WO2022013738A1

WO2022013738A1 - Worker health and safety system and method

Info

Publication number: WO2022013738A1
Application number: PCT/IB2021/056293
Authority: WO
Inventors: Derick Wessels Moolman; Mark SILBERBAUER; Dirk Wagener; Louis Marius MARAIS
Original assignee: Stone Three Digital (Pty) Ltd
Priority date: 2020-07-16
Filing date: 2021-07-13
Publication date: 2022-01-20

Abstract

There is provided a worker health and safety system and associated method. A server is provided for receiving sensor data and health data of a plurality of workers registered at the server. A plurality of sensors are in data communication with the server and capable of sensing sensor data and communicating the sensor data to the server over a data communications network. One or more health data storage devices are also in data communication with the server to communicate health data of the plurality of workers to the server. A data analytics module is implemented by the server to perform analysis of the received sensor data and health data to determine if any of the received sensor data or health data exceeds a threshold, and to generate a notification based on the analysis. The notification is communicated to one or more users of the system.

Description

WORKER HEALTH AND SAFETY SYSTEM AND METHOD

CROSS-REFERENCE TO RELATED APPLICATION

This application claims priority from South African provisional patent application number 2020/04362 filed on 16 July 2020, which is incorporated by reference herein.

FIELD OF THE INVENTION

This invention relates to worker health and safety. More particularly, but not exclusively, this invention relates to a worker health and safety system and method that may be implemented in an industrial environment.

BACKGROUND TO THE INVENTION

Although current heavy industry workplaces are far safer than a couple of decades ago, accidents, health incidents or even fatalities still occur frequently. Some techniques that were effective at reducing incidents in the past are now yielding diminishing returns and the industry has been unable to move closer to a zero-harm environment.

A key reason why industry has been struggling to achieve this is because data is heavily siloed into separate health and safety systems. The data is not available in real-time, not updated frequently, and worker health is not individualised but rather viewed as part of a population exhibiting general health issues. Industries like mining are heavily impacted by perceptions within the surrounding communities and the public in general. Known as a “social licence to operate”, mining companies rely on acceptance by the community as well as the general public who, in this modern age of media exposure, wield considerable power. It is therefore imperative that companies clearly show how they improve the health and safety of workers on a continuous basis.

Safety incidents or accidents are detrimental to employee well-being and can cause disability, mental health problems, physical health problems, motivation challenges and suffering. This can lead to increased staff turnover, absenteeism or presenteeism, which directly impacts productivity. Workplace fatalities affect families and communities severely. In addition, fatalities result in operations being put on hold, bringing production to a halt. Besides the human tragedy associated with safety incidents and fatalities, there are significant costs incurred by employees. These include increased insurance premiums, worker’s compensation costs, healthcare costs, legal costs and fines. Moreover, poor safety records may even diminish mining companies’ share prices.

Worker health and safety is important in heavy industries such as the mining industry, however it is also important in any environment where employees, workers, contractors, visitors or any humans may possibly be exposed to a harmful environment. There exists numerous critical controls designed to produce safer worker behaviour, a safer and healthier working environment and reduced risk. As an example, workers in such environments are generally required to wear Personal Protective Equipment (PPE) such as hard hats, protective gloves, goggles, facemasks, ear protection, and other PPE items. Protection is generally required against dangerous physical objects, dispersed particles (such as fine coal particles in coal mines), gases, loud noises, light exposure, and many others. With the recent viral spread of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) commonly referred to as the Coronavirus or Covid-19, the use of PPE has become even more important and extends across all industries or sectors. Facemasks are in many cases obligatory, in an effort to combat the spread of Covid-19.

However, it remains difficult for employers or other interested parties to effectively monitor or track the efficacy of critical controls and to effectively improve worker health and safety. Furthermore, it is also difficult to detect, identify or monitor health effects on workers that may have been exposed to harmful environments, over short, medium or long time periods.

Harmful environments result in disease or other harmful effects to workers. There are several examples of these. Firstly, cardiovascular disease remains a major cause of death worldwide and in particular those workers exposed to risk factors such as carbon monoxide, noise, vibration, temperature extremes and shift work. Secondly, lung disease may be caused by exposure to harmful airborne particles such as coal (coal workers' pneumoconiosis), asbestos and silica dust. Thirdly, noise induced hearing loss (NIHL) may be caused by continuous exposure to harmful levels of noise. Many other harmful environments may also cause harm to workers.

The applicant considers there to be room for improvement.

The preceding discussion of the background to the invention is intended only to facilitate an understanding of the present invention. It should be appreciated that the discussion is not an acknowledgment or admission that any of the material referred to was part of the common general knowledge in the art as at the priority date of the application. SUMMARY OF THE INVENTION

In accordance with an aspect of the present disclosure there is provided a worker health and safety system comprising: a server for receiving sensor data and health data of a plurality of workers registered at the server; a plurality of sensors in data communication with the server and capable of sensing sensor data and communicating the sensor data to the server over a data communications network, the server arranged to associate the received sensor data with one or more of the registered workers; one or more health data storage devices in data communication with the server to communicate health data of the plurality of workers to the server; and a data analytics module implemented by the server to perform analysis of the received sensor data and health data to determine if any of the received sensor data or health data exceeds a threshold, and to generate a notification based on the analysis, wherein the server is arranged to implement one or more user communication modules for transmitting the notification to one or more users of the system.

The system, or components thereof, may include a memory for storing computer-readable program code and a processor for executing the computer-readable program code.

The data analytics module may also be arranged to perform one or more of: determining an insight, reaching a conclusion and/or making a prediction based on the processing of the sensor data or health data. The notification may be in the form of a report, a warning, an alert message or an alarm.

The plurality of sensors may form part of a distributed sensor network. The plurality of sensors may be arranged to sense the sensor data in near real-time.

The server may be arranged to generate a worker profile associated with each of the registered workers, based on the received sensor data and the received health data.

The notification may include one or more actionable recommendations. A list of actionable recommendations may be associated with each of the worker profiles.

The one or more user communication modules may be one or more user portals accessible through one or more user devices. The one or more users of the system may be registered at the server for use of the system.

The plurality of sensors may sense or generate the sensor data in near real-time.

The plurality of sensors may include any one or more of: temperature sensors, noise sensors, gas sensors, particle sensors, dust sensors, humidity sensors, image sensors or digital cameras, light sensors, radiation sensors or detectors, access control sensors, or proximity sensors.

The system may include a health and safety related event and/or infringement detection component that identifies and logs potentially harmful or risky objects and/or behaviours through analysis of one or more video feeds. The data analytics module may be arranged to identify and log potentially harmful or risky objects and/or behaviours through analysis of one or more video feeds.

One or more of the plurality of sensors may be provided by smart watches, smartphones or other electronic devices that generate location data, acceleration data, or other environmental data relevant to one of the workers.

The system may include a worker identification component arranged to detect an identification, a location, or a presence or absence of a registered worker in the vicinity of one or more of the sensors or any other specified location in a working environment where a worker is located in use.

The system may further include a timing component arranged to associate the received sensor data with a time or date and to associate the presence or absence of a registered worker with the received environmental data or sensor data at that time or date, so that the server may determine if the worker is or had been exposed to a potentially harmful environment or potentially harmful equipment.

The one or more health data storage devices may include any one or more of: a database that includes health data, health parameters, or historical health records of a registered worker; or any electronic device whereon the health data is stored, such as a wearable electronic device of the worker or personal electronic device whereon health data of the worker is stored.

Optionally, the plurality of health data storage devices may incorporate one or more health sensors which may for example be provided by wearable electronic devices or wearable medical devices such as heart rate monitors or electrocardiography devices, blood pressure monitors, glucose monitors, biosensors or the like.

The data analytics module may be an artificial intelligence (Al) module or a rule based module or an expert rule based (ERB) module. Alternatively, the data analytics module may include an Al or ERB module or the data analytics module may have access to an Al or ERB module.

The data analytics module may be arranged to analyse the received sensor data and/or the received health data in near real-time. This may enable the one or more users to react proactively to the notification.

The data analytics module or Al module implemented by the server may be a neural network (NN) having a deep learning network architecture. The neural network may be a convolutional neural network (CNN) or a fully convolutional deep neural network (FCDNN or FCNN).

The data analytics module or Al module may implement data processing and analysis by using artificial intelligence rules and/or expert rules and/or algorithms, to analyse the received sensor data and health data in order to generate the notification and the actionable recommendation.

The server may be provided by a cloud infrastructure operable to receive the sensor data and the health data, the cloud infrastructure being operable to provide a user interface by way of the one or more user portals.

The server may be a physical server or a virtual server and it may include or form part of one or more server clusters. Computing, processing or analysis by the server may be pe performed centrally, or in a distributed manner.

The server may be in data communication with one or more further servers arranged to receive the sensor data and health data. Either of, or both of the sensor data and the health data may be pre-processed by a computing device before it is transmitted to the server.

In accordance with another aspect of the present disclosure there is provided a worker health and safety system comprising: a server for receiving sensor data and health data of a plurality of workers registered at the server; a sensor data receiving component for receiving sensor data from a plurality of sensors that sense the sensor data, the sensor data being received over a data communications network, and the server arranged to associate the sensor data with one or more of the registered workers; a health data receiving component for receiving health data of the plurality of workers from a plurality of health data storage devices; and a data analytics module implemented by the server to perform analysis of the received sensor data and health data to determine if any of the received sensor data or health data exceeds a threshold, and to generate a notification based on the analysis, wherein the server is arranged to implement one or more user communication modules for transmitting the notification to one or more users of the system.

Further features of the system of the present aspect may include features applicable to the other aspects of the present disclosure.

In accordance with another aspect of the present disclosure there is provided a computer- implemented method for monitoring worker health and safety, the method carried out at a server and comprising: receiving from a plurality of sensors in data communication with the server, sensor data sensed by the sensors; associating the received sensor data with one or more of a plurality of workers that are registered at the server; receiving health data of the plurality of workers from one or more health data storage devices in data communication with the server; instructing the performing of analysis of the received sensor data and health data to determine if any of the received sensor data or health data exceeds a threshold, and generating a notification based on the analysis; and communicating the notification to one or more users.

The method may include instructing the performing by artificial intelligence near real-time analysis of the received sensor data and health data to determine if any of the received sensor data or health data exceeds the threshold.

