Reducing illness and infection caused by ineffective cleaning by tracking and controlling cleaning effectiveness

Abstract

The wearable computing device can be used to track the effectiveness of one or more cleaning actions that have been performed. The device may include one or more sensors that detect and measure motion associated with a cleaning event. In a different example, motion data generated by the device may be compared to reference motion data to determine whether an individual has cleaned all objects expected to be cleaned and / or whether the individual has cleaned a given object sufficiently well. As another example, the motion data generated by the device may be analyzed to distinguish between cleaning and non-cleaning behaviors and to distinguish between different types of cleaning behaviors during a cleaning operation. The quality of each cleaning behavior may be evaluated. In an optional configuration, the device may take action in response to determining that ineffective cleaning is being performed, causing a corrective cleaning behavior to be implemented.

Description

Technical Field

[0001] Cross-reference This application claims the benefit of U.S. Provisional Patent Application No. 62 / 801,865, filed Feb. 6, 2019, and U.S. Provisional Patent Application No. 62 / 801,875, filed Feb. 6, 2019, the entire contents of each of which are incorporated herein by reference.

[0002] The present disclosure relates to devices and techniques for reducing diseases and infections caused by ineffective cleaning, including monitoring and controlling the effectiveness of cleaning through a wearable computing device worn by an individual performing the cleaning.

Background Art

[0003] Ineffective cleaning is one of the main causes of pathogen transmission, causing millions of illnesses and infections every year. For example, the U.S. Centers for Disease Control and Prevention estimates that in the United States, 48 million people get sick from food poisoning each year, 128,000 are hospitalized, and 3,000 die. Further, the World Health Organization estimates that hundreds of millions of patients worldwide are affected by healthcare-associated infections each year, and 7-10% of all hospitalized patients contract at least one healthcare-associated infection during their hospital stay. Viruses and bacteria can easily pass through other public or semi-public places such as airports, sports stadiums, museums, and hotels if care is not taken in managing the infection pathways of pathogens.

[0004] Implementing robust and proactive hygiene practices is the best way to protect against pathogen entry and infection. The types of hygiene practices used vary depending on the operating environment, but may include systematic handwashing, controlled food preparation techniques, and systematic cleaning and sterilization of contact surfaces in the environment. While it is possible to establish plans and practices to manage hygiene activities in the environment, the lack of a hygiene compliance monitoring system makes it difficult to track and control compliance. Furthermore, employees responsible for cleaning tasks are often new recruits, have high turnover rates, and in some cases have low motivation and commitment to perform their assigned tasks, which exacerbates the challenges associated with ensuring hygiene compliance. [Overview of the project]

[0005] Generally, this disclosure covers devices, systems, and technologies for managing hygiene activities by deploying a computing device associated with an individual performing a cleaning and tracking the effectiveness of their cleaning actions. The computing device may include one or more sensors that detect and measure cleaning movements related to the movement of the computing device caused by the individual's movements, such as during a cleaning event. In some examples, the computing device is worn by the individual performing the cleaning, for example, at a location between their shoulder and fingertips (e.g., wrist, upper arm). In any case, the computing device may detect movements associated with the individual performing an assigned task, which may include movements during cleaning activities and movements in between cleaning activities. The movement data generated by the computing device can be analyzed to determine the effectiveness of the cleaning being performed by the individual. In some configurations, the operation of the computing device is controlled based on the determined cleaning effectiveness, causing the individual performing the cleaning to modify their cleaning activities in response to the operation. Additionally or alternatively, the determined cleaning effectiveness may be stored for cleaning events and provide cleaning verification information for the environment being cleaned.

[0006] The type of hygiene activity monitored during a cleaning event may vary depending on the established hygiene practices for the environment being cleaned. For example, an individual performing a cleaning may be assigned a specific number of surfaces to be cleaned. In a healthcare setting, for instance, surfaces to be cleaned might include light switches, tabletops, bed rails, doorknobs, medication dispensers, and faucet handles. In a food preparation setting (e.g., a restaurant or catering facility), surfaces might include food preparation counters, floor surfaces, fryers, grills, stovetops, microwave surfaces, and refrigerator surfaces. In either case, an individual performing a cleaning may be assigned several surfaces to be cleaned.

[0007] During operation, the computing device can generate signals corresponding to the device's movement caused by the individual performing the cleaning task. Each surface to be cleaned may have a different movement signal associated with the cleaning of that surface. The movement data generated by the computing device can be compared to reference movement data associated with each surface. If the movement data indicates that the individual performing the cleaning has missed a surface, the computing device can take action. For example, the computing device can provide an alert in near real-time instructing the user to complete the cleaning of any missed surfaces.

[0008] Additionally or alternatively, the cleaning quality of any particular target surface can also be determined using motion data generated by a computing device during the cleaning operation. For example, motion data generated by a computing device during the cleaning of a particular surface can be compared to reference motion data associated with the cleaning quality of that target surface. The reference motion data associated with the cleaning quality may correspond to the thoroughness of the cleaning of the target surface and / or the extent or area of ​​the target surface.

[0009] In some applications, an individual carrying a computing device may be tasked with performing cleaning and non-cleaning tasks, and / or multiple different cleaning tasks. For example, an individual's protocol might instruct them to clean one or more target surfaces in the environment and then perform a separate hand-sanitizing event before moving on to other tasks. The computing device can generate signals corresponding to movement throughout the entire process of this activity. The movement data generated by the computing device can be compared with reference movement data to classify and distinguish between cleaning and non-cleaning actions. Movement data identified as corresponding to cleaning actions can be further analyzed to determine the specific type of cleaning action performed (e.g., surface cleaning rather than hand washing). In some examples, the quality of that particular cleaning action is further evaluated by referring to movement data associated with the quality of cleaning for that particular cleaning action. In this way, an integrated hygiene management system can be provided to monitor and / or control multiple different types of hygiene activities.

[0010] As described herein, by adding hygiene-compliant monitoring and control, users of this technology can reduce pathogen infection events through ineffective or incomplete cleaning. For example, an organization operating a food preparation environment can see a reduction in facility-related food poisoning incidents after implementing this technology compared to before. Another example is a healthcare organization that can see a reduction in healthcare-associated infections after implementing this technology compared to before. Other environments and applications can also benefit from this technology.

[0011] One example describes a method for reducing illness and infection caused by ineffective cleaning through tracked cleaning effects. The method includes detecting movement associated with a wearable computing device during a cleaning event, using a wearable computing device worn by an individual performing cleaning on multiple target surfaces. The method also includes determining whether the individual performed a cleaning action on each of the multiple target surfaces by comparing movement data generated by the wearable computing device with reference movement data associated with the cleaning of each of the multiple target surfaces, based on the movement associated with the wearable computing device. Furthermore, the method includes performing an action by the wearable computing device in response to determining that the individual did not perform a cleaning action on at least one of the multiple target surfaces.

[0012] Another example describes a wearable computing device. The device includes at least one sensor configured to detect motion associated with the wearable computing device, at least one processor, and memory containing instructions that, when executed, cause the at least one processor to perform a specific action. This example specifies that the action includes receiving motion data of the wearable computing device from at least one sensor while an individual wearing the wearable computing device is performing a cleaning action on multiple surface objects during a cleaning event. The action also includes determining, based on the motion data, whether the individual performed a cleaning action on each of the multiple surface objects by comparing the motion data with at least reference motion data associated with cleaning each of the multiple surface objects. The action also includes performing an action in response to determining that the individual did not perform a cleaning action on at least one of the multiple surface objects.

[0013] Another example describes a method for establishing a customer-specific system for tracking cleaning effectiveness. This method involves an individual wearing a wearable computing device performing a cleaning action on each of several target surfaces, which are selected as surfaces for which cleaning is desired to be tracked in relation to subsequent cleaning events. The method also involves the wearable computing device generating motion data associated with the movement of the wearable device during the cleaning action performed on each of the several target surfaces. The method further involves associating different portions of the motion data generated during the cleaning action with a specific one of the several target surfaces on which the individual performed the cleaning action. Furthermore, for each of the several different target surfaces, the method includes determining reference data indicating the cleaning action being performed from the relevant different portions of the motion data for each of the several different target surfaces. The method further includes storing the reference data for each of the several different target surfaces for use in relation to subsequent cleaning events.

[0014] Another example describes a method for controlling the cleaning effect. This method includes detecting movement associated with a wearable computing device during a cleaning event, using a wearable computing device worn by an individual performing cleaning on a target surface. The method also includes determining the quality of cleaning of the target surface by comparing, based on the movement associated with the wearable computing device, at least the movement data generated by the wearable computing device with reference movement data associated with a cleaning threshold quality of the target surface. The method further includes taking action by the wearable computing device in response to determining that the target surface has not been effectively cleaned to a cleaning threshold quality.

[0015] Another example describes a wearable computing device. The device includes at least one sensor configured to detect motion associated with the wearable computing device, at least one processor, and memory containing instructions that, when executed, cause the at least one processor to perform a specific action. The action includes receiving motion data of the wearable computing device from at least one sensor while the individual wearing the wearable computing device is performing a cleaning action on a target surface during a cleaning event. The action also includes determining the quality of cleaning of the target surface based on the motion data by comparing the motion data with at least reference motion data associated with a threshold quality of cleaning for the target surface. The action further includes performing an action in response to determining that the target surface has not been effectively cleaned to a threshold quality of cleaning.

[0016] Another example describes a method for comprehensive hygiene management. This method includes determining at least one movement feature indicating that the wearer of a wearable computing device is performing a washing action, based on the movement of the wearable computing device, thereby distinguishing the movement of the wearable computing device during non-washing actions. This method includes determining a particular type of washing action performed by the wearer of a wearable computing device based on a comparison of movement features with reference to movement data associated with different types of washing actions. This method also includes determining the quality of cleaning for a particular type of washing action performed by the wearable computing device by comparing the movement data generated by the wearable device during the particular type of washing action with reference movement data associated with a threshold quality of cleaning for that particular type of washing action. This method further includes having the wearable computing device perform an action in response to determining that a particular type of washing action performed by the wearer of the wearable computing device does not meet the threshold quality of cleaning.

[0017] Another example describes a wearable computing device. The device includes at least one sensor configured to detect movement associated with the wearable computing device, at least one processor, and memory containing instructions that, when executed, cause the at least one processor to perform a specific action. The action includes receiving movement data associated with the wearable computing device from at least one sensor, and determining, based on the movement data, at least one feature of movement indicating that an individual wearing the wearable computing device is performing a washing action, thereby distinguishing the movement of the wearable computing device during non-washing actions. The action further includes determining a particular type of washing action performed by the wearer of the wearable computing device based on a comparison of movement features with reference to movement data associated with different types of washing actions. The action also includes determining the quality of washing for a particular type of washing action performed by comparing the movement data generated during the particular type of washing action with reference movement data associated with the threshold quality of washing for that particular type of washing action. The action further includes performing an action in response to determining that a particular type of washing action performed does not meet the threshold quality of washing.

[0018] Details of one or more examples are described in the accompanying drawings and the following description. Other features, purposes, and advantages will become apparent from the description and drawings, as well as from the claims. [Brief explanation of the drawing]

[0019] [Figure 1] This is a conceptual diagram illustrating an example of a computing system configured to track the effectiveness of individual cleanings performed during a cleaning event.

[0020] [Figure 2]A block diagram showing an example of a wearable computing device configured according to one or more aspects of the present disclosure.

[0021] [Figure 3A] It shows exemplary surfaces and / or devices that may be cleaned using optionally exemplary tools and are evaluated according to the present disclosure. [Figure 3B] It shows exemplary surfaces and / or devices that may be cleaned using optionally exemplary tools and are evaluated according to the present disclosure. [Figure 3C] It shows exemplary surfaces and / or devices that may be cleaned using optionally exemplary tools and are evaluated according to the present disclosure.

[0022] [Figure 4] A flowchart showing an exemplary process for training an exemplary wearable computing device and then determining whether an individual performing the cleaning has cleaned each of a plurality of target surfaces intended to be cleaned as part of an established protocol.

[0023] [Figure 5] A flowchart showing an exemplary process for training an exemplary wearable computing device and then determining whether an individual performing the cleaning has effectively cleaned a target surface to a threshold quality of cleaning.

[0024] [Figure 6] For example, as part of an overall hygiene management system, a flowchart showing an exemplary process for training an exemplary wearable computing device to later evaluate a plurality of different cleaning actions.

[0025] [Figure 7] It shows an example of a hand hygiene protocol that can be specified for a wearer of a wearable computing device.

[0026] [Figure 8] This flowchart illustrates exemplary operation of an exemplary wearable computing device configured to track the effectiveness of cleaning to reduce diseases and infections caused by ineffective cleaning, according to one or more aspects of the present disclosure.

[0027] [Figure 9] This flowchart illustrates another exemplary operation of an exemplary wearable computing device configured to track the effectiveness of cleaning to reduce diseases and infections caused by ineffective cleaning, according to one or more additional aspects of the present disclosure.

[0028] [Figure 10] This flowchart illustrates exemplary operation of an exemplary wearable computing device configured to track cleaning effectiveness for comprehensive hygiene management, according to one or more aspects of the present disclosure.

[0029] [Figure 11] This is a plot of linear acceleration and rotational velocity data generated during the experiment. [Figure 12] This is a plot of linear acceleration and rotational velocity data generated during the experiment.

[0030] [Figure 13] Figures 11 and 12 show examples of single time-domain feature representations generated from raw sample data for the experiments.

[0031] [Figure 14] Figures 11-13 show the top two features determined from the candidate features for binary classification of the experimental data.

[0032] [Figure 15] This is a drawing illustrating the identification of three exemplary types of tools used as part of a simulated restaurant context floor care study utilizing motion data.

[0033] [Figure 16] This is a drawing illustrating the exemplary identification of five target surfaces, conducted as part of a simulated hospital context study utilizing motion data.

[0034] [Figure 17A] This section shows a series of exemplary user interface graphics that may be displayed to the user to help guide them through the execution of the cleaning protocol. [Figure 17B] This section shows a series of exemplary user interface graphics that may be displayed to the user to help guide them through the execution of the cleaning protocol. [Figure 17C] This section shows a series of exemplary user interface graphics that may be displayed to the user to help guide them through the execution of the cleaning protocol. [Figure 17D] This section shows a series of exemplary user interface graphics that may be displayed to the user to help guide them through the execution of the cleaning protocol. [Modes for carrying out the invention]

[0035] Generally, this disclosure covers devices, systems, and technologies that utilize wearable computing devices (e.g., activity trackers, computerized watches, etc.) to detect personal movement while performing one or more hygiene-related tasks. A computing system (e.g., a server, a mobile phone, etc.) can communicate with a wearable computing device (e.g., an activity tracker, a watch) over a network. The wearable computing device can detect movement (e.g., changes in acceleration, angular velocity, tilt, etc.) over time and provide information about the detected movement (e.g., as movement data) to the computing system over the network. In some implementations, the computing system and / or the wearable computing device can identify features of the movement data that correspond to a specific hygiene activity being performed.

[0036] For example, a computing system can determine whether a particular object to be cleaned has actually been cleaned by comparing motion data associated with the cleaning of each object with reference motion data corresponding to the cleaning of that object. Another example is that a computing system can determine whether a particular object to be cleaned has been effectively cleaned by comparing motion data associated with the level of cleaning of that object with reference motion data associated with a threshold level of cleaning for that object.

[0037] As yet another example, a computing system can distinguish between different types of sanitary activities performed during a movement and evaluate the sanitary compliance associated with one or more of those activities. For example, a computing system can determine that a wearer of a computing device performed a first type of cleaning action (e.g., floor surface cleaning, equipment cleaning) and a second type of cleaning action (e.g., washing the wearer's hands). The computing system can determine the quality of one or both of the cleaning actions and / or the order in which the cleaning actions were performed. The computing system can further determine whether the quality of the cleaning actions and / or the order of cleaning conform to the sanitary compliance standards set for the environment in which the actions were performed.

[0038] In some implementations, a computing system generates and stores cleaning verification information associated with an environment in which one or more sanitary actions have been performed. Unlike some currently used cleaning compliance programs that do not have the ability to monitor or verify that the cleaning actions in question have actually been performed, the technology described herein can provide data-verified evidence of cleaning compliance. Cleaning compliance data may store information corresponding to one or more cleaning actions performed, for example, indicating that specific surfaces and / or objects were cleaned during a cleaning event, the quality of cleaning of one or more surfaces and / or objects, and / or the type of cleaning action performed. Cleaning compliance data may also include a timestamp corresponding to the time the cleaning action was performed, and / or data corresponding to the actual cleaning actions performed during the cleaning action, and / or other metadata corresponding to the context of the measurement (e.g., room identification, GPS positioning). In this way, cleaning providers can provide verification information that proves the sanitary services performed, and place owners or operators can have evidence of sanitary compliance for their facilities.

