JP7656472B2 - Apparatus, method and system for data evaluation - Patents.com - Google Patents

Description

The present disclosure relates generally to data evaluation, and more specifically to evaluating the effectiveness of actions taken in a target environment.

In recent years, data evaluation has become an important part of service operations. Data evaluation refers to the process of evaluating data to gain insights. Data evaluation techniques can be used to gain insights from data in various applications such as quality control, business management, and monitoring.

Conventionally, data evaluation techniques have been proposed for evaluating risk indices for humans and the environment.
For example, U.S. Patent No. 8,831,972 (Patent Document 1) discloses, "A computer-implemented method, apparatus, and computer-usable program product for generating a customer risk assessment score. In one embodiment, the process identifies patterns of events by analyzing dynamic data related to a customer. The dynamic data consists of metadata describing the customer's appearance and behavior. The patterns of events are analyzed to identify risk assessment factors for the customer. A risk assessment analysis is performed dynamically using the customer's risk assessment factors to generate a risk assessment score for the customer while the customer is shopping at the retail establishment. The risk assessment score is indicative of the potential risk the customer poses to the retail establishment."
In addition, JP 2019-139602 A (Patent Document 2) discloses a means for providing a risk assessment system that includes a detection unit 300 that detects contact of a living body with each area on the surface of at least one piece of equipment over time, and a control unit 202 that outputs assessment information for the risk of contact infection based on the number of contacts detected by the detection unit 300 for each area.
Furthermore, U.S. Patent Application Publication No. 2018/0052993 (Patent Document 3) discloses that "the present invention provides a method, system, and computer program product for analyzing risk associated with, for example, a potential data leak. The risk of an activity may be measured as a function of risk factors associated with the person involved in the activity, the confidentiality of the risky data, the endpoint receiving the risky data, the type of activity, etc. The risk may take into account the probability of a leak event given a given activity and a risk cost reflecting the above risk factors. The risk calculation may be influenced by using manually and/or automatically adjusted parameters. Risk associated with a person and/or file may be obtained by initializing a risk score for the individual or file based on a rule set, adjusting the risk score in response to continuous monitoring of events, identifying commonalities between people or files, and propagating the risk score based on the commonalities."

U.S. Pat. No. 8,831,972 JP 2019-139602 A US Patent Application 2018/0052993

Patent Literature 1 discloses a risk assessment technique that analyzes metadata indicating the appearance and behavior of a customer in a retail establishment and dynamically calculates a risk assessment score for the customer, which indicates the potential risk that the customer poses to the retail establishment.
Furthermore, Patent Document 2 discloses a risk assessment technique for determining the risk of contact infection of a surface based on the number of times the surface has come into contact with a living body.
Furthermore, Patent Document 3 discloses a risk assessment technique that analyzes human behavior, data sensitivity, types of activities, and the like, and determines the risk associated with data leakage.

However, the techniques disclosed in Patent Documents 1 to 3 are primarily intended to assess specific risks posed by specific agents or causes, and do not provide a comprehensive means for comprehensively assessing the risks that people pose to the environment, or the risks that the environment poses to people. Furthermore, these techniques do not provide a means for evaluating the effectiveness of tracking actions taken in the environment to bring the environment closer to a target state (e.g., a sufficiently safe state, a sufficiently productive state, etc.).

The present disclosure therefore aims to provide an apparatus, method, and system for data evaluation that can generate recommended actions for progressing an environment toward a goal state based on the mutual influence between the environment and assets in the environment, and evaluate the effectiveness of the recommended actions.

One representative example of the present disclosure relates to a data evaluation device including: a data receiving unit that receives first sensor data related to an asset in a target environment from a sensor installed in the target environment; an evaluation unit that generates a first evaluation result indicating a discrepancy between the first state of the asset and a target state of the asset by analyzing the first sensor data based on a first evaluation criterion that defines a threshold for quantifying the first state of the asset; a notification generating unit that generates an action notification indicating a recommended action for progressing the first state of the asset toward the target state of the target asset based on the first evaluation result; a notification output unit that outputs the action notification to an information device usable by one or more of the assets; a tracking data receiving unit that receives second sensor data related to the asset in the target environment from one or more of the sensor and the information device; and a tracking evaluation unit that generates a second evaluation result indicating a level of effectiveness of the recommended action by analyzing the second sensor data based on a second evaluation criterion that defines a threshold for quantifying the second state of the asset.

The present disclosure provides an apparatus, method, and system for data evaluation that can generate recommended actions for progressing an environment toward a goal state based on the environment and its mutual impact with assets, and evaluate the effectiveness of the recommended actions.

Other issues, configurations, and advantages will become clearer in the description of the embodiments of the invention below.

FIG. 1 illustrates an example of a computing architecture for implementing embodiments of the present disclosure. FIG. 2 illustrates an example of a configuration of a data evaluation system according to an embodiment of the present disclosure. FIG. 3 is a block diagram showing a logical configuration of the data evaluation system according to an embodiment of the present disclosure. FIG. 4 is a block diagram illustrating an example of a configuration of a target environment according to an embodiment of the present disclosure. FIG. 5 is a diagram illustrating an example in which the target environment is a supermarket according to an embodiment of the present disclosure. FIG. 6 is a block diagram showing a data flow in the data evaluation device according to an embodiment of the present disclosure. FIG. 7 is a flowchart showing the overall flow when the data evaluation process according to the present disclosure is applied to a risk evaluation scenario. FIG. 8 is a flowchart showing the flow of an environmental risk assessment process according to an embodiment of the present disclosure. FIG. 9 illustrates an example of non-living asset attribute data according to an embodiment of the present disclosure. FIG. 10 is a table illustrating classified data according to an embodiment of the present disclosure. FIG. 11 is a flowchart showing the flow of a life asset risk assessment process according to an embodiment of the present disclosure. FIG. 12 illustrates an example of life form asset attribute data according to an embodiment of the present disclosure. FIG. 13 illustrates an example of risk index output data stored in a risk index output database according to an embodiment of the present disclosure. FIG. 14 is a flowchart showing the flow of a notification generation process according to an embodiment of the present disclosure. FIG. 15 shows an example of the notification selection criteria, notification target data, and notification list database. FIG. 16 is a flowchart showing the flow of a tracking evaluation process according to an embodiment of the present disclosure. FIG. 17 is a flow chart illustrating transfer function processing according to an embodiment of the present disclosure. FIG. 18 illustrates a table showing example values used in the transfer function processing according to an embodiment of the present disclosure. FIG. 19 is a flowchart illustrating an example of a parameter setting process according to an embodiment of the present disclosure.

The following describes embodiments of the present invention with reference to the drawings. Please note that the embodiments described in this specification do not limit the invention according to the claims, and each of the elements and combinations thereof described in connection with the embodiments are not strictly necessary to implement the aspects of the present invention.

Various aspects are disclosed in the following description and in the associated drawings. These aspects may be modified in alternative ways without departing from the scope of the present disclosure. Furthermore, well-known elements of the present disclosure may not be described in detail or may be omitted without obscuring the relevant matters of the present disclosure.

The terms "exemplary" and/or "example" are used herein to mean "serving as an example, instance, or illustration." Any aspect described herein as "exemplary" and/or "example" is not necessarily to be construed as preferred or advantageous over other aspects. Similarly, the term "aspects of the disclosure" does not require that all aspects of the disclosure include a particular feature, advantage or mode of operation.

Furthermore, many aspects are described in terms of sequences of operations to be performed by, for example, elements of a computing device. It will be recognized that the various operations described herein may be performed by specific circuitry (e.g., an application specific integrated circuit (ASIC)), program instructions executed by one or more processors, or a combination of both. Moreover, the sequences of operations described herein may be considered to be fully embodied in any form of computer-readable storage medium having stored therein a corresponding set of computer instructions that, when executed, cause an associated processor to perform the functions described herein. Thus, the various aspects of the present disclosure may be embodied in several different forms, all of which are contemplated to be within the scope of the claims.

As described herein, aspects of the present disclosure relate generally to data evaluation, and more specifically, to evaluating the effectiveness of actions taken in a target environment.

The data evaluation means of the present disclosure may be used for various purposes, such as identifying potential risks that may adversely affect service operations, and productivity evaluations that seek to identify areas of potential growth or improvement. By way of example, applications of data evaluation for risk evaluation may include crime prevention, equipment failure, infection prevention, health management, and the like. Furthermore, applications of data evaluation for productivity evaluation may include productivity management, incentive-based business models, business operations, inventory management, or resource management, and the like.

In some embodiments, when used for risk assessment, the data assessment means of the present disclosure can analyze time series information regarding assets (e.g., objects or organisms) in a target environment over a particular time period, generate recommended actions for risk reduction, and evaluate the effectiveness of the recommended actions in the target environment. Based on the effectiveness of the recommended actions, a corrective factor can be generated to update the risk assessment process. Application of the data assessment means to risk management can facilitate the safe performance of business operations even in the presence of risks (e.g., infectious diseases).

In other embodiments, when used for productivity assessment, the data assessment means of the present disclosure can analyze time series information about assets (e.g., objects or living organisms) in a target environment over a particular time period, generate recommended actions to improve productivity, and evaluate the effectiveness of the recommended actions in the target environment. Based on the effectiveness of the recommended actions, a corrective factor can be generated to update the productivity assessment process. By applying the data assessment means to productivity management, incentives can be devised to encourage collaboration in a business environment.

Aspects of the present disclosure may benefit both service providers and customers. For example, service providers may be able to perform their work with less risk to employees and customers, leading to increased productivity and employee satisfaction and a higher quality of service. Furthermore, a safe environment and high quality of service may lead to increased customer satisfaction and foster the development of trusting relationships between service providers and customers.

Referring to the drawings, FIG. 1 shows a high-level block diagram of a computer system 100 for implementing various embodiments of the present disclosure. The mechanisms and apparatus of various embodiments disclosed herein may be applied to any suitable computing system. The main components of the computer system 100 include one or more processors 102, memory 104, terminal interface 112, storage interface 113, I/O (input/output) device interface 114, and network interface 115. These components may be communicatively coupled, directly or indirectly, via a memory bus 106, an I/O bus 108, a bus interface unit 109, and an I/O bus interface unit 110.

Computer system 100 may include one or more general purpose programmable central processing units (CPUs) 102A and 102B, collectively referred to herein as processors 102. In some embodiments, computer system 100 may include multiple processors, and in other embodiments, computer system 100 may be a single CPU system. Each processor 102 executes instructions stored in memory 104 and may include one or more levels of on-board cache.