The method may include implementing a data analytics module to analyse the received health data and sensor data. The method may include one or more of: determining an insight, reaching a conclusion and/or making a prediction based on the processing of the sensor data or health data. The notification may be in the form of a report, a warning, an alert or an alarm. The one or more users may be registered at the server for use of the method.

The method may further include a method carried out by a plurality of sensors in data communication with the server, including sensing the sensor data, preferably in near real-time, and communicating the sensor data to the server over a data communications network.

The method may further include a method carried out by one or more health data storage devices in data communication with the server including communicating health data of the plurality of workers to the server.

The method may also include implementing one or more user communication modules, or one or more user portals in data communication with the server, wherethrough the notification may be communicated to one or more users registered at the server.

Further features of the method of the present aspect may include features applicable to the other aspects of the present disclosure.

In accordance with a further aspect of the present disclosure there is provided a computer program product for monitoring worker health and safety, the computer program product comprising a computer-readable medium having stored computer-readable program code for performing the steps of: by a server, receiving sensor data and health data of a plurality of workers registered at the server; receiving from a plurality of sensors in data communication with the server, sensor data sensed by the sensors; associating the received sensor data with one or more of the plurality of registered workers; receiving health data of the plurality of workers from one or more health data storage devices in data communication with the server; instructing the performing of analysis of the received sensor data and health data to determine if any of the received sensor data or health data exceeds a threshold, and generating a notification based on the analysis; and communicating the notification to one or more users.

Further features may provide for the computer-readable medium to be a non-transitory computer- readable medium and for the computer-readable program code to be executable by a processing circuit. Embodiments of the present disclosure will now be described, by way of example only, with reference to the accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

In the drawings: Figure 1 is a high-level block diagram illustrating an example embodiment of a worker health and safety system;

Figure 2 is a block diagram of an exemplary server which may form part of the system of Figure 1 ;

Figure 3 is a block diagram of an exemplary user device which may form part of the system of Figure 1 ;

Figure 4 is a swim-lane flow diagram of an exemplary method for monitoring worker health and safety;

Figure 5 illustrates an example of a computing device in which various aspects of the disclosure may be implemented;

Figure 6 is a high-level block diagram of another embodiment of a worker health and safety system; and

Figure 7 is another high-level block diagram, showing more detail of the exemplary system of Figure 6.

DETAILED DESCRIPTION WITH REFERENCE TO THE DRAWINGS

In this specification, the term “sensor data” will be used to include any data generated or sensed by a sensor. Part of, or all of the sensor data may be raw data, which may optionally be pre- processed by a computing device associated with the sensor. It should be appreciated that an image capturing device or camera may also be a sensor (which senses, captures or records light and/or sound) and the sensor data may include images, frames or video captured by the camera. The sensor data may also be indicative of human behaviour or worker behaviour.

There is provided a system and method for monitoring employee health and safety. A plurality of workers, employees or humans may be required to work or visit a location or site where work or other activities are performed. The site may for example be a heavy industry site such as a mine, mineral processing industry, manufacturing plant, or a refinery. However, other sites may also be monitored, such as hospitals, commercial businesses, ships, offshore structures, rigs, plants, or any location where workers may possibly be exposed to a harmful environment. An operator or managing entity may implement a central backend or server to provide some or all of the features of the systems and methods described herein. A plurality of sensing devices may form part of an Internet of Things (loT) network. These devices may also be referred to as edge devices or endpoints, and these devices may be interconnected. One or more further servers may also be provided, for example at the location where the possibly harmful environment is located. The system may also implement a plurality of wearable electronic devices that may for example be associated with one or more of the workers or employees. A data analytics module or an artificial intelligence (Al) or machine learning architecture may be implemented by the backend or server. Health data or metrics may be transmitted to the backend, as well as physical quantities or measurements that relate to the environment of each of the sensing devices. The backend may be arranged to perform analysis of received data, including health data and environmental data, and to communicate advisory actions or recommendations to end users or customers that make use of the system. These advisory actions may be based on analysis by the data analytics module or machine learning architecture.

Figure 1 is a schematic diagram which illustrates an exemplary worker health and safety system (10). Figures 2 and 3 show high-level block diagrams of components which may form part of the system (10). An associated exemplary method is shown in the swim-lane flow diagram in Figure 4. Figures 6 and 7 show examples of another embodiment of the worker health and safety system and method which may include features of the system and method of Figures 1 to 4. It will also be appreciated that the system and method of Figures 1 to 4 may include features of the embodiment shown in Figures 6 and 7.

Referring to Figure 1 , the system (10) may include a server (12) which may be provided by any suitable computing device performing a server role such as a server cluster, a distributed server, a cloud-based server or the like. A plurality of interconnected servers may also be implemented. The server (12) may, optionally, be operated by, or connected to an operator (14) providing a service to a plurality of users (16) or end-users. In the example embodiment, the users (16) may be entities or organisations involved in industry, who wish to monitor the health and safety of a plurality of employees or workers (18). In the present embodiment, the workers may for example be workers that are required to work at a mine (20), however the present disclosure extends to other types of industry, or working environments. The operator (14) may be an entity operating the server (12) and/or an operator providing some or all of the features of the system to the users (16) or end-users of the system (10). The users (16) may also be referred to as supervisors. It should be appreciated that the server (12) may be a central server, or a plurality of servers may be implemented, e.g. with a local server (17) located at or near the relevant industry or working environment (e.g. at or near the mine (20) in the present case) and in data communication with the central server (12). Some or all of the features of the present disclosure may be implemented by the server (12), or by the local server (17) or by a combination of these, as the case may be. Some or all of the functionality of the present disclosure may be provided remotely, for example using cloud computing. The operator (14) may provide remote services, remote monitoring and infrastructure.

The server (12) may be arranged for receiving sensor data and health data of the plurality of workers (18) as will be described in more detail below. Each of the plurality of workers (18) may preferably be registered at the server (12). A plurality of sensors (22, 24, 26, 28, 30, 32, 34, 36, 38) may be in data communication with the server (12) and may be capable of sensing or generating sensor data in real-time, or near real-time and communicating the sensor data to the server (12) over a data communications network, presently by way of the Internet. It will be appreciated that sensing need not necessarily be performed in real-time or near real-time, and data may be sensed, stored and communicated at a later stage. The sensors may form part of a variety of devices that may be monitored by the server (12). The plurality of sensors may include: one or more gas sensors or dispersed particle sensors (22), one or more noise sensors (24), one or more temperature sensors (26) or sensors arranged to monitor harsh environments, one or more cameras or image capturing devices (28), one or more access control sensors (30) such as Radio Frequency Identification (RFID) tags and sensors for monitoring workers, one or more wearable electronic devices such as mobile devices (32), identification tags (34), wearable smartwatches (36) or other worker tracking devices, as well as biometric sensors (38) or sensors capable of sensing worker health, biological data of a worker, movement data etc. Proximity sensors may also be implemented by the systems and methods of the present disclosure. The various sensors and their functionality are described in more detail below. The plurality of sensors (22, 24, 26, 28, 30, 32, 34, 36, 38) may be provided by a plurality of electronic devices, forming part of an Internet of Things (loT) network (50) or an loT sensor network. The plurality of sensors may also be referred to as, or may form part of, a distributed sensor network. The loT network (50) may incorporate a plurality of transmitters and/or receivers, for communicating with the server (12) over the Internet, or over a wireless or wired communications network. Each of the sensors or devices forming part of the loT network (50) may be assigned a unique identifier which may be registered at the server (12). Each of the workers may also be assigned a unique identifier at the server, during a registration process of each worker.

The server (12) may include a database (40), and/or a separate database (42) may be provided which includes worker health data or historical worker health data or health records (44). The separate database may be accessible by the server (12), and it may be provided by the users (16), or more typically by a third-party operator (not shown). The one or more health data storage devices (32, 36, 38, 42) may include any one or more of: the database (42), or any personal electronic device such as a wearable electronic device of the worker whereon health data or health parameters of the worker is stored electronically.

The users (16) or end-users of the system (10) may have a plurality of associated user devices (46), such as laptop computers, mobile phones, smartphones, desktop computers, or any electronic device able to communicate with the server (12). One or more user portals (52) may be provided by the server (12) by way of the user devices (46) to facilitate use of the system (10). A web-based portal may for example be used. The server (12) may implement a cloud-based infrastructure (54) to provide some or all of the features of the system (10). Alternatively, the server (12) may be provided by the cloud infrastructure (54), and be operable to receive the sensor data and the health data. The cloud infrastructure may be operable to provide a user interface by way of the one or more user portals (52) to the users (16) or end-users. The server (12) may be in data communication with one or more further servers (for example the local server (17) at the mine (20)) arranged to receive the sensor data and health data.

Instead of, or in addition to providing the user portal (52), the server (12) may also be arranged to implement one or more user communication module(s) (81) (See Figure 2) for transmitting a notification (62) to one or more of the user devices (46). The notification (62) is described in more detail below. The notification (62) may be transmitted to the one or more user devices (46) by way of email, Short Message Service (SMS), WhatsApp ™ or in any other way. One-way communications from the server to the user device(s) (52) may be provided, or two-way communications between the server (12) and the user devices (46) may be possible. The notification (62) may also be transmitted to the user device(s) (46) by way of the portal (52). The user communication module (81 ) may optionally include a user device portal interface component (80) which is shown diagrammatically in Figure 2.

Referring again to Figure 1 , the server (12) may implement a data analytics module (57). The data analytics module (57) may be arranged to perform analysis of received sensor data and received health data and/or other received or accessed data. Processing and analysis may be performed in various ways, including the use of rules and algorithms, and analysing data by a rule-based system, expert rules, Artificial Intelligence (Al) or machine learning. The data analytics module (57) may optionally include, or it may have access to an Artificial Intelligence (Al) module (56), shown diagrammatically in Figure 1 . In the case of Al being implemented, the data analytics module and the Al module may be one and the same. The data analytics module (57) may alternatively, or in addition, include an Expert Rule Based (ERB) Module (59) which may be arranged to implement rule-based algorithms or rule-based machine learning. The Al module (56) and/or the ERB module (59) may optionally be implemented by the local server (17), or the Al module may form part of the server (12), or it may be implemented, instructed or accessed by the server (12) which may be operated by the operator (14). The Al module (56) and the data analytics module (57) are described in more detail below.

