WO2020105154A1 - Data analysis system and data analysis method - Google Patents

Data analysis system and data analysis method

Info

Publication number
WO2020105154A1
WO2020105154A1 PCT/JP2018/043053 JP2018043053W WO2020105154A1 WO 2020105154 A1 WO2020105154 A1 WO 2020105154A1 JP 2018043053 W JP2018043053 W JP 2018043053W WO 2020105154 A1 WO2020105154 A1 WO 2020105154A1
Authority
WO
WIPO (PCT)
Prior art keywords
person
data
environmental
data analysis
mathematical model
Prior art date
Application number
PCT/JP2018/043053
Other languages
French (fr)
Japanese (ja)
Inventor
聡美 辻
信夫 佐藤
Original Assignee
株式会社日立製作所
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社日立製作所 filed Critical 株式会社日立製作所
Priority to JP2020557089A priority Critical patent/JPWO2020105154A1/en
Priority to PCT/JP2018/043053 priority patent/WO2020105154A1/en
Publication of WO2020105154A1 publication Critical patent/WO2020105154A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Definitions

  • the present invention relates to a technique for recommending an effective work space for a business purpose based on sensor data of people and the environment.
  • Patent Document 1 discloses a technique of using such data to provide work style advice for increasing a behavior index related to productivity of work.
  • Patent Document 1 JP-A-2017-200805
  • Office workers have various business purposes depending on the situation, such as wanting to concentrate on writing and talking with colleagues to come up with ideas.
  • the work space suitable for each purpose is different. For example, a quiet space may be preferable to concentrate on writing, and a noisy space or an outdoor space may be preferable to generate an idea.
  • the environment of the office specifically, room temperature, illuminance, environmental sound, and the number of people change in real time.
  • the characteristics of the space where it is easy to obtain an effect differ depending on the personality and state of the person. Therefore, staying in a specific area does not always provide the same productivity. Therefore, it is useful to dynamically match people and work spaces by reflecting the situation at each moment.
  • an object of the present invention is to provide a system that recommends an effective work space for a business purpose based on sensor data of people and the environment.
  • a typical example of the means for solving the problems according to the present invention is a data analysis system, which is a mathematical expression showing the relationship between a target index related to the productivity of a person and an environmental index related to the environment of the activity place of the person.
  • a storage unit that holds a model, environment data that is data about the environment of a person's activity place acquired from a sensor, and business goal data including a goal related to the activity of the person input by the person are accepted, and the business goal is received.
  • Based on the data and the mathematical model to search the conditions of the environmental index suitable for increasing the productivity of the person, based on the environmental index conditions and the environmental data, the productivity of the person
  • a recommendation processing unit that searches for information about an activity place suitable for enhancing and outputs information about the activity place obtained by the search.
  • FIG. 1 It is a sequence diagram which shows the procedure of the sensing performed in a wearable sensor, an environment measuring device, and a surveillance camera in the learning phase of embodiment of this invention, and the procedure until it stores the data in an analysis server.
  • the procedure of generating a mathematical model performed in the analysis server and the procedure of copying, extracting or integrating the mathematical model DB of the analysis server to update the mathematical model DB of the application server are described.
  • FIG. 9 is a sequence diagram showing a procedure in which an application server generates a recommendation and presents it on a screen with respect to a business goal input by a user operating a client in the operation phase of the exemplary embodiment of the present invention.
  • It is explanatory drawing which shows an example of a structure of the objective variable table contained in mathematical model DB of embodiment of this invention.
  • It is explanatory drawing which shows an example of a structure of the mathematical model table table contained in mathematical model DB of embodiment of this invention.
  • the present invention is a system that recommends an effective work space in real time for business purposes, and is characterized by using sensor data that measures the situation of people and the environment.
  • FIG. 1 is an explanatory diagram showing an outline of a real-time office space utilization recommendation system according to an embodiment of the present invention.
  • a learning phase for creating a mathematical model
  • an operating phase for operating the office space utilization recommendation system using the mathematical model
  • the learning phase consists of a wearable sensor (IR), environment measuring device (EM), surveillance camera (SC) and analysis server (SS).
  • IR wearable sensor
  • EM environment measuring device
  • SC surveillance camera
  • SS analysis server
  • the surveillance camera (SC) is not an essential component.
  • US wears wearable sensor
  • TR wearable sensor
  • a sensor that measures a physical quantity in the wearable sensor (TR) acquires sensing data regarding the movement of the wearer and sensing data regarding interaction with another wearer (for example, face-to-face or proximity state).
  • the wearable sensor (TR) has a triaxial acceleration sensor (not shown), and the triaxial acceleration data measured by the wearable sensor (TR) is used as sensing data relating to the motion of the wearer, but other types of sensors measure it. Other physical quantities may be used.
  • the interaction is detected, for example, by transmitting and receiving an infrared signal or another wireless signal between the wearable sensors (TR) when the users (US) face each other. Further, the infrared beacon (IB) installed on the desk or the like and the wearable sensor (TR) communicate with each other, so that the sensing data regarding the place and time when the user (US) stays can be acquired. These acquired sensing data are stored in the analysis server (SS) through a wireless or wired network (NW).
  • SS analysis server
  • NW wireless or wired network
  • an environment measuring machine that mainly measures the environment of the indoor (outdoor may be included) at a predetermined timing (for example, at regular intervals) is installed.
  • the environment measuring machine (EM) has a sensor group (for example, a temperature sensor, a humidity sensor, a noise measuring machine, etc., but other means may be used) for measuring the state of the space, and uses them.
  • the acquired sensing data is stored in the analysis server (SS) through a wireless or wired network (NW).
  • a video or still image showing the space situation is recorded by a surveillance camera (SC) installed on the wall or ceiling of the work space, and stored in the analysis server (SS) via a wireless or wired network (NW).
  • SC surveillance camera
  • SS analysis server
  • NW wireless or wired network
  • the analysis server (SS) extracts the feature amount related to the behavior from the data from the wearable sensor (TR), and generates the feature amount related to the environment from the data from the environment measuring device (EM) and the data from the monitoring camera (SC). , Combine and perform statistical analysis.
  • the analysis server (SS) uses behavior characteristic quantities related to human work performance, for example, other characteristic characteristic quantities and environmental characteristics that are statistically related to the objective variable such as the concentration duration or the conversation interactivity. Figure out the amount.
  • the analysis server (SS) stores the combination between the feature quantities in the mathematical model DB (SSME_MD).
  • the operation phase is composed of application server (AS), client (CL), environment measuring machine (EM) and surveillance camera (SC).
  • AS application server
  • CL client
  • EM environment measuring machine
  • SC surveillance camera
  • the operation phase may further include a wearable sensor (TR), but for the sake of simplicity, the explanation will be given with a configuration not included in the present invention.
  • Mathematical model DB (SSME_MD) in the analysis server (SS) is manually or automatically copied to the mathematical model DB (ASME_MD) in the application server (AS) at a specific timing. Further, the sensing data of the environment measuring machine (EM) and the monitoring camera (SC) are stored in real time in the work space information DB (ASME_SD) in the application server (AS).
  • the application server searches the mathematical model DB (