or on a particular item of machinery for example.

[0079] The disclosure is not limited to this however, and in some examples of the disclosure, the database is only allowed to store biometric data and the corresponding mental attention metrics if the user has given permission to do so. In particular, the first electronic device 40 may display a message (not shown) requesting permission to store the user's personal information on the database. In response to receiving an affirmative input providing the user's permission, the user's biometric data and corresponding mental attention metrics may be stored in the database 330. The first electronic device 40 may further provide the option for storing the user's data anonymously, and/or for storing the user's data for a predetermined amount of time.

[0080] As discussed above, the wearable device 20 transmits the biometric data to the apparatus 30 via the first electronic device 40, such that the first electronic device 40 acts as a conduit between the wearable device 20 and the apparatus 30. In the first example of the disclosure, the first electronic device 40 is arranged to encrypt the biometric data that is received from the wearable device 20 before transmitting onto the apparatus 30. In doing so, the apparatus 30 receives encrypted biometric data. The biometric data may be encrypted by any suitable security protocol, such as by Transport Layer Security (TLS). As such, the database 330 stores encrypted biometric data, thereby improving security.

[0081] In the first example of the disclosure, the first electronic device 40 and/or second electronic device 50 are also arranged to display a menu (not shown) including options to display insights and trends of the mental attentiveness of the user over various windows of time, for example over a period of a day, week, week, month, etc. or other period of time that the user may set. In particular, the user of the first electronic device and/or the user of the second electronic device may select from the menu a window of time from one of the options for displaying the trend, for example, the user may select a particular initial time point and end time point to select the window of time. In response to receiving the input, the first electronic device 40 and/or second electronic device 50 is arranged to output a request for the trend to the apparatus 30. In response to receiving the request for the trend, the processing circuitry 320 of the apparatus 30 is arranged to retrieve biometric data obtained at a plurality of historical time points from the database corresponding to the selected window of time, together with the corresponding mental attention metrics and time points at which the biometric data was obtained mapped against the retrieved biometric data.

[0082] In the first example of the disclosure, the processing circuitry 320 is arranged to analyse the retrieved biometric data and corresponding mental attention metrics and time points and the presently obtained information to determine a trend of the mental attention of the user over the selected window of time corresponding to the plurality of time points.

The processing circuitry 320 in the first example of the disclosure uses a model for determining the trend, such as a rules-based algorithm, that compares the historical biometric data and corresponding mental attention metrics against one another over a period of time. In particular, the apparatus 30 is arranged to store the model for determining the trend alongside the MBLL model and the trained classifier, which the processing circuitry 320 can access to determine the trend. However, the disclosure is not limited to this, and in other examples of the disclosure, the processing circuitry 30 may determine the trend using machine learning. The classifier may be a machine-learning classifier such as a neural network classifier.

[0083] In the first example of the disclosure, the processing circuitry 320 is arranged to control the communication circuitry 310 to output the determined trend to the first electronic device 40 and/or the second electronic device 50. In response to receiving the signal, the first electronic device 40 is arranged to display the determined trend. In the first example of the disclosure, the trend is displayed as a graph plotting the determined mental attention metric as a function of time so as to illustrate visually how the user's mental attentiveness varies over time. The trend may however be displayed in any suitable manner, for example as a table or the like.

[0084] In some examples of the disclosure, the database 330 may store not only the biometric data corresponding to a particular user, but also the biometric data of a plurality of users, together with corresponding mental attention metrics and time points at which the raw biometric data was obtained. As such, trends may be determined across the plurality of users when requested. The plurality of users may for example be employees at the same company. This may be particularly beneficial for employers, who can make a request for a trend via an electronic device (e.g. the second electronic device and/or further electronic device) to oversee how focus levels vary for their workforce, and thus effectively plan risk management strategies, particularly in remote environments.

[0085] Fig. 5 shows a first method 500 for monitoring mental attention levels according to a second example of the disclosure. The first method 500 is performed by an apparatus, such as the apparatus 30 described in the first example of the disclosure, but in other examples of the disclosure is performed by a wearable device, such as the wearable device 20 described in the first example of the disclosure. The first method 500 includes step 510 of obtaining biometric data, which includes light absorption data obtained by performing functional near-infrared spectroscopy, fNIRS. The biometric data may be obtained by a wearable device, such as the wearable device 20 described in the first example of the disclosure. Where the first method is performed by the apparatus 30 as in the first example of the disclosure, the first method 500 further includes (not shown) the apparatus receiving the obtained biometric data from the wearable device. The first method 500 includes step 520 of analysing the biometric data, step 530 of obtaining information corresponding to a mental attention metric based on the analysed biometric data, and step 540 of comparing the obtained information to a threshold to determine if the user has attained at least a predetermined mental attention level. The biometric data may be analysed, the information obtained and the comparison performed as described in the first example of the disclosure. The first method 500 includes step 550 of outputting a signal that the mental attention level of the user is low, in the event that the predetermined attention level has not been attained based on the comparison. The signal may be output as described in the first example of the disclosure to one or more electronic devices, such as the first electronic device 40, second electronic device 50 and/or further electronic devices.