In some embodiments, memory 104 may include random access semiconductor memory, storage devices, or storage media (either volatile or non-volatile) for storing or encoding data and programs. In some embodiments, memory 104 represents the entire virtual memory of computer system 100 and may also include virtual memory of other computer systems coupled to computer system 100 or connected over a network. While memory 104 may be conceptually considered as a single monolithic entity, in other embodiments, memory 104 may be a more complex configuration, such as a hierarchical structure of caches and other memory devices. For example, memory may exist in multiple levels of caches, and these caches may be further divided by function. Thus, one cache may hold instructions and another cache may hold non-instruction data used by one or more processors. Memory may be further distributed and associated with different CPUs or sets of CPUs, as is known in any of the so-called non-uniform memory access (NUMA) computer architectures.

Memory 104 may store all or a portion of various programs, modules, and data structures for handling data transfers as described herein. For example, memory 104 may store data evaluation application 150. In an embodiment, data evaluation application 150 may include instructions or statements that execute on processor 102 or that are interpreted by instructions or statements that execute on processor 102 to perform functions as described further below. In an embodiment, data evaluation application 150 may include instructions or statements that execute on processor 102 or that are interpreted by instructions or statements that execute on processor 102 to perform functions as described further below.
In some embodiments, data evaluation application 150 may be implemented in hardware via semiconductor devices, chips, logic gates, circuits, circuit cards, and/or other physical hardware devices instead of or in addition to a processor-based system. In some embodiments, data evaluation application 150 may include data other than instructions or descriptions. In some embodiments, cameras, sensors, or other data input devices (not shown) may be provided in direct communication with bus interface unit 109, processor 102, or other hardware of computer system 100. In such a configuration, the need for processor 102 to access memory 104 and potential cause identification applications may be reduced.

Computer system 100 may include a bus interface unit 109 for communication between processor 102, memory 104, display system 124, and I/O bus interface unit 110. I/O bus interface unit 110 may couple to an I/O bus 108 for transferring data to and from various I/O units. I/O bus interface unit 110 may communicate via I/O bus 108 with a number of I/O interface units 112, 113, 114, and 115, also known as I/O processors (IOPs) or I/O adapters (IOAs). Display system 124 may include a display controller, a display memory, or both. The display controller may provide video, audio, or both data to display device 126. Computer system 100 may also include one or more sensors or other devices configured to collect data and provide the data to processor 102.
By way of example, computer system 100 may include biosensors to collect heart rate data, stress level data, etc., environmental sensors to collect humidity data, temperature data, pressure data, etc., and motion sensors to collect acceleration data, movement data, etc. Other types of sensors may also be used. Display memory may be dedicated memory for buffering video data. Display system 124 may be connected to a display device 126, such as a separate display screen, a computer monitor, a television, a tablet or handheld device, etc.
In some embodiments, display device 126 may include one or more speakers for playing audio. Alternatively, one or more speakers for playing audio may be connected to the I/O interface unit. In other embodiments, one or more functions provided by display system 124 may be implemented in an integrated circuit that includes processor 102. Additionally, one or more functions provided by bus interface unit 109 may be implemented in an integrated circuit that includes processor 102.

The I/O interface unit provides the ability to communicate with various storage and I/O devices. For example, the terminal interface unit 112 can be fitted with user I/O devices 116, such as user output devices (e.g., a video display device, speakers, and/or a television set, etc.) and user input devices (e.g., a keyboard, mouse, keypad, touchpad, trackball, buttons, light pen, or other pointing device, etc.). A user may use a user interface to input data or instructions to the user I/O devices 116 and the computer system 100 by manipulating the user input devices, and to receive output data using the user output devices. The user interface may be displayed on a display device, played through speakers, or printed via a printer, for example, via the user I/O devices 116.

Storage interface 113 allows attachment of one or more disk drives or direct access storage devices 117 (usually magnetic disk drive storage devices, but may also be arrays of disk drives arranged to appear as a single large storage device to a host computer, or other storage devices including solid state drives such as flash memory). In some embodiments, storage device 117 may be implemented as any secondary storage device. Contents of memory 104 may be stored in storage device 117 and retrieved as needed. Input/output device interface 114 provides an interface to any of a variety of input/output devices such as printers, fax machines, etc. Network interface 115 provides one or more communication paths from computer system 100 to other digital devices and computer systems. These communication paths may include, for example, one or more networks 130.

1 shows a particular bus structure providing direct communication paths between the processor 102, memory 104, bus interface unit 109, display system 124, and I/O bus interface unit 110, but in other embodiments, the computer system 100 may include different buses or communication paths that may be configured in various forms, such as point-to-point links in a hierarchical, star, or web configuration, multiple hierarchical buses, parallel and redundant paths, or any other suitable type of configuration. Furthermore, while the I/O bus interface unit 110 and the I/O bus 108 are each shown as single units, in reality the computer system 100 may include multiple I/O bus interface units 110 and/or multiple I/O buses 108. Also, although multiple I/O interface units are shown isolating the I/O bus 108 from other communication paths running to various I/O devices, in other embodiments, some or all of the I/O devices are directly connected to one or more system I/O buses.

In various embodiments, computer system 100 may be a device that receives requests from other computer systems (clients) without a direct user interface, such as a multi-user mainframe computer system, a single-user system, or a server computer. In other embodiments, computer system 100 may be implemented as a desktop computer, a portable computer, a laptop or notebook computer, a tablet computer, a pocket computer, a telephone, a smartphone, or any other suitable type of electronic device.

Next, an example of the configuration of a data evaluation system 200 according to an embodiment of the present disclosure will be described with reference to FIG.

FIG. 2 shows an example of the configuration of a data evaluation system 200 according to an embodiment. The data evaluation system 200 is a system for evaluating data related to assets in a target environment, proposing recommended actions to be performed in the target environment, and performing a tracking evaluation of the effectiveness of the recommended actions. Here, the target environment refers to an indoor or outdoor location where the recommended action is performed. By way of example, the target environment may include a retail facility (e.g., a convenience store, a supermarket, a restaurant, a home appliance store), a public facility (e.g., an airport, a train station, a library), a workplace (e.g., a factory, an office building), a medical facility (e.g., a clinic, a hospital), or any other location.

As shown in FIG. 2, the data evaluation system 200 mainly includes a sensor 210, an information device 220, a communication network 225, and a data evaluation device 230. The sensor 210, the information device 220, and the data evaluation device 230 may be communicatively connected via the communication network 225. Here, the communication network 225 may include a LAN (Local Area Network) connection, the Internet, a WAN (Wide Area Network) connection, a MAN (Metropolitan Area Network) connection, etc.

The sensor 210 may include a data collection device installed in the target environment and configured to collect information about the target environment and the assets located in the target environment. The sensor 210 may include a camera (e.g., RGB camera, LIDAR), a biosensor (e.g., to collect heart rate data, stress level data), an environmental sensor (e.g., to collect humidity data, temperature data, barometric pressure data), a motion sensor (e.g., to collect acceleration data, motion data), or other device configured to monitor the target environment and the assets. In some embodiments, the sensor 210 may be installed in the target environment such that data can be collected about the entire target environment and each of the assets located in the target environment.

The information device 220 includes a device configured to receive and transmit information from the data evaluation device 230. In some embodiments, the information device 220 may include a personal computing device (e.g., a smartphone, a tablet, a smartwatch, a laptop computer) used by an asset in the target environment. In some embodiments, the information device 220 may include a computing device or a display device installed in the target environment. For example, the information device 220 may include a digital sign or display screen owned or managed by a service provider that provides services in the target environment. The asset may use the information device 220 to input information into the data evaluation device 230 or to view notifications (e.g., action notifications indicating recommended actions) sent from the data evaluation device 230.

The data evaluation device 230 is a device configured to evaluate data related to assets in a target environment, propose recommended actions to be executed in the target environment, and perform a tracking evaluation of the effectiveness of the recommended actions. The data evaluation device 230 may include a cloud-side server device that is geographically separated from the target environment and connected to the sensor 210 and the information device 220 via a communication network 225. As shown in FIG. 2, the data evaluation device 230 includes a data receiving unit 231, an evaluation unit 232, a notification generating unit 233, a notification output unit 234, a tracking data receiving unit 235, and a tracking evaluation unit 236. In an embodiment, the data receiving unit 231, the evaluation unit 232, the notification generating unit 233, the notification output unit 234, the tracking data receiving unit 235, and the tracking evaluation unit 236 (collectively referred to herein as "functional units") may be implemented as software modules included in a data evaluation application (e.g., the data evaluation application 150 shown in FIG. 1) configured to be executed by the data evaluation device 230.
The data evaluation device 230 is not limited to the functional units shown in FIG. 2, and other functional units will be described later.

The data receiving unit 231 is a functional unit configured to receive first sensor data related to an asset in the target environment from a sensor 210 installed in the target environment. Here, an asset refers to any entity in the target environment, including living entities (e.g., humans and animals, hereafter referred to as "living assets") and non-living entities (e.g., tables, chairs, shelves, cash registers, service counters, products for sale, hereafter referred to as "non-living assets"). Furthermore, the first sensor data may include any type or form of data collected by the sensor 210. For example, the first sensor data may include images or videos showing the asset, biometric data of the asset, environmental data related to the target environment (e.g., temperature data, humidity data), etc.

The evaluation unit 232 generates a first evaluation result indicating a mismatch of the first state of the asset with respect to a target state of the target environment by analyzing the first sensor data based on a first evaluation criterion that defines a threshold for quantifying the first state of the asset. Here, the first evaluation criterion may include a standard, rule, threshold, weight, guideline, or rubric for evaluating the first sensor data and determining the first state of the asset. The first state refers to the state of the asset at a first time corresponding to when the first sensor data is collected. Furthermore, the target state may refer to a desired state of the asset. As an example, for an asset called a "shopping aisle," the first evaluation criterion may define a threshold for quantifying congestion of the shopping aisle. If the first sensor data indicates that the number of people in the shopping aisle exceeds a threshold defined by the first evaluation criterion, the shopping aisle may be determined to be in a first state of "congested" (i.e., crowded). The first state may also indicate a risk index to provide a quantitative indication of a level of danger associated with the asset. Here, the "mismatch" indicated by the first evaluation result may indicate the extent to which the first state of the asset differs from the target state.

The notification generating unit 232 is a functional unit that generates an action notification indicating a recommended action for progressing the first state of the asset toward the goal state of the target environment based on the first evaluation result. Here, the expression "progressing the first state of the asset toward the goal state" means making the asset more compliant, consistent, uniform, or similar to the goal state. The action notification may include a message formulated in a natural language indicating one or more recommended actions for moving the first state of the asset closer to the goal state of the target environment. As an example, referring to the example of a congested shopping aisle described above, the action notification may indicate a recommended action of "limiting the number of people allowed in the shopping aisle to five or less." Such a recommended action leads to benefits related to reducing the risk of infection transmission between shoppers or physical collisions between shopping carts.