[0039] In addition to providing cleaning verification information, or instead, the computing system according to this disclosure may invoke the execution of an action based on cleaning effectiveness information determined based on motion data detected by the wearable cleaning device during a cleaning event, or the wearable computing device may initiate such an action. For example, the wearable cleaning device may activate a user alert function and / or output information to the individual wearing the device indicating a violation of cleaning compliance standards. Such a violation may indicate that the individual performing the cleaning overlooked a surface to be cleaned, did not clean the surface to a cleaning quality threshold level, and / or performed an incorrect sequence of cleaning actions (e.g., performed hand hygiene actions before equipment cleaning actions, or vice versa). In some implementations, the wearable cleaning device may perform an action to notify the wearer that a violation has occurred and in substantially real time. As a result, the wearer can take immediate corrective action to address the cleaning compliance violation. Additionally or alternatively, actions performed by the wearable cleaning device may issue training to the wearer of the wearable cleaning device to instruct the user on the corrective actions to be performed.

[0040] By providing cleaning compliance monitoring and control in accordance with one or more aspects of this disclosure, users of the Technology can reduce pathogen infection events through ineffective or incomplete cleaning. For example, an organization operating a food preparation environment can verify a reduction in facility-related food poisoning incidents after implementing the Technology compared to before. As another example, a healthcare organization can verify a reduction in healthcare-associated infection incidents after implementing the Technology compared to before. The incidence of infections and / or illnesses resulting from ineffective cleaning may decrease by at least 20%, e.g., at least 40%, at least 60%, at least 80%, or at least 90%, after implementing the Technology compared to before.

[0041] This disclosure describes examples in which a computing system (e.g., a server) and / or a computing device (e.g., a wearable computing device) can analyze information associated with the computing system and / or the computing device (e.g., acceleration, orientation, etc.). Such examples may be implemented so that the computing system and / or computing device can perform the analysis only after receiving permission from the user (e.g., a person wearing the wearable computing device) to analyze the information. For example, in the following circumstances in which a mobile computing device can collect or utilize information associated with a user and the computing system and / or computing device, the user may be given the opportunity to provide input to control whether a program or function of the computing system and / or computing device can collect and utilize user information (e.g., the user's occupation, contacts, working hours, work history, training history, user preferences, and / or information about the user's past and present locations), and / or to instruct whether and / or how the computing system and / or computing device can receive content that may be relevant to the user. Furthermore, certain data may be processed in one or more ways before being stored or used by computing systems and / or computing devices, resulting in the removal of personally identifiable information. For example, a user's identity may be processed so that personally identifiable information about the user cannot be determined, or a user's geographical location may be generalized so that location information (such as city, zip code, or state level) cannot be obtained, thereby preventing the determination of the user's specific location. Thus, users can control how information about them is collected and used by computing systems and / or computing devices.

[0042] Figure 1 is a conceptual diagram showing an example of a computing system 10 configured to track the effectiveness of cleaning by an individual performing cleaning during a cleaning event. System 10 includes a wearable computing device 12, which may be worn by the individual performing cleaning and capable of generating data indicating the individual's movements during the cleaning event, according to one or more aspects of this disclosure. System 10 also includes a remote computing system 14 and a network 16.

[0043] Figure 1 shows a wearable computing device 12 positioned within an environment 18 where one or more hygienic actions (e.g., surface cleaning) may be performed. In the illustrated example, environment 18 is depicted as a healthcare environment having a bedroom 20 and a bathroom 22. The bedroom 20 may have one or more target surfaces intended to be cleaned during a cleaning event, to name a few exemplary surfaces, such as a television remote control 20A, a bed rail 20B, and a medication support pole 20C. Similarly, the bathroom 22 may have one or more target surfaces intended to be cleaned during a cleaning event, to name a few exemplary surfaces again, such as a sink / faucet 22A and a toilet 22B. Such healthcare environments are susceptible to the contraction of hospital-acquired infections and enable strict adherence to hygiene and cleaning protocols critical to patient health. That said, the technology of the Disclosure is not limited to such exemplary environments. Rather, the technology of the Disclosure can be used in any location where it is desirable to have verified evidence of hygiene compliance. Exemplary environments in which aspects of this disclosure may be used include, but are not limited to, food preparation environments, hotel room environments, food processing plants, and dairy farms.

[0044] The wearable computing device 12 may be worn, held, or otherwise physically attached to a person, and may be any type of computing device including one or more processors configured to process and analyze instructions for the wearable computing device's movements (e.g., sensor data). Examples of the wearable computing device 12 include, but are not limited to, a watch, an activity tracker, computerized eyewear, computerized gloves, computerized jewelry (e.g., a computerized ring), a mobile phone, or any combination of hardware, software, and / or firmware that can be used to detect the movements of a person wearing, holding, or otherwise attaching the wearable computing device 12. Such a wearable computing device may be attached to a person's fingers, wrists, arms, torso, or any other location on the body sufficient to detect movements related to the wearer's actions during a washing event. In some examples, the wearable computing device 12 may have a housing attached to a band that is physically secured to a part of the wearer's body (e.g., around the body). In other examples, the wearable computing device 12 may be insertable into a pocket of the wearer's clothing without having a separate fastening band to physically attach the wearable computing device to the wearer.

[0045] Although shown in Figure 1 as a separate element from the remote computing system 14, in some examples, some or all of the functions of the remote computing system 14 may be implemented by the wearable computing device 12. For example, modules 26 and data stores 28, 30, and 32 may be locally present in the wearable computing device 12 to receive information about the movement of the wearable computing device and perform the analysis described herein. Thus, although it is stated herein that certain functions are performed by the wearable computing device 12 and the remote computing system 14 respectively, some or all of the functions may be shifted from the remote computing system to the wearable computing device, or vice versa, without departing from the scope of this disclosure.

[0046] As used herein, the phrase “cleaning behavior” refers to a cleaning behavior that involves multidimensional movements and may or may not involve the use of tools to perform the cleaning. Some examples of cleaning behavior include an individual cleaning a specific object (e.g., a doorknob, a toilet) using a specific tool of their choice (e.g., a rag, a brush, a mop), and an individual cleaning a part of their own body (e.g., washing their hands). Cleaning behavior may include preparatory steps taken before the cleaning action is performed, such as spraying a cleaner onto a surface, wringing water out of a mop, filling a bucket with water, or soaking a rag.

[0047] As used herein, the term “substantially real time” means while an individual is still performing a cleaning, or while an individual is still in or near the environment in which the cleaning occurred in order to perform a corrective cleaning action, or while in sufficiently close temporal proximity to the completion of the cleaning.

[0048] When used herein in relation to surfaces to be cleaned, the term “healthcare environment” means the surfaces of instruments, devices, carts, cages, furniture, structures, buildings, etc., that are employed as part of healthcare activities. Examples of medical surfaces include the surfaces of medical or dental instruments, the surfaces of medical or dental instruments, the surfaces of electronic devices used to monitor patient health, and the surfaces of floors, walls, or fixtures in structures where medical care is performed. Healthcare surfaces are found in hospitals, operating rooms, rooms for the frail, birthing rooms, funeral homes, and clinical diagnostic rooms. These surfaces may be “hard surfaces” (e.g., walls, floors, bedpans), or woven surfaces, such as knitted, woven, and nonwoven surfaces (e.g., surgical clothing, curtains, bed linens, bandages), or patient care equipment (e.g., ventilators, diagnostic instruments, shunts, body scopes, wheelchairs, beds), or represented by surgical and diagnostic equipment. Medical surfaces also include articles and surfaces used in veterinary medicine.

[0049] Where used herein in relation to surfaces to be cleaned, the term “food preparation surface” refers to the surface of tools, machinery, equipment, structures, or buildings used as part of food preparation, cooking, or preservation activities. Examples of food preparation surfaces include the surfaces of food preparation or cooking equipment (e.g., slicing equipment, canning equipment, or transport equipment, including water channels), food preparation supplies (e.g., kitchen utensils, dishes, washing supplies, and bar glasses), and the surfaces of floors, walls, or fixtures of structures where food preparation takes place. Examples of food preparation surfaces can be found in ovens, fryers, grills, microwave ovens, refrigerators, countertops, storage containers, sinks, beverage chillers and warmers, and cold or hot water for meat.

[0050] As used herein, the term “cleansing action” refers to a cleansing movement and the corresponding action. A cleansing action may be an action taken by an individual to support soil removal, reduction of pathogen populations, and a combination thereof.

[0051] As used herein, the term “reference motion data” refers to both the raw sensor data corresponding to reference motion and the data derived from or based on the raw sensor data corresponding to reference motion. In implementations where reference motion data is derived from or based on raw sensor data, the reference motion data can provide a more compact representation of the raw sensor data. For example, the reference motion data may be stored in the form of one or more time-frame granularity features, coefficients in a model, or other mathematical transformations of the raw reference data.

[0052] In Figure 1, network 16 represents any public or private communication network. The wearable computing device 12 and the remote computing system 14 can send and receive data over network 16 using any preferred communication technology. For example, the wearable computing device 12 may be operably coupled to network 16 using network link 24A. The remote computing system 14 may be operably coupled to network 16 by network link 24B. Network 16 may include network hubs, network switches, network routers, etc., which are operably interconnected and thereby provide information exchange between the wearable computing device 12 and the remote computing system 14. In some examples, network links 24A and 24B may be Ethernet®, Bluetooth®, ATM, or other network connections. Such connections may be wireless and / or wired connections.

[0053] The remote computing system 14 of system 10 represents any suitable mobile or fixed remote computing system that can send and receive information to and from network 16 via network link 24B, such as one or more desktop computers, laptop computers, mobile computers (e.g., mobile phones), mainframes, servers, and cloud computing systems. In some examples, the remote computing system 14 represents a cloud computing system that provides one or more services through network 16. One or more computing devices, such as a wearable computing device 12, can use the remote computing system 14 to access one or more services provided by the cloud. For example, the wearable computing device 12 can use the remote computing system 14 to store and / or access data in the cloud. In some examples, some or all of the functions of the remote computing system 14 may reside within a mobile computing platform, such as a mobile phone or tablet computer, and may or may not be in the same geographical location as the wearable computing device 12. For example, in some examples, some or all of the functions of the remote computing system 14 may reside within a mobile computing device in an environment 18 with the wearable computing device 12 and run from there, and / or reside within the wearable device itself and be implemented therein.

[0054] In some implementations, the wearable computing device 12 can generate and store data indicating movement for processing by the remote computing system 14, even when the wearable computing device is not communicating with the remote computing system. In practice, for example, the wearable computing device 12 may periodically lose connection with the remote computing system 14 and / or the network 16. In these and other situations, the wearable computing device 12 can operate in an offline / disconnected state and perform the same or more limited functions that the wearable computing device performs when it is online / connected to the remote computing system 14. When the connection between the computing device 12 and the remote computing system 14 is re-established, the computing device can transfer the stored data generated during the period the device was offline. In a different example, the computing device 12 may re-establish connection with the remote computing system 14 when the wireless connection is re-established over the network 16, or when the computing device is connected to a docking station, to facilitate the download of information temporarily stored in the computing device.

[0055] The remote computing system 14 in the example of Figure 1 includes a cleaning effectiveness determination module 26 and one or more data stores, illustrated as including a target surface comparison data store 28, a cleaning quality comparison data store 30, and a cleaning behavior comparison data store 32. The cleaning effectiveness determination module 26 can perform operations described using software, hardware, firmware, or a mixture of hardware, software, and firmware present in and / or running on the remote computing system 14. The remote computing system 14 can run the cleaning effectiveness determination module 26 using multiple processors or multiple devices. The remote computing system 14 can run the cleaning effectiveness determination module 26 as a virtual machine running on underlying hardware. The cleaning effectiveness determination module 26 can run as a service of an operating system or computing platform. The cleaning effectiveness determination module 26 can run as one or more executable programs in the application layer of a computing platform.

[0056] The function described as a data store can represent any suitable storage medium for storing real data, modeled data, or otherwise derived data that the cleaning effectiveness determination module 26 can access to determine whether the wearer of the wearable computing device 12 performed a compliant cleaning action. For example, the data store may include lookup tables, databases, charts, graphs, functions, equations, etc., that the cleaning effectiveness determination module 26 can access to evaluate data generated by the wearable computing device 12. The cleaning effectiveness determination module 26 may, depending on features generated from information contained in one or more data stores, determine whether the sensor data acquired from the wearable computing device 12 indicates that a person performed a specific cleaning compliant action, such as cleaning all surfaces to be cleaned, properly and thoroughly cleaning one or more target surfaces, and / or performing a specific designated cleaning action. The data stored in the data store may be generated from and / or based on one or more training sessions, as described in more detail with respect to Figures 4 to 6. The remote computing system 14 can provide access to the data stored in the data store as a cloud-based service to devices connected to the network 16, such as the wearable computing device 12.

[0057] The cleaning effectiveness determination module 26 may respond to a request for information (e.g., a request from the wearable computing device 12) indicating whether the individual performing the cleaning and wearing or having worn the wearable computing device 12 has performed the compliant cleaning activity. The cleaning effectiveness determination module 26 can receive sensor data from the wearable computing device 12 via link 24B and network 16 and compare the sensor data with one or more comparison datasets stored in the data store of the remote computing system 14. The cleaning effectiveness determination module 26 can respond to a request by transmitting information from the remote computing system 14 to the wearable computing device 12 via the network 16 through the link.

[0058] The cleaning effectiveness determination module 26 may be implemented to determine several different characteristics of a cleaning action and compliance with cleaning protocols based on information detected by the wearable computing device 12. Generally, the wearable computing device 12 can output information indicating the wearer's movements (e.g., data indicating the direction, location, orientation, position, height, etc. of the wearable computing device 12) for transmission to the remote computing system 14, as will be described in more detail below. The cleaning effectiveness determination module 26 may, for example, refer to data stored in the remote computing system 14 to identify movements related to cleaning actions from movements unrelated to cleaning actions during cleaning events or periods in which movement data is captured. The cleaning effectiveness determination module 26 may further analyze the movement data related to cleaning actions to determine, for example, whether such actions comply with one or more standards based on comparative data stored in one or more data stores.

[0059] In one embodiment, the person performing the cleaning may be assigned a schedule of multiple surfaces to be cleaned during a cleaning event. The schedule of surfaces to be cleaned may correspond to surfaces that are frequently touched by individuals in the environment and are susceptible to contamination, or surfaces that are desired to be cleaned as part of a cleaning-compliant protocol. The person performing the cleaning may be instructed which surfaces to clean during the cleaning event, and optionally, the order in which the surfaces should be cleaned and / or the degree of thoroughness to which each surface should be cleaned.

[0060] During the cleaning event, the wearable computing device 12 can output information corresponding to the movement of the wearable computing device. The cleaning effect determination module 26 can receive movement data from the wearable computing device 12 and analyze the movement data by referring to the target surface comparison data stored in the data store 28. The target surface comparison data store 28 may also contain cleaning-related data for each target surface that the individual performing the cleaning has scheduled to clean.

[0061] In some examples, the cleaning effect determination module 26 determines one or more features of motion data corresponding to the cleaning of a particular surface. Each surface to be cleaned may have dimensions and / or orientation in three-dimensional space that are unique to that surface and distinguish it from other surfaces intended to be cleaned. Thus, the motion associated with the cleaning of each surface can provide a unique sign or comparison dataset that distinguishes the motion associated with the cleaning of each surface in the dataset. The specific features of the data that define the surface may vary depending, for example, on the characteristics of the surface and the characteristics of the sensor data generated by the wearable computing device 12. The surface comparison data store 28 may contain data corresponding to the cleaning of each surface intended to be cleaned. For example, the surface comparison data store 28 may contain features generated from reference motion data associated with the cleaning of each of a plurality of surfaces scheduled to be cleaned.

[0062] The cleaning effect determination module 26 can determine which target surfaces an individual cleaned by analyzing one or more features of motion data generated during a cleaning event in relation to features in the target surface comparison data store 28. Based on a reference to the target surface comparison data store 28, the cleaning effect determination module 26 can determine whether one or more target surfaces scheduled to be cleaned were cleaned or not. If it is determined that at least one target surface scheduled to be cleaned during a cleaning event was not cleaned, the remote computing system 14 can communicate with the wearable computing device 12 and start operating via the wearable computing device.