The server (12) may be arranged to associate the sensor data with one of the registered workers (18). The sensor data may be generated by one or more of the sensors (22, 24, 26, 28, 30, 32, 34, 36, 38), and this sensor data may be indicative of a variety of environmental effects or environmental parameters relevant to a particular worker. The sensor data may include (or it may be indicative of), but it need not be limited to: whether the worker is exposed to a harsh environment, for example when the worker is in the vicinity of an environment with loud noise (e.g. sensed by the noise sensor (24)), when the worker is in an environment where potentially harmful particles are sensed by the gas sensor or dispersed particle sensor (22) (or, where these sensed particles exceed a predefined threshold, and the worker is detected in its vicinity), or even if the worker performs a human activity or behaviour (e.g. determined by video analysis), which will be described in more detail below. The server (12) and/or the data analytics module (57) may be able to determine whether the worker is or has been in such a potentially harmful or harsh environment, or if the worker is or had been in such an environment for a predefined time period. The presence or absence of a worker in any of these environments may be determined by analysing sensor data from the image capturing device (28), and the data analytics module (57) may for example implement facial recognition to identify a worker and correlate the presence of the worker with environmental data received from one or more of the other sensors, such as the dispersed particle sensor (22) or noise sensor (24) in this case. It will be appreciated that sensor data may include images or data generated by the image capturing device (28). Timing data may be generated by a timing component (58) (see Figure 2) which may form part of the server (12), and this timing data may be used by the server (12) or the data analytics module (57) to determine the time period which a worker is or has been exposed to the potentially harmful environment, as well as to correlate the presence of the worker with a detected or sensed harmful environment. Data analytics may be performed to analyse or integrate exposure data with health data in order to determine a risk or risk level of a worker. This risk or risk level may form part of the notification generated by the server (12) or by the data analytics module (57).

In the example embodiment, a worker (18) may check into a premises or location where work is being performed, for example at the mine (20). Access control (30) may be implemented by one or more access control sensors, and the server (12) and/or the data analytics module (57) may monitor each worker’s presence or absence at the mine (20) by using RFID tags, or facial recognition, or other forms of digital worker identification (e.g. through the camera(s) (28) or other surveillance equipment). Biometric authentication may also be implemented to track movements or access of the worker into, within and out of the mine (20) or other premises.

As another example, the worker (18) may, after starting a shift of work at the mine (20), enter a zone or environment where harsh temperatures (for example sensed by the temperature sensor (26)) is located. The server (12) and/or the data analytics module (57) may determine that the worker is exposed to such harsh environment by receiving sensor data (in this case environmental data) from the temperature sensor (26), and the server (12) or data analytics module (57) may correlate this sensor data or environmental data with the presence or absence of the worker in the particular environment.

The sensor data from the various sensors may be received by the server (12) in real-time or near real-time, and the data analytics module (57) may analyse these parameters or data in near real time. However, data may also be stored, accessed, and analysed at a later stage. It should be appreciated that many other types of harsh environments may be monitored by the present disclosure. For example, the camera or image capturing device (28) (or a plurality of these devices, as the case may be) may provide a video feed to the server (12) and/or to the data analytics module (57). In this case, the video feed may be treated as sensor data and this sensor data or video feed may be analysed by the data analytics module (57) on a frame-by-frame basis, and relevant information, sensor data or environmental parameters may be extracted from digital images provided to the data analytics module (57). This may include worker identification, or facial recognition as mentioned above, however, the data analytics module (57) may further be arranged to identify or detect whether a worker is engaging in risky behaviour and / or being exposed to risk, for example whether a worker is wearing Personal Protective Equipment (PPE) or not. Other types of human behaviour or worker behaviour may be indicated by performing video analytics, for example if a worker is in close proximity with another worker (which may go against a regulation imposed by the user (16) or other entity, for example in light of Covid-19). Other examples of video analytics or detections include, but are not limited to, identifying risky behaviour such as smoking or cell phone usage in certain areas, workers falling down, workers lying down, workers entering prohibited areas, hazardous objects, hazardous substances (e.g. oil spills), and/or hazardous events (e.g. smoke and/or fire). Captured images of workers may be received from the camera or image capturing device (28) by the server (12) and the data analytics module (57) may detect from these received images whether a worker is engaging in risky behaviour or subjected to risk, or whether a worker is wearing PPE or not. Health and safety video analytics may be implemented by a software platform that detects safety anomalies through the video feed or stream of received images, in this example embodiment from a heavy industry such as a mining operation (20). Risky or dangerous behaviour or the presence of risk, or the presence of PPE worn may be detected by video or image analytics (by analysing the sensor data from the camera (28)). Some or all of the video analytics may be performed by the local server (17), or by a computing device associated with the camera (28) or smart camera. This may also be referred to as pre-processing of raw data. The video analytics may be performed by the data analytics module (57), which may be provided locally or remotely. Artificial intelligence may be implemented to identify or detect worker behaviour, including possibly dangerous or risky behaviour, for example by analysing digital data of images or video captured by the image capturing device (28). The data analytics module (57) may partially or wholly be implemented by a computing device associated with one or more of the sensors, or with one or more of the health storage devices. Pre-processing may be performed by a data analytics module associated with a sensor or with a health storage device before the sensor data, or health data, as the case may be, is transmitted to the server (12) for further processing.

It will be appreciated that video data may also be referred to as sensor data, because a video camera or camera may also be referred to as a sensor for sensing light. The sensor data or image data may include human behavioural data, or worker behavioural data. It may be possible for the system to determine human behaviour from the analysed sensor data (in other words, by analysing images in the video feed). It may also be possible to determine if humans or workers are in close proximity to one another, or if they are in close proximity with a potentially dangerous or harmful environment or an item of equipment that may be dangerous or harmful. It will further be appreciated that the present disclosure extends to other industries as well. People or workers may be monitored and detected, and the system may implement forbidden zones, hard hat detection, detection of safety glasses or goggles, face masks, ear protection devices, or even detection of the use of cell phones (for example in a zone where cell phones are not permitted for some reason). The sensor data received by the server may include some or all of this data. The data analytics module (57) may be arranged to analyse the received sensor data and to generate “events” or “catches”. Data relating to these events or catches may be transmitted to the server (12). These events or catches may be flagged or labelled by the server (12) for further processing. It will be appreciated that data analysis performed by the data analytics module (57) may be performed without the use of Al, and binary logic, rules or algorithms may be used.

Video analytics performed by the server (12) or the data analytics module (57) may further include detection of Covid-19 relevant data, which may also be classified as sensor data or environmental parameters, or optionally it may be classified as health data or health parameters. It will further be appreciated that an environment where Covid-19 may be spread may be considered a potentially harmful environment. For example, a user (16) (who may for example be an entity operating the mine (20)) may obligate workers or humans entering their premises to wear a face mask. The image capturing device(s) (28) may detect or identify whether any one of the registered workers is wearing a facemask or not. The system (10) may also be arranged to monitor other personnel or humans, such as visitors, contractors or the like, and these individuals may preferably be required to register at the server, whereafter such an individual may be treated as a worker for the purposes of data analytics. The server (12, 17) may also flag or label the presence of an unidentified human at the premises, and communicate this to the user (16). If any humans or workers are detected not to be wearing a facemask, or not to comply to another regulation imposed by the user (16), then the data analytics module (57) may detect it and process the received sensor data relating to such an occurrence or event, and communicate this to the user (16). Proximity sensors may also be used to sense the proximity of workers to one another, or the proximity to a potentially harmful environment, or potentially harmful item of equipment (e.g. a noisy piece of machinery).

Still referring to Figure 1 , one or more health data storage devices (32, 36, 38, 42) may be in data communication with the server (12) or with the data analytics module (57), to communicate health data of the plurality of workers (18) to the server (12). These health data storage devices may be provided by any electronic device capable of storing health data about the relevant worker. For example, a worker’s mobile device or mobile phone (32) may include health data, such as movement data or acceleration data. The worker’s mobile device (32) may optionally be in data communication with the server (12). It will be appreciated that some or all of the health data storage devices may also include sensors for generating sensor data relevant to the worker. For example, an accelerometer or sensor of the mobile device (32) (or smartwatch (36)) may generate movement data of the worker, or it may even generate acceleration data indicative that the worker is undergoing a dangerous activity such as falling, running in a zone where it is not allowed, or standing or moving in an area that is vibrating. This data may also be received by the server and it may be treated as sensor data. One or more of the plurality of sensors (22, 24, 26, 28, 30, 32, 34, 36, 38) may thus be provided by smart watches, smartphones or other electronic devices that generate location data, acceleration data, or other environmental data relevant to the worker (18).

Other health data storage devices associated with one or more of the workers (18) may include smart watches (36) or other wearable devices such as heart rate monitors or any electronic device (preferably an loT enabled device) capable of sensing or storing health data or health parameters of the worker (18). A further example of a health data storage device may be a database (42) which may include health records (44) or historical health data of one of the registered workers (18). Optionally, the plurality of health data storage devices may incorporate one or more health sensors which may for example be provided by wearable electronic devices or wearable medical devices such as heart rate monitors or electrocardiography devices, blood pressure monitors, glucose monitors, biosensors or any sensor capable of sensing a health related parameter or health data relevant to the worker (18).

The server (12) and/or the data analytics module (57) may be arranged to process worker health data or health parameters from various sources such as the electronic health records (44), medical aid records and health risk management systems. Health data or health parameters may include weight, waist circumference or measurement, height, glucose levels, cholesterol levels, haematocrit, blood pressure, oxygen saturation, heart sounds, heart rate and heart rhythm. Some or all of this health data or these health parameters may be transmitted by the health data storage devices (32, 36, 38, 42) to the server (12, 17) and/or to the data analytics module (57) for further processing.