The notification output unit 234 is a function that outputs the action notification to one or more information devices 220 in the target environment. For example, in some embodiments, the notification output unit 234 may send the action notification to an information device 220 used by one or more of the assets, or to an information device 220 configured to display information to everyone in the target environment.
In some embodiments, the notification output unit 234 may be configured to provide a registration interface for the information devices, receive registration requests from one or more information devices via the registration interface, register these information devices as registered information devices, and output action notifications to all registered information devices, where the registration interface may include a web application accessible via a QR code provided in the target environment.
In this manner, the notification action may be provided to information devices 220 owned by staff, employees, or volunteers of the target environment. The determination of the information devices 220 to which the action notification should be output may be based on the nature of the recommended action, the nature of the asset (e.g., qualifications, role), the first sensor data, etc.

The tracking data receiver 235 is a functional unit configured to receive second sensor data related to assets in the target environment from the sensor 210 and/or the information device 220. Here, like the first sensor data, the second sensor data may include any type or form of data collected by the sensor 210. For example, the second sensor data may include images or video showing the assets, biometric data of the assets, environmental data related to the target environment (e.g., temperature data, humidity data), etc. In some embodiments, the second sensor data may be data collected specifically about a subset of assets affected by a recommended action of the action notification. As described herein, the second sensor data may be used to evaluate the effectiveness of the recommended action.
In some embodiments, the tracking data receiver 235 may be configured to provide a data collection interface to the registered information device registered by the notification output and to receive second sensor data from the registered information device, where the second sensor data may include a questionnaire, survey, or other feedback provided by a user of the registered information device.

The tracking evaluation unit 236 is a functional unit configured to generate a second evaluation result indicating a level of effectiveness of the recommended action by analyzing the second sensor data based on a second evaluation criterion that defines a threshold for quantifying the second state of the asset. Here, similar to the first of the first evaluation criteria, the second evaluation criterion may include a standard, rule, guideline, or rubric for evaluating the second sensor data and determining the second state of the asset. The second state refers to the state of the asset at a second time corresponding to when the second sensor data was collected.

In some embodiments, data evaluator 230 may be configured to simultaneously perform data evaluations for multiple different target environments. Additionally, in some embodiments, data evaluator 230 may be configured to use insights gained from data evaluations for one target environment when performing a data evaluation for another target environment. More specifically, data evaluator 230 may determine a recommended action for a first target environment based on the effectiveness level of the recommended action in the second target environment.
For example, the data evaluation device 230 may be configured to generate an evaluation result (e.g., a third evaluation result) indicating the effectiveness level of a recommended action (the second recommended action) in the second target environment by analyzing sensor data (e.g., third sensor data) received from a second sensor installed in a second target environment different from the target environment, and to generate an action notification indicating a recommended action for progressing a first state of the asset toward a goal state of the target asset in the first target environment based on the evaluation result.
Additionally, in some embodiments, the data evaluator 230 may generate and provide comprehensive condition information for a larger region by aggregating insights gained from data evaluations in multiple target regions. As an example, the data evaluator 230 may determine a risk index (i.e., condition) of several supermarkets in a particular region and create a hazard map showing the risk index of each supermarket in the region. This hazard map may be provided to the information appliance (e.g., a registered user).

The data evaluation system 200 shown in FIG. 2 allows for the generation of recommended actions to progress an environment toward a goal state based on the environment and its mutual impact with assets, and for evaluating the effectiveness of the recommended actions. The data evaluation system 200 shown in FIG. 2 may be used for a variety of data evaluation purposes, including risk assessment and productivity assessment. Aspects of the data evaluation system 200 shown in FIG. 2 reduce risk to assets in the subject and target environments, increase the productivity and satisfaction of employees working in the subject environments, and lead to improved customer satisfaction for customers using the target environments.

Next, the logical configuration of the data evaluation system will be explained with reference to Figure 3.

FIG. 3 is a block diagram showing a logical configuration of a data evaluation system 200 according to an embodiment of the present disclosure. As shown in FIG. 3, the data evaluation system 200 mainly includes a data collection layer 302, a data evaluation layer 303, and a service provision layer 304.

The data collection layer 302 refers to a functional unit that is locally deployed in the target environment. In the data collection layer 302, the sensors 210 and the information devices 220 are used to collect information (e.g., first sensor data, second sensor data) about the target environment and assets in the target environment. The information collected in the data collection layer 302 is transmitted to the data evaluation layer 303 via the communication network 225.

The data evaluation layer 303 refers to a functional unit deployed in a cloud environment. In the data evaluation layer 303, the data receiving unit 231, the evaluation unit 232, the notification generating unit 233, the notification output unit 234, the tracking data receiving unit 235, and the tracking evaluation unit 236 of the data evaluation device 230 are used to evaluate the sensor data collected in the data collection layer 302, and generate an action notification indicating a recommended action to be performed in the target environment. The action notification is transmitted to one or more information devices of the information device 220 in the target environment. Here, the various functional units of the data evaluation device 230 may be individually updated and scaled based on the characteristics of the cloud to which it is deployed.

The service provision layer 304 refers to a function that is locally deployed in the target environment and receives data from the data evaluation layer 303. In the service provision layer 304, the action notification generated in the data evaluation layer 303 is provided to the information device 220 of the target environment. As described herein, in some embodiments, the action notification may be sent to an information device 220 used by one or more assets of an asset (e.g., an administrator, staff, or other person who has registered the information device 220), or to an information device 220 configured to display information to everyone in the target environment (e.g., a digital sign, a screen).

Next, an example of the configuration of the target environment will be described with reference to Figures 4 and 5.

FIG. 4 is a block diagram showing an example of a configuration of a target environment 400 according to an embodiment of the present disclosure. As shown in FIG. 4, the target environment 400 includes an asset 420, an area 430, a sensor 210, and an information device 220.

As described herein, assets 420 refer to any entity in the target environment 400, including animate assets 424, such as people and animals, and inanimate assets 428, such as tables, chairs, shelves, cash registers, service counters, products for sale, etc. Additionally, animate assets 424 may include unidentified assets, such as visitors or customers, for whom no identifying information has been collected, and identified assets, such as registered employees or staff of a service provider operating in the target environment 400, or other persons for whom identifying information has been collected. As described herein, in certain embodiments, unidentified assets may be reclassified as identified assets by completing a registration process (e.g., QR code scan, RFID tag, registration application) via a personal computing device (e.g., personal information appliance 220) and providing identifying information. Identified assets may be provided with access to information regarding the state of the target environment 400 (e.g., a risk index for a particular area).

Area 430 refers to a physical area in the target environment 400. As shown in FIG. 4, area 430 may include a first area 431, a second area 432, and a third area 433. Each area of area 430 may have a different purpose. For example, first area 431 is a shopping area, second area 432 is a cafeteria, and third area 433 is a seating area. Here, an example is shown in which area 430 includes a first area 431, a second area 432, and a third area 433, but the present disclosure is not limited thereto, and the number and configuration of areas 430 may be appropriately determined based on the nature and purpose of the target environment 400.

The sensors 210 may include data collection devices installed in the target environment 400 and configured to collect information about the target environment 400 and the assets 420 located in the target environment 400. The sensors 210 may include cameras (e.g., RGB cameras, LIDAR), biometric sensors (e.g., to collect heart rate data, stress level data), environmental sensors (e.g., to collect humidity data, temperature data, barometric pressure data), motion sensors (e.g., to collect acceleration data, motion data), or other devices configured to monitor the target environment and assets.

Information device 220 includes devices configured to receive and transmit information from a data assessment device (not shown in FIG. 4). In some embodiments, information device 220 may include a personal computing device (e.g., a smartphone, tablet, smartwatch, laptop computer) used by assets 420 in target environment 400. In some embodiments, information device 220 may include a computing device or display device installed in the target environment.

As described herein, the target environment 400 of the present disclosure may include a retail facility (e.g., convenience store, supermarket, restaurant, electronics retailer), a public facility (e.g., airport, train station, library), a workplace (e.g., factory, office building), a medical facility (e.g., clinic, hospital), or any other indoor or outdoor location where data evaluation is desired. FIG. 5 illustrates an example where the target environment is a supermarket (hereinafter, "supermarket target environment 500").

As shown in FIG. 5, the supermarket target environment 500 is divided into multiple areas including a first area 531 as a produce section, a second area 532 as a seafood section, a third area 533 as a frozen food section, a fourth area 534 as an eat-in area, a fifth area 535 as an entrance/exit area, a sixth area 536 as a food stall area, a seventh area 537 as a checkout area, and an eighth area 538 as an entrance/exit area.

Sensors 210 are installed throughout the supermarket target environment 500 to collect sensor data regarding the supermarket target environment 500 and the assets 552 in the supermarket target environment. Here, the sensors 210 may include LIDAR sensors, security cameras, RFID sensors, etc. Additionally, information devices 220 may be installed throughout the supermarket target environment 500 to collect information from and provide information to the assets 552 in the supermarket target environment 500. By way of example, the information devices 220 may include a cash register display device, a digital display sign, or a personal computing device used by the assets 552.

As described herein, assets 552 refer to any entity in the supermarket target environment 500, including animate assets such as people and animals, and inanimate assets such as tables, chairs, shelves, cash registers, service counters, products for sale, etc. Here, assets 552 may include identified assets such as supermarket staff and employees, and unidentified assets such as shoppers visiting the supermarket target environment 500.

Next, we will explain the data flow in the data evaluation device with reference to Figure 6.

FIG. 6 is a block diagram showing the flow of data in the data evaluation device 230 according to an embodiment. As shown in FIG. 6, in one embodiment, the data evaluation device 230 may be divided into an evaluation management unit 610 for processing first sensor data (e.g., data indicating a first state of an asset in a target environment) and a tracking management unit 620 for processing second sensor data (e.g., data indicating a second state of an asset in a target environment).

First, the data receiving unit 231 receives first sensor data from a sensor 210 installed in the target environment. Here, the first sensor data may include information about assets in the target environment. In some embodiments, the data receiving unit 231 may format the first sensor data as a group of individual or bulk time series data. Then, the data receiving unit 231 transmits the first sensor data to the evaluation unit 232.

The evaluation unit 232 analyzes the first sensor data to generate a first evaluation result indicating a mismatch of the first state of the asset with respect to a target state of the target environment. Here, the evaluation unit 232 may generate the first evaluation result by analyzing the first sensor data based on a first evaluation criterion 615 that specifies a threshold value for quantifying the first state of the asset. More specifically, the first evaluation criterion 615 may include asset data 616 that specifies separate threshold values for clustering the data and weight values for weighting each cluster.

The notification generator 293 then generates an action notification indicating a recommended action to progress the first state of the asset towards the target state of the target environment based on the first assessment result. Furthermore, the visualization unit 619 may generate a visual representation of the target environment based on the first assessment result. As an example, when the data evaluator 230 is applied to a risk reduction scenario, the visualization unit 619 may generate a hazard map that highlights different areas of the target environment in different colors based on the current risk index.