[0063] Alternatively, the individual performing the cleaning may be instructed on the quality of cleaning the target surface during the cleaning event. The quality of cleaning may be instructed through a cleaning protocol that trains the individual on how to properly clean the target surface. Exemplary characteristics of the cleaning protocol may specify the technique used to clean the target surface, the amount of force applied through the cleaning instrument when cleaning the target surface, the extent or area of ​​the target surface to be cleaned, and / or the duration of cleaning to be performed on the target surface.

[0064] In some examples, a cleaning protocol may specify one or more consecutive activities to be performed, and / or specific cleaning techniques or sequences of techniques to be used when performing one or more cleaning activities. Examples of cleaning activities that may be specified as part of a cleaning protocol include the order in which surfaces are cleaned (e.g., from top to bottom of a room, from wet to dry, and / or from less soiled to more soiled). Examples of cleaning techniques that may be specified include specific types of cleaning used on a particular surface (e.g., scrubbing using overlapping strokes), and / or a series of consecutive cleaning steps performed on a particular surface (e.g., disinfecting after removing visible dirt).

[0065] During the cleaning event, the wearable computing device 12 can output information corresponding to the movement of the wearable computing device. The cleaning effect determination module 26 can receive movement data from the wearable computing device 12 and analyze the movement data by referring to cleaning quality comparison data stored in the data store 30. The cleaning quality comparison data store 30 may include data corresponding to the cleaning quality of the target surface that is intended to be cleaned by the individual performing the cleaning.

[0066] In some examples, the cleaning effectiveness determination module 26 determines one or more features of motion data corresponding to the quality of surface cleaning. The motion data may indicate the amount or intensity of the cleaning action performed. Additionally or alternatively, the motion data may indicate the area of ​​the surface being cleaned (e.g., dimensions and orientation in three-dimensional space), and may indicate whether the individual performing the cleaning cleaned the entire surface. Further, additionally or alternatively, the motion data may indicate the type of cleaning technique performed on the surface, or a set of different cleaning techniques. Specific features of the data defining the quality of cleaning may vary depending, for example, the characteristics of the cleaning protocol that directs the quality cleaning, the characteristics of the surface being cleaned, and / or the characteristics of the sensor data generated by the wearable computing device 12.

[0067] The cleaning quality comparison data store 30 may include data corresponding to the cleaning quality of each surface, and the cleaning quality is intended to be evaluated. The cleaning quality comparison data store 30 may also include features generated from reference motion data associated with the compliant cleaning quality of each surface, and the cleaning quality is intended to be evaluated. The reference motion data may correspond to cleaning threshold levels indicated by the source of the reference motion data, corresponding to preferred or compliant quality levels.

[0068] The cleaning effectiveness determination module 26 can analyze one or more features of motion data generated during a cleaning event by comparing them with features in the cleaning quality comparison data store 30 to determine whether the surface cleaned by the individual was cleaned to a threshold quality level. The cleaning effectiveness determination module 26 can refer to the cleaning quality comparison data store 30 to determine whether the target surface was cleaned to a threshold quality level or not. If it is determined that the target surface was not cleaned to a threshold quality level, the remote computing system 14 can communicate with the wearable computing device 12 and start operating via the wearable computing device.

[0069] As another exemplary implementation, an individual performing cleaning may be assigned multiple cleaning actions to be performed as part of a work protocol. Each particular type of cleaning action may be different from another particular type of cleaning action, and in some examples, they may preferably be performed in a specified order. For example, one type of cleaning action that may be performed is an environmental cleaning action in which one or more surfaces in the environment 18 are to be cleaned. Examples of these types of cleaning actions include cleaning actions on floor surfaces (e.g., sweeping, mopping) and cleaning actions on non-floor surfaces (e.g., cleaning equipment in the environment 18). Another type of cleaning action that may be performed is a personal cleaning action, such as a hand hygiene cleaning event in which the individual performs a handwashing protocol (e.g., using an alcohol-based disinfectant, soap and water). As part of an overall hygiene management program, the effectiveness and / or order of each of the different types of cleaning actions performed by the individual can be evaluated.

[0070] For example, the wearable computing device 12 can output information corresponding to the movement of the wearable computing device during a period in which the wearer performs multiple washing and non-washing actions. The washing effect determination module 26 can receive movement data from the wearable computing device 12 and analyze the movement data by referring to the washing action comparison data store 32. The washing action comparison data store 32 may contain data corresponding to multiple different types of washing actions that may be performed by the individual wearing the wearable computing device 12. Each type of washing action may have a movement sign associated with the washing action stored in the washing action comparison data store 32.

[0071] The cleaning effectiveness determination module 26 can refer to the cleaning behavior comparison data store 32 to distinguish motion data associated with cleaning behavior from motion data associated with non-cleaning behavior. The cleaning effectiveness determination module 26 can further determine specific types of cleaning behavior performed by the wearer of the wearable computing device 12 by referring to the cleaning behavior comparison data store 32. In some implementations, the cleaning effectiveness determination module 26 can further refer to the cleaning quality comparison data store 30 to further determine the cleaning quality of one or more specific types of cleaning behavior performed by the wearer.

[0072] In some examples, the cleaning effect determination module 26 determines one or more features of motion data corresponding to multiple cleaning actions performed by the wearer. Each cleaning action may have associated motion data that distinguishes it from other types of cleaning actions. Thus, motion data generated during the performance of multiple cleaning actions can distinguish each particular cleaning action from other specific cleaning actions. The specific features of the data that define a particular cleaning action may vary, for example, depending on the type of cleaning action performed and the characteristics of the sensor data generated by the wearable computing device 12. The cleaning action comparison data store 32 may include data that distinguishes cleaning actions from non-cleaning actions. The cleaning action comparison data store 32 may further include data corresponding to each type of cleaning action, the conformance of which is intended to be evaluated. For example, the cleaning action conformance data store 32 may include features generated from reference motion data associated with each type of cleaning action, which can be determined from the motion data.

[0073] The cleaning effectiveness determination module 26 can analyze one or more features of movement generated during the course of movement by comparing them with features that define different cleaning behaviors. For example, the cleaning effectiveness determination module 26 can analyze one or more features of movement data generated during the duration of movement (e.g., a cleaning event) and, for example, refer to the cleaning behavior compliance data store 32, distinguish between periods of movement corresponding to cleaning behavior and periods of movement corresponding to non-cleaning behavior. Additionally or alternatively, the cleaning effectiveness determination module 26 can analyze one or more features of movement corresponding to a cleaning period and, for example, refer to the cleaning behavior compliance data store 32, determine a specific type of cleaning behavior performed during each cleaning period. The cleaning behavior compliance data store 32 can further determine whether one or more of the specific types of cleaning behavior performed were performed at a threshold level of quality, for example, by referencing the cleanliness quality comparison data store 30.

[0074] In some examples, the cleaning effectiveness determination module 26 can analyze one or more features of the motion data generated during the duration of the motion, for example by referring to the cleaning behavior-compliant data store 32, to distinguish between periods of motion corresponding to cleaning behavior and periods of motion corresponding to non-cleaning behavior. The cleaning effectiveness determination module 26 can further analyze one or more features of the motion data, for example by referring to the cleaning behavior-compliant data store 32, to determine whether a specified cleaning sequence (e.g., from top to bottom of the room, from wet to dry, and / or from less dirty to more dirty areas) was performed. Additionally or alternatively, the cleaning effectiveness determination module 26 can further analyze one or more features of the motion data, for example by referring to the cleaning behavior-compliant data store 32, to further determine whether a particular surface was cleaned using a specified technique or a specified set of techniques (e.g., scrubbing using overlapping strokes, disinfecting after removing visible dirt).

[0075] The remote computing system 14 can communicate with the wearable computing device 12 to initiate operation via the wearable computing device if, for example, the cleaning activity performed does not conform to the protocol standard, a particular type of cleaning action that was expected to be performed was not performed, and / or a particular type of cleaning action was performed below a threshold level of cleaning quality.

[0076] In some examples, the wearable computing device 12 can output information containing motion instructions for the wearable computing device 12 (e.g., data indicating direction, speed, location, orientation, position, height, etc.) for transmission to the remote computing system 6. In response to outputting information containing motion instructions, the wearable computing device 12 can receive information from the remote computing system 14 regarding the effectiveness of cleaning that is being performed or has been performed. The information may indicate that cleaning has been performed and the individual wearing the wearable computing device 12 has performed cleaning actions on all surfaces to be cleaned, or conversely, that cleaning actions were not performed on at least one surface to be cleaned. Additionally or alternatively, the information may indicate that cleaning has been performed and the individual wearing the wearable computing device 12 has performed cleaning to a threshold quality level, or conversely, that cleaning has not been performed to a threshold quality level. As yet another example, the information may indicate that an individual performing a wash and wearing a wearable computing device 12 did not perform a particular type of wash action that is expected to be performed as part of a memorized wash protocol, and / or that the individual performed a particular type of wash action but did not perform it to a threshold level of quality, and / or performed it in the wrong order.

[0077] In the example in Figure 1, the wearable computing device 12 is shown as a wrist-mounted device such as a watch or activity tracker. As described above, the wearable computing device 12 can be implemented using a variety of different hardware devices. Regardless of the specific type of device used as the wearable computing device 12, the device may be configured with a variety of features and functions.

[0078] In the example in Figure 1, the wearable computing device 12 is shown as including a user interface 40. The user interface 40 of the wearable computing device 12 can function as an input device and an output device of the wearable computing device 12. The user interface 40 may be implemented using various technologies. For example, the user interface 40 can provide an audio-based user interface by functioning as an input device using a microphone and an output device using a speaker. The user interface 40 can function as an input device using a presence-sensitive input display, such as a resistive touchscreen, surface acoustic wave touchscreen, capacitive touchscreen, projected capacitive touchscreen, pressure-sensitive screen, acoustic pulse-recognition touchscreen, or another presence-sensitive display technology. The user interface 40 can function as an output (e.g., display) device using any one or more display devices, such as a liquid crystal display (LCD), dot matrix display, light-emitting diode (LED) display, organic light-emitting diode (OLED) display, e-ink, or a similar monochrome or color display capable of outputting visible information to the user of the wearable computing device 12.

[0079] The user interface 40 of the wearable computing device 12 may include physically pressable buttons and / or a presence-sensitive display capable of receiving haptic input from the user of the wearable computing device 12. The user interface 40 can receive haptic input instructions by detecting one or more gestures from the user of the wearable computing device 12 (for example, the user touching or pointing to one or more locations on the user interface 40 using a finger or stylus pen). The user interface 40 can present outputs to the user, for example, on the presence-sensitive display. The user interface 40 can present outputs as graphical user interfaces that can be associated with functions provided by the wearable computing device 12. For example, the user interface 40 can present various user interfaces of applications that run on or are accessible by the wearable computing device 12 (e.g., an e-messaging application, an internet browser application, etc.). The user can interact with each user interface of the application to cause the wearable computing device 12 to perform functions-related actions. Additionally or alternatively, the user interface 40 may provide tactile feedback, for example, through a haptic generator.

[0080] Figure 1 shows that the wearable computing device 12 includes one or more sensor devices 42 (also referred to herein as “sensors 42”) for generating data corresponding to the device’s movement in three-dimensional space. Many examples of sensor devices 42 exist, including microphones, cameras, accelerometers, gyroscopes, magnetometers, thermometers, galvanic skin response sensors, pressure sensors, barometers, ambient light sensors, heart rate monitors, altimeters, and the like. In some examples, the wearable computing device 12 may include a Global Positioning System (GPS) radio as part of one or more sensor devices 42 for receiving GPS signals (e.g., from GPS satellites) having field data and sensor data corresponding to the current location of the wearable computing device 12. The sensors 42 generate data indicating the movement of the wearable computing device in one or more dimensions, and this movement data can be output to one or more modules of the wearable computing device 12, such as module 44. In some implementations, the sensor device 42 is implemented using a three-axis accelerometer. Additionally or alternatively, the sensor device 42 may be implemented using a three-axis gyroscope.

[0081] The wearable computing device 12 may include a user interface module 44 and, optionally, additional modules (e.g., a cleaning effect determination module 26). Each module can perform operations described using software, hardware, firmware, or a mixture of hardware, software, and firmware present in and / or running on the wearable computing device 12. The wearable computing device 12 may run each module using one or more processors. The wearable computing device 12 may run each module as a virtual machine running on underlying hardware. Each module may run as one or more services of an operating system and / or computing platform. Each module may run as one or more remote computing services, such as one or more services provided by a cloud and / or cluster-based computing system. Each module may run as one or more executable programs in the application layer of a computing platform.

[0082] The user interface module 44 not only provides user interface functions associated with the wearable computing device 12, but can also function as the primary control module of the wearable computing device 12 by acting as an intermediary between the wearable computing device 12 and other modules (e.g., module 46) and other components (e.g., user interface 40, sensor device 42), as well as the remote computing system 14 and / or network 16. By acting as an intermediary or control module on behalf of the wearable computing device 12, the user interface module 44 can ensure that the wearable computing device 12 provides the user with stable and expected functionality. The user interface module 44 may rely on machine learning or other types of rule-based techniques or probabilistic artificial intelligence techniques to control how the wearable computing device 12 operates.

[0083] The user interface module 44 can, for example, cause the user interface 40 to perform one or more actions in response to one or more cleaning decisions made by the cleaning effect determination module 26. For example, the user interface module 44 can cause the user interface 40 to present audio (e.g., sound), graphics, or other types of output (e.g., haptic feedback) related to the user interface. The output can respond to one or more cleaning decisions made and, in some examples, can provide cleaning information to the wearer of the wearable computing device 12 in order to correct cleaning behavior that has been determined to be non-compliant.

[0084] For example, the user interface module 44 can receive information from the cleaning effect determination module 26 via the network 16, thereby controlling the user interface 40 to output information to the wearer of the wearable computing device 12. For example, when the cleaning effect determination module 26 determines whether the user has performed a specific compliant cleaning action (e.g., performing a cleaning operation on each surface to be cleaned, cleaning the target surface to a cleaning threshold quality, and / or performing a specific type of cleaning action, and / or performing such action to a cleaning threshold quality), the user interface module 44 can receive information via the network 16 corresponding to the decision made by the cleaning effect determination module 26. In response to the determination of whether the wearable computing device 12 has performed a specific compliant cleaning action, the user interface module 44 can control the wearable computing device 12 to perform the action, an example of which is described in more detail below.

[0085] The cleaning effectiveness information determined by System 10 can be used in a variety of different ways. As described above, the cleaning effectiveness information can be stored for cleaning events to provide cleaning verification information for the environment being cleaned. Additionally or alternatively, the cleaning effectiveness information may be communicated to a scheduling module running on System 10 or another computing system, for example, to schedule the availability of specific resources in the environment in which the cleaning operation is being performed. In a healthcare environment, for example, the scheduling module can determine the availability of a room (e.g., a patient room, an operating room) and schedule patient assignments / procedures to the room based on the time the room has been cleared from previous use (e.g., cleaned) and is available. As another example, the scheduling module can determine the availability of equipment to be used based on the time the equipment has been cleared from previous use (e.g., cleaned) and is available. The cleaning effectiveness information determined by System 10 may be communicated to the scheduling module to determine the time when resources (e.g., rooms, equipment) are expected to be cleaned and / or when the cleaning will be completed. For example, the scheduling module may determine, based on virtually real-time cleaning effect and progress information generated by system 10, that a resource is expected to be available for a specific time period (e.g., X minutes). The scheduling module can then schedule subsequent use of the resource based on this information.

[0086] As another example, the cleaning effectiveness information determined by system 10 can be used to train and / or incentivize the cleaner using the system. The computing system 10 may include or communicate with an incentive system that uses the system to issue one or more incentives to the cleaner based on cleaning performance monitored by the wearable computing device 12. The incentive system may issue awards (e.g., encouraging messages issued via the user interface 40 and / or via email and / or text messages) and / or rewards (e.g., monetary rewards, prizes) in response to an individual user achieving one or more goals (e.g., efficiency goals, quality goals) determined based on exercise data generated by the wearable computing device worn by the user.