The data analytics module (57) may be implemented by the server (12) to perform near real-time analysis of the received sensor data and health data to determine if any of the received sensor data or health data exceeds a threshold (60) (shown schematically in Figure 1 ). This may enable the one or more users (16) to react, preferably proactively, to the notification (62). In other words, the users (16) may be enabled to act proactively in response to the notification, so as to inhibit harm or injury to workers, or to provide safety even across a large industrial site or the like. This may find particular application, or it may provide advantages in relatively larger industrial applications or remote workspaces where monitoring health and safety of workers may be difficult using known methods or systems. The user device (46) may be arranged to implement one or more actionable recommendations based, inter alia, on the notification (62). The analysis need not be performed in real-time or in near real-time, and data or received sensor data or received health data may be analysed by the data analytics module (57) “after the fact”, or after a period of time. Data processing and analysis of the received sensor data and health data may be performed, and the data analytics module (57) may implement rules and algorithms to analyse the received data. If it is determined that any of the health data, or any of the sensor data exceeds the threshold, then the data analytics module (57) or the server (12) may generate the notification (62) based on the analysis. Different thresholds may be selected for different types of sensor data, or for different types of health data, and the received data may be compared to these thresholds. The notification (62) may be a single notification indicative of a potentially dangerous event, or an event related to the safety or health of one or more of the workers (18), or the notification may also be a list of notifications, depending on the particular application. As described above, the server (12) may further be arranged to implement one or more user portals (52) in data communication with the server (12), wherethrough the notification may be communicated to one or more registered users (16) of the system (10). Alternatively, the server (12) may communicate the notification to one or more of the user devices (46) through the user communication module (81 ). The data analytics module (57) may thus implement data processing and analysis by using artificial intelligence rules or algorithms or machine learning algorithms, to analyse the received sensor data and health data in order to generate one or more notifications and one or more actionable recommendations, for example depending on sensor data received that may be indicative of a potentially harmful environment, or received health data that may be indicative of a potentially harmful health parameter or health condition of the worker. This may be indicative of a risk level or risk assessment of the relevant worker. The data analytics module (57) may also be arranged to perform one or more of: determining an insight, reaching a conclusion or making a prediction based on the processing of the sensor data and/or health data. Any one or more of these may be included in the notification (62), list or message. The notification (62) may be in the form of a report, a warning, an alert message or an alarm.

It will be appreciated that the data analytics module (57) or the server (12) may analyse the received health data and sensor data and determine if any one or more of these exceeds a threshold. In many cases, a contextualization of data from various sources may be implemented by means of algorithms, for example scanning vast amounts of data and/or detecting or predicting potential risk, harm, negative health trends, positive health trends etc. As an example, the health data and/or sensor data may be indicative that: a worker (18) is obese or that an obesity threshold is exceeded (for example based on health data or sensor data received from a wearable device (36), or health data retrieved by the server from the worker’s health record(s) (44)); that the worker (18) has high blood pressure or that a blood pressure threshold is exceeded (again, based on received health data or sensor data); that the worker is working too much or that a work time threshold is exceeded (for example when the worker is working shifts that are excessive, based on timing data and/or received sensor data, or access control data); and that the temperature of a working environment of the worker (18) is too high or that a temperature threshold is exceeded for the worker (based on sensor data received from the temperature sensor (26)). The health data and sensor data may be received by the data analytics module (57), analysis of the data may be performed, and the notification (62) may be generated. Any of the aforementioned data may be used in the analysis, depending on practical considerations. The notification may be an alert or alert message indicative of danger to the worker’s (18) health, or the notification may be in the form of an alarm. It should be understood that various algorithms may be implemented by the data analytics module to generate the notification, warning or alarm.

The server (12) may further be arranged to generate a worker profile (64) associated with each of the registered workers (18), based on the received sensor data and the received health data. Optionally, the worker profile (64) may be accessible through a user interface or portal (52) available to the user (16) on their user device (46) (see also Figure 3). The worker profile may include the received sensor data, the received health data and other information about the relevant worker (18). It is further possible for the worker profile (64) to also include the notification (62). The notification (62) may optionally include one or more actionable recommendations. These actionable recommendations may be determined based on the received sensor data, or health data, or based on the particular worker, as the case may be. A list of actionable recommendations may be associated with each of the worker profiles (64). These actionable recommendations, or the notification, may be transmitted by the server (12) to the user devices (46) of the users (16) in real-time or in near real-time. This may provide the advantage of enabling the user to act proactively, to inhibit harm to employees or workers, and to improve efficiency of the relevant industry such as the mine (20). The worker profile (64) may optionally include the health data or the sensor data relevant to the worker with which the worker profile is associated. A computing device (46) or user device associated with the user may also be enabled to make decisions or to perform processes based on the notification (62).

The data analytics module (57) may intelligently track each worker and it may associate detected events or detected sensor data with a detected worker located (for example sensed by a proximity sensor) at or near the environment where the environmental parameter originates from. For example, the camera (28) may sense a worker, the data analytics module may recognize or detect the identity of the worker by facial recognition, or the worker may be tracked in another way, for example with an RFID tag and an RFID reader. The data analytics module (57) or server (12) may associate the time and place where the worker is located with received sensor data at that time and place, for example the worker may be located at a time and place where loud noise is detected by the noise sensor (24), or at a time and place where dispersed particles or harmful gases or fluids are detected by the dispersed particle sensor (22), or at a time or place where potentially harmful temperatures are sensed by the temperature sensor (26), or any other harmful environmental effects that may be included in the sensor data received from the plurality of sensors. This may also include the camera (28) or image capturing device, which may also be referred to as an image sensor (28) which may capture images of the worker not wearing PPE. The data analytics module may identify the worker and it may detect from the received image that the worker is not wearing PPE. In such a case the image may form part of the sensor data received.

It will be appreciated that the server (12) and/or the data analytics module (57) may be enabled to keep track of historical data of each worker and this historical data may be included in that worker’s profile (64). The historical data may include sensor data or health data relevant to the worker. For example, a worker may have a health history of heart problems indicated by the health data or health parameters received from that worker’s health records (44), or from health data or health parameters received from a wearable device such as a heart rate monitor (38) of the worker. The data analytics module (57) may keep track of the health data of each worker over short, medium or long periods of time. For example, the server or data analytics module may receive sensor data of the worker that indicate that the worker was in a noisy environment for an extended period of time, and it may also be determined by the data analytics module (57) from received images from the camera (28) that that worker was not wearing ear protection. Alternatively, it may be determined that the worker was in a harmful environment where coal dust or other harmful particles are located (which may optionally be sensed by the dispersed particle sensor (22)). All this data may be tracked over a period of time to create or to populate the worker profile (64) which may be a digital profile associated with the worker. Each of the received health data and sensor data (whether environmental or health related) may be analysed by the server (12 or 17) and/or the data analytics module (57) to determine if the received data exceeds the threshold (60). For example, it might be acceptable for the worker to be in a noisy environment for a short period of time (if wearing ear protection), but once the worker is in that environment for a longer period (exceeding the threshold for noise (or a noise threshold) or a vibration threshold), then the notification or warning may be generated by the server (12) and/or the data analytics module (57). Further thresholds may be determined for each type of sensor data and for each type of health data, as the case may be. A light sensor or radiation detector may also be provided, to generate sensor data that may be transmitted to the server for example if the worker is located at a location where harmful light or radiation is present. Light thresholds, dust thresholds, gas thresholds, radiation thresholds, temperature thresholds, or any other threshold for a potentially harmful environment of the worker may be implemented. Health thresholds may also be implemented, for example if the worker’s heart rate exceeds a heart rate threshold (of the worker’s heart rate is irregular), or if the worker’s body temperature exceeds a threshold (for example showing fever symptoms). A non-contact body temperature sensor may for example be implemented to generate sensor data of the worker’s body temperature. The camera may also capture images of the worker and the data analytics module (57) may determine if the worker is wearing eye protection or not. It will be appreciated that the threshold (60) may be indicative of the health data or sensor data exceeding a threshold, or whether the health data or sensor data is less than a threshold, depending on the particular application.

Figure 2 is a block diagram illustrating an exemplary server (12) that may form part of the system (10) of Figure 1. The server (12) may include a processor (67) for executing the functions of components described herein, which may be provided by hardware or by software units executing on the server (12). The software units may be stored in a memory component (68) or in a database (70) and instructions may be provided to the processor (67) to carry out the functionality of the described components. In some cases, for example in a cloud computing implementation, software units arranged to manage and/or process data on behalf of the server (12) may be provided remotely. Some or all of the components may be provided by a software application downloadable onto and executable on the server (12). The server (12) may include a comparing component (72), which may be arranged to compare the received sensor data and the received health data to the threshold (60), which may be a predetermined threshold, for each of the sensor data or health data, as the case may be. A sensor data receiving component (74) may be arranged to receive the sensor data, whereas a health data receiving component (76) may be arranged to receive the health data. The sensor data receiving component (74) may also be referred to as an environmental parameter receiving component. The sensor data receiving component (74) may be arranged to receive sensor data or environmental parameters from sensors (22, 24, 26, 28, 30, 32, 34, 36, 38) in near real-time (or at any time). The health data receiving component (76) may, in turn, be arranged to receive health data or health parameters from health data storage devices (32, 36, 38, 42). The server (12) may also include, or it may implement, or be connected to the data analytics module (57). The data analytics module (57) implemented by the server (12) may be a neural network (NN) having a deep learning network architecture. The neural network may be a convolutional neural network (CNN) or a fully convolutional deep neural network (FCDNN or FCNN). Other types of machine learning techniques, neural networks or Al may also be implemented. The data analytics module (57) may optionally include, or be connected to, or have access to a machine learning or Al module (56). The data analytics module (57) may optionally include, or be connected to, or have access to an Expert Rule Based (ERB) module (59).

The server (12) may further include a notification generating component (78) (which may optionally form part of the data analytics module (57)). The notification generating component (78) may be arranged to generate the notification (62) as described above, or to generate the actionable recommendations, or the worker profiles (64), as the case may be. The server (12) may also implement a timing component (58) which may be operable to provide timing data such as the date and time related to any of the health data or sensor data, or the presence or absence of a worker in a harsh or harmful environment, at a particular time. The server (12) may include a user communication module (81 ) which may be arranged to transmit the notification (62) to the one or more user devices (46). The server (12) may optionally implement a user device portal interface component (80) which may for example be arranged to provide the user portal(s) (52) or user interface(s). The server (12) may include a transmitting component (82) and a receiving component (84) for sending and receiving data, parameters, notifications etc.

The system (10) or the server (12) may also include a worker identification component (86) which may be arranged to identify or detect the presence or absence of a registered worker in the vicinity of one or more of the sensors or any other specified location in a working environment where a worker is located in use. The worker identification component may also be arranged to monitor workers, and to identify if the worker is or has been in a harmful environment, or if the worker is or has any health condition (which may be potentially dangerous or harmful), which may be identified by the data analytics module (57) by analysing the received health data. The various components of the server (12) may correlate data, and the timing component may for example “date stamp” or “time stamp” data or parameters that are processed by the server (12), in order to facilitate recommendations to be made. The worker identification component (86) may be implemented by the data analytics module (57) (or it may form part thereof), which may analyse data from identification devices or sensors (such as the camera(s) (28), access control devices or sensors (30), or any other sensors) to identify and/or track workers (18). The timing component (58) may also be arranged to associate the received sensor data with a time or date and to associate the presence or absence of a registered worker with received sensor data or environmental data at that time or date, so that the server (12) and/or the data analytics module (57) may determine if the worker is exposed to a potentially harmful environment. The optional local server (17) may be similar to the server (12) and it may include some or all of the components of the server (12), including the data analytics module (57). Embodiments may also be possible where only a local server is provided instead of a remote server. The system (10) may also include a health and safety related event and/or infringement detection component that identifies and logs potentially harmful or risky objects and/or behaviours through analysis of one or more video feeds. This may for example be implemented by the data analytics module (57) which may be arranged to identify and log potentially harmful or risky objects and/or behaviours through analysis of one or more video feeds.