[0086] In some examples of the disclosure, the first method 500 further includes the one or more electronic devices that receive the signal outputting an indication that the mental attention of the user is low (not shown). The indication may be output as described in the

first example of the disclosure.

[0087] Fig. 6 shows a second method 600 for monitoring attention levels according to a third example of the disclosure. According to this second method, the fNIRS data is captured as part of the method rather than obtained from another source. The second method 600 is performed by a system, such as the system 10 described in the first example of the disclosure. The second method 600 includes step 610 of performing fNIRS to obtain biometric data. The fNIRS may be performed by a wearable device, such as the wearable device 20 described in the first example of the disclosure. The second method 600 includes step 620 of processing the biometric data. The biometric data may be processed by an apparatus, such as the apparatus 30 described in the first example of the disclosure. In other examples of the disclosure, the biometric data is processed locally by the wearable device, for example, by a trained machine learning model or rules-based algorithm installed on processing circuitry of the wearable device. Step 620 of processing the biometric data is performed by at least steps 520 and 530 of the first method in order to obtain the mental attention metric derived from the biometric data. Whilst steps 540 and 550 may be performed to signal the one or more electronic devices when the mental attention level has fallen below the threshold, the second method 600 further includes step 630 of storing the biometric data and the corresponding mental attention metric and time at which the biometric data was obtained, which may be stored in a database, such as the database 330 described in the first example of the disclosure. In particular, the storing step 630 of the second method 600 is performed regardless of whether the predetermined mental attention level has been attained, so as to facilitate for a profile of the user's mental attention to be built. In doing so, not only can it be identified when the user's mental focus falls below the predetermined attention level, but the user's overall mental attentiveness over time may also be determined, including when they are highly attentive.

[0088] Fig. 7 shows a third method 700 of monitoring attention according to a fourth example of the disclosure. The third method 700 may be performed by an apparatus, such as the apparatus to monitor mental attention 30 described in the first example of the disclosure. The third method 700 includes step 710 of receiving a request for a mental attention trend. The request may be received from an electronic device, such as the first electronic device 40, second electronic device 50 or further electronic devices described in the first example of the disclosure. The third method 700 includes retrieving stored biometric data detected at a plurality of times and corresponding information of a mental attention metric associated with the stored biometric data, which may be retrieved from a database, such as the database 330 described in the first example of the disclosure. The third method 700 includes step 730 of determining a trend of the mental attention of the user by analysing the retrieved data and corresponding information. The trend may be determined as described in the first example of the disclosure. The third method 700 includes step 740 of outputting a signal for displaying the trend. The signal may be output to the electronic device that made the request for the trend, and the trend may be displayed as described in the first example of the disclosure.

[0089] In the first example of the disclosure, machine readable instructions are provided corresponding to the method steps set out in the first, second and third methods above, so as to cause processing circuitry to carry out the method steps schematically illustrated by the flow charts of Figures 5 to 7. The computer program product in the first example of the disclosure is arranged to be stored tangibly on a computer readable data storage medium, such as a USB storage device. A data carrier signal may also carry the computer program product as software.

[0090] Throughout the description and claims of this specification, the words "comprise" and "contain" and variations of them mean "including but not limited to", and they are not intended to (and do not) exclude other moieties, additives, components, integers or steps.

Throughout the description and claims of this specification, the singular encompasses the plural unless the context otherwise requires. In particular, where the indefinite article is used, the specification is to be understood as contemplating plurality as well as singularity, unless the context requires otherwise.

[0091] Further example implementations can be realised comprising one or more features of any herein described implementation taken jointly and severally in any and all permutations. Yet further example implementations may also be realised by combining features of one or more of the appended claims with one or more selected features of any example implementation described herein.

[0092] Where functional units have been described as circuitry, the circuitry may be general purpose processor circuitry configured by program code to perform specified processing functions. The circuitry may also be configured by modification to the processing hardware. Configuration of the circuitry to perform a specified function may be entirely in hardware, entirely in software or using a combination of hardware modification and software execution. Program instructions may be used to configure logic gates of general purpose or special-purpose processor circuitry to perform a processing function.

[0093] Circuitry may be implemented, for example, as a hardware circuit comprising custom Very Large Scale Integrated, VLSI, circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. Circuitry may also be implemented in programmable hardware devices such as field programmable gate arrays (FPGA), programmable array logic, programmable logic devices, A System on Chip (SoC), graphics processing units (GPU), or the like.