The notification output unit 234 then outputs the action notification generated by the notification generation unit 233 and the visual representation generated by the visualization unit 619 to an information device 220 located in the target environment. One or more of the assets may perform the recommended action indicated by the action notification on the target environment to bring the first state of the asset closer to the goal state of the target environment. In some embodiments, the notification output unit 234 may output the action notification to a transfer function 627 for use in performing a follow-up evaluation of the recommended action.

The tracking data receiver 235 then receives second sensor data from the sensor 210 and/or the information device 220, where the second sensor data may include information about the assets in the target environment after execution of the recommended action. In some embodiments, the tracking data receiver 235 may format the second sensor data as a group of individual or bulk time series data. The tracking data receiver 235 then transmits the second sensor data to the tracking evaluator 236.

Next, the tracking evaluation unit 236 analyzes the second sensor data to generate a second evaluation result indicating the effectiveness level of the recommended action. Here, the tracking evaluation unit 236 may generate the second evaluation result by analyzing the second sensor data based on a second evaluation criterion 625 for quantifying the second state of the asset. Furthermore, the tracking evaluation unit 236 may compare the second state with a target state using a transfer function 627 to quantify the effectiveness of the recommended action (e.g., the recommended action indicated by the action notification from the notification output unit 234) for the target environment. In some embodiments, the second evaluation result may include a correction factor 629 for updating the first evaluation criterion based on the effectiveness level of the recommended action. The correction factor may be input to the evaluation unit 232 to facilitate updating the first evaluation criterion.

The data evaluation device 230 shown in FIG. 6 can generate recommended actions for progressing an environment toward a goal state based on the environment and the mutual effects of the assets in the environment, and can evaluate the effectiveness of the recommended actions. The data evaluation system 230 shown in FIG. 6 can be used for various data evaluation purposes, including risk assessment and productivity assessment.

As described herein, the data evaluation system according to the present disclosure may be used for various data evaluation purposes, including risk evaluation and productivity evaluation. In the following, for convenience of explanation, aspects of the data evaluation system are described with reference to a risk evaluation scenario. However, it should be noted that the data evaluation system according to the present disclosure is not limited to risk evaluation, and may be suitably configured for use in other scenarios, such as productivity evaluation (e.g., productivity management).
When matched to a productivity assessment, the first assessment result indicates a productivity level of the asset in a first state, the recommended actions include productivity improvement actions for improving the productivity level of the asset, and the target state includes a state associated with a productivity level that achieves a predetermined productivity threshold.

Next, referring to FIG. 7, the overall flow of the data evaluation process for risk assessment according to an embodiment of the present disclosure will be described.

Figure 7 is a flowchart showing the overall flow when the data evaluation process 700 according to the present disclosure is applied to a risk assessment scenario. The data evaluation process 700 may be used to evaluate the effectiveness of recommended actions for reducing a risk index of a target environment. The data evaluation process 700 may be executed by various functional units of the data evaluation device 230.

First, in step S702, an initial state is established for both the target environment and the assets in the target environment. Here, the initial state of the target environment and the assets may be a state of the target environment and the assets that serves as a reference for determining changes occurring with respect to the target environment or the assets at a later time. In one embodiment, the initial state of the target environment and the assets may be established based on sensor data collected by a sensor (e.g., sensor 210 shown in FIG. 2) installed in the target environment. As an example, if the target environment is a retail facility, the initial state may be established based on sensor data collected by a sensor prior to the start of business operations at the retail facility on a particular day.

Next, in step S704, the assets and the target environment are monitored for changes in state. Here, the assets and the target environment may be monitored for changes in state in real time or periodically, depending on the nature of the target environment and the goal of the data evaluation. Here, the monitoring of the assets and the target environment may be performed by analyzing sensor data collected by sensors installed in the target environment.

Next, in step S706, if a state change for the assets and/or the target environment is detected in step S704, an environmental risk assessment process is performed to determine a risk index for the non-living assets of the target environment. Here, the risk index refers to a quantitative indication of the degree of danger associated with the assets. In some embodiments, the risk index may be expressed in the form of a value between 0 and 1, where a lower value indicates a lower degree of risk and a higher value indicates a higher degree of risk. The environmental risk assessment process will be described in detail with reference to FIG. 8, and will not be described in detail here.

Next, in step S707, the risk index (referred to herein as the "non-living asset risk index") determined as a result of the environmental risk assessment process executed in step S706 is compared against a predetermined severity threshold. If the non-living asset risk index exceeds the severity threshold (i.e., is considered to be a substantially serious risk), the data evaluation process 700 proceeds to step S708. On the other hand, if the non-living asset risk index does not exceed the severity threshold (i.e., is not considered to be a substantially serious risk), the data evaluation process 700 proceeds to step S714.

Next, in step S708, a life asset risk assessment process is executed, and a risk index for the life asset in the target environment (referred to as the "life asset risk index" in this specification) is determined. The life asset risk assessment process will be described in detail with reference to FIG. 11, so details will be omitted here.

Next, in step S709, the organism asset risk index determined as a result of the organism asset risk assessment process executed in step S708 is compared against a predetermined severity threshold. If the organism asset risk index exceeds the severity threshold (i.e., is considered to be a substantially serious risk), the data assessment process 700 proceeds to step S710. On the other hand, if the organism asset risk index does not exceed the severity threshold (i.e., is not considered to be a substantially serious risk), the data assessment process 700 proceeds to step S714.

Next, in step S710, an action notification is generated and transmitted to one or more of the information devices in the target environment. Here, the action notification may indicate a living asset risk index, a non-living asset risk index, and a recommended action to reduce the living asset risk index or the non-living asset risk index to a desired level (e.g., a recommended action to progress the first state of the asset toward a goal state of the target environment). In some embodiments, the living asset risk index and the non-living asset risk index may be combined (e.g., by a weighted average technique or other calculation) to generate a total risk index (e.g., a first state) of the target environment. One or more of the assets receiving the action notification via an information device located in the target environment may perform the recommended action indicated by the action notification on the target environment to reduce the total risk index. The action notification generation process will be described in detail with reference to FIG. 14, and will not be described in detail here.

Next, in step S712, a tracking evaluation process is performed to evaluate the effectiveness of the recommended actions in reducing the total risk index. Here, the tracking evaluation process may be performed by analyzing a second sensor data set collected from sensors installed in the target environment using a transfer function to quantify the effectiveness of the recommended actions. Furthermore, the tracking evaluation process may generate a correction factor that is used to update the evaluation criteria or other parameters used in the non-living asset risk evaluation process. The tracking evaluation process will be described in detail with reference to FIG. 16, so details will be omitted here.

Next, in step S714, a visual representation of the total risk index may be generated and transmitted to one or more information devices in the target environment. As described herein, the visual representation of the total risk index may include a hazard map that highlights different areas of the target environment in different colors based on the current risk index.

Next, the overall flow of the environmental risk assessment process according to an embodiment of the present disclosure will be described with reference to FIG.

Figure 8 is a flowchart showing the flow of an environmental risk assessment process 800 according to an embodiment of the present disclosure. The environmental risk assessment process 800 may be used to determine a risk index of a non-living asset in a target environment (i.e., a non-living asset risk index). The environmental risk assessment process 800 shown in Figure 8 substantially corresponds to step S706 of the data assessment process 700 shown in Figure 7. The environmental risk assessment process 800 may be executed by a data receiving unit and an assessment unit of a data assessment device.

First, in step S802, an asset payload may be extracted from a first set of sensor data 801. Here, the first sensor data 801 may be collected by a sensor installed in the target environment and may be time series data related to assets in the target environment. The asset payload may be extracted from the first sensor data 801 by a data receiver (e.g., the data receiver 231 illustrated in FIG. 2 and FIG. 6). The first sensor data 801 may be streamed from the sensor in real time, or may be aggregated and stored in a storage device for periodic processing. Furthermore, in some embodiments, the first sensor data 801 may be subjected to one or more pre-processing steps to reduce redundancy or convert the data into a structured format to facilitate processing. Here, the asset payload may be a subset of the first sensor data 801. As an example, the asset payload may be a subset of the first sensor data 801 corresponding to a particular time period.

Next, in step S804, a payload type check is performed on the asset payload based on the non-living asset attribute data 805, where the non-living asset attribute data 805 includes information for defining and classifying the non-living assets of the asset payload included in the first sensor data 801, and may define information such as an asset identifier, asset name, asset description, asset type, asset subtype, asset location, etc. for any number of given non-living assets. Using the non-living asset attribute data 805, the asset payload may be formatted into categorized data 806, where information related to the non-living assets is organized according to type, subtype, category, etc.

Next, in step S810, stepwise clustering is performed on the classified data 806 based on the threshold value 808 included in the first evaluation criteria 807. As described herein, the first evaluation criteria may include a standard, rule, threshold value, weight, guideline, or rubric for evaluating the first sensor data and determining the first state of the asset. Here, performing stepwise clustering on the classified data 806 may include grouping each non-living asset into one or more clusters based on the threshold value 808. Each cluster may correspond to a different risk index (e.g., state) of the asset. In this manner, for each non-living asset of the assets included in the classified data 8906, a risk index may be determined based on the threshold value 808. As an example, as a result of performing stepwise clustering on the classified data 806, an asset with a "shopping aisle" may be grouped into a cluster corresponding to a state of "congested" if the number of people in the shopping aisle exceeds a threshold value of "10 people", and may be grouped into a state of "not congested" if the number of people in the shopping aisle is less than a threshold value of "5 people". Stepwise clustering may be performed to group each non-living asset included in the classified data 806 into a corresponding cluster based on a threshold value 808.

In one embodiment, the cluster values obtained from the stepwise clustering process may be used as a normalized risk index. As an example, if cluster steps [0, 1, 2, 3, 4] are performed, the following formula may represent the normalized risk index I for each asset:

Next, in step S812, the cluster values from step S810 may be weighted based on weights 809 included in the first evaluation criteria 807, where the weights 809 indicate the relative importance of a particular cluster with respect to other clusters. More specifically, the weights may indicate the relative impact of a particular cluster on the risk index of a particular non-living asset. The weights 809 may be predefined for each type of asset. As an example, referring to the "shopping aisle" asset example above, a higher weight may be assigned to clusters corresponding to a "congested" state and a lower weight may be assigned to clusters corresponding to a "non-congested" state. The resulting weighted normalized data represents a non-living asset risk index 814 for each non-living asset.

Further, a cumulative risk index 816 may be calculated for each non-living asset based on the risk index history data stored in the risk output database 821 and the accumulation criteria 815. Here, the accumulation criteria 815 may include standards, rules, or guidelines that define how each non-living asset risk index 814 changes over time. As an example, for an asset "microwave oven" grouped into a cluster corresponding to a state of "burning", the accumulation criteria 815 and risk index history data may be used to generate a cumulative risk index 816 indicative of the cumulative increase in the non-living asset risk index 814 over time.