Figure 3 is a block diagram illustrating an exemplary user device (46) that may form part of the system (10) of Figure 1. The user device (46) may include a processor (88) for executing the functions of components described below, which may be provided by hardware or by software units executing on the user device (46). The software units may be stored in a memory component (90) or in a database (92) and instructions may be provided to the processor (88) to carry out the functionality of the described components. In some cases, for example in a cloud computing implementation, software units arranged to manage and/or process data on behalf of the user device (46) may be provided remotely. Some or all of the components may be provided by a software application downloadable onto and executable on the user device (46). The user device may include the user portal component (58) which may interface with the user device portal interface component (80) of the server (12). A user interface may be provided to each user (16) via the user device (46). The users (16) may be enabled to use the portals to view worker profiles (64), notifications (62) or recommendations (or actionable recommendations) or lists of recommendations of a workforce of workers (18) of the user (16), or associated with the user (16). A notification receiving component (94) may be implemented to receive the notification from the server (12). This notification may also be referred to as a warning, alarm or alert. One or more of the sensor data or health data associated with each of the workers may also be communicated to the relevant user device (46) if needed. The user device (46) may include a transmitting component (96) and a receiving component (98) for sending and receiving data, parameters, notifications etc.

The system (10) described above may implement a method for monitoring worker health and safety. An exemplary method (100) for monitoring worker health and safety is illustrated in the swim-lane flow diagram of Figure 4 (in which respective swim-lanes delineate steps, operations or procedures performed by respective entities or devices). It will be appreciated that the method may be carried out by the server, or by the sensors, or by the health data storage devices, or by the user devices, or by a combination of one or more of these entities or devices.

The plurality of sensors (22, 24, 26, 28, 30, 32, 34, 36, 38) that may be in data communication with the server (12) may sense (102) the sensor data in near real-time, and may transmit (104) or communicate the sensor data to the server (12) over the data communications network. The server (12) may receive (106) the sensor data and it may associate the received sensor data with one or more of the plurality of registered workers (18). The one or more health data storage devices (32, 36, 38, 42) may transmit (108) health data of one or more of the registered workers (18) to the server (12) over the communications network. The server (12) may receive (106) health data of the plurality of workers from the one or more health data storage devices (32, 36, 38, 42). The received health data may also be associated with one or more of the registered workers (18), e.g. by the server (12). The data analytics module (57) may form part of the server (12), or in the present embodiment, the data analytics module (57) may be implemented (110) by the server (12). The server (12) may also implement (110) data analytics of the received data by way of the data analytics module (57). Alternatively, the server (12) may be capable of instructing the performing of analysis of the received sensor data and health data to determine if any of the received sensor data or health data exceeds a threshold. The data analytics module (57) may perform near real-time analysis of the received sensor data and health data. It will be appreciated that data analytics need not necessarily be performed in near real-time or real-time, and data may be stored and analysed at a later stage. The data analytics module (57) may determine (112) if any of the received sensor data or health data (as the case may be) exceeds a threshold. If the sensor data or environmental parameter, or the health data or health parameter (as the case may be) does not exceed the threshold, the data analytics module (57) may continue monitoring and/or analysing (110) the received data or received parameters. If any one of the received health data or sensor data exceeds the threshold, a notification may be generated (114) based on the analysis. The notification or message may be transmitted or communicated to a user device (46) of a user (16) registered for use of the method, where it may be received (116), for example by way of the user portal of that user device, or through the user communication module (81). The notification may include one or more actionable recommendations, and these actionable recommendation(s) may optionally be implemented (118) by the user device (46) in data communication with the server (or the actionable recommendation(s) may be performed by the server). It should be appreciated that the notification may also be sent if one or more of the sensor data or health data does not exceed the threshold or is less than the threshold.

Referring again to Figure 1 , domain expert and technical support services may be delivered with the aid of one or more software suites from a remote monitoring and diagnostics centre that may be provided by the operator (14). The operator (14) may provide domain experts, technical know how and infrastructure suited to providing a responsive, professional service. A services value chain may include service requests created by one or more of the users (16) or customers. The data analytics module (57), and the operator may identify a required action based on system status, received sensor data or received health data or data input. The cloud-based infrastructure (54) may be provided by a cloud platform such as Microsoft Azure™, however other types of cloud-based infrastructures may be implemented.

The system architecture may be scalable, and more users with more premises or industries may be implemented as needed. The system and software implementation may be arranged to be scaled depending on the particular application. Different types of numbers of sensors may also be implemented, depending on the type of industry involved. The present disclosure may provide a framework for leveraging Al and/or expert rules for real-time or near real-time analytics. The system and method disclosed may implement a hybrid cloud and edge architecture design. The portal (52) may optionally include a Key Performance Indicators (KPI) dashboard and management portal framework. Machine learning models for video analytics such as PPE detection, harmful environment detection and/or worker behaviour detection(s) may be implemented by the server (12) and/or by the data analytics module (57). The operator (14) and the database (40) of the server may include an industrial database for machine learning training, which may be implemented, accessed or used by the data analytics module (57). The data analytics module (57) may also implement video labelling technology, for example to label images of workers wearing PPE or not, or labelling potentially harmful environments, or potentially harmful environments or equipment. The data analytics module (57) may be trained with a plurality of training images. A system performance measurement platform may be provided to enable regression testing. The server (12) and/or the operator (14) may further provide a remote healthcare consultation platform, which may for example have Food and Drug Administration (FDA) approval and registration as a medical device by the relevant entity, such as the South African Flealthcare Products Regulation Authority (SAHPRA) in South Africa. The server (12) or operator (14) may further provide a digital platform enabling the transfer of patient sounds such as heart and lung sounds measured by digital devices over the internet from a remote patient to a doctor. In such a case, the worker (18) may also be referred to as a patient. A machine learning based heart valve online and automated diagnostics system (or sub-system) may also be implemented by the operator (14) or server (12), and this sub-system may also be FDA approved and it may include a validated training database for machine learning models that may be implemented by the data analytics module (57).

The system and method of the present disclosure may provide a cloud-based software platform with interactive dashboards that may be standalone and that may integrate with existing enterprise platforms, for example an enterprise platform managed by the user (16). A management portal (52) may be provided to configure all sensory input networks and systems. The data analytics module (57) may implement analytics that may provide a correlation between a worker’s (18) history (health and exposure as may be indicated by the received health data and sensor data) and their health risk profile including a decision-making system providing actionable advisories or actionable recommendations. The system and method may find particular application with the prevention or inhibition of cardiovascular disease, lung disease and noise induced hearing loss of workers, or providing safety or protection against these or other harmful effects.

Video analytics features may be updated and maintained by the operator (14) to implement the latest market information, regulatory pressures and COVID-19 factors. The video analytics or image analytics performed by the data analytics module (57) may include or implement features such as detecting masks, crowd forming (where workers are not adhering to social distancing protocols), whether a worker is wearing a hazmat suit or not, whether a worker is wearing a high visibility jacket, whether a worker is wearing an overall, detection of open manholes, detection of an access door being blocked by an object, detection of an access door left ajar, detection of an abandoned or idling vehicle, detection of a worker that is running, detection of worker smoking, detection of workers or person loitering, detection of object(s) taken or stolen, detection of a new object in a scene or environment, and detection of an object abandoned in an environment. Some or all of this detection may be performed by the data analytics module (57) analysing images received (the images including sensor data or environmental parameters) from surveillance camera(s) (28), or some of the detection and analysis may be performed based on sensor data or environmental parameters received from other sensors. For example, a smoke detector or sensor may be used to detect smoke, whether it is a worker smoking in an area where flammable fluid or gas is located, or whether it is the detection of smoke, fumes or dispersed particles that may be harmful to the worker(s) (18).

One or more of the cameras (18) may be smart cameras. The smart cameras may include onboard deep learning and thermal sensing capabilities, and these smart cameras may generate sensor data or meta data which may be received by the server (12) and/or the data analytics module (57). Optionally, some or all of the sensor data may be processed locally by a computing device associated with the camera (28), or by the local server (17). The server (12) or local server (17), as the case may be, may be arranged to extract this meta data from the smart cameras (in this case the meta data may be referred to as sensor data or environmental parameters) and the server or data analytics module (57) may interpret and analyse this meta data to compare it to a threshold, or to generate the notification, if need be. The server (12) and/or the data analytics module (57) may implement methods to communicate with Video surveillance Management Software (VMS) and/or Network Video Recorder NVR systems. A network video recorder (NVR) may be referred to as a specialized computer system that may include a software program that records video in a digital format to a disk drive, USB flash drive, SD memory card or other mass storage device. The NVR may be typically deployed in an Internet Protocol video surveillance system. The camera (28) or image sensor may be an NVR. Network video recorders may be distinct from digital video recorders (DVR) as their input may be sourced from a network rather than a direct connection to a video capture card or tuner. Video on a DVR may be encoded and processed at the DVR, while video on an NVR may be encoded and processed at the camera, then streamed to the NVR for storage or remote viewing or analysis. Additional processing may be done at the NVR, such as further compression or tagging with meta data. The camera (28) or image sensor or image capturing system may be any one of an NVR or a DVR. Hybrid NVR/DVR surveillance systems may also be implemented which incorporate functions of both NVR and DVR, and the surveillance system may be wireless or wired. Some or all of the features of the data analytics module (57) may be provided or performed by a computing device associated with the camera (28) or the local server (17).