[0087] Figure 2 is a block diagram showing an example of a wearable computing device configured according to one or more aspects of the present disclosure. For example, the wearable computing device of Figure 2 may be configured to determine whether the wearer of the device has performed a specific compliant cleaning action (e.g., performing a cleaning action on each surface to be cleaned, cleaning the target surface to a cleaning threshold quality, and / or performing a specific type of cleaning action, and / or performing such actions to a cleaning threshold quality, and / or performing them in a target cleaning order). The wearable computing device 12 of Figure 2 is described below in the context of the system 10 of Figure 1. Figure 2 shows only one specific example of the wearable computing device 12 of the system 10, and many other examples of the wearable computing device 12 may be used in other examples and may include a subset of components, additional components, or different components that are not included in the exemplary wearable computing device 12 shown in Figure 2.

[0088] As shown in the example in Figure 2, the wearable computing device 12 includes a user interface 40, a sensor device 42, one or more processors 50, one or more input devices 52, one or more communication units 54, one or more output devices 56, and one or more storage devices 58. The storage device 48 of the wearable computing device 12 also includes a user interface module 44, a cleaning effect determination module 60, application modules 62A to 62Z (collectively referred to as "application modules 62"), and data stores 64, 66, and 68.

[0089] The cleaning effect determination module 60 may generally correspond to the cleaning effect determination module 26 of the remote computing system 14 of system 10. Data stores 64, 66, and 68 may correspond to data stores 28, 30, and 32 of the remote computing system 14 in Figure 1, respectively. Therefore, functions described as being performed by or on the remote computing system 14 (in combination with functions performed on the wearable computing device 12) may also be performed only on the wearable computing device 12, and / or processing tasks may be shifted from the remote computing system 14 to the wearable computing device 12.

[0090] The communication channel 70 can interconnect each of the components of the wearable computing device 12 (physically, communicatively, and / or operationally) for inter-component communication. In some examples, the communication channel 70 may include a system bus, a network connection, an inter-process communication data structure, or any other method for communicating data.

[0091] One or more input devices 52 of the wearable computing device 12 can receive input. Examples of inputs include haptic, audio, and video inputs. For example, the input devices 52 of the wearable computing device 12 include a presence-sensitive display, a touch-sensitive screen, a mouse, a keyboard, a voice response system, a video camera, a microphone, or any other type of device for detecting input from a human or machine. One or more output devices 56 of the wearable computing device 12 can generate output. Examples of output include haptic, audio, and video outputs. For example, the output devices 56 of the wearable computing device 12 include a haptic generator that provides tactile feedback to the wearer.

[0092] One or more communication units 54 of the wearable computing device 12 can communicate with an external device (e.g., a remote computing system 14) over one or more networks by transmitting and / or receiving network signals over one or more networks. For example, the wearable computing device 12 can use the communication units 54 to send and receive data to and from the remote computing system 14 shown in Figure 1. The wearable computing device 12 can use the communication units 54 to transmit and / or receive radio signals over a radio network, such as a cellular radio network. Similarly, the communication units 54 can transmit and / or receive satellite signals over a satellite network, such as a Global Positioning System (GPS) network. Examples of communication units 54 include network interface cards (e.g., Ethernet cards), optical transceivers, radio frequency transceivers, GPS receivers, or any other type of device capable of transmitting and / or receiving information. Other examples of communication units 54 include shortwave radio, cellular data radio, wireless Ethernet network radio, and Universal Serial Bus (USB) controllers.

[0093] In some examples, the user interface 40 of the wearable computing device 12 may also include the functionality of an input device 52 and / or an output device 56. Although shown as an internal component of the wearable computing device 12, the user interface 40 also represents an external component that shares a data path with the wearable computing device 12 to transmit and / or receive inputs and outputs. For example, in one example, the user interface 40 represents an embedded component of the wearable computing device 12 that is located within the external package of the wearable computing device 12 (e.g., a mobile phone screen) and is physically connected to it. In another example, the user interface 40 represents an external component of the wearable computing device 12 that is located outside the package of the wearable computing device 12 and is physically separated from it (e.g., a device that shares a wired and / or wireless data path with other components of the wearable computing device 12).

[0094] One or more storage devices 64-68 within the wearable computing device 12 can store information for processing during the operation of the wearable computing device 12 (for example, the wearable computing device 12 may store target surface comparison data 64 corresponding to data store 28 in Figure 1, cleaning quality comparison data 66 (corresponding to data store 30 in Figure 1), and / or cleaning behavior comparison data 68 (corresponding to data store 32 in Figure 1). Such data may be accessed by other modules and functions of the wearable computing device 12 while it is running. In some examples, storage device 58 is temporary memory, meaning that the primary purpose of storage device 58 is not long-term storage. Storage device 58 on the wearable computing device 12 may be configured to store information for a short period as volatile memory, and therefore will not retain its stored contents when powered off. Examples of volatile memory include random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), and other forms of volatile memory known in the art.

[0095] In some examples, the storage device 58 also includes one or more computer-readable storage media. The storage device 58 may be configured to store larger amounts of information than volatile memory. The storage device 58 may further be configured to retain information after power-on / off cycles for long-term storage of information as non-volatile memory space. Examples of non-volatile memory include magnetic hard disks, optical disks, floppy disks, flash memory, or in the form of electrically programmable memory (EPROM) or electrically erasable and programmable (EEPROM) memory. The storage device 58 may store program instructions and / or data to implement the features and functions described herein as being implemented by any module, device, and / or system.

[0096] One or more processors 50 can implement functions and / or execute instructions within the wearable computing device 12. For example, a processor 50 on the wearable computing device 12 can receive and execute instructions stored by the storage device 58, which perform functions of the user interface module 44, the cleaning effect determination module 60, and the application module 62. These instructions executed by the processor 50 allow the wearable computing device 12 to store information in the storage device 58 during program execution. The processor 50 can execute instructions from modules (e.g., 44, 60, 62) to cause the wearable computing device 12 to determine compliance with one or more characteristics of cleaning, and in some examples, to control the execution of actions in response to determining one or more non-compliant actions. For example, the processor 50 can execute instructions to the user interface 40 to output at least one of an audible alert, a visual alert, and / or a haptic feedback alert. One or more such alerts may provide information indicating non-compliance with the cleaning protocol (e.g., not cleaning all surfaces targeted for cleaning, not cleaning certain surfaces to a threshold level of cleaning quality), instruct the user on actions to correct the non-compliance, identify details of the non-compliant activity (e.g., identify any missed target surfaces), and / or notify the user that the cleaning performed did not meet compliance standards.

[0097] The application module 62 may include any additional types of applications that the wearable computing device 12 can run. The application module 62 may be a standalone application or process. In some examples, the application module 62 represents an operating system or computing platform for the wearable computing device 12 to perform or control functions and actions performed by other applications.

[0098] One or more aspects of this disclosure can be used to clean a variety of different surfaces and objects. Examples of such surfaces are described in detail below in relation to Figure 4. In some examples, one or more surfaces to be cleaned are located in a healthcare environment, as discussed below in relation to Figure 1. In other examples, one or more surfaces to be cleaned are located in a food preparation environment. Figures 3A–3C show exemplary surfaces and / or equipment that may be cleaned using optionally exemplary tools to evaluate the cleaning effect in accordance with this disclosure. Figure 3A shows an example of a floor cleaning protocol that may be specified for a wearer of the wearable computing device 12 to follow. Figure 3B shows an example of a grill cleaning protocol that may be specified for a wearer of the wearable computing device 12 to follow. Figure 3C shows an exemplary fryer cleaning protocol that may be specified for a wearer of the wearable computing device 12 to follow.

[0099] To determine one or more cleaning effectiveness using the wearable computing device 12, one or more calibration processes can be performed to generate comparative data stored in a data store for reference during subsequent cleaning events. For example, a monitoring process can be used in which an individual wearing the wearable computing device during a subsequent cleaning activity undergoes a calibration process using the device or an equivalent (e.g., a device that generates motion data equivalent to that generated by the wearable computing device 12). Alternatively, global, non-user-specific training may be performed to generate comparative data to be referenced during the use of the wearable computing device, which may help eliminate the need for user-specific calibration but may have lower accuracy. Therefore, in some implementations, the reference motion data stored in a data store (e.g., within the wearable computing device 12 and / or remote computing system 14) is generated from motion data acquired during one or more training episodes, in which one or more trainers (different from the individual who will later perform the cleaning) perform cleaning actions (e.g., on each of several target surfaces or their equivalents) while wearing the wearable computing device 12 or an equivalent. In other implementations, the reference motion data stored in the data store is generated from motion data acquired during one or more training episodes in which an actual individual performing a subsequent cleaning operation (e.g., on each of several target surfaces or their equivalents) is wearing the wearable computing device 12 or its equivalent.

[0100] Regardless of how the comparison data is generated, the computing system 10 can be used to generate and / or store comparison data associated with different surfaces and / or areas being cleaned, and / or different levels of cleaning performed on those surfaces and / or areas (e.g., different cleaning protocols). In some examples, a user can provide the computing system 10 with user input indicating that the wearable computing device 12 is being reassigned to monitor the cleaning of one or more surfaces, rooms, and / or areas different from those previously used by the wearable computing device. Alternatively, the computing system 10 can automatically determine that the wearable computing device 12 has been reassigned based on motion data generated by the wearable computing device. In either case, the computing system 10 can reset the comparison data to be compared during subsequent operations, based on the context of the measurement and / or the motion data generated by the wearable computing device 12. Additionally or alternatively, the computing system 10 can change the level of cleaning performed and / or the protocol to which the cleaning data is compared (e.g., if a patient room is being switched from daily maintenance cleaning to a more thorough drainage cleaning).

[0101] Figure 4 is a flowchart illustrating an exemplary process for training an exemplary wearable computing device to determine whether an individual performing a wash has washed each of several target surfaces intended to be washed as part of an established protocol. The process shown in Figure 4 may be performed by one or more processors in a computing device such as the wearable computing device 12 shown in Figures 1 and 2. For illustrative purposes, Figure 4 is described below in the context of the computing system 10 in Figure 1. It should be understood that the process in Figure 4 may be performed by the individual wearing the wearable computing device 12 during the subsequent wash, or by a different individual other than the individual who will perform the subsequent wash (e.g., a trainer). In some examples, the process in Figure 4 is performed by a single individual, while in other implementations, multiple different individuals perform the process to generate a collective dataset corresponding to a broader user population. For example, the generation of reference motion data by any of the techniques described herein may be performed by (1) a single individual in a single session, (2) multiple individuals in each single session, (3) a single individual across multiple sessions, and / or (4) multiple individuals across multiple sessions.

[0102] In the example in Figure 4, an individual wearing a wearable computing device 12 performs a cleaning operation on each of several target surfaces (100). The multiple target surfaces may be at least two surfaces, such as at least five surfaces, or at least ten surfaces, or at least fifteen surfaces. In some implementations, each target surface is a target object. Therefore, a description of performing a cleaning operation on a target surface can be implemented by performing such a cleaning operation on a target object. Each target object may have a boundary in three-dimensional space that defines the extent of the object to be cleaned. The boundary of each target object may differ from other target objects intended to be cleaned, such that the cleaning operation performed on each target object results in a different movement than the cleaning operation performed on each other target objects.

[0103] Each cleaning action may optionally be a movement action corresponding to cleaning a target surface or object, along with a preparatory cleaning movement preceding the cleaning of the target surface or object. Each cleaning action may be performed by an individual wearing a wearable computing device 12 with or without the help of a tool (e.g., a mop, brush, sprayer, sponge, or wiping cloth). Each cleaning action may involve movement in one or more dimensions of the individual's hand, arm, and / or body. For example, a cleaning action may involve horizontal, vertical, and / or rotational movements of the hand corresponding to the cleaning, thereby transmitting force from the individual's hand to the target surface being cleaned, for example, through a cleaning tool. For example, one type of cleaning action that may be performed is a cleaning movement in which the individual moves their body to wipe the target surface. Another type of cleaning action that may be performed is a floor cleaning action in which the individual performs a floor wiping or mopping motion, for example, in which the individual stands upright and transmits force through a tool that extends to the floor surface. Another example of a type of cleaning action that may be performed is a cleaning action of equipment. The cleaning operation of the equipment may be an action performed by an individual to clean equipment that is active or in use during normal operation in the environment.

[0104] The surfaces or objects to be cleaned may be selected according to a cleaning protocol that specifies the surfaces to be cleaned during a cleaning event. The specific surfaces selected for cleaning according to the protocol will vary depending on the application and environment in which the cleaning protocol is performed. Examples of surfaces that may be cleaned (e.g., in a hotel or healthcare environment) include, but are not limited to, light switches, tabletops, bed rails, doorknobs, drug dispenser poles, television remotes, and combinations thereof. Other examples of surfaces that may be cleaned (e.g., in a food preparation environment) include, but are not limited to, those that define the equipment used in the environment, such as grills, fryers, refrigerators, microwave ovens, and combinations thereof.

[0105] Generally, the types of surfaces to be cleaned include floor surfaces and non-floor surfaces, and may also include surfaces and objects higher than the floor on which they reside. For example, an individual wearing the wearable computing device 12 can perform mopping, sweeping, and / or deck brushing cleaning actions on a floor surface. Additionally or alternatively, an individual wearing the wearable computing device 12 may perform cleaning actions on non-floor surfaces, such as cleaning sinks, faucet handles, toilets, countertops, and combinations thereof. Each target surface can be defined as an object having a flat horizontal surface, a flat vertical surface, a cavity, a cylinder, a sphere, and combinations thereof.

[0106] An individual performing a cleaning operation on each target surface while wearing the wearable computing device 12 can perform the cleaning operation according to a protocol. The protocol can specify how to perform the cleaning operation on each target surface, for example, the type of cleaning tool to use, the area of ​​the surface to be cleaned, and / or the type and direction of force to apply at one or more stages of the cleaning operation. In other words, the cleaning protocol can specify the techniques to be followed to clean each target surface, which will be followed while wearing the wearable computing device 12 according to the training techniques in Figure 4, and which will also be instructed to be followed during subsequent cleaning events.

[0107] According to the technology shown in Figure 4, the sensor device 42 of the wearable computing device 12 can generate motion data related to the movement of the wearable computing device 12 during a cleaning operation performed on each of a plurality of target surfaces (102). Such motion data can indicate the three-dimensional acceleration of the wearable computing device 12 during the cleaning operation performed on each target surface, and / or the three-dimensional orientation of the wearable computing device during the cleaning operation. Other sensor data that may be generated include the data described above, such as GPS data.

[0108] Motion data generated by the sensor device 42 of the wearable computing device 12 during one or more training sessions can be associated with the cleaning of different target surfaces according to the technique shown in Figure 4(104). For example, one or more modules (e.g., module 26) running within the computing system 10 can receive the data generated by the sensor device 42 and associate different parts of the motion data with each of a specific target surface on which the individual wearing the wearable computing device 12 performed a cleaning action.

[0109] For example, motion data generated by the sensor device 42 of the wearable computing device 12 may be transmitted wirelessly to the remote computing system 14 via the network 16 for analysis by one or more modules running in the remote computing system. Different parts of the motion data generated by the sensor device 42 may be associated with corresponding target surfaces in several different ways. As an example, an individual associated with a training event can notify the remote computing system 14 (for example, via the user interface 40) when a cleaning operation is being performed on a target surface (for example, by indicating the start and stop of the cleaning operation). In other words, an individual associated with a training event can assign the cleaning of each target surface to a corresponding part of the motion data, and the remote computing system 14 can associate the motion data generated during a cleaning operation performed on a particular target surface with that target surface.

[0110] As another example, a communication unit associated with a tool used to clean a target surface and / or the target surface itself can provide an indicator of when the target surface is being cleaned. For example, a wearable computing device 12 can receive communication signals from a communication unit associated with a tool and / or the target surface itself (e.g., a short-range radio, Wi-Fi radio, CB radio, Bluetooth® radio, etc.) associated with cleaning a particular target surface, thereby indicating when that target surface is being cleaned. A remote computing system 14 can receive data corresponding to the time a particular target surface is being cleaned (e.g., corresponding to signals provided by a cleaning tool associated with the target surface and / or the target surface emitter) and associate motion data corresponding to the cleaning operation on that target surface with its target surface.