Next, in step S818, a severity check may be performed on the non-living asset risk index 814 and the cumulative risk index 816 based on a predetermined severity definition 817. Here, the severity definition 817 may be used to classify the severity of the non-living asset risk index 814 and the cumulative risk index 816 into corresponding severity levels. As an example, the severity definition 817 may specify a set of thresholds for classifying the non-living asset risk index 814 and the cumulative risk index 816 into severity levels of "high severity", "medium severity", or "low severity" based on the relationship between the non-living asset risk index 814 and the cumulative risk index 816.

Next, in step S820, the non-living asset risk index 814, the cumulative risk index 816, and the severity level corresponding to each non-living asset may be output and stored in the risk output database 821.

特殊事情リスク指数８２３及び総環境リスク指数８２５は、リスク出力データベース８２１に格納されてもよい。 Next, in step S822, one or more risk index correction operations may be performed on the non-living asset risk index 814 or cumulative risk index 816 stored in the risk output database 821. In some embodiments, the non-living asset risk index 814 or cumulative risk index 816 corresponding to assets present in a particular area, present at a particular time, belonging to a particular type, involved in a particular event, or having other particular characteristics may be aggregated or filtered as necessary to generate a special situation risk index 823. As an example, the non-living asset risk index 814 or cumulative risk index 816 corresponding to the non-living assets located in the "eat-in area" may be aggregated to assess the level of risk in the "eat-in area".
Additionally, in some embodiments, the non-living asset risk index 814 or cumulative risk index 816 for all assets in the target environment may be aggregated to generate a total environmental risk index 825 for the target environment.
Here, the risk indexes of multiple assets may be aggregated by calculating a weighted average of the risk indexes of each asset according to the following formula:

The special circumstances risk index 823 and the total environmental risk index 825 may be stored in a risk output database 821 .

According to the environmental risk assessment process 800 shown in FIG. 8, a risk index for non-living assets in a target environment can be determined. As described herein, the non-living asset risk index for the target environment can be used in conjunction with the animate asset risk index for the target environment to generate an action notification indicating a recommended action to mitigate risk in the target environment.

Next, an example of non-living asset attribute data according to an embodiment of the present disclosure will be described with reference to FIG.

9 illustrates an example of non-living asset attribute data 805 according to an embodiment of the present disclosure. As described herein, in the environmental risk assessment process 800 illustrated in FIG. 8, an asset payload included in the first sensor data collected by a sensor installed in the target environment may be classified based on the non-living asset attribute data. Here, the non-living asset attribute data 805 includes information for defining and classifying the non-living asset of the asset payload included in the first sensor data, and may define information such as an asset identifier, an asset name, an asset description, an asset type, an asset subtype, and an asset location for any number of predetermined non-living assets. As an example, if the target environment is a retail facility, the non-living asset attribute data 805 may be predefined for a number of non-living assets, including areas in the retail facility, objects of interest in the retail facility (e.g., tables, chairs, cash registers), and the like.

An example of the non-living asset attribute data 805 is shown in FIG. 9. As shown in FIG. 9, the non-living asset attribute data 805 may include an asset identifier with "08306..993227c681", an asset name with "ASSET SAMPLE 1", an asset description with "Logical Congestion Area", an asset type with "Area", an asset subtype with "Aisle", an asset location with "(X,Y,Z,O)", etc. By comparing the asset payload included in the first sensor data with the non-living asset attribute data 805, the non-living assets of the asset payload may be classified according to their type (e.g., area, object). Further, after the asset payload is classified by type as described herein, a first evaluation criterion including thresholds and weights defined for different asset types may be used to quantify the non-living asset risk index of the non-living assets included in the asset payload.

Next, an example of classified data will be described with reference to FIG. 10.

FIG. 10 is a table illustrating categorized data 806 according to an embodiment of the present disclosure. As described herein, categorized data 806 may represent asset payload information formatted according to non-animate asset attribute data such that non-animate assets are organized according to type, subtype, category, etc.

An example of the classified data 806 is shown in FIG. 10. As shown in FIG. 10, the classified data 806 may include an asset payload 1001 indicating data collected about a non-living asset, a sensor 1002 indicating an identifier of the sensor that collected the asset payload 1001, a type 1003 indicating a type of the asset payload 1001 (e.g., a sealed area, an area that needs disinfecting, an area that needs cleaning), an area 1004 indicating an area in the target environment corresponding to the asset payload 1001, a category 1005 indicating a category of the asset payload 1001, a threshold 1006 indicating a threshold corresponding to the asset payload 1001, a cluster 1007 indicating a cluster into which the asset payload 1001 is grouped, and a weight 1008 indicating the relative impact of the particular cluster 1007 on the total risk index of the asset.

Next, the overall flow of the life asset risk assessment process according to an embodiment of the present disclosure will be described with reference to FIG.

11 is a flowchart showing the flow of a living asset risk assessment process 1100 according to an embodiment of the present disclosure. The living asset risk assessment process 1100 may be used to determine a risk index (i.e., a living asset risk index) of a living asset (e.g., a person) in a target environment. The living asset risk assessment process 1100 may be performed based on a non-living asset risk index determined for a non-living asset in the target environment in the above-described environmental risk assessment process 800 shown in FIG. 8. More specifically, the living asset risk index may be determined based on the location of the living asset in the target environment, its physical relationship with other living assets and non-living assets, the time spent in the target environment, and the like.
The living entity asset risk assessment process 1100 shown in Figure 11 corresponds substantially to step S708 of the data assessment process 700 shown in Figure 7. The living entity asset risk assessment process 1100 may be performed by a data receiving and assessing portion of a data assessment device.

First, in step S1102, a risk index payload is extracted from the risk output database 821. Here, the risk index payload may be extracted from the risk output database 821 by a data receiving unit (e.g., the data receiving unit 231 shown in Figures 2 and 6). The risk index payload may include a subset of the non-living asset risk indices determined for non-living assets of the target environment in the aforementioned environmental risk assessment process 800 shown in Figure 8 and stored in the risk output database 821. As an example, the risk index payload may include a non-living asset risk index for non-living assets located in a particular area of the target environment, a non-living asset risk index for a particular type of non-living asset, etc.

Next, in step S1104, a life asset risk index 1107 is determined for a life asset of the target environment based on the risk index payload extracted in step S1102, the life asset attribute data 1105, and the observation information 1103. Here, the life asset attribute data 1105 includes information defining attributes of the life asset of the target environment, and may include information such as an asset identifier, an asset type, a device identifier of an information device used by the asset, a role, a designated area, and information related to the time spent by the life asset in different activities (e.g., performing cleaning work, waiting in a crowded line, eating at a cafeteria) in the target environment. The observation information 1103 includes a subset of the first sensor data related to the life asset, and may include information regarding the location, appearance, and activities performed by the life asset. By mapping the observation information 1103 with the life asset attribute data 1105, the life asset can be identified and classified (e.g., as an employee of the target environment, a customer visiting the target environment, etc.).
The physical relationship between the classified animate assets and non-animate asset risk indices included in the risk index payload of step S1102 can then be analyzed to determine a animate asset risk index 1107 for the animate asset, where the animate asset risk index 1107 is a quantitative indicator of the risk associated with the animate asset. In some embodiments, the animate asset risk index 1107 for a particular animate asset may be determined based on the animate asset's proximity to other assets (living and non-living) in the target environment, the risk indices of the nearby assets, and the time the animate asset has spent in proximity to these other assets. In this manner, a animate asset risk index 1107 can be calculated for the animate asset that is proportional to the animate asset's proximity to other assets, risk indices, and the time spent in proximity. Here, the animate asset risk index 1107 may be calculated according to one or more of several statistical methods.

Further, a cumulative risk index 1109 may be calculated for each organism asset based on the risk index history data stored in the risk output database 821 and the cumulative criteria 815. As described herein, the cumulative criteria 815 may include standards, rules, or guidelines that define how each organism asset risk index 1107 changes over time. As an example, for an organism asset with a "cleaning worker" performing cleaning work in a target environment without proper protective equipment (e.g., mask, gloves), the cumulative criteria 815 and historical risk index data may be used to generate a cumulative risk index 1109 indicating a cumulative increase in risk of infectious disease transmission to the organism asset risk index 1107 over time.

Next, in step S1112, a severity check may be performed on the life asset risk index 1107 and the cumulative risk index 1109 based on a predetermined severity definition 817. As described herein, the severity definition 817 may be used to classify the severity of the life asset risk index 1107 and the cumulative risk index 1109 into corresponding severity levels. As an example, the severity definition 817 may define a set of thresholds for classifying the life asset risk index 1107 and the cumulative risk index 1109 into severity levels of "high severity", "medium severity", or "low severity" based on the relationship between the life asset risk index 1107 and the cumulative risk index 1109.

Next, in step S1114, the life asset risk index 1107, cumulative risk index 1109, and corresponding severity level for each life asset may be output and stored in the risk output database 821.

The living organism asset risk assessment process 1100 shown in FIG. 11 can determine a risk index for living organism assets in a target environment. As described herein, the risk index for living organism assets in a target environment can be used in conjunction with the risk index for non-living organism assets in the target environment to generate an action notification indicating a recommended action to mitigate risk in the target environment.

Next, an example of life form asset attribute data according to an embodiment of the present disclosure will be described with reference to FIG. 12.

12 illustrates an example of the life form asset attribute data 1105 according to an embodiment of the present disclosure. As described herein, in the life form asset risk assessment process 1100 illustrated in FIG. 11, a life form asset risk index is determined for a life form asset of a target environment based on the life form asset attribute data 1105 and a risk index payload including a non-life form asset risk index. Here, the life form asset attribute data 1105 includes information defining attributes of the life form asset of the target environment, and may include information such as an asset identifier, an asset type, a device identifier of an information device used by the asset, a role, a designated area, and information related to the time spent by the life form asset in different activities (e.g., performing cleaning work, waiting in a crowded line, eating at a cafeteria) in the target environment. The life form asset attribute data 1105 may be defined for a number of predetermined life form assets expected to be present in the target environment. For example, if the target environment is a retail facility, the life form asset attribute data 1105 may be predefined for a number of life form assets, such as employees of the retail facility, customers of the retail facility, etc.

An example of the animate asset attribute data 1105 is shown in FIG. 12. As shown in FIG. 12, the animate asset attribute data 1105 may include an asset identifier with "d5d7a3b...2d2031", an asset type with "Manager", a type identifier with "mg0003", an equipment identifier with "E9B0...0FB4", a role with "Logistics", a designated area with "Orders", "Shopping Mall 2nd Floor", and the like. By comparing the observational information collected about the animate assets of the asset in the target environment to the animate asset attribute data 1105, the animate assets of the asset payload may be classified according to their type, role, location, or other characteristics. Furthermore, as described herein, after the animate assets are classified, a non-animate asset risk index may be determined for the non-animate assets included in the asset payload.