The data analytics module (57) may implement algorithms making use of various sources of data including methods of extracting data from access control systems (30) and wearable devices (32, 36). A person or worker (18) location identification algorithm may be implemented which may make use of various data sources such as video feeds, wearables and access control systems. These data sources may be used to receive sensor data, environmental data or environmental parameters relevant to the worker and it will be appreciated that a worker’s location at a particular time and place may also be considered as an environmental parameter or sensor data of the worker. Health data or health parameters may be received by the server (12) from existing platforms such as health record systems, or health records (44) of the worker in the database (42), however health data or health parameters may also be received from wearable devices of the worker. Sensor data and/or environmental parameters may be received from environmental sensors which may be referred to as site-based sensors as they may be located at the relevant site, premises or location (for example at the mine (20) in the example embodiment shown in Figure 1 ).

Software may be deployed via the Internet and installed remotely through a remote commissioning and installation process. The software may be deployed via the cloud (54) to a plurality of devices or sensors that may be located at distributed locations. These devices or sensors may be referred to as on-site edge devices, in other words, devices that may be provided at the location of the industry (e.g. at the mine (20)).

The system (10) may include a plurality of data analytics modules and one or more of these data analytics modules may be implemented by the local server (17) or even by one or more electronic devices or computing devices associated with the plurality of sensors or health data storage devices. The size of the data analytics modules may be fairly large (several of GB) and may take a relatively long time to deploy to site, but software layering and dynamic or intelligent updating (for example by way the loT network) may be implemented to mitigate this.

Firewall ports may need to be opened to various Azure resources to ensure connectivity. The server (12), or the local server (17) may be capable of implementing one or more, or all of the features of the present disclosure. Depending on the features that will be deployed and the number of camera feeds that needs to be consumed or implemented, a careful analysis may be performed to allocate server resources to ensure that requirements may be met.

The systems and methods disclosed may implement a Worker Health and Safety system or product which may provide ongoing value to the customer or user (16) in the form of a subscription model. The system may be licenced to customers or users and the operator (14) may ensure that software is up to date. Ongoing services may be provided such as technical support to ensure continued uptime and performance. This may include continuous remote health monitoring, a help desk, a support ticketing system and the troubleshooting of technical problems. Machine learning may be implemented by the data analytics module (57), which may include efficient capture of training data, data labelling and preparation, appropriate model selection and training, model performance evaluation, ongoing model improvements. Machine learning or machine intelligence may be catered to health and safety requirements and the health and safety machine intelligence may be kept up to date, in line with the latest research or information. Actionable insights or recommendations may be provided by the system and these may be used by customers or users (16).

The present disclosure may provide a cloud-based software platform and remote services offering that may combine employee or worker health data (which may also be referred to as health parameters) and workplace environmental data or sensor data (which may also be referred to as environmental parameters). The software platform may analyse the data through expert rules and machine learning algorithms and it may provide actionable advisories and insights to users (16). Software algorithms implemented may rely on deep domain knowledge and the algorithms may be developed in close collaboration with Occupational Health and Safety experts and doctors. Employee health data, health parameters or health data may be sourced from various health record sources and environmental data or sensor data may be sourced from loT based sensor networks including CCTV video cameras.

The present disclosure may address the emerging needs of heavy industries such as mining and mineral processing plants to monitor and act upon health and safety data whilst taking advantage of Industry 4.0. Worker health and worker safety may be handled as interrelated functions with interrelated phenomena instead of separate concerns while considering employee health from an individualised, worker-centric perspective. The server (12, 17) and/or the data analytics module (57) may process environmental data such as temperature, humidity, dust levels, vibration, gas levels, lightning strikes and any many more to gain insights into worker exposure. One or more sensors may be implemented for sensing these physical properties, and may generate sensor data or environmental parameters. For example, a humidity sensor, dust sensor, vibration sensor, gas level sensor or lightning sensor may form part of the loT sensor network (50). The server (12,17) or data analytics module may process video feeds from existing CCTV camera networks to detect safety anomalies, PPE, people, objects and risky behaviour. Detections may also include behaviours that may affect the spreading of a disease or virus such as COVID-19, such as the wearing of masks, coughing, hand shaking and social distancing. Sensor data or health data or other data from wearables and access control systems (including thermal camera screening) may be performed by the server (12, 17) and/or the data analytics module (57) to enable insights into worker biometrics and location history. The artificial intelligence implemented by the data analytics module as well as the rules and algorithms implemented may be designed from the ground up in close collaboration with industry experts, for example focussing on risks related to i) cardiovascular disease including hypertension, pathological valve disease and heart rhythm abnormalities, ii) pulmonary disease and iii) hearing loss. Health data relating to any one or more of the above may be received by the server (12, 17).

The findings of the data analytics module, or notification may be provided as one or more actionable insights or recommendations in a visual standalone dashboard or portal (52) with customisable reports. The system (10) may also be arranged to integrate with existing health and safety related software platforms that customers or users are already using. The server may be arranged to transmit one or more notifications, warnings or alerts (in case of health and safety findings or analysis about workers (18), and/or analysis of health data and sensor data, high risk or life-threatening findings by the data analytics module (57) and/or the data analytics module (57)) and notifications may be transmitted through various platforms including WhatsApp™, SMS, Email or any other communication network to relevant employers, customers or users (16), or to the workers (18) or employees. As described herein, notifications may be transmitted by way of the user communication module (81) shown in Figure 2. Ongoing value may be provided to users (16) through remote services such as technical system support and domain specific services enabled by the cloud environment such as Microsoft Azure ™. The cloud infrastructure (54) may be a secure cloud infrastructure. An IS027k General Data Protection Regulation (GDPR) information security management system may be implemented.

Latest health research may provide insights into correlations between a worker’s health history, latest biometrics and future risks. Clinical experts may use this domain knowledge to establish correlations between worker health history and potential health risks. A worker’s health status may be determined from pre-existing health conditions, health history, latest health metrics, historical and real-time biometrics data or received health data or received health parameters. A worker’s health risk profile or worker profile (64) may be determined by incorporating up-to-date information and records regarding worker exposure to harmful environments and worker behaviour, which may enable both employers or users (16) and workers (18) or employees to take the necessary actions and precautions to protect lives. The present disclosure may find particular application in the mining industry. Prevalent health risks associated with the mining industry (or any other industry) may be inhibited or mitigated by using the systems and methods disclosed. Examples of these are as follows. Firstly, cardiovascular disease may be addressed, mitigated or inhibited. Cardiovascular disease remains a major cause of death worldwide and in particular those workers (18) exposed to risk factors such as carbon monoxide, noise, vibration, temperature extremes and shift work. Secondly, lung disease may be inhibited, prevented or mitigated. Lung disease may be caused by exposure to harmful airborne particles such as coal (coal workers' pneumoconiosis), asbestos and silica dust. The particle sensor(s) (22) may detect the presence or absence or these sensors may detect levels of these harmful particles that a worker may be exposed to. Thirdly, noise induced hearing loss (NIHL) may be caused by continuous exposure to harmful levels of noise and NHL may be predictable and preventable by implementing the present disclosure. Lastly, musculoskeletal disease may be caused by physical labour such as recurring physical movements or uncomfortable postures and may include lumbar sprains and spasms, shoulder sprains and spams, spinal disc problems, knee pain and ankle sprains. Many other harmful environmental or health effects may also be mitigated or inhibited by the present disclosure to protect workers.

The video analytics or image analytics performed by the data analytics module(s) (57) may implement deep learning artificial intelligence techniques to analyse a plurality of (typically thousands of) video feeds or sensor data in real-time or near real-time to detect equipment, people, anomalies, incidents and behaviours that relate to workers’ health and safety. Video feeds and/or sensor data may be analysed on a frame-by-frame basis, and machine learning algorithms may scan and identify events on video frames, which may be tagged or labelled. These labelled images or frames may be presented to users or other systems to take the necessary action. The video analytics implemented by the system (10) may utilise a hybrid architecture consisting of a Microsoft Azure cloud environment and a graphics processing unit (GPU) enabled, site-based edge device (server (17)) to run the machine learning algorithms and perform the intensive machine vision processing. Some or all of these features may also be provided remotely, for example on the server (12), or through the cloud infrastructure (54). Software engineering may be implemented to take domain specific algorithms and to convert this into machine readable and executable code that controls the functioning of the system (10).

The present disclosure may unify or integrate two typically separate domains, namely health and safety. The system (10) may source data from both people and their working environments, and it may process the data in real-time or near real-time. The system may make findings or recommendations based on deep medical domain knowledge and the system may be accessible to the user (16) in one place, for example via a platform or portal (52) of the customer’s or user’s choice. Alternatively, the server (12) may communicate the notification to one or more of the user devices (46) through the user communication module (81 ).

Video analytics may also be performed by the data analytics module (57) and the analysis of received sensor data or environmental parameters (in this case forming part of received images) need not involve the use of Al. For example, the data analytics module (57) may perform video or image analysis of the received images or video feed to determine that a worker is located in the vicinity of a boiler. Thermal imaging may for example be used, or data may be received from a temperature sensor. The timer or timing component may be arranged to time the duration that the worker is in the vicinity of the boiler and the data analytics module (57) may generate the notification (62) if the worker is located in the vicinity of the boiler for a period of time that exceeds the threshold (60). Many other scenarios are possible, and the threshold (60) may be defined in a variety of ways, (e.g. the threshold may be related to another type of sensor data or environmental parameter or another type of health data or health parameter). For example, the threshold may be exceeded if a metric (e.g. health data or sensor data) exceeds a predefined value, or the threshold may be exceeded if the metric is less than or equal to the predefined value.

The present disclosure may inhibit or prevent harm to workers, and it may inhibit or prevent accidents or fatalities of workers, protecting the workers. Data including health data or health parameters; and sensor data or environmental parameters may be centrally located or it may be stored in a central repository, for example the database (40 or 42). This data repository may be kept up to date, updated frequently, repetitively or in real-time. The present disclosure may provide a predictive, proactive management or monitoring system or method of monitoring health and safety or monitoring health and safety risks. The present disclosure may be implemented for heavy industry companies, for example those involved in mining, oil and gas, manufacturing, chemical and energy organizations or many other industries throughout the private and public sectors. The portal (52) and/or user interface provided to the users (16) may be arranged to be intuitive, to facilitate ease of use.

Systems and methods of the present disclosure may also facilitate compliance with all relevant international standards and regulations for occupational health and safety. Many countries today enforce stringent health and safety regulations on heavy industry operations. In South Africa, regulations are provided by the South African Council of Health and Safety in Mining (MHSC), and the system may be arranged to implement one or more of these regulations, or requirements set by the relevant authority in any country where the systems or methods are implemented.