[0111] Regardless of the specific technique used to correlate different parts of the motion data generated during cleaning, the exemplary technique in Figure 4 includes determining reference data for each of several different target surfaces that represent the cleaning operations performed on the target surface (106). For example, a module running on the remote computing system 14 (e.g., a feature generation module) can process the motion data associated with each target surface to generate one or more features from the motion data that represent the cleaning operations performed on that target surface. The motion data associated with the cleaning operations performed on each target surface can be filtered using a time-domain feature timeframe and / or a frequency-domain timeframe with a set duration (e.g., 1 second), where a shorter duration timeframe provides more granularity. In contrast, a longer duration timeframe reduces processing requirements and provides an opportunity for more cycles of cleaning motion (e.g., wiping, scrubbing, mopping) to be displayed in the frequency domain. Candidate features for characterizing the motion data may be stored in a data store associated with the remote computing system 14 and applied to the generation of motion data. Each candidate feature may correspond to a different aspect of the kinetic motion that constitutes the cleaning operation associated with a particular target surface.

[0112] Candidate features may be generated for different aspects of motion sensor data generated by the sensor device 42 and / or for different regions of the data. For example, if the sensor device 42 is configured to generate inertial motion data (e.g., acceleration data, gyroscope data) across one or more axes, single-axis and / or multi-axis features can be generated for the sensor data. A single-axis feature is a transformation of a single inertial measurement unit (IMU) axis (e.g., acceleration or gyroscope readings on the x, y, or z axis). Sensitivity features can also be multi-axis features, which are transformations of multiple IMU axes at a given time point.

[0113] Additionally or alternatively, candidate features may be generated for different regions of motion sensor data generated by the sensor device 42. For example, time-domain features may be generated by applying a transformation to each time-domain time frame of the sensor data. As another example, frequency-domain Fourier features may be generated by applying a transformation to the spectrum resulting from the discrete Fourier transform of the sensor data in each frequency-domain time frame. As yet another example, wavelet features may be generated by a transformation applied to the spectrum resulting from the discrete wavelet transform of the sensor data in each frequency-domain time frame.

[0114] One example of the class of features that can be generated is a uniaxial time-domain feature. Basic functions that can be applied to each time-domain time frame of each uniaxial IMU data (e.g., accelerometer data (e.g., x, y, and / or z) and / or gyroscope sensor data (e.g., x, y, and / or z)) include, but are not limited to, the mean, median, variance, standard deviation, maximum, minimum, time frame range, root mean square (RMS), univariate signal amplitude area (SMA), zero crossing, mean absolute jerk, standard deviation of absolute jerk, univariate SMA jerk, and combinations thereof.

[0115] Another example of the class of features that can be generated is multi-axis time-domain features. Basic functions that can be applied to each time-domain timeframe across multiple axes of sensor data include, but are not limited to, xy correlation, yz correlation, xz correlation, sum of signal magnitude areas, mean of signal vector magnitude, standard deviation of signal vector magnitude, maximum xy difference, maximum yz difference, and maximum xz difference.

[0116] A further class of possible features is the uniaxial frequency-domain Fourier feature. Basic functions applicable to the spectrum resulting from the domain Fourier transform of a time-domain signal in each frequency-domain time frame include, but are not limited to, the DC offset, peak frequencies (e.g., top 3), peak amplitudes (e.g., top 3), and spectral energy.

[0117] A further class of examples of functions that can be generated is the uniaxial wavelet feature. Fundamental functions applicable to the spectrum resulting from the discrete wavelet transform of a time-domain signal in each frequency-domain time frame include, but are not limited to, wavelet persistence (e.g., low, low-mid, mid-high, and high bands) and spectral energy (e.g., low, low-mid, high-mid, and high bands).

[0118] The sensor device 42 of the wearable computing device 12 can generate arbitrary or all candidate features for each duration segment of data associated with the cleaning of a specific target surface. The features thus generated can form feature vectors for each duration or time frame of the analyzed motion, and the time series of all such vectors forms a feature matrix on which feature selection is performed.

[0119] After generating multiple candidate features to characterize the motion data associated with cleaning operations performed on each target surface, one or more specific candidate features can be selected to define reference motion data used for subsequent analysis and characterization of motion data during cleaning events. Specific features can be selected from a pool of candidate features (e.g., by a module running on a remote computing system 14) based on the separability of the features in space. That is, desired reference data, for example, features that appropriately or best distinguish the cleaning of one target surface compared to different target surfaces, can be selected.

[0120] Candidate features can be generated and selected using any type of supervised learning algorithm. Examples of supervised learning algorithms that can be used include, but are not limited to, combinations of supervised learning algorithms called Bayesian networks, neural networks, k-nearest neighbors, random forests, support vector machines, and / or ensemble classifiers.

[0121] In the technique shown in Figure 4, reference data for each target surface on which a cleaning operation is performed for characterization can be stored (for example, in data store 64 on the wearable computing device 12 and / or data store 28 on the remote computing system 14) (108). The reference motion data can be stored in the form of raw data. Additionally or alternatively, the reference motion data may be stored in the form of a set of features identified through the feature selection process described above, which distinguishes the motion associated with a cleaning operation performed on one target surface from the motion associated with cleaning operations performed on each other target surface. Therefore, it should be understood that the description of the reference motion data does not mean that raw reference motion data must be used in subsequent analysis, but rather that data derived from or based on raw reference motion data can be used. In any case, the reference data associated with cleaning operations performed on each of the multiple target surfaces may be stored for use in connection with the evaluation and / or characterization of subsequent cleaning events.

[0122] Figure 5 is a flowchart illustrating an exemplary process for training an exemplary wearable computing device to determine whether an individual performing the cleaning has effectively cleaned the target surface to a cleaning threshold quality. The process shown in Figure 5 may be performed by one or more processors in a computing device, such as the wearable computing device 12 shown in Figures 1 and 2. For illustrative purposes, Figure 5 is also described below within the context of the computing system 10 in Figure 1. It should be understood that the process in Figure 5 may be performed by the individual wearing the wearable computing device 12 during the subsequent cleaning, or by a different individual (e.g., a trainer) other than the individual who will perform the subsequent cleaning, as described above in relation to Figure 4.

[0123] In the example of Figure 5, an individual wearing a wearable computing device 12 performs a cleaning operation on one or more target surfaces, and the quality of the cleaning is intended to be characterized during a subsequent cleaning event (120). The target surfaces may be any of those surfaces or objects described herein, including those described above in relation to Figure 4. Each target surface can define an object having a boundary in three-dimensional space that defines the extent of the object to be cleaned.

[0124] An individual wearing a wearable computing device 12 can perform cleaning operations on a target surface according to a protocol. The protocol can define a threshold quality for surface cleaning. For example, the protocol can be established such that compliance with the protocol indicates that the surface has been cleaned to a threshold quality, and non-compliance indicates that the surface has not been cleaned to a threshold quality.

[0125] The protocol can specify how to perform a cleaning operation on a target surface, for example, the type of cleaning tool to use, the extent of the surface to be cleaned, and / or the type and direction of force to apply at one or more stages of the cleaning operation. For example, a cleaning protocol can instruct the techniques to be followed to clean a target surface, which, when followed while wearing a wearable computing device 12 during a subsequent cleaning event, will indicate that the surface is clean to a cleaning threshold quality. The protocol may be developed by a cleaning expert with knowledge of the cleaning characteristics of various surfaces, pathogen killing times, and other empirical or experimental data that guides the development of protocols for achieving cleaning threshold quality.

[0126] According to the technology shown in Figure 5, the sensor device 42 of the wearable computing device 12 can generate motion data related to the movement of the wearable computing device 12 during a cleaning operation performed on a target surface (122). In some examples, one or more modules running in a remote computing system 14 can receive the data generated by the sensor device 42 for further processing. For example, the motion data generated by the sensor device 42 of the wearable computing device 12 may be transmitted wirelessly to the remote computing system 14 via the network 16 for analysis by one or more modules running in the remote computing system. If the motion data generated by the sensor device 42 includes motion data other than that associated with cleaning the target object according to a protocol for establishing a cleaning threshold quality, a portion of the motion data generated by the sensor device 42 corresponding to cleaning may be associated with cleaning, for example, as described above in relation to Figure 4.

[0127] The exemplary technique in Figure 5 includes determining reference data that indicates a threshold quality of cleaning performed on a target surface (124). For example, a module running on a remote computing system 14 (e.g., a feature generation module) can process motion data related to cleaning the target surface to generate characteristics of the reference data. For example, by processing raw motion data, a number of candidate features can be generated to characterize motion data related to the quality of cleaning performed on the target surface, for example, according to the feature generation technique described above in relation to Figure 4. Then, one or more specific candidate features can be selected to define reference motion data to be used for subsequent analysis and characterization of motion data generated during cleaning to characterize the quality of cleanliness of the target surface, for example, according to the feature selection technique described above in relation to Figure 4.

[0128] Reference data generated for a target surface corresponding to the quality of cleaning of the target surface may be stored (for example, in a data store 66 on a wearable computing device 12 and / or in a data store 30 on a remote computing system 14) (126). Reference motion data may be stored in raw data form. Additionally or alternatively, reference motion data may be stored in the form of a set of features identified through a feature selection process that identifies motions related to the quality of cleaning performed on the target surface. Regardless of the data format, reference data associated with the quality of cleaning performed on a surface may be stored for use in relation to the evaluation and / or characterization of subsequent cleaning events.

[0129] Figure 6 is a flowchart illustrating an exemplary process for training an exemplary wearable computing device, for example, as part of an integrated hygiene management system, to later evaluate multiple different cleaning actions. Multiple different cleaning actions may include at least two different types of cleaning actions, such as three or more cleaning actions. Examples of cleaning actions that can be performed include cleaning floor surfaces, cleaning equipment, and hand hygiene. Other types of cleaning actions that can be performed include cleaning non-floor and non-equipment surfaces, such as cleaning high surfaces (e.g., toilets, doorknobs, counters, and other surfaces mentioned above). The process shown in Figure 6 may be performed by one or more processors in a computing device, such as the wearable computing device 12 shown in Figures 1 and 2. For illustrative purposes, Figure 6 will also be described below within the context of the computing system 10 in Figure 1. It should be understood that the process in Figure 6 may be performed by an individual wearing the wearable computing device 12 during subsequent cleaning, or by a different individual (e.g., a trainer) other than the individual who will perform the subsequent cleaning, as described above in relation to Figure 4.

[0130] In the example of Figure 6, an individual wearing the wearable computing device 12 performs several different cleaning actions, each of which may be performed during a subsequent cleaning event (130). Target cleaning actions may include non-hand hygiene cleaning actions performed on any surface or object as described herein, including those described above with respect to Figure 4. Each target surface can define an object having a boundary in three-dimensional space that defines the extent of the object to be cleaned. Target cleaning actions may also include hand hygiene cleaning actions in which the wearer of the wearable computing device 12 cleans the wearer's hands.

[0131] An individual wearing the wearable computing device 12 to perform cleaning can carry out each cleaning action according to the corresponding protocol. For cleaning actions other than hand hygiene, the protocol can specify how to perform the cleaning action on the target surface, for example, as described above in relation to Figures 3A-3C, 4, and 5. For hand hygiene cleaning actions, the corresponding hand hygiene cleaning protocol can be used. Figure 7 shows an example of a hand hygiene protocol that can be used but which the wearer of the wearable computing device 12 can be specified to follow.

[0132] According to the technology shown in Figure 6, the sensor device 42 of the wearable computing device 12 can generate motion data relating to the movement of the wearable computing device 12 during each washing action performed, and optionally, between washing actions when a non-washing action is being performed (132). In some examples, one or more modules running in a remote computing system 14 can receive the data generated by the sensor device 42 for further processing. For example, the motion data generated by the sensor device 42 of the wearable computing device 12 may be transmitted wirelessly to the remote computing system 14 via the network 16 for analysis by one or more modules running in the remote computing system. If the motion data generated by the sensor device 42 includes multiple washing actions, a portion of the motion data generated by the sensor device 42 corresponding to each washing action can be associated with that washing action, for example, as described above in relation to Figure 4.

[0133] The exemplary technique in Figure 6 includes determining reference data representing each type of cleaning action performed, which distinguishes each particular type of cleaning action from each other type of cleaning action (134). For example, a module running on a remote computing system 14 (e.g., a feature generation module) can process motion data associated with each cleaning action to generate characteristics of the reference data. For example, raw motion data can be processed to generate a number of candidate features for characterizing the motion data associated with each cleaning action, for example, according to the feature generation technique described above with respect to Figure 4. Then, one or more specific candidate features can be selected to define reference motion data to be used for subsequent analysis and characterization of motion data generated during the performance of multiple cleaning actions, for example, according to the feature selection technique described above with respect to Figure 4.

[0134] Reference data generated for each type of washing behavior may be stored (for example, in a data store 68 on a wearable computing device 12 and / or in a data store 32 on a remote computing system 14) (136). The reference motion data may be stored in raw data form. Additionally or alternatively, the reference motion data may be stored in the form of a set of features identified through a feature selection process that distinguishes motion associated with one particular type of washing behavior from motion associated with other particular types of washing behavior. Regardless of the data format, reference data associated with each particular type of washing behavior may be stored and used in connection with the evaluation and / or characterization of subsequent washing events.

[0135] The exemplary calibration techniques described above in relation to Figures 4-6 may be performed on common surfaces with similar properties, but with different dimensions than those surfaces that will actually be cleaned in subsequent use. For example, one or more training sessions may be conducted during which a representative substitute of the target surface to be cleaned is cleaned. As an example, the cleaning operation may be performed on a common sink that is different from the actual sink that will be cleaned in subsequent use. The data generated by cleaning the common sink may be stored as reference motion data associated with the sink cleaning and subsequently used to characterize the cleaning of the actual sink. Using common substitutes of the actual surfaces that are intended to be cleaned in subsequent use facilitates the development of a global, or non-customer-specific, reference motion dataset.

[0136] In other implementations, the exemplary calibration techniques described above in relation to Figures 4-6 may be performed on actual surfaces (or substantially accurate replicas thereof) that will be cleaned in subsequent use. For example, one or more of the described calibration techniques may be performed on actual target surfaces (or substantially accurate replicas thereof) in an environment where the cleaning effect is subsequently intended to be evaluated, in order to generate more accurate reference motion data.

[0137] In subsequent use, the cleaning effect determination module 26 can analyze motion data generated during a cleaning event by referring to comparative data stored in one or more data stores. The cleaning effect determination module 26 may determine whether the motion during the cleaning event is related to cleaning behavior or non-cleaning behavior, and / or whether the motion during the cleaning event indicates that the cleaning behavior conforms to one or more standards.

[0138] In practice, certain cleaning events may deviate from the normal or planned cleaning process. For example, a cleaning event may deviate from the planned cleaning process if the area to be cleaned is significantly dirtier than normally expected. This may require additional cleaning of one or more surfaces beyond what is specified in the cleaning protocol for those surfaces. Heavily soiled areas may also require cleaning of one or more surfaces not specified as part of the cleaning protocol. Another example is when a cleaning event is interrupted and the person performing the cleaning does not complete the cleaning protocol. This may occur, for example, if the person performing the cleaning is reassigned to perform an alternative task during the cleaning event, or if external conditions necessitate terminating the cleaning event (for example, if a cleaner performing maintenance cleaning of a patient's room in a healthcare setting recognizes an urgent patient need).

[0139] The user interface 40 of the wearable computing device 12 may be configured to allow an individual associated with the wearable computing device to indicate when a cleaning event deviates from the expected cleaning protocol, for example, because the cleaning protocol was not completed. The user interface 40 may include a physically pressable button and / or may receive one or more gestures from the user of the wearable computing device 12 to indicate that the cleaning event deviates from the expected course of action, such as when the planned cleaning protocol is not performed as specified by the protocol (e.g., the user touches or points to one or more locations on the user interface).

[0140] In response to user input indicating that cleaning deviates from the planned cleaning protocol, various different actions may be taken. For example, motion data associated with a cleaning event may be designated as deviating from the expected cleaning protocol. Such designated motion data may be filtered out from other motion data during a cleaning event that has not been designated via the user interface 40 as deviating from the expected protocol, or otherwise handled separately. This allows for the generation, display, and / or storage of more accurate cleaning validation information by separating abnormal cleaning events from standard cleaning events. Additionally or alternatively, the number and frequency of cleaning events designated as deviating from the expected protocol can be tracked and compared, for example, across thresholds and / or different cleaners. This provides insights into which cleaners are experiencing more cleaning events designated as deviating from the expected protocol than others, which may indicate supplemental training for cleaners, changes to specific cleaning protocols, and / or environmental changes to reduce the number of exceptionally designated cleaning events.