Next, an example of risk index output data will be described with reference to FIG. 13.

As described herein, risk indices for animate and non-animate assets are stored in a risk index output database along with severity and attribute information associated with the assets. FIG. 13 illustrates an example of risk index output data 1300 stored in a risk index output database according to an embodiment of the present disclosure.

As shown in FIG. 13 , risk index output data 1300 may include a risk index 1301 (e.g., a non-living asset risk index or a living asset risk index, depending on the asset), risk severity 1302, risk type 1303, asset type 1304, asset subtype 1305, and asset location designation 1306.
Risk index 1301 may be a value between 0 and 1 that quantitatively indicates the level of risk of the asset. Risk severity 1302 includes a qualitative indication of the severity of the risk of the asset (e.g., low severity, medium severity, process severity). Risk type 1303 indicates the nature of the risk (e.g., congestion, disinfection, pollution, traffic accidents, hazardous waste, crime, natural disaster). Asset type 1304 indicates broad characteristics of the asset (e.g., location, object, person), and asset subtype indicates more detailed characteristics of the asset (e.g., hallway, restroom, employee). Asset location designation 1306 indicates the designated location of the asset (e.g., accounting area, ground floor).

Next, the overall flow of the notification generation process according to an embodiment of the present disclosure will be described with reference to FIG.

14 is a flow chart illustrating a notification generation process 1400 according to an embodiment of the present disclosure. The notification generation process 1400 may be used to generate an action notification indicating a recommended action to progress a first state of an asset (e.g., a state associated with a high level of risk) toward a target state of the target environment (e.g., a state associated with a low level of risk). The notification generation process 1400 may be based on asset attribute data (e.g., non-living asset attribute data or animate asset attribute data) and risk quotient output data stored in a risk output database.
The notification generation process 1400 shown in Figure 14 corresponds substantially to step S710 of the data evaluation process 700 shown in Figure 7. The notification generation process 1400 may be performed by a notification generation component of the data evaluator.

First, in step S1402, the risk quotient output data 1300 extracted from the risk output database 821, the asset attribute data 1401, the notification selection criteria 1403, and the notification list database 1404 can be used to select predefined notifications, where notifications may be selected for one or more subgroups of assets (e.g., customers, employees). Here, the asset attribute data 1401 may include non-living asset attribute data (e.g., non-living asset attribute data 805 shown in FIG. 9), animate asset attribute data (e.g., animate asset attribute data 1105 shown in FIG. 12), or a combination of both. The asset attribute data 1401 may be selected based on the assets present in the target environment. The notification list database 1404 includes a set of predefined notification candidates. These predefined notification candidates may include natural language sentences or phrases indicating recommended actions to reduce the risk of a particular asset in the target environment.
The risk notification selection criteria 1403 may include a set of standards, rules, thresholds, guidelines, or rubrics that define which predefined notifications in the notification list database 1404 apply to a particular asset based on risk type, risk index, risk level, etc. As an example, the risk notification selection criteria 1403 may indicate that a risk type of "congestion" with a risk index of "0.50" corresponds to a "please do not gather in groups" notification. In this manner, the notification selection criteria 1403 may be used in conjunction with the notification list database 1404 to select an appropriate notification from the notification list database 1404 based on the risk index output data 1300 and the asset attribute data 1401.

Next, in step S1406, the notification selected in step S1402 may be modified based on modification variables 1409 related to the target environment. Here, the modification variables 1409 may include predefined characteristics such as place name, object name, time period, activity, notification target, notification type, etc., used to adapt the notification to a specific target environment or a specific asset. As an example, a predefined notification of "Disinfect 'Object C' because {Area A} was used by {Person B}" may be modified based on the modification variables, with the generic placeholders for {Area A}, {Person B}, and {Object C} being replaced with the specific attributes of the specific target environment. As a result of this modification, the predefined notification may become "Disinfect 'Table' because {Eat-in area} was used by {Customer}". In this way, each of the predefined notifications selected in step S1402 may be customized to correspond to a specific target environment. The modified notification may be output as an action notification 1407.

Next, in step S1410, a notification check is performed to determine whether notification 1407 contains redundancy (e.g., the same notification repeated for different assets located in the same area, the same notification repeated within a short period of time, the same notification repeated for the same object). If redundancy is identified in action notification 1407, notification generation process 1400 proceeds to step S1414. However, if redundancy is not identified in action notification 1407, action notification 1407 is output to action notification database 1414 as action notification output 1413. Action notification output 1413 may then be transmitted from action notification database 1414 to one or more information devices in the target environment.

In step S1412, if redundancy is identified in the action notification 1407, one or more notification optimization operations may be performed to reduce the redundancy. As an example, performing the notification optimization operations may include using natural language processing techniques to determine semantic or syntactic similarity of multiple notifications in the action notification 1407 and removing redundant notifications that achieve a threshold of semantic or syntactic similarity. As another example, performing the notification optimization operations may include filtering the action notification 1407 to remove similar notifications that are output to the same destination within a predetermined period of time (e.g., 5 minutes, 10 minutes, 30 minutes). After the notification optimization operations are completed, the modified action notification may be output to the action notification database 1414 as the action notification output 1413. The action notification output 1413 may then be transmitted from the action notification database 1414 to one or more information devices in the target environment.

Notification generation process 1400 shown in FIG. 14 can generate action notifications that indicate recommended actions that are specifically tailored for a particular target environment. These action notifications can be sent to one or more information devices to execute the recommended actions in the target environment to facilitate progressing a first state of an asset (e.g., a state associated with a high level of risk) toward a goal state of the target environment (e.g., a state associated with a lower level of risk).

Next, referring to FIG. 15, an example of notification selection criteria, notification destinations, and a notification list database will be described.

As described herein, notification selection criteria 1403 and notification list database 1404 can be used in conjunction with risk quotient output data and asset attribute data extracted from the risk output database to select predefined notifications for modification and subsequent transmission to notification targets. FIG. 15 illustrates an example of notification selection criteria 1403, notification target data 1510, and notification list database 1404.

The notification list database 1404 includes a collection of predefined notification candidates, which may include natural language sentences or phrases that indicate recommended actions to reduce risk to specific assets in the target environment.
The notification selection criteria 1403 may include a set of standards, rules, thresholds, guidelines, or rubrics that define which predefined notifications in the notification list database 1404 apply to a particular asset based on risk type, risk index, risk level, asset type, asset subtype, etc.
Notification target data 1510 defines the target asset for which the action notification is to be sent.

As shown in FIG. 15, notification selection criteria 1403 may include risk type, such as congestion, disinfection, cleaning (abbreviated as “c”, “d”, “s” in FIG. 15), risk index, risk level, asset type, asset subtype, units of measurement for quantifying risk, etc.
The notification target data 1510 may define the target asset, such as "customer,""staff," or "management," the notification category, and the number of times notifications have been sent to this target asset. In some embodiments, the notification target data 1510 may include address information for an information device corresponding to the target asset.
The notification list database 1404 may include action notifications formulated in natural language. In some embodiments, the action notifications may be structured in a variable format that can be modified based on the change variables described above to customize the action notifications to a particular target environment. By way of example, predefined notification candidates may include "Do not gather in groups", "Staff in this area are at higher risk. Rotate staff regularly", etc.

15, each action notification in the notification list database 1404 corresponds to a subset of the notification target data 1510 and the notification selection criteria 1403. In this manner, based on the notification selection criteria 1403, an appropriate action notification can be selected from the notification list database 1404 along with the risk index output data and asset attribute data (not shown in FIG. 15) and forwarded to the information device of the target asset specified by the notification target data 1510. As an example, the risk notification selection criteria 1403 may indicate that a risk type with "disinfection" with a risk index of "0.80" for an asset type with "staff" corresponds to an action notification of "Staff in this area are at higher risk. Rotate staff regularly." This action notification may be sent to the information device of an administrator in the target environment as specified by the notification target data 1510.

Next, the overall flow of the tracking evaluation process according to an embodiment of the present disclosure will be described with reference to FIG.

16 is a flow chart illustrating a tracking evaluation process 1600 according to an embodiment of the present disclosure. The tracking evaluation process 1600 can be used to evaluate the effectiveness of a recommended action indicated by an action notification sent to an information device of one or more assets in a target environment.
The tracking evaluation process 1600 shown in Figure 16 corresponds substantially to step S712 of the data evaluation process 700 shown in Figure 7. The tracking evaluation process 1600 may be performed by a tracking evaluation device of the data evaluation device.

In step S1610, the effectiveness of each recommended action 1602 in the action notification output 1413 is evaluated using a transfer function based on the second sensor data 1605 collected by the sensor device 210 and the information device 220.
As described herein, the second sensor data 1605 may include any type or form of data collected by the sensor 210 or the information device 220. For example, the second sensor data may include images or video showing the asset, biometric data of the asset, environmental data about the target environment (e.g., temperature data, humidity data), etc. In some embodiments, the second sensor data 1605 may be data collected specifically about a subset of assets affected by the recommended action indicated by the action notification output 1413. Additionally, the second sensor data 1605 may be data collected by a monitoring operation performed by the sensor device 210 or data manually entered into the information device 220 by a living asset (e.g., staff using a smart device to enter information).

In some embodiments, the transfer function may be configured to use a machine learning processing technique to process the second sensor data 1605 based on the second assessment criteria to derive a second state of the asset set in the target environment. The second state of the asset may include a risk index of the asset in the target environment and may be determined according to the environmental risk assessment process 800 and the life asset risk assessment process 1100 described above. Furthermore, in some embodiments, the second state of the asset may be determined based on the behavior of the asset in the target environment, the environmental changes that occurred in the target environment, or the business activities that took place in the target environment after transmitting the action notification output 1413 to the information device 220. The identified behavior, environmental changes, or business activities may be associated with a particular recommended action 1602 from the action notification output 1413. The second state may be compared to a target state of the target environment to quantify the effectiveness level of the recommended action. Details of the transfer function are described with reference to FIG. 17.

In an embodiment, the transfer function may be used to generate the remediation factor 1612. Here, the remediation factor 1612 may include information specifying changes to the evaluation criteria 807 (e.g., the evaluation criteria used to determine the risk index for the assets in the target environment), the risk index stored in the risk output database 821, or the notification selection criteria 1403 based on the effectiveness level of the recommended action. For example, the remediation factor 1612 may adjust the weight of a cluster associated with a particular type of risk so that a higher risk index is assigned to this particular type of risk. As another example, the remediation factor 1612 may increase or decrease the risk index assigned to a particular type of risk in the risk output database 821 based on the effectiveness level of the recommended action (e.g., a risk for which there is a recommended action with high effectiveness can be assigned a lower risk index). As yet another example, the remediation factor 1612 may correct the notification selection criteria 1403 to change the type of recommended action selected for a particular risk (e.g., if the recommended action indicated by the action notification is invalid, the action notification may be changed to suggest a different recommended action).