The present disclosure may implement stringent information security compliance from customers or users. Internationally recognised information security and data protection standards and regulations may be implemented by the server (12) or the system (10) as a whole. This may provide a framework for an information Security Management System (ISMS) which may be integrated into the system. Relevant standards and regulations may include: i) ISO 27001 :2013 Information Security Management Systems (ISMS); ii) General Data Protection Regulation (EU) 2016/679 (GDPR); iii) The South African Protection of Personal Information Act, No. 4 of 2013 (POPIA); and Other legislation and regulations required by local authorities in a region or country where the systems and methods of the present disclosure are implemented. The present disclosure may implement clinical domain knowledge which may form part of the received health data or health parameters that are received by the server (12) to identify the relevant correlations between medical history, exposure information and health risk status. Health data or health parameters may also be generated by the server (12), for example by accessing health databases or information. Data may be sourced or received from clinical and occupational health specialists or databases associated with health entities.

The present disclosure may enable proactive actions to be taken, instead of reactive responses due to fatalities, injuries or harm that has already occurred. This may enable the health and safety of workers to be protected more efficiently than would have been possible using known systems or methods. The present disclosure may also provide a centralised health and safety database whereby data about worker health and safety may be sourced in real-time which is frequently, repetitively, or continuously updated. This may provide advantages over known systems and methods where data is heavily siloed into separate health and safety systems, where the data is not available in real-time and/or not updated frequently, and where worker health is not individualised but rather viewed as part of a population exhibiting general health issues.

In Figure 6 is shown a high-level block diagram of another example embodiment of a worker health and safety system (1000). Another high-level block diagram of this embodiment is shown in Figure 7, showing more detail. It should be appreciated that the embodiments shown in Figures 6 and 7 may include any or all of the features of the other embodiments described herein, and the other embodiments of Figures 1 to 5 may also include one or more of the features of the present embodiment of Figures 6 and 7. Data (including sensor data and health data) may be generated (1010) through sensors or activities of workers. Video feeds or sensor data from cameras (1028) may be processed and analysed by the system (1000). Sensor data or other data from access control systems or sub-systems may also be generated (1034). Sensor data or environmental data may be generated (1026) by environmental sensors (for example temperature sensors or other sensors described above). Sensor data or health data may be generated (1036) (or it may be pre-stored) by health data storage devices or wearable devices. Health data may further be generated (1038) or it may be pre-stored by computing devices associated with clinical devices or screening procedures. Sensor data and health data may be transmitted to a streaming and analytics module (1057.1 ), which may be implemented by any computing device, but typically it may be implemented by a server or computing device for pre-processing. This pre-processing may for example be performed by a computing device associated with a sensor, or with a health data storage device, or by a local server. The pre-processing may be performed locally or remotely. Video analytics (1029) may be performed on sensor data or video feeds received from camera(s) such as Closed-circuit television (CCTV) or video surveillance cameras. The streaming analytics module (1057.1 ) may form part of a data analytics module (See (57) in Figure 1 , for example).

Events may be detected from the analysed video or images, and people, workers, worker behaviour or items may be analysed. A worker’s identity may be determined, and a worker’s location may be analysed (1031 ), in particular when the location of the worker is relevant to health and safety of the worker. Clinical sounds and/or images may also be analysed (1033), for example originating from health data received from (or generated by) health data storage devices or real time (and/or near real-time) measurements. Data (including health data and sensor data) may be stored at a local server or at a remote server (as the case may be) and it may be updated (1035) in real-time or near real-time. It will be appreciated that the health data and sensor data or other data may also be updated repetitively or periodically (and this updating need not necessarily be in real-time or near real-time). The data processed by the system (1000) may include health data or health and safety data (1037) as well as sensor data (1039) or environmental data. All this data may be stored at a database associated with a server. As described above with reference to Figure 1 , health data may also be accessed from health records (1044) of each worker. The sensor data and health data may be received by a central server (1012) or backend, which may be provided locally or remotely. Expert rules and Al may compare and process (1057.2) the health data (1037) (which may be referred to as health and safety data), as well as health data accessed in electronic health records (1044). This processing may be performed by a data analytics module accessible by the server or backend. The health data may for example be compared to a health threshold, or a safety threshold. Expert rules and Al may further compare and process (1057.2) the sensor data (1037) or environmental data, and it may be compared to a threshold, depending on the type of sensor (See Figure 1 and related description for examples). Actionable insights, notifications, messages or advisories may be generated (1043) and optionally communicated to one or more user devices (See examples in Figure 1). Dashboards and notifications may be provided (1045) to users of the system (1000). The systems and methods of the present disclosure may provide a cloud-based software platform and remote services offering that may combines employee health data and workplace environmental data. Actionable advisories and insights may be provided to users. Software algorithms may rely on deep domain knowledge developed in close collaboration with Occupational Health and Safety experts and doctors. Employee or worker health data may be sourced from various health record sources. Health record data may be generated by:

Health data generated by devices measuring patient vitals during clinical assessments;

- Asking patient questions during medical consultations and accessing health data relating to these questions;

Health data relating to clinical test results; Health data relating to medical procedures and/or medical history;

Environmental data or sensor data may be sourced from loT based sensor networks including:

- CCTV video cameras;

- Wearable devices;

- Access control systems;

The system (1000) may provide information or data to users in dashboards (Standalone or Customer) and as notifications.

More detail of the system (1000) of the exemplary embodiment is shown in Figure 7. Video feeds from cameras (1028) may be analysed by the streaming analytics module (1057.1 ) as described above. Events (1047) may be detected in the analysed images, and these events may form part of the health data, or it may form part of the sensor data. In the present embodiment this data is referred to as health and safety data (1037). Movement data (designated “MMT”) (1049) of one or more of the workers may be generated, for example by wearable devices (1036) of the workers. This movement data may be analysed by a movement data analytics module (1051) which may be provided by the streaming and analytics module (1057.1 ) and/or by the data analytics module (57) (See Figure 1). The movement data (1049) may be included in the health and safety data (1037). It will be appreciated that the health and safety data (1037) may also be referred to as sensor data. Data generated by the wearable device (1036) such as a smartwatch or mobile device, may include acceleration data (1053) which may be indicative of a worker’s movements.

One or more thermal scanners (1055) may be implemented, for example to measure body temperature and/or to detect if the worker has a fever or not. One or more video cameras may be implemented, for example to determine an identity of a worker or to generate identity data of the worker. Location data of the worker may be generated by the wearable device, or by an access control system (1034) (or sub-system) which may interface with the system (1000). This location data and identity data may be input to an identity (ID) and location (LOC) analytics module (1059). Integration services (1061 ) may be provided if needed. The location data (LOC) and identity data (ID) of workers may be processed, and stored (1063), for example in a database accessible by the backend or server (12). Biometric data (1065) may also be generated or accessed, and it may be stored in health records (1044) of the worker. Environmental data or sensor data may be generated by sensors such as environmental sensors (1026) as described herein, and this environmental data or sensor data (1039) may be stored, preferably, but not necessarily in real time or in near real-time.

The system (1000) may include, or it may receive data from one or more clinical or medical devices (1069). These devices may be electronic devices that generate health data of a worker, or data may be input by medical practitioners conducting clinical tests, health risk assessments, consultations, medical procedures or medical aid claims. Remote consultations may also be conducted and health data captured. The health data of a worker may also be generated by hearing analytics (1073) or a hearing analytics module (for example to determine hearing data of the worker), or by cardiac analytics (1075) or a cardiac analytics module to determine health data such as heart condition related data or the like. The health data may be input and stored in electronic health records (1044) of each of the workers. One or more aggregators (1071) or an open medical record system (MRS) may be implemented to source data from various other databases.

As shown in Figure 7, the data including the sensor data and health data from various sources may be received by the server or backend (12). The data analytics module (1057.2) may implement the expert rules and/or Al to compare and process:

- Medical history;

- Noise exposure;

- Airborne contaminants exposure;

Heat exposure;

Excessive working hours;

Risky behaviour;

- etc.

Optionally, the data analytics module may be arranged to focus on cardiovascular disease, pulmonary disease, musculoskeletal disease, or noise induced hearing loss. The system may be arranged to analyse the health data and sensor data to predict these diseases, and/or to prevent these diseases from occurring in the first place. As described above, actionable advisories or notifications may be generated (1043) and provided to the users via one or more dashboards (1045) or user portals. These dashboards or user portals may be standalone or they may be integrated into a customer or user portal associated with the user (for example the user (16) operating the mine in the example embodiment of Figure 1).

It should be appreciated that any one or more of the features, steps or processes described herein with reference to the data analytics module may be implemented by the server, or by the Al module, or by implementing the ERB module, or by implementing rules and algorithms to analyse the received sensor data and health data.

Figure 5 illustrates an example of a computing device (500) in which various aspects of the disclosure may be implemented, such as the server (12), local server (17), data analytics module (57), user devices (46) worker devices (32, 36), or sensing devices or sensors (22, 24, 26, 28, 30, 32, 34, 36, 38). The computing device (500) may be embodied as any form of data processing device including a personal computing device (e.g. laptop or desktop computer), a server computer (which may be self-contained, physically distributed over a number of locations), a client computer, or a communication device, such as a mobile phone (e.g. cellular telephone), satellite phone, tablet computer, personal digital assistant or the like. Different embodiments of the computing device may dictate the inclusion or exclusion of various components or subsystems described below.

The computing device (500) may be suitable for storing and executing computer program code. The various participants and elements in the previously described system diagrams may use any suitable number of subsystems or components of the computing device (500) to facilitate the functions described herein. The computing device (500) may include subsystems or components interconnected via a communication infrastructure (505) (for example, a communications bus, a network, etc.). The computing device (500) may include one or more processors (510) and at least one memory component in the form of computer-readable media. The one or more processors (510) may include one or more of: CPUs, graphical processing units (GPUs), microprocessors, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs) and the like. In some configurations, a number of processors may be provided and may be arranged to carry out calculations simultaneously. In some implementations various subsystems or components of the computing device (500) may be distributed over a number of physical locations (e.g. in a distributed, cluster or cloud-based computing configuration) and appropriate software units may be arranged to manage and/or process data on behalf of remote devices.

The memory components may include system memory (515), which may include read only memory (ROM) and random access memory (RAM). A basic input/output system (BIOS) may be stored in ROM. System software may be stored in the system memory (515) including operating system software. The memory components may also include secondary memory (520). The secondary memory (520) may include a fixed disk (521 ), such as a hard disk drive, and, optionally, one or more storage interfaces (522) for interfacing with storage components (523), such as removable storage components (e.g. magnetic tape, optical disk, flash memory drive, external hard drive, removable memory chip, etc.), network attached storage components (e.g. NAS drives), remote storage components (e.g. cloud-based storage) or the like.