[0141] Figure 8 is a flowchart illustrating exemplary operation of an exemplary wearable computing device configured to track the effectiveness of cleaning to reduce diseases and infections caused by ineffective cleaning, according to one or more aspects of the present disclosure. The technology shown in Figure 8 may be implemented by one or more processors in a computing device such as a wearable computing device 12 and / or a remote computing system 14.

[0142] In the exemplary technique shown in Figure 8, the wearable computing device 12 can detect device-related motion during a cleaning event (150). The motion may be generated by the individual performing the cleaning during the cleaning event, on multiple target surfaces that are intended to be cleaned during the event. The wearable computing device 12 can detect the motion via the sensor device 42 and generate motion data corresponding to the motion.

[0143] The multiple surfaces to be cleaned during a cleaning event may be any of the surfaces and objects described herein, including those described above in relation to Figure 4. The person performing the cleaning during the cleaning event may be instructed to clean each of the multiple target surfaces according to a cleaning protocol, which may be, for example, the same protocol used to generate reference motion data corresponding to the cleaning actions performed on each target surface.

[0144] At least one sensor of the wearable computing device 12 can generate motion data corresponding to movements during the cleaning operation. One or more processors of the wearable computing device 12 can receive the generated motion data and control its transmission to the remote computing system 14. One or more processors 50 running on the remote computing system 14 can receive the data and issue instructions to the cleaning effect determination module 26 to evaluate the effectiveness of the cleaning performed.

[0145] A cleaning effectiveness determination module 26 running on the remote computing system 14 can determine whether the individual performing the cleaning performed the cleaning operation on each of the multiple surfaces to be cleaned (152). The cleaning effectiveness determination module 26 can make such a determination by comparing motion data generated by the sensor device 42 of the wearable computing device 12 during the cleaning event with reference motion data in the data store 28 associated with the cleaning of each of the multiple target surfaces. For example, the cleaning effectiveness determination model 26 may compare motion data generated over the entire duration of the cleaning event with reference motion data associated with each of the multiple target surfaces to determine, for example, whether motion data generated during any time period in the cleaning event corresponds to each of the multiple target surfaces. If it is determined that the motion data generated during the cleaning event does not correspond to reference data associated with at least one target surface, the cleaning effectiveness determination module 26 may determine that no cleaning operation was performed on the target surface during the cleaning event.

[0146] In some implementations, the cleaning effect determination module 26 determines at least one signal feature of the received motion data and compares the motion data generated during the cleaning event with reference motion data. For example, the cleaning effect determination module 26 may determine multiple signal features for the received motion data generated by the sensor device 42 during the cleaning event. One or more signal features generated for the received motion data can distinguish a cleaning operation performed on one target surface from a cleaning operation performed on a different target surface, corresponding to features selected during the calibration process. For example, one or more signal features may correspond to those described above in relation to Figure 4. The cleaning effect determination module 26 may compare one or more signal features determined for the motion data generated during the cleaning event with reference signal feature data generated during calibration and stored in the data store 28, corresponding to each of the cleanings of multiple target surfaces, for example, as described above in relation to Figure 4.

[0147] If the wearable computing device 12 is implemented with multiple sensors (e.g., including an accelerometer and a gyroscope), each of the multiple sensors can generate corresponding motion data during a cleaning event. A cleaning effect determination module 26 running on a remote computing system 14 can determine one or more signal features based on the motion data generated by and received from each of the multiple sensors. For example, the cleaning effect determination module 26 can receive first motion data corresponding to the acceleration of the wearable computing device 12 and second motion data corresponding to the angular velocity of the wearable computing device (in the case of a gyroscope). The cleaning effect determination module 26 can characterize the motion performed during a cleaning event by determining at least one signal feature based on the first motion data and at least one additional signal feature based on the second motion data.

[0148] Depending on the characteristics of the surface to be cleaned, an individual wearing the wearable computing device 12 can perform multiple different types of cleaning actions. For example, one type of surface to be cleaned may be a horizontal surface (e.g., a countertop) where the cleaning action involves a horizontal wiping motion. Another type of surface to be cleaned may be a vertical surface (e.g., a medication support portal) where the cleaning action involves a vertical wiping motion. Yet another type of surface to be cleaned may be a doorknob having an arc-shaped form to be cleaned, characterized by yet another type of cleaning action involving a rotational wiping motion. Thus, depending on the type of surface to be cleaned and / or the protocol specified for cleaning each type of surface, an individual wearing the wearable computing device 12 can perform one or more cleaning actions during a cleaning event.

[0149] In some examples, the person performing the cleaning performs at least a first cleaning operation on a first surface among several target surfaces, and a second cleaning operation on a second surface among several target surfaces that is different from the first cleaning operation. In some additional examples, the person performing the cleaning performs different cleaning operations on each of several different surfaces to be cleaned.

[0150] The technology in Figure 8 includes a wearable computing device 12 that performs an action when it is determined that the individual performing the cleaning has not performed a cleaning operation on at least one of several target surfaces (154). For example, the user interface module 44 of the wearable computing device 12 may receive information from a remote computing system 14 via a network 16 indicating that at least one of the surfaces to be cleaned during a cleaning event has not actually been cleaned. In response to receiving such instructions, the user interface module 44 may control the wearable computing device 12 to perform one or more actions.

[0151] For example, the user interface module 44 may perform its operation by controlling the user interface 40 to issue at least one of audible, tactile, and visual alerts. The alert may be a general alert that notifies the wearer of the alert status of the wearable computing device 12, or it may provide the wearer with more specific information about the content of the alert. For example, a user alert may indicate, via audible and / or visual (e.g., text) delivery, that the individual performing the cleaning has not performed the cleaning operation on at least one of the target surfaces. In some examples, the user alert outputs information that identifies a specific surface that the user has not cleaned, for example, by describing the name of the target surface or other identifying information. In other implementations, the wearable computing device 12 may perform its operation by communicating with an external system, such as a scheduling system, a training system, or other system that utilizes data indicating cleaning and / or hygiene performance.

[0152] Actions performed by the wearable computing device 12 may be performed at any desired time after it has been determined that a cleaning operation has not been performed on the target surface. For example, an action controlling the wearable computing device 12 to indicate that a cleaning operation was not performed on the target surface may be performed after the cleaning event is completed, for example, as part of a training exercise and / or a cleaning quality control assessment. In another example, an action may be performed to issue an alert via the wearable computing device 12 in substantially real time regarding the performance of the cleaning event. For example, the alert may be issued with sufficient temporal proximity to the end of the cleaning event to prompt the individual to perform a corrective cleaning action (e.g., to perform a cleaning operation on one or more overlooked surfaces that were targeted for cleaning) while the cleaning event is still in progress and / or to prompt the individual to perform a corrective cleaning action (e.g., to perform a cleaning operation on one or more overlooked surfaces that were targeted for cleaning).

[0153] To facilitate cleaning compliance and / or to help provide substantially real-time feedback on cleaning effectiveness, the person performing the cleaning may be instructed to perform cleaning operations on each target surface in a target order. In other words, the person performing the cleaning may have an instructed sequential order in which the surfaces will be cleaned. The cleaning effectiveness determination module 26 can determine the order in which each surface on which a cleaning operation has been performed was cleaned. The cleaning effectiveness determination module 26 can compare the surface cleaning order with the target order in which each surface is expected to be cleaned and determine whether there is any deviation between the actual cleaning order and the target order of cleaning (stored, for example, in the data store of the remote computing system 14 and / or wearable computing device 12). For example, the cleaning effectiveness determination module 26 can perform a cleaning event and a substantially real-time sequence analysis as a cleaning operation is performed on each surface and can determine substantially real-time if a target surface has been missed. Such a target surface may be missed in that the person performing the cleaning forgot to perform a cleaning operation on the surface, or the person performing the cleaning failed to clean the surface in the target order and has not yet returned to clean the surface.

[0154] The wearable computing device 12 may issue a user alert in response to the individual performing the cleaning determining that the cleaning operation has not been performed on each of the target surfaces in the target order. The user alert may be any of the user alerts described above and may or may not include information identifying the incorrect order in which the cleaning operations were performed. Additionally or alternatively, the information may be stored in a data store associated with the wearable computing device 12 and / or the remote computing system 14 that identifies the order in which the cleaning operations were performed (e.g., the order in which the surfaces were cleaned), along with a timestamp corresponding to the cleaning and / or information identifying the target order of the cleaning.

[0155] In the exemplary technique shown in Figure 8, the cleaning verification information may be stored in a data store associated with the wearable computing device 12 and / or the remote computing system 14, in addition to, or instead of, performing the action (156). For example, if the cleaning effectiveness determination module 26 determines that the individual performing the cleaning has cleaned each of several target surfaces, the cleaning verification information associated with the multiple target surfaces, the time of the cleaning event (e.g., a timestamp), and / or other metadata corresponding to the measurement context (e.g., room identification, GPS positioning) may be stored in the data store. Motion data generated by the sensor device 42 associated with the cleaning event may or may not be stored as part of the cleaning verification information. In either case, the cleaning verification information can provide quantifiable evidence that the individual performing the cleaning actually performed the cleaning according to the required protocol standards. It should be understood that while cleaning verification information associated with compliant cleaning actions may be stored, information associated with non-compliant actions (e.g., cleaning not performed on all target surfaces) may also be stored, for example, training, analysis, and improvement.

[0156] In some implementations, the cleaning effectiveness determination module 26 can also evaluate the quality of cleaning performed by the wearer of the wearable computing device 12 on one or more target surfaces that are considered clean (e.g., on which a cleaning action has been performed). In one example, the cleaning effectiveness determination module 26 can compare the duration of the cleaning action performed on the target surface with a threshold duration stored in a data store corresponding to the quality of cleaning. The threshold duration can specify the minimum time required to clean each target surface, which may vary depending on the size and shape of the object and its tendency to become contaminated. If the cleaning effectiveness determination module 26 determines that the duration of the cleaning action performed on the target surface is greater than or equal to the threshold duration, the module may determine that the quality of cleaning performed on the target surface meets the threshold quality of cleaning.

[0157] Additionally or alternatively, the cleaning effectiveness determination module 26 may analyze motion data related to the cleaning of a specific target surface and refer to motion data related to the quality of cleaning of that target surface in the data store 30. Further details regarding an exemplary process in which the cleaning effectiveness determination module 26 can refer to the data store 30 to determine the quality of cleaning are described in relation to Figure 9 below.

[0158] Figure 9 is a flowchart illustrating exemplary operation of an exemplary wearable computing device configured to track the effectiveness of cleaning to reduce diseases and infections caused by ineffective cleaning, according to one or more additional aspects of the present disclosure. The technology shown in Figure 9 may be implemented by one or more processors in computing devices such as the wearable computing device 12 and / or the remote computing system 14.

[0159] In the exemplary technique shown in Figure 9, the wearable computing device 12 can detect device-related motion during a cleaning event (160). The motion may be generated by the individual performing the cleaning during the cleaning event, and the target surface is intended to be cleaned to a cleaning threshold quality during the event. The wearable computing device 12 can detect motion via the sensor device 42 and generate motion data corresponding to the motion.

[0160] The surfaces to be cleaned up to the cleaning threshold quality during a cleaning event may be any surfaces and objects described herein, including those described in relation to Figure 4. Individuals performing cleaning during a cleaning event may be instructed to clean the surfaces according to a cleaning protocol, which may be, for example, the same protocol used to generate reference motion data corresponding to the cleaning threshold quality and stored in data store 30.

[0161] At least one sensor in the wearable computing device 12 can generate motion data corresponding to movements during the cleaning operation. One or more processors in the wearable computing device 12 can receive the generated motion data and control its transmission to the remote computing system 14. One or more processors 50 running on the remote computing system 14 can receive the data and issue instructions to the cleaning effect determination module 26 to evaluate the effect of the cleaning performed.

[0162] A cleaning effectiveness determination module 26 running on the remote computing system 14 can determine whether the individual performing the cleaning has cleaned the target surface to a cleaning threshold quality (162). The cleaning effectiveness determination module 26 can make such a determination by comparing motion data generated by the sensor device 42 of the wearable computing device 12 during the cleaning event with reference motion data related to the cleaning threshold quality of the surface stored in the data store 30.

[0163] In some implementations, the cleaning effect determination module 26 determines at least one signal feature of the received motion data and compares the motion data generated during the cleaning event with reference motion data. For example, the cleaning effect determination module 26 may determine multiple signal features for the received motion data generated by the sensor device 42 during the cleaning event. One or more signal features generated for the received motion data may correspond to those features selected during the calibration process to establish the quality of surface cleaning. For example, one or more signal features may correspond to those described above in relation to Figures 4 and 5. The cleaning effect determination module 26 may compare one or more signal features determined for the motion data generated during the cleaning event with reference signal feature data generated during calibration corresponding to the quality of cleaning on the surface and stored in the data store 30, for example, as described above in relation to Figure 5.

[0164] If the wearable computing device 12 is implemented with multiple sensors (e.g., including an accelerometer and a gyroscope), each of the multiple sensors can generate corresponding motion data during a cleaning event. A cleaning effect determination module 26 running on a remote computing system 14 can determine one or more signal features based on the motion data generated by and received from each of the multiple sensors. For example, the cleaning effect determination module 26 can receive first motion data corresponding to the acceleration of the wearable computing device 12 and second motion data corresponding to the angular velocity of the wearable computing device (in the case of a gyroscope). The cleaning effect determination module 26 can characterize the motion performed during a cleaning event by determining at least one signal feature based on the first motion data and at least one additional signal feature based on the second motion data.

[0165] In some examples, the cleaning effectiveness determination module 26 receives motion data generated over the entire duration of the cleaning event, including motion other than that associated with the cleaning action being performed on the target surface. For example, the motion data may include periods of cleaning and non-cleaning actions. In another example, the motion data may include periods during which surfaces other than the target surface for which the cleaning quality is being evaluated are cleaned.

[0166] The cleaning effect determination module 26 can separate motion data received from the sensor device 42 by associating different parts of the motion data with different cleaning actions. For example, the cleaning effect determination module 26 can associate a portion of the motion data received during a cleaning event with the time the target surface is being cleaned. The cleaning effect determination module 26 can associate a portion of the motion data with a specific surface being cleaned using any preferred technique, including those association techniques described above in relation to Figure 4. Additionally or alternatively, the cleaning effect determination module 26 can algorithmically divide the motion data into periods corresponding to cleaning and non-cleaning activities, for example, based on a feature analysis of the motion data.

[0167] Therefore, in some examples, the cleaning effect determination module 26 can determine one or more signal features that indicate the quality of cleaning only for that portion of the motion data corresponding to the time the target surface is being cleaned, in contrast to the overall duration of the cleaning event. The cleaning effect determination module 26 can then compare one or more signal features generated based on the relevant motion data with reference motion data stored in the data store 30.

[0168] In some examples, the reference motion data stored in the data store 30 corresponds to the thoroughness of the cleaning (e.g., indicating the cleaning technique used and / or the amount of work applied when performing the cleaning). Additionally or alternatively, the reference motion data stored in the data store 30 may correspond to an area or range of the target surface to be cleaned. For example, the reference motion data may define the boundaries of the target surface in three-dimensional space. In these examples, the cleaning effect determination module 26 can determine the area of ​​cleaning performed on the target surface based on the data generated by the sensor device 42. The cleaning area may correspond to a two-dimensional or three-dimensional space in which the cleaning operation was performed. Thus, the cleaning effect determination module 26 can determine the quality of cleaning by comparing the area of ​​cleaning performed on the target surface with reference area data on the target surface stored in the data store 30. For example, the cleaning effect determination module 26 can determine whether the cleaning area performed on the target surface is larger than the threshold target area to be cleaned in order to determine whether the cleaning operation meets the threshold quality of cleaning.

[0169] The technique in Figure 9 includes the wearable computing device 12 taking action when it is determined that the individual performing the cleaning has not cleaned the surface (156) to a threshold quality. For example, the user interface module 44 of the wearable computing device 12 may receive information from a remote computing system 14 via the network 16 indicating that the surface to be cleaned during the cleaning event has not been cleaned to a threshold quality. In response to receiving such instructions, the user interface module 44 may control the wearable computing device 12 to perform one or more actions.

[0170] For example, the user interface module 44 may perform its operation by controlling the user interface 40 to issue at least one of audible, tactile, and visual alerts. The alert may be a general alert that notifies the wearer of the alert status of the wearable computing device 12, or it may provide the wearer with more specific information about the content of the alert. For example, a user alert could be delivered via audible and / or visual (e.g., text) delivery to indicate that the individual performing the cleaning has not performed the cleaning action on the surface up to the cleaning threshold quality.