[0094] Machine readable program instructions may be provided on a transitory medium such as a transmission medium or on a non-transitory medium such as a storage medium.

Such machine readable instructions (computer program code) may be implemented in a high level procedural or object oriented programming language. However, the program(s) may be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language, and combined with hardware implementations. Program instructions may be executed on a single processor or on two or more processors in a distributed manner.

[0095] For the purposes of the description, a phrase in the form "A / B" or in the form "A and/or B" means (A), (B), or (A and B). For the purposes of the description, a phrase in the form "at least one of A, B, and C" means (A), (B), (C), (A and B), (A and C), (B and C), or (A, B and C).

Claims

CLAIMS1. An apparatus to monitor mental attention, the apparatus comprising processing circuitry arranged to: obtain biometric data comprising light absorption data, the light absorption data obtained by performing functional near-infrared spectroscopy, fNIRS; analyse the biometric data; obtain information corresponding to a mental attention metric based on the analysed biometric data; compare the obtained information to a threshold to determine if the user has attained at least a predetermined mental attention level; and output a signal indicative of the mental attention level of the user based on the comparison.
2. The apparatus of claim 1, wherein the signal indicative of the mental attention of the user is output if the predetermined attention level has not been attained based on the comparison, wherein the signal is indicative that the mental attention level of the user is low.
3. The apparatus of claim 1, comprising a sensor arranged to perform fNIRS to obtain the light absorption data.
4. The apparatus of claim 1 or claim 2, wherein the biometric data further comprises motion data associated with the light absorption data.
5. The apparatus of claim 3, wherein the processing circuitry is further arranged to analyse the light absorption data in dependence of the motion data, wherein the motion data is for compensating poor quality light absorption data.
6. The apparatus of any one of claims 2 to 4, comprising a motion sensor arranged to detect the motion data.
7. The apparatus of claim 1, wherein, prior to analysing the biometric data, the processing circuitry is arranged to receive, from a first electronic device, the biometric data.
8. The apparatus of any one of the preceding claims, wherein the light absorption data includes wavelength data in a range from 700 nm to 900 nm.
9. The apparatus of any one of the preceding claims, wherein the information corresponding to the mental attention metric includes haemodynamic information of a prefrontal cortex of the brain of a user of the apparatus to monitor mental attention.
10. The apparatus of any one of the preceding claims, wherein the processing circuitry is arranged to analyse the biometric data based on a modified Beer-Lambert law.
11. The apparatus of any one of the preceding claims, wherein the processing circuitry is arranged to classify the analysed biometric data to obtain the information and wherein the biometric data is analysed by classification using a trained classifier.
12. The apparatus of any one of the preceding claims, wherein the signal is for indicating that the user is unsafe.
13. The apparatus of any one of the preceding claims, further arranged to encrypt the biometric data.
14. The apparatus of any one of the preceding claims, wherein the processing circuitry is further arranged to store, in a database, the biometric data, the time of detection and the obtained information corresponding to the mental attention metric.
15. The apparatus of claim 14, wherein the processing circuitry is further arranged to: retrieve, from the database, stored biometric data detected at a plurality of times for a given user of the apparatus and corresponding information of a mental attention metric associated with the stored biometric data, analyse the retrieved data and corresponding information, and determine a trend of the mental attention of the user based on the analysed retrieved data and corresponding information and the obtained information.
16. The apparatus of claim 15, wherein the processing circuitry is further arranged to output information corresponding to the analysed trend.
17. A system for monitoring mental attention, the system comprising: the apparatus of any one of the preceding claims; and a first electronic device arranged to receive the signal, wherein, in response to receiving the signal, the first electronic device is arranged to output an indication associated with the mental attention level of the user.
18. The system of claim 17, wherein the first electronic device is arranged to display the indication.
19. A method for monitoring mental attention, the method comprising: obtaining biometric data comprising light absorption data, the light absorption data obtained by performing functional near-infrared spectroscopy, fNIRS; analysing the biometric data; obtaining information corresponding to a mental attention metric based on the analysed biometric data; comparing the obtained information to a threshold to determine if the user has attained at least a predetermined mental attention level; and outputting a signal indicative of the mental attention level of the user based on the comparison.
20. The method of claim 19, wherein obtaining the biometric data comprises performing functional near-infrared spectroscopy, fN IRS.
21. The method of claim 19 or claim 20, wherein obtaining the biometric data comprises obtaining motion data.
22. The method of any one of claims 19 to 21, further comprising, in response to receiving the signal, outputting at least one of a visual, haptic and audio indication associated with the mental attention level of the user.
23. Machine readable instructions which, when executed by processing circuitry, cause the processing circuitry to carry out a method according to any one of claims 19 to 22.
24. A computer readable data storage medium having tangibly stored thereon the machine readable instructions of claim 23.