The computing device (500) may include an external communications interface (530) for operation of the computing device (500) in a networked environment enabling transfer of data between multiple computing devices (500) and/or the Internet. Data transferred via the external communications interface (530) may be in the form of signals, which may be electronic, electromagnetic, optical, radio, or other types of signal. The external communications interface (530) may enable communication of data between the computing device (500) and other computing devices including servers and external storage facilities. Web services may be accessible by and/or from the computing device (500) via the communications interface (530).

The external communications interface (530) may be configured for connection to wireless communication channels (e.g., a cellular telephone network, wireless local area network (e.g. using Wi-Fi™), satellite-phone network, Satellite Internet Network, etc.) and may include an associated wireless transfer element, such as an antenna and associated circuitry. The external communications interface (530) may include a subscriber identity module (SIM) in the form of an integrated circuit that stores an international mobile subscriber identity and the related key used to identify and authenticate a subscriber using the computing device (500). One or more subscriber identity modules may be removable from or embedded in the computing device (500).

The external communications interface (530) may further include a contactless element (550), which is typically implemented in the form of a semiconductor chip (or other data storage element) with an associated wireless transfer element, such as an antenna. The contactless element (550) may be associated with (e.g., embedded within) the computing device (500) and data or control instructions transmitted via a cellular network may be applied to the contactless element (550) by means of a contactless element interface (not shown). The contactless element interface may function to permit the exchange of data and/or control instructions between computing device circuitry (and hence the cellular network) and the contactless element (550). The contactless element (550) may be capable of transferring and receiving data using a near field communications capability (or near field communications medium) typically in accordance with a standardized protocol or data transfer mechanism (e.g., ISO 14443/NFC). Near field communications capability may include a short-range communications capability, such as radio frequency identification (RFID), Bluetooth™, infra-red, or other data transfer capability that can be used to exchange data between the computing device (500) and an interrogation device. Thus, the computing device (500) may be capable of communicating and transferring data and/or control instructions via both a cellular network and near field communications capability.

The computer-readable media in the form of the various memory components may provide storage of computer-executable instructions, data structures, program modules, software units and other data. A computer program product may be provided by a computer-readable medium having stored computer-readable program code executable by the central processor (510). A computer program product may be provided by a non-transient or non-transitory computer- readable medium, or may be provided via a signal or other transient or transitory means via the communications interface (530).

Interconnection via the communication infrastructure (505) allows the one or more processors (510) to communicate with each subsystem or component and to control the execution of instructions from the memory components, as well as the exchange of information between subsystems or components. Peripherals (such as printers, scanners, cameras, or the like) and input/output (I/O) devices (such as a mouse, touchpad, keyboard, microphone, touch-sensitive display, input buttons, speakers and the like) may couple to or be integrally formed with the computing device (500) either directly or via an I/O controller (535). One or more displays (545) (which may be touch-sensitive displays) may be coupled to or integrally formed with the computing device (500) via a display or video adapter (540).

The computing device (500) may include a geographical location element (555) which is arranged to determine the geographical location of the computing device (500). The geographical location element (555) may for example be implemented by way of a global positioning system (GPS), or similar, receiver module. In some implementations the geographical location element (555) may implement an indoor positioning system, using for example communication channels such as cellular telephone or Wi-Fi™ networks and/or beacons (e.g. Bluetooth™ Low Energy (BLE) beacons, iBeacons™, etc.) to determine or approximate the geographical location of the computing device (500). In some implementations, the geographical location element (555) may implement inertial navigation to track and determine the geographical location of the communication device using an initial set point and inertial measurement data.

The foregoing description has been presented for the purpose of illustration; it is not intended to be exhaustive or to limit the invention to the precise forms disclosed. Persons skilled in the relevant art can appreciate that many modifications and variations are possible in light of the above disclosure.

Any of the steps, operations, components or processes described herein may be performed or implemented with one or more hardware or software units, alone or in combination with other devices. In one embodiment, a software unit is implemented with a computer program product comprising a non-transient or non-transitory computer-readable medium containing computer program code, which can be executed by a processor for performing any or all of the steps, operations, or processes described. Software units or functions described in this application may be implemented as computer program code using any suitable computer language such as, for example, Java™, C++, or Perl™ using, for example, conventional or object-oriented techniques. The computer program code may be stored as a series of instructions, or commands on a non- transitory computer-readable medium, such as a random access memory (RAM), a read-only memory (ROM), a magnetic medium such as a hard-drive, or an optical medium such as a CD- ROM. Any such computer-readable medium may also reside on or within a single computational apparatus, and may be present on or within different computational apparatuses within a system or network.

Flowchart illustrations and block diagrams of methods, systems, and computer program products according to embodiments are used herein. Each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, may provide functions which may be implemented by computer readable program instructions. In some alternative implementations, the functions identified by the blocks may take place in a different order to that shown in the flowchart illustrations.

Some portions of this description describe the embodiments of the invention in terms of algorithms and symbolic representations of operations on information. These algorithmic descriptions and representations, such as accompanying flow diagrams, are commonly used by those skilled in the data processing arts to convey the substance of their work effectively to others skilled in the art. These operations, while described functionally, computationally, or logically, are understood to be implemented by computer programs or equivalent electrical circuits, microcode, or the like. The described operations may be embodied in software, firmware, hardware, or any combinations thereof.

The language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based hereon. Accordingly, the disclosure of the embodiments of the invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.

Finally, throughout the specification and accompanying claims, unless the context requires otherwise, the word ‘comprise’ or variations such as ‘comprises’ or ‘comprising’ will be understood to imply the inclusion of a stated integer or group of integers but not the exclusion of any other integer or group of integers.

Claims

CLAIMS:

1 . A worker health and safety system comprising: a server for receiving sensor data and health data of a plurality of workers registered at the server; a plurality of sensors in data communication with the server and capable of sensing sensor data and communicating the sensor data to the server over a data communications network, the server arranged to associate the received sensor data with one or more of the registered workers; one or more health data storage devices in data communication with the server to communicate health data of the plurality of workers to the server; and a data analytics module implemented by the server to perform analysis of the received sensor data and health data to determine if any of the received sensor data or health data exceeds a threshold, and to generate a notification based on the analysis, wherein the server is arranged to implement one or more user communication modules for transmitting the notification to one or more users of the system.

2. The system as claimed in claim 1 , wherein the data analytics module is arranged to perform one or more of: determining an insight, reaching a conclusion, and making a prediction, based on the processing of the sensor data and health data.

3. The system as claimed in claim 1 or claim 2, wherein the notification is in the form of a report, or an alert message.

4. The system as claimed in any one of the preceding claims, wherein the server is arranged to generate a worker profile associated with each of the registered workers, based on the received sensor data and the received health data.

5. The system as claimed in any one of the preceding claims, wherein the notification includes one or more actionable recommendations.

6. The system as claimed in any one of the preceding claims, wherein the plurality of sensors are arranged to sense the sensor data in near real-time.

7. The system as claimed in claim 6, wherein the data analytics module is arranged to analyse the received sensor data or the received health data in near real-time, and to transmit the notification in near real-time.

8. The system as claimed in any one of the preceding claims, wherein the plurality of sensors include any one or more of: temperature sensors, noise sensors, gas sensors, particle sensors, dust sensors, humidity sensors, image sensors or digital cameras, light sensors, radiation sensors or detectors, access control sensors, and proximity sensors.

9. The system as claimed in any one of the preceding claims, wherein the data analytics module is arranged to identify and log potentially harmful objects or behaviours through analysis of one or more video feeds.

10. The system as claimed in any one of the preceding claims, wherein the system includes a worker identification component arranged to detect an identification, a location, or a presence or absence of a registered worker in the vicinity of one or more of the sensors or any other specified location in a working environment where a worker is located in use.

11. The system as claimed in claim 10, wherein the system further includes a timing component arranged to associate the received sensor data with a time or date and to associate the presence or absence of a registered worker with the received sensor data at that time or date, so as to enable the server to determine if the worker is or had been exposed to a potentially harmful environment or potentially harmful equipment.

12. The system as claimed in any one of the preceding claims, wherein the one or more health data storage devices include any one or more of: a database that includes health data, health parameters, or historical health records of a registered worker; and an electronic device whereon the health data of a worker is stored.

13. The system as claimed in any one of the preceding claims, wherein the plurality of health data storage devices incorporate one or more health sensors.

14. The system as claimed in any one of the preceding claims, wherein the data analytics module includes or has access to an artificial intelligence (Al) module.

15. The system as claimed in claim 14, wherein the Al module implements data processing and analysis by using one or more of: artificial intelligence rules, expert rules, and algorithms, to analyse the received sensor data and health data in order to generate the notification.

16. A worker health and safety system comprising: a server for receiving sensor data and health data of a plurality of workers registered at the server; a sensor data receiving component for receiving sensor data from a plurality of sensors that sense the sensor data, the sensor data being received over a data communications network, and the server arranged to associate the sensor data with one or more of the registered workers; a health data receiving component for receiving health data of the plurality of workers from a plurality of health data storage devices; and a data analytics module implemented by the server to perform analysis of the received sensor data and health data to determine if any of the received sensor data or health data exceeds a threshold, and to generate a notification based on the analysis, wherein the server is arranged to implement one or more user communication modules for transmitting the notification to one or more users of the system.

17. A computer-implemented method for monitoring worker health and safety, the method carried out at a server and comprising: receiving from a plurality of sensors in data communication with the server, sensor data sensed by the sensors; associating the received sensor data with one or more of a plurality of workers that are registered at the server; receiving health data of the plurality of workers from one or more health data storage devices in data communication with the server; instructing the performing of analysis of the received sensor data and health data to determine if any of the received sensor data or health data exceeds a threshold, and generating a notification based on the analysis; and communicating the notification to one or more users.

18. The method as claimed in claim 17, wherein the method includes implementing a data analytics module to analyse the received health data and sensor data, and wherein the method includes one or more of: determining an insight, reaching a conclusion, and making a prediction based on the processing of the sensor data and health data.

19. The method as claimed in claim 17 or claim 18, wherein the method includes implementing one or more user communication modules in data communication with the server, wherethrough the notification is communicated to one or more users registered at the server.