[0171] The actions performed by the wearable computing device 12 may be performed at any desired time. For example, an action controlling the wearable computing device 12 to indicate that threshold quality cleaning has not been performed on a surface may be performed after the cleaning event is completed, for example, as part of a training exercise and / or a cleaning quality control assessment. In another example, an action may be performed to issue an alert via the wearable computing device 12 in substantially real time regarding the execution of a cleaning event. For example, the alert may be issued while the individual is still performing the cleaning and / or with sufficient temporal proximity to the end of the cleaning event for the individual to perform a corrective cleaning action (e.g., further cleaning the surface).

[0172] In some implementations, cleaning verification information may be stored in a data store associated with the wearable computing device 12 and / or remote computing system 14 in addition to, or instead of, performing the action (166). For example, if the cleaning effectiveness determination module 26 determines that the individual performing the cleaning has cleaned the target surface to a cleaning threshold quality, cleaning verification information associated with the surface, the time of the cleaning event (e.g., a timestamp), and / or other metadata corresponding to the measurement context (e.g., surface identification, GPS positioning) may be stored in the data store. Motion data generated by the sensor device 42 associated with the cleaning event may or may not be stored as part of the cleaning verification information. In either case, the cleaning verification information can provide quantifiable evidence that the individual performing the cleaning actually performed the cleaning according to the required quality standards. It should be understood that while cleaning verification information associated with compliant cleaning actions may be stored, information associated with non-compliant actions (e.g., cleaning that does not meet the cleaning threshold quality) may also be stored, for example, training, analysis, and improvement.

[0173] Figure 10 is a flowchart illustrating exemplary operation of an exemplary wearable computing device configured to track cleaning effectiveness for overall hygiene management, according to one or more aspects of the present disclosure. The technology shown in Figure 10 may be implemented by one or more processors in computing devices such as the wearable computing device 12 and / or the remote computing system 14.

[0174] In the exemplary technique shown in Figure 10, a wearable computing device 12 can generate motion data during the course of an activity that may include washing and non-washing actions (178). The motion data may be generated, for example, by the individual performing the activity during a washing event. Washing activities may correspond to one or more specific types of cleaning actions, while non-washing actions may correspond to movements before, during, and / or after washing actions.

[0175] At least one sensor of the wearable computing device 12 can generate motion data corresponding to the movements of the wearer of the wearable computing device, for example, during washing and non-washing activities. One or more processors of the wearable computing device 12 can receive the generated motion data and control its transmission to the remote computing system 14. One or more processors 50 running on the remote computing system 14 can receive the data and issue instructions to the washing effect determination module 26 to evaluate the effectiveness of the washing performed.

[0176] A cleaning effect determination model 26 running on the remote computing system 12 can determine at least one feature of motion data indicating that the wearer of the wearable computing device 12 is performing a cleaning action (180). One or more signal features generated for the received motion data can distinguish cleaning from non-cleaning actions, corresponding to those features selected during the calibration process. For example, one or more signal features may correspond to those described above in relation to Figures 4 and 6. The cleaning effect determination module 26 can compare one or more signal features determined for the motion data received and generated from the wearable computing device 12 with reference signal feature data generated during calibration and stored in the data store 32.

[0177] If the wearable computing device 12 is implemented with multiple sensors (e.g., including an accelerometer and a gyroscope), each of the multiple sensors can generate corresponding motion data during a cleaning event. A cleaning effect determination module 26 running on a remote computing system 14 can determine one or more signal features based on the motion data generated by and received from each of the multiple sensors. For example, the cleaning effect determination module 26 can receive first motion data corresponding to the acceleration of the wearable computing device 12 and second motion data corresponding to the angular velocity of the wearable computing device (in the case of a gyroscope). The cleaning effect determination module 26 can characterize the motion performed during a cleaning event by determining at least one signal feature based on the first motion data and at least one additional signal feature based on the second motion data.

[0178] Exemplary types of cleaning actions that may be performed include environmental cleaning actions in which one or more surfaces within the environment 18 are cleaned. Examples of these types of cleaning actions include cleaning floor surfaces (e.g., sweeping, mopping) and cleaning non-floor surfaces (e.g., cleaning equipment within the environment 18). Another type of cleaning action that may be performed is personal cleaning action, such as a hand hygiene cleaning event in which an individual performs a handwashing protocol (e.g., using an alcohol-based disinfectant, soap, and water). In contrast, non-cleaning actions may be any activity that generates motion data unrelated to personal or environmental cleaning activities.

[0179] The exemplary technique in Figure 10 further includes determining a specific type of cleaning action to be performed from motion data generated by a wearable computing device 12 (182). For example, a cleaning effect determination model 26 running on a remote computing system 12 can determine at least one feature of motion data corresponding to each of several types of cleaning actions performed and generated by the wearable computing device 12. One or more signal features generated for the received motion data can distinguish specific types of cleaning activities from each other in correspondence with those features selected during the calibration process. For example, one or more signal features may correspond to those described above in relation to Figures 4 and 6. The cleaning effect determination module 26 can compare one or more signal features determined for the motion data associated with each cleaning activity with reference signal feature data generated during calibration and stored in the data store 32.

[0180] In the example shown in Figure 10, the cleaning effectiveness determination module 26 can analyze motion data associated with one or more specific types of cleaning actions by referring to motion data related to the cleaning quality of that particular type of cleaning action in the data store 30 (184). Additional details regarding the exemplary process by which the cleaning effectiveness determination module 26 can refer to the data store 30 to determine the cleaning quality of a particular type of cleaning action are described with respect to Figure 9 above.

[0181] In some implementations, individuals performing multiple washing actions may be instructed to perform each washing action in a specific order. In other words, an individual performing washing may have a sequential order in which different washing actions are instructed to be performed. For example, the instructed order may specify that the individual performs all non-hand hygiene washing actions first, and then perform hand hygiene washing actions (e.g., before performing any subsequent non-washing activities).

[0182] The cleaning effectiveness determination module 26 can determine the order in which each specific type of cleaning action is performed. The cleaning effectiveness determination module 26 can compare the cleaning action order with the target order in which each action is expected to be performed and determine whether there is any deviation between the actual cleaning order and the target cleaning order (which may be stored, for example, in the data store of the remote computing system 14 and / or wearable computing device 12). For example, the cleaning effectiveness determination module 26 can perform sequence analysis in virtually real time using the cleaning actions being performed.

[0183] In response to determining that an individual wearing the wearable computing device 12 has not performed each washing action in the target order, the wearable computing device 12 may issue a user alert. The user alert may be any of the aforementioned user alerts and may or may not include information identifying the incorrect order of the washing actions performed. Additionally or alternatively, the information may be stored in a data store associated with the wearable computing device 12 and / or the remote computing system 14, along with a timestamp corresponding to the washing and / or information identifying the target order of the washing, at the option of identifying the order of the washing actions performed.

[0184] The technique in Figure 10 includes the wearable computing device 12 performing an action when it is determined that an individual performing a particular type of washing behavior has not performed washing to the threshold quality of that behavior (186). For example, the user interface module 44 of the wearable computing device 12 may receive information from a remote computing system 14 via the network 16 indicating that a particular washing behavior (e.g., a hand hygiene behavior or a non-hand hygiene behavior) has not been performed to the threshold quality of washing. In response to receiving such instructions, the user interface module 44 may control the wearable computing device 12 to perform one or more actions.

[0185] For example, the user interface module 44 may perform the action by controlling the user interface 40 to issue at least one of audible, tactile, and visual alerts. The alert may be a general alert that notifies the wearer of the alert status of the wearable computing device 12, or it may provide the wearer with more specific information about the content of the alert. For example, a user alert may indicate, via audible and / or visual (e.g., text) delivery, that an individual performing a wash has not yet performed the wash action to the wash threshold quality. In other examples, the action may be performed to issue an alert via the wearable computing device 12 substantially in real time as the wash action is performed. For example, the alert may be issued while the individual is still performing the wash action and / or with sufficient temporal proximity to the end of the wash action for the individual to perform a corrective wash action (e.g., wash further).

[0186] In some implementations, the wash verification information may be stored in a data store associated with the wearable computing device 12 and / or the remote computing system 14 in addition to, or instead of, performing the action (188). Motion data generated by the sensor device 42 related to the wash action may or may not be stored as part of the wash verification information. In either case, the wash verification information can provide quantifiable evidence that the individual performing the wash actually performed the specific wash action and / or performed the wash action in accordance with the required quality standards. It should be understood that while wash verification information associated with compliant wash actions may be stored, information associated with non-compliant actions (e.g., washes that do not meet the wash threshold quality) may also be stored, for example, training, analysis, and improvement.

[0187] As described above in relation to Figure 1, the user interface module 44 can cause the user interface 40 of the wearable computing device 12 to present audio (e.g., sound), graphics, or other types of output associated with the user interface (e.g., haptic feedback). The output can respond to one or more cleaning decisions made and, in some examples, can provide cleaning information to the wearer of the wearable computing device 12 in order to correct cleaning actions that have been determined to be non-compliant. For example, once the cleaning effectiveness determination module 26 determines whether the user has performed a particular compliant cleaning action (e.g., performed a cleaning action on each surface to be cleaned, cleaned the target surface to a cleaning threshold quality, and / or performed a particular type of cleaning action, and / or performed such action to a cleaning threshold quality), the user interface module 44 can control the wearable computing device 12 to output an alert regarding the compliant or non-compliant action.

[0188] In addition to controlling the user interface 40 based on compliance or non-compliance with a specific cleaning procedure, or alternatively, the user interface 40 of the wearable computing device 12 may provide information that helps guide the user through the cleaning protocol. For example, the user interface 40 may provide audible, tactile, and / or visual information that informs the user of the wearable computing device 12 of the cleaning protocol to be implemented. The information may provide step-by-step instructions, such as the order in which the surfaces to be cleaned and / or the order in which the cleaning technique is performed on one or more surfaces to be cleaned.

[0189] In some implementations, the completion of a specific step of the cleaning protocol (e.g., cleaning a specific surface, using a specific cleaning technique on a surface) is automatically detected based on motion data generated by the wearable computing device 12. The user interface 40 can issue information to inform the user of the next step in the cleaning protocol, which is performed in response to the automatic detection of the completion of the previous step of the protocol. Additionally or alternatively, the user can interact with the user interface 40 to manually indicate that a specific step of the cleaning protocol has been completed and / or navigate to guidance outputs for different steps of the cleaning protocol. The user interface 40 can issue information to inform the user of steps in the cleaning protocol that are performed in response to manual input from the user, for example, information to inform the user of the next step in the cleaning protocol, which is performed in response to an instruction that the previous step of the protocol has been completed.

[0190] Figures 17A–17D show a sequence of exemplary user interface graphics that may be displayed to the user to help guide them through the execution of a cleaning protocol. Figure 17A shows an exemplary wearable computing device 12 with an image of a dresser or bedside table, guiding the user to clean the dresser or bedside table. Figure 17B shows an exemplary wearable computing device with an image of a tray table, guiding the user to clean the tray table after the cleaning of the dresser or bedside table is complete. Figure 17C shows an exemplary wearable computing device with an image of a chair, guiding the user to clean the chair after the cleaning of the tray table is complete. Figure 17D shows an exemplary wearable computing device with an image of a light switch, guiding the user to clean the light switch after the cleaning of the chair is complete.

[0191] In the examples described above, the functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functionality may be stored or transmitted as one or more instructions or codes on a computer-readable medium and executed by a hardware-based processing unit. The computer-readable medium may include a computer-readable storage medium corresponding to a tangible medium such as a data storage medium, or a communication medium including any medium that facilitates the transfer of a computer program from one place to another according to a communication protocol, for example. Thus, the computer-readable medium may generally correspond to (1) a non-transient tangible computer-readable storage medium, or (2) a communication medium such as a signal or carrier wave. The data storage medium may be any available medium that can be accessed by one or more computers or one or more processors to retrieve instructions, codes, and / or data structures for implementing the technology described herein. A computer program product may include computer-readable medium.

[0192] As an example, and not an limitation, such computer-readable storage media may consist of RAM, ROM, EEPROM, CD-ROM, or other optical disk storage, magnetic disk storage, or other magnetic storage devices, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and can be accessed by a computer. Connections are also appropriately referred to as computer-readable media. For example, if instructions are transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, or microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, or microwave are included in the definition of media. However, it should be understood that computer-readable storage media and data storage media do not include connections, carriers, signals, or other temporary media, but instead refer to non-temporary, tangible storage media. As used herein, the terms "disk" and "disc" include compact discs (CDs), laserdiscs, optical discs, digital-purpose discs (DVDs), floppy disks, and Blu-ray® discs, where discs typically reproduce data magnetically, and discs reproduce data optically using a laser. Combinations of the above should also be included in the scope of computer-readable media.

[0193] Instructions may be performed by one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Therefore, as used herein, the terms “processor” or “controller” may refer to any of the aforementioned structures or any other structure suitable for implementing the technologies described herein. Furthermore, in some embodiments, the functions described herein may be provided within dedicated hardware and / or software modules. These technologies may also be fully implemented in one or more circuits or logic elements.

[0194] The technology of this disclosure can be implemented in a wide variety of devices or apparatus. While various components, modules, or units are described in this disclosure to highlight the functional aspects of a device configured to implement the disclosed technology, implementation by different hardware units is not necessarily required. Rather, as described above, the various units may be provided by a set of interoperable hardware units, including one or more processors, combined with hardware units or suitable software and / or firmware.

[0195] The following examples may provide additional details regarding hygiene tracking and compliance systems and technologies as provided in this disclosure. [Examples]

[0196] An experiment was conducted to evaluate the ability to track and / or monitor washing activities using wearable devices. The experiment was repeated several times using various data logger apps running on mobile phones and standalone devices (e.g., smartwatches) attached to various anatomical locations (wrist, arm, pocket). The results provided by each device configuration were consistent.

[0197] In this particular example, measurement data was acquired using a wrist-worn inertial measurement unit (IMU) with a tri-axis accelerometer and a tri-axis gyroscope. One subject performed the cleaning sequence as follows: (1) slowly wiping the tabletop back and forth four times, followed by (2) quickly scrubbing the tabletop seven times, and (3) slowly wiping the tabletop in a circular motion once. The subject paused for a few seconds between each cleaning motion.

[0198] The wrist-worn IMU generated raw data sampled at 50 Hz, containing the following six quantities: (1) linear acceleration in the x, y, and z axes (sampled from a triaxial accelerometer) and (2) rotational speed in the x, y, and z axes (sampled from a triaxial gyroscope). The experimental session lasted 126 seconds, generating 126 x 50 = 6300 rows of these six values ​​in time series. Figures 11 and 12 show plots of the linear acceleration and rotational speed data generated during the experiment.

[0199] The session was video recorded, and two sequences of activity labels were created: (1) binary object: wash or not wash, and (2) multiclass object: wipe, scrub, or not wash. Supervised learning involves training a model from an initial training set of labeled data, where a given object sequence determines the type of predictive model (binary or multiclass) the pipeline will train. For simplicity, to create a multiclass object, this experiment only includes variations in technique (wiping and scrubbing). In general, many other multiclass labels are possible, including the tools used, the object being washed, the washing technique, or any combination thereof.

[0200] The wearable IMU data was filtered for further processing. The data was affected by various noise sources that could impact signal quality, such as wearable loosening, contact with clothing, and / or sudden collisions with surrounding objects. Therefore, it was considered desirable to smooth the data through a filtering operation. The algorithm used was an N-point moving median filter, which effectively removes undesirable spikes and troughs from the raw data.

[0201] After filtering, the following two sliding timeframes were passed over the data to generate a feature matrix: a 1-second time-domain feature timeframe and a 5-second frequency-domain timeframe. The frequency-domain timeframe completely overlaps with the time-domain timeframe, and as a result, both timeframes slide every second, so only the 1-second new data is covered in the 5-second frequency-domain timeframe. The frequency-domain timeframe also serves as the timeframe for generating wavelet features. Figure 13 shows an exemplary single time-domain feature representation generated from raw sample data.