The tracking evaluation process 1600 shown in FIG. 16 can evaluate the effectiveness level of the recommended actions indicated by the action notifications sent to the information devices of one or more assets in the target environment, and can generate corrective factors for updating the risk index, evaluation criteria, or notification selection criteria to improve the performance of the risk evaluation process.

Next, the overall flow of the transfer function according to an embodiment of the present disclosure will be described with reference to FIG.

17 is a flow chart illustrating a transfer function process 1700 according to an embodiment of the present disclosure. The transfer function process 1700 can be used to evaluate the level of effectiveness of a recommended action indicated by an action notification sent to an information appliance of one or more assets in a target environment and generate a corrective factor based on the effectiveness of the recommended action.
The transfer function process 1700 shown in Figure 17 corresponds substantially to step S1610 of the tracking evaluation process 1600 shown in Figure 16. The transfer function process 1700 may be performed by a tracking evaluation unit of a data evaluation device.

First, in step S1705, a second state of the asset in the target environment may be determined based on the second sensor data 1605 and the second evaluation criteria 1702. The second state refers to the state of the asset at a second time point corresponding to when the second sensor data 1610 is collected. As an example, the second state may include a risk index indicating a quantitative indication of the risk of the asset. As described above, the risk index may be a total risk index calculated from the non-living asset risk index and the animate asset risk index determined for the asset based on the second sensor data 1605 and the second evaluation criteria 1702.
The second evaluation criteria 1702 may include standards, rules, thresholds, weights, guidelines, or rubrics for evaluating the second sensor data 1605 and determining the second state of the asset, where, as described herein, determining the second state of the asset may include performing stepwise clustering and weighting on the second sensor data 1605 to classify the asset into one of several predefined states (e.g., “congested,” “not congested,” “disinfected,” etc.).

In step S1710, a goal state is determined for the asset. Here, the goal state refers to a desired appearance of the asset (e.g., a risk index below a threshold, productivity above a threshold). In some embodiments, the goal state may be determined based on an action notification output to the asset and included in the action notification database 1414, and environmental variables 1707 included in the goal state database 1704. Here, the goal state database 1704 may include a collection of information about the target environment for use in conjunction with the recommended action 1706 to derive a goal state for a particular asset. By way of example, the goal state database 1704 may include information about the physical configuration of the target environment (e.g., the spacing between shopping aisles in a supermarket), occupancy rate, hygiene level, temperature, humidity, etc. Based on the environmental variables 1707 and the recommended action 1706, the goal state of the asset may be determined.

Next, in step S1715, an effectiveness level 1717 of the recommended action may be determined by comparing the second state of the asset determined in step S1705 with the target state of the asset determined in step S1710. Here, the effectiveness level 1717 may be expressed as a percentage value in the range of 0-100%, where a lower value indicates a lower degree of effectiveness and a higher value indicates a higher degree of effectiveness. As an example, in an embodiment, a similarity between the second state and the target state may be calculated and the effectiveness level 1717 may be determined based on the similarity between the second state and the target state, where a higher similarity indicates a higher effectiveness and a lower similarity indicates a lower effectiveness.

Next, in step S1718, a confidence level of the validity result 1717 is determined. The confidence level indicates a level of certainty of the validity 1717. In one embodiment, the confidence level of the validity result may be determined based on a measurement error of the second sensor data 1605 used to determine the second state of the asset. If the confidence level reaches a predetermined confidence threshold, the transfer function process 1700 proceeds directly to step S1722. If the confidence level does not reach a predetermined confidence threshold, the transfer function process 1700 proceeds to step S1720 for user evaluation.

In step S1720, a user evaluation of the effectiveness level 1717 is performed. More specifically, the effectiveness level 1717 may be displayed on an information device used by a particular user (e.g., a staff member, an administrator, or a supervisor) at the asset, and the user may verify the accuracy of the effectiveness level 1717. For example, the user may provide input indicating whether the effectiveness level 1717 accurately represents his or her sense of the effectiveness of the recommended action, or information to adjust the effectiveness level 1717 (e.g., increase or decrease).

Next, in step S1722, a remediation factor 1612 may be determined based on the effectiveness level 1717. As described herein, the remediation factor 1612 may include information specifying changes to the first evaluation criteria, the risk quotient stored in the risk output database 821, or the notification selection criteria. In an embodiment, determining the remediation factor 1612 may include increasing or decreasing a risk quotient associated with a particular risk in proportion to the effectiveness level 1717, such that the risk quotient is increased for risks where the effectiveness was low (e.g., below a threshold) and the risk quotient is decreased for risks where the effectiveness was high (e.g., above a threshold).

The transfer function process 1700 shown in FIG. 17 can evaluate the level of effectiveness of a recommended action indicated by an action notification sent to an information device of one or more assets in a target environment, and can generate a corrective factor for updating a risk index, evaluation criteria, or notification selection criteria to improve the performance of the risk assessment process.

Next, referring to FIG. 18, a table showing an example of various values used in the transfer function process 1700 will be described.

Figure 18 shows tables 1810-1850 showing examples of various values used in transfer function processing according to an embodiment of the present disclosure.

Table 1810 shows ranges of values for correction factor 1812, risk index 1813, cumulative risk index 1814, and asset payload 1815. For example, table 1810 may define minimum and maximum values for each of correction factor 1812, risk index 1813, cumulative risk index 1814, and asset payload 1815.

Table 1820 shows the relationship between the recommended actions and the asset activities that are triggered by the recommended actions and are performed by the assets in the target environment. For example, if there are three recommended actions, recommended action 1 1822, recommended action 2 1824, and recommended action 3 1826, table 1820 may show that recommended action 1 1822 corresponds to the third asset activity 1829, recommended action 1824 corresponds to the first asset activity 1827, and recommended action 3 1826 corresponds to the second asset activity 1828, but the results are ambiguous.

Table 1830 shows the relationship between environmental variables and recommended actions in the target environment. For example, as shown in table 1830, recommended action 1 1822 may have an average inactivity time of 5 minutes 1838 and a headcount limit of 7 people 1839, recommended action 2 1824 may take place in an area/location 1 meter from a window, and a third recommended action 3 1826 may have an uncertain average inactivity time 1838 and a headcount limit of 6 people 1839.

Table 1840 shows the effectiveness of each recommended action in several regions. For example, as shown in table 1840, recommended action 1 1822 is 50% effective in the third region 1849 (i.e., needs to be retried), recommended action 2 1824 is 100% effective in the first region 1847, and recommended action 3 1826 is 30% effective in the second region 1848 (i.e., needs user check).

Table 1850 shows a certainty status 1851, a correction factor 1852, and an updated cumulative risk index 1853 for each of recommended actions 1822, 1824, and 1826. For example, the certainty status 1851 may show a certainty status 1851 for recommended action 2 1824, a certainty status 1851 for recommended action 1 1822, and an uncertain status 1851 for recommended action 3 1826. The correction factor may show a correction factor of 0 for recommended action 2 1824, 0.5 for recommended action 1 1822, and 0.3 for recommended action 3 1826. The updated cumulative risk index 1853 may show an updated cumulative risk index of 0.0 for recommended action 2 1824, 0.5 for recommended action 1 1822, and 0.3 for recommended action 3 1826.

Next, an example of a parameter setting process according to an embodiment of the present disclosure will be described with reference to FIG.

As described herein, in embodiments of the present disclosure, various parameters are used to quantify, categorize, weight, and evaluate information. For example, as described herein, thresholds 808 and weights 809 are used to quantify a first state (e.g., risk index) of an asset in a target environment (see FIG. 8), a cumulative criterion 815 is used to define how the risk index changes over time (see FIGS. 8 and 11), a severity definition 817 is used to evaluate the severity of a risk associated with a given risk index (see FIGS. 8 and 11), and a target state of the target environment may be defined based on a number of environmental variables 1707 (see FIG. 17). FIG. 19 is a flowchart illustrating an example of a parameter setting process 1900 according to an embodiment of the present disclosure.

In some embodiments, parameters according to the present disclosure may be generated based on definitions or guidelines provided by a target environment administrator and definitions provided by an official agency. Thus, in step S1920, target environment administrator parameter definitions 1905 and official agency parameter definitions 1910 may be received.
The target environment manager parameter definition 1905 may define a specific value for a particular parameter (e.g., a value of "20" for the maximum number of people in the target environment at the same time) or may indicate a general requirement for the target environment (e.g., preventing congestion around the accounting area). The target environment manager parameter definition 1905 may be input directly to the data evaluator via an information device (e.g., an information device having an information identifier authenticated as being owned by the target environment manager).
Official agency parameter definition 1910 may include qualitative or quantitative rules, standards, or guidelines from an official agency (e.g., a public health department, a chemical agency, an engineering code or standard) that provide information for defining parameters used to perform one or more methods or processes according to embodiments of the present disclosure. As an example, official agency parameter definition 1910 may include a guideline from a public health department stating that a distance of two meters between individuals should be maintained to prevent the spread of infectious diseases.

The received target environment administrator parameter definitions 1905 and public agency parameter definitions 1910 may be aggregated, formalized, filtered, analyzed, and structured according to a number of existing statistical techniques to generate global parameters 1930 that are applicable to multiple target environments. These global parameters 1930 may further be modified based on the specific conditions or goals of a particular target environment.

Therefore, the various parameters used in the processes disclosed herein can be set appropriately based on both information from public institutions and input provided by the administrator of the target environment.

According to the present disclosure described above, it is possible to provide an apparatus, method, and system for data evaluation that can generate recommended actions to progress an environment toward a goal state based on the environment and the mutual influence of the assets in the environment, and evaluate the effectiveness of the recommended actions. The data evaluation means according to the embodiment of the present disclosure can be used for various purposes, such as identifying potential risks that may adversely affect service operations, and productivity evaluation that seeks to identify areas of potential growth or improvement. When used for risk evaluation, the data evaluation means according to the present disclosure can provide a risk evaluation for the target environment, which is used, for example, to mitigate risks to customers and employees of the target environment. Further applications of data evaluation for risk evaluation may include crime prevention, equipment failure, infection prevention, health management, and the like.
Furthermore, as described herein, the data assessment means of the present disclosure may be suitably adapted for productivity assessment, where the data assessment means is capable of performing data assessment to determine a productivity level of an asset, generate recommended actions for improving the productivity level of the asset, and assess a level of effectiveness of the recommended actions.