[0202] In the next step of the data analysis process, candidate features were generated from the data to expose various aspects of the primitive kinetic motion that constitutes the washing activity. Each feature represents a compact, second-by-second representation of the original raw data. The candidate generation step created features by combining transformations (i.e., transforming) fundamental functions within different feature families, as described above in relation to Figure 4. For the experimental data, a total of 189 candidate features were generated for each second of filtered data, and feature vectors of that second's motion were generated. The time series of all such vectors formed a feature matrix from which feature selection was performed.

[0203] During feature selection, a feature selection routine was specified to select the dimension that best distinguishes the activity objects in the feature space. As implemented, the number of top features was a configurable parameter at feature selection, but all 189 received scores and rankings. In the experimental data, the top 5 features selected for binary symmetric classification were as follows: [Table 1]

[0204] Making features good candidates involves properly separating classes in the feature space. Pairs and triples in the feature space can be represented via scatter plots using activity classes labeled in different colors. Figure 14 shows the top two features determined from candidate features for binary classification of experimental data. The data shows that these two features provide good linear separability between the target classes (wash, do not wash). More features were needed to accurately classify into more classes (do not wash, scrub, and wipe).

[0205] Following feature selection, the feature matrix was added to target labels in seconds to create a training set for a supervised learning classifier. The exact classification algorithm was a parameter passed through the pipeline. While various classification algorithms were tested, the class of ensemble classifiers that tended to perform effectively on the experimental data (in both binary and multi-class settings) was the random forest classifier. The following table shows the classification report of the random forest for 10 features evaluated by 10-fold cross-validation applied to the experimental data. [Table 2] [Table 3]

[0206] In the previous example, multi-class labeling was used to train a model's segmented cleaning movements by technique only (wiping and scrubbing). More generally, the output of a cleaning classifier can utilize a combination of tool, object, and technique to label training samples. Each of these can extract predicted cleaning behavior in a more natural way. (1) Tool: The cleaning device handled by the object in the cleaning behavior (e.g., rag, toilet brush, mop, broom, duster), (2) Object: The set of surfaces that make up the object being cleaned by the object, (3) Technique: The way the subject performs the cleaning behavior. Figure 15 is a drawing showing the identification of three types of tools, performed as part of a simulated restaurant context floor care study using motion data: broom (sweeping), mop, and deck brush. Figure 16 is a drawing showing the exemplary identification of five object surfaces, performed as part of a simulated hospital context study using motion data.

Claims

1. 1. A method for reducing illness and infection caused by ineffective cleaning through tracked cleaning effectiveness, said method comprising: detecting, by a wearable computing device worn by an individual performing cleaning on a plurality of target surfaces, motion associated with the wearable device during the cleaning event; determining, based on movement associated with the wearable computing device, whether the individual performed a cleaning action on each of a plurality of target surfaces by at least comparing movement data generated by the wearable device to reference movement data associated with cleaning each of the plurality of target surfaces; and performing an action by the wearable computing device in response to determining that the individual has not performed the cleaning action on at least one of the plurality of target surfaces.

2. 10. The method of claim 1, further comprising, in response to determining that the cleaning action has been performed on each of the plurality of target surfaces, storing cleaning verification information associated with the plurality of target surfaces and a time of the cleaning event.

3. The method of claim 1 , wherein performing the action includes issuing one of an audible, a tactile, and a visual alert via the wearable computing device.

4. The method of claim 1 , wherein performing the action includes issuing a user alert indicating that the individual has not performed the cleaning action on at least one of the plurality of the target surfaces.

5. 5. The method of claim 4, wherein issuing the user alert includes outputting, by the wearable computing device, information identifying one of the plurality of target surfaces on which the user has not performed the cleaning action.

6. The method of claim 1 , wherein the plurality of target surfaces comprises flat horizontal surfaces, flat vertical surfaces, cavities, cylinders, spheres, and combinations thereof.

7. The method of claim 1 , wherein the plurality of target surfaces are located within a healthcare environment and include light switches, tabletops, bed rails, doorknobs, and medication dispensing poles.

8. The method of claim 7 , wherein the movement associated with the wearable device during the cleaning action comprises a wiping action.

9. The method of claim 1 , wherein the plurality of target surfaces includes floor and non-floor surfaces.

10. 10. The method of claim 9, wherein the cleaning operations include a first cleaning operation on a first surface of the plurality of target surfaces and a second cleaning operation, different from the first cleaning operation, on a second surface of the plurality of target surfaces.

11. 10. The method of claim 9, wherein the plurality of target surfaces are located in a food preparation environment, and wherein movements associated with the wearable device during the cleaning operation include movements selected from the group consisting of mopping a floor surface, sweeping a floor surface, brushing a grill, brushing a fryer, and combinations thereof.

12. Detecting movement associated with the wearable computing device includes receiving movement data from at least one sensor of the wearable computing device; determining whether the individual performing the cleaning has performed the cleaning action on each of the plurality of target surfaces; determining at least one signal characteristic of the motion data; and comparing the at least one signal feature of the movement data to reference signal feature data associated with cleaning each of the plurality of target surfaces.

13. 13. The method of claim 12, wherein the reference signal feature data is generated from motion data acquired during one or more training episodes in which at least one trainer performs the cleaning action on each of the plurality of target surfaces or their equivalents while wearing the wearable computing device or their equivalent.

14. 13. The method of claim 12, wherein the reference signal feature data is generated from motion data acquired during one or more training episodes in which the individual performs the cleaning action on each of the plurality of target surfaces or their equivalents while wearing the wearable computing device or their equivalent.

15. receiving motion data includes receiving, from at least a first sensor of the wearable computing device, first motion data corresponding to an acceleration of the wearable computing device; and receiving, from at least a second sensor of the wearable computing device, second motion data corresponding to an angular velocity of the wearable computing device; The method of claim 12 , wherein determining at least one signal characteristic of the motion data comprises determining at least one signal characteristic of the first motion data and at least one signal characteristic of the second motion data.

16. determining a surface cleaning order in which the cleaning actions were performed on each of the plurality of target surfaces based on a movement associated with the wearable computing device; comparing the surface cleaning sequence to a target sequence in which the plurality of target surfaces are expected to be cleaned; in response to determining that the individual has not performed the cleaning actions on the plurality of target surfaces in the target sequence; issuing, by the wearable computing device, a user alert; and storing wash sequence information associated with the wash event.

17. The method of claim 1 , further comprising determining a quality of the cleaning of each of the plurality of target surfaces on which the individual performed the cleaning action based on the movement associated with the wearable computing device.

18. 20. The method of claim 17, wherein determining the quality of the cleaning of each of the plurality of target surfaces on which the individual performed the cleaning action includes determining the duration of cleaning of each of the plurality of target surfaces on which the individual performed the cleaning action.

19. Determining the cleaning quality of each of the plurality of target surfaces on which the individual has performed the cleaning action includes determining the cleaning quality of each of the plurality of target surfaces on which the individual has performed the cleaning action by at least: associating different portions of the motion data received during the cleaning operation with a particular surface of each of the plurality of target surfaces on which the individual performed the cleaning operation; determining at least one signal feature indicative of the quality of the cleaning for each associated different portion of the motion data corresponding to a particular surface of each of the plurality of target surfaces on which the individual has performed the cleaning action; 20. The method of claim 17, comprising: determining the at least one signal feature indicative of the cleaning quality for each relevant different portion of motion data by comparing the at least one signal feature indicative of the cleaning quality with reference signal feature data associated with cleaning quality.

20. determining the cleaning quality for each of the plurality of target surfaces on which the individual has performed the cleaning action; associating different portions of the motion data received during the cleaning operation with a particular surface of each of the plurality of target surfaces on which the individual performed the cleaning operation; determining an area of ​​cleaning performed on the particular surface of each of the plurality of target surfaces on which the individual performed the cleaning action; 20. The method of claim 17, further comprising comparing the area of ​​cleaning for each associated different portion of motion data with reference area data associated with the particular surface of each of the plurality of target surfaces on which the individual performed the cleaning action.

21. 18. The method of claim 17, wherein performing the action includes issuing an alert via the wearable computing device indicating that the cleaning quality of a particular surface of the plurality of target surfaces on which the individual performed the cleaning action is below a threshold cleaning quality, the alert being issued substantially in real time as the individual is performing the cleaning action on the particular surface of the plurality of target surfaces.

22. 22. The method of claim 21, wherein the alert provides information to guide the individual to perform additional cleaning of the particular surface of the plurality of target surfaces.

23. The method of claim 1 , wherein the wearable computing device is selected from the group consisting of a wristband device and an armband device.

24. The method of claim 1 , wherein the wearable computing device is locatable within a pocket of clothing worn by the individual performing the washing.

25. The method of claim 1 , wherein the wearable computing device comprises at least one of a graphical user interface and a haptic generator.

26. wirelessly transmitting motion data generated by the wearable computing device to one or more remote computing devices; determining, at the one or more remote computing devices, whether the individual performed the cleaning action on each of the plurality of target surfaces; wirelessly transmitting data from the one or more remote computing devices to the wearable computing device indicating that the individual has not performed the cleaning action on at least one of the plurality of target surfaces; 10. The method of claim 1, further comprising: performing the action by the wearable computing device in response to the wearable computing device receiving data indicating that the individual has not performed the cleaning action on at least one of the plurality of target surfaces.

27. the plurality of target surfaces are located in a healthcare facility or a facility where food is prepared; the healthcare facility has a reduced number of healthcare-associated infections after implementing the method compared to before implementing the method; 10. The method of claim 1, wherein the facility where the food is prepared experiences a decrease in the number of foodborne illnesses associated with the facility after implementing the method compared to before implementing the method.

28. at least one sensor configured to detect movement associated with the wearable computing device; at least one processor; a memory containing instructions, The instructions, when executed, cause the at least one processor to: receiving movement data of the wearable computing device from the at least one sensor while an individual wearing the wearable computing device performs cleaning actions on a plurality of target surfaces during a cleaning event; determining whether the individual performed the cleaning action on each of the plurality of target surfaces based on the motion data by at least comparing the motion data to reference motion data associated with cleaning each of the plurality of target surfaces; performing an action in response to determining that the individual has not performed the cleaning action on at least one of the plurality of target surfaces.

29. 30. The device of claim 28, wherein the instructions, when executed, cause the at least one processor to store cleaning verification information associated with the plurality of target surfaces and the time of the cleaning event.

30. 30. The device of claim 28, wherein the instructions, when executed, cause the at least one processor to perform the action by issuing at least one of an audible, tactile, and visual alert via the wearable computing device.

31. 30. The device of claim 28, wherein the instructions, when executed, cause the at least one processor to perform an action by at least issuing a user alert indicating that the individual has not performed the cleaning action on at least one of the plurality of target surfaces.

32. The instructions, when executed, cause the at least one processor to determine whether the individual performed the cleaning action on each of the plurality of target surfaces by at least: determining at least one signal characteristic of the motion data; comparing the at least one signal feature of the movement data with reference signal feature data associated with cleaning each of the plurality of target surfaces; The device of claim 28, wherein the determination is made by

33. the at least one sensor comprising: a first sensor configured to generate first movement data corresponding to an acceleration of the wearable computing device; and a second sensor configured to generate second movement data corresponding to an angular velocity of the wearable computing device; 33. The device of claim 32, wherein the instructions, when executed, cause the at least one processor to determine at least one signal feature of the movement data by determining at least a first signal feature of the first movement and a second signal feature of the second movement data.

34. The instructions, when executed, cause the at least one processor to: determining a surface cleaning order in which the cleaning operations were performed on each of the plurality of target surfaces based on the motion data; comparing the surface cleaning sequence to a target sequence in which the plurality of target surfaces are expected to be cleaned; in response to determining that the individual has not performed the cleaning actions on the plurality of target surfaces in the target sequence; issuing, by the wearable computing device, a user alert; and and storing in said memory wash sequence information associated with said wash event.

35. 30. The device of claim 28, wherein the instructions, when executed, cause the at least one processor to determine a cleaning quality of each of the plurality of target surfaces on which the individual performed the cleaning action based on the movement data.

36. The instructions, when executed, cause the at least one processor to calculate the quality of the cleaning for each of the plurality of target surfaces on which the individual performed the cleaning action by at least: associating different portions of the motion data with particular surfaces of each of the plurality of target surfaces on which the individual performed the cleaning action; determining at least one signal feature indicative of the quality of the cleaning for each associated different portion of the motion data corresponding to a particular surface of each of the plurality of target surfaces on which the individual has performed the cleaning action; comparing the at least one signal feature indicative of the cleaning quality of each relevant different portion of motion data with reference signal feature data associated with the cleaning quality; The device of claim 35, wherein the determination is made by:

37. The instructions, when executed, cause the at least one processor to calculate the cleaning quality of each of the plurality of target surfaces on which the individual has performed the cleaning action by at least: associating different portions of the motion data with particular surfaces of each of the plurality of target surfaces on which the individual performed the cleaning action; determining an area of ​​cleaning performed on the particular surface of each of the plurality of target surfaces on which the individual performed the cleaning action; comparing the area of ​​cleaning for each associated different portion of motion data with reference area data associated with the particular surface of each of the plurality of target surfaces on which the individual performed the cleaning action; The device of claim 35, wherein the determination is made by:

38. 29. The device of claim 28, wherein the instructions, when executed, cause the at least one processor to perform the action by at least issuing an alert via the wearable computing device indicating that the cleaning quality of a particular surface of the plurality of target surfaces on which the individual performed the cleaning action is below a threshold cleaning quality, the alert being issued substantially in real time as the individual is performing the cleaning action on the particular surface of the plurality of target surfaces.

39. 1. A method for establishing a customer specific system for tracking cleaning effectiveness, said method comprising: performing, by an individual wearing a wearable computing device, a cleaning action on each of a plurality of target surfaces, the plurality of target surfaces being selected as target surfaces for which cleaning is desired to be tracked in connection with subsequent cleaning events; generating, by the wearable computing device, motion data associated with motion of the wearable device during the cleaning operation performed on each of a plurality of target surfaces; associating different portions of the motion data generated during the cleaning operation with particular surfaces of each of the plurality of target surfaces on which the individual performed the cleaning operation; determining, for each of the plurality of different target surfaces, reference data indicative of the cleaning action being performed from associated different portions of the movement data of each of the plurality of different target surfaces; and storing the reference data for each of the plurality of different target surfaces for use in connection with a subsequent cleaning event.

40. determining the reference signal data; 40. The method of claim 39, comprising determining at least one signal feature for each associated different portion of motion data indicative of the cleaning action being performed on the particular one of the plurality of target surfaces corresponding to the associated different portion of motion data.

41. 41. The method of claim 40, wherein determining at least one signal feature for each associated different portion of motion data comprises determining a first signal feature indicative of the cleaning operation being performed on a first surface of the plurality of target surfaces and a second signal feature different from the first signal feature indicative of the cleaning operation being performed on a second surface of the plurality of target surfaces.

42. 40. The method of claim 39, wherein the plurality of target surfaces are located within a healthcare environment and include light switches, tabletops, bed rails, doorknobs, and medication dispensing poles.

43. The method of claim 42, wherein the movement associated with the wearable device during the cleaning operation comprises a wiping motion.

44. 40. The method of claim 39, wherein the plurality of target surfaces includes floor and non-floor surfaces.

45. 46. ​​The method of claim 45, wherein the cleaning operation includes a first cleaning operation on a first surface of the plurality of target surfaces and a second cleaning operation, different from the first cleaning operation, on a second surface of the plurality of target surfaces.

46. 46. ​​The method of claim 45, wherein the plurality of target surfaces are located in a food preparation environment, and wherein movements associated with the wearable device during the cleaning operation include movements selected from the group consisting of mopping a floor surface, sweeping a floor surface, brushing a grill, brushing a fryer, and combinations thereof.

47. and performing a subsequent cleaning event by a second individual wearing the wearable computing device or equivalent, wherein performing the subsequent cleaning event comprises: detecting, by the wearable computing device or its equivalent worn by the second individual performing cleaning on a plurality of target surfaces or its equivalent, movement associated with the wearable device or its equivalent during the subsequent cleaning event; determining whether the second individual performed the cleaning action on each of the plurality of target surfaces or their equivalents based on the movement associated with the wearable computing device or their equivalent by at least comparing movement data generated by the wearable computing device or their equivalents with the reference data; and performing an action by the wearable computing device or equivalent in response to determining that the second individual has not performed the cleaning action on at least one of the plurality of target surfaces.

48. 48. The method of claim 47, further comprising, in response to determining that the cleaning action has not been performed on each of the plurality of target surfaces, storing cleaning verification information associated with the plurality of target surfaces and a time of the subsequent cleaning event.

Images