The present invention may be a system, a method, and/or a computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions for causing a processor to perform aspects of the present invention.

A computer readable storage medium may be a tangible device capable of holding and storing instructions for use by an instruction execution device. A computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer readable storage media includes: portable computer diskettes, hard disks, random access memories (RAMs), read only memories (ROMs), erasable programmable read only memories (EPROMs or flash memories), static random access memories (SRAMs), portable compact disk read only memories (CD-ROMs), digital versatile disks (DVDs), memory sticks, floppy disks, mechanically encoded devices such as punch cards or raised structures with instructions recorded within grooves, and any suitable combination of the foregoing.
As used herein, a computer-readable storage medium should not be construed as being a transitory signal per se, such as an electric wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., light pulses passing through a fiber optic cable), or an electrical signal transmitted through a wire.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams that illustrate methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.

These computer-readable program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing device, and executed via the processor of the computer or other programmable data processing device to provide a machine that provides means for implementing the functions/operations specified in one or more blocks of the flowcharts and/or block diagrams. These computer-readable program instructions may be stored on a computer-readable storage medium that can instruct a computer, programmable data processing device, and/or other device to function in a particular manner, such that the computer-readable storage medium on which the instructions are stored is an article of manufacture that includes instructions that implement aspects of the functions/operations specified in a block or blocks of the flowcharts and/or block diagrams.

The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be executed on the computer, other programmable apparatus, or other device, such that the instructions executing on the computer, other programmable apparatus, or other device perform the functions/operations specified in one or more blocks of the flowcharts and/or block diagrams, to generate a computer-implemented process.

Embodiments of the present disclosure may be provided to end users via a cloud computing infrastructure. Cloud computing generally refers to the provision of scalable computing resources as a service over a network. More formally, cloud computing may be defined as a computing capability that provides an abstraction between computing resources and their underlying technical architecture (e.g., servers, storage, networks), enabling convenient, on-demand network access to a shared pool of configurable computing resources that can be rapidly deployed and released with minimal administrative effort or service provider intervention. Thus, cloud computing allows users to access virtual computing resources (such as storage, data, applications, and even complete virtualized computing systems) in the "cloud" regardless of the underlying physical systems (or the location of those systems) used to provide the computing resources.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, segment, or part of an instruction, comprising one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions described in the blocks may be executed in a different order than that described in the figures. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may be executed in the reverse order, depending on the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart diagrams, and combinations of blocks in the block diagrams and/or flowchart diagrams, may be implemented by a special purpose hardware-based system that executes the specified functions or operations, or executes a combination of special purpose hardware and computer instructions.

The above is directed to exemplary embodiments, however, other/further embodiments of the present invention may be devised without departing from the basic scope of the present invention, the scope of the present disclosure being defined by the following claims. The description of various embodiments of the present disclosure has been presented for purposes of illustration, but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terms used in this specification have been selected to explain the principles of the embodiments, practical applications or technical improvements to the technology found in the market, or to enable those skilled in the art to easily understand the embodiments disclosed herein.

The terms used herein are for the purpose of describing particular embodiments only and are not intended to be limiting of the various embodiments. As used herein, the singular forms "a", "an", and "the" are intended to include the plural unless the context clearly indicates otherwise. A "set", "group", "part", and the like are intended to include one or more. As used herein, the terms "comprise" and/or "may include" specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof. In the foregoing detailed description of exemplary aspects of the various embodiments, reference is made to the accompanying drawings, which are a part of this specification and in which like reference numerals represent like elements, showing by way of example specific exemplary embodiments for practicing the various aspects.
Reference has been made to the above-mentioned references. Although these embodiments have been described in sufficient detail to enable one skilled in the art to practice the embodiments, other embodiments may be used, and logical, mechanical, electrical changes, and the like, may be made without departing from the scope of the various embodiments. In the above description, numerous specific details are set forth in order to provide a thorough understanding of the various embodiments. However, the various embodiments may be practiced without these specific details. Also, in other places, well-known circuits, structures, and techniques have not been shown in detail so as not to obscure the embodiments.

200 Data evaluation system 210 Sensor 220 Information device 225 Communication network 230 Data evaluation device 231 Data receiving unit 232 Evaluation unit 233 Notification generating unit 234 Notification output unit 235 Tracking data receiving unit 236 Tracking evaluation unit

Claims (10)

a data receiving unit that receives first sensor data related to an asset in a target environment from a sensor installed in the target environment;
an evaluation unit that generates a first evaluation result indicative of a discrepancy of the first state of the asset with respect to a target state of the asset by analyzing the first sensor data based on a first evaluation criterion that defines a threshold for quantifying a first state of the asset;
a notification generating unit configured to generate an action notification indicating a recommended action for progressing the first state of the asset toward a target state of the asset based on the first evaluation result;
a notification output unit that outputs the action notification to an information device that can be used by one or more of the assets;
a tracking data receiver configured to receive second sensor data related to the asset in the target environment from one or more of the sensor and the information device;
a tracking evaluator configured to generate a second evaluation result indicative of a level of effectiveness of the recommended action by analyzing the second sensor data based on a second evaluation criterion that defines a threshold for quantifying a second state of the asset; and
A data evaluation device comprising:
the first evaluation result indicates a risk index of the asset;
The risk index includes a non-living asset risk index and a living asset risk index;
the recommended actions include risk reduction actions to reduce the risk quotient of the asset;
the second assessment result indicates a level of effectiveness of the risk reduction action in reducing the risk quotient of the asset;
The goal state includes a state associated with a risk index that achieves a predetermined safety threshold.
A data evaluation device comprising: The evaluation unit is
extracting a first asset payload from the first sensor data, the first asset payload including information about a non-living asset of the asset;
classifying the first asset payload based on predetermined non-living asset attribute data;
grouping the first asset payloads into clusters based on a threshold defined by the first evaluation criterion;
weighting the clusters based on weights defined by the first evaluation criterion;
calculating the non-living asset risk quotient for the non-living assets based on the weights and the clusters;
2. The data evaluation device according to claim 1 . The evaluation unit is
extracting a second asset payload from the first sensor data, the second asset payload including information regarding a living organism asset of the asset;
classifying the second asset payload based on predetermined life form asset attribute data;
calculating the animate asset risk quotient for the animate asset based on the non-animate asset risk quotient and a spatial relationship between the animate asset and the non-animate asset;
3. The data evaluation device according to claim 2 . The notification generation unit,
selecting a first notification candidate from the notification list database based on the risk quotient for the asset, a notification list database including a set of predefined notification candidates, and notification selection criteria defining a relationship between the predefined notification candidates and the asset;
generating the action notification by modifying the first notification candidate based on modification variables to adapt the notification candidate to the target environment;
modifying the action notification by removing candidate actions that achieve a redundancy threshold;
4. The data evaluation device according to claim 3 . The tracking evaluation unit is
determining the target state of the asset based on environmental variables related to the target environment and the recommended action;
Calculating the effectiveness level of the recommended action by comparing the target state of the asset to the second state of the asset;
determining a remediation factor for updating any one of the first evaluation criteria, the notification selection criteria, and the risk index of the asset based on the effectiveness level of the recommended action;
5. The data evaluation device according to claim 4 . and a visualization unit configured to generate a hazard map for the target environment based on the risk index;
The notification output unit transmits the hazard map to the information device.
6. The data evaluation device according to claim 5 . the first assessment result being indicative of a productivity level of the asset;
the recommended actions include productivity actions for increasing the productivity level of the asset;
the goal state includes a state associated with a productivity level that achieves a predetermined productivity threshold;
2. The data evaluation device according to claim 1 . A data evaluation method for a data evaluation device including a data receiving unit, an evaluation unit, a notification generating unit, a notification output unit, a tracking data receiving unit, and a tracking evaluation unit ,
The data receiving unit receives first sensor data related to an asset in a target environment from a sensor installed in the target environment;
generating a first evaluation result indicative of a discrepancy of the first state of the asset with respect to a target state of the asset by analyzing the first sensor data based on a first evaluation criterion defining a threshold for quantifying a first state of the asset;
generating an action notification indicating a recommended action for progressing the first state of the asset toward a goal state of the asset based on the first assessment result;
the notification output unit outputs the action notification to an information device usable by one or more assets among the assets;
receiving , by the tracking data receiver, second sensor data related to the asset in the target environment from one or more of the sensor and the information device;
generating a second evaluation result indicative of a level of effectiveness of the recommended action by analyzing the second sensor data based on a second evaluation criterion defining a threshold for quantifying a second state of the asset;
Including,
the first evaluation result indicates a risk index of the asset;
The risk index includes a non-living asset risk index and a living asset risk index;
the recommended actions include risk reduction actions to reduce the risk quotient of the asset;
the second assessment result indicates a level of effectiveness of the risk reduction action in reducing the risk quotient of the asset;
The goal state includes a state associated with a risk index that achieves a predetermined safety threshold.
A data evaluation method comprising: A sensor installed in a target environment to collect information about the target environment and assets located in the target environment;
a data evaluator for evaluating the validity of actions to be performed in the target environment;
an information device usable by one or more assets and configured to communicate data with the data evaluator;
the sensor, the data evaluation device, and the information device are communicatively connected via a communication network;
The data evaluation device includes:
a data receiving unit that receives first sensor data related to an asset in the target environment from the sensor installed in the target environment;
an evaluation unit that generates a first evaluation result indicative of a discrepancy of the first state of the asset with respect to a target state of the asset by analyzing the first sensor data based on a first evaluation criterion that defines a threshold for quantifying a first state of the asset;
a notification generating unit configured to generate an action notification indicating a recommended action for progressing the first state of the asset toward a target state of the asset based on the first evaluation result;
a notification output unit that outputs the action notification to the information device;
a tracking data receiver configured to receive second sensor data related to the asset in the target environment from one or more of the sensor and the information device;
a tracking evaluator configured to generate a second evaluation result indicative of a level of effectiveness of the recommended action by analyzing the second sensor data based on a second evaluation criterion that defines a threshold for quantifying a second state of the asset; and
A data evaluation system comprising:
The notification output unit is
providing a registration interface to said information appliance;
receiving a registration request from a first one of the information devices via the registration interface;
registering the first information device as a registered information device in the registered information device;
outputting the action notification to the registered information device;
The data evaluation device includes:
generating a third evaluation result indicating an effectiveness level of a second recommended action in the second target environment by analyzing third sensor data received from a second sensor installed in a second target environment different from the target environment;
generating an action notification indicating a recommended action for progressing the first state of the asset toward a goal state of the asset in the target environment based on the third assessment result;
A data evaluation system comprising: The tracking data receiving unit is
providing a data collection interface to the registered information device;
receiving information indicating an effectiveness level of the recommended action as the second sensor data from the registered information device;
10. The data evaluation system according to claim 9 .

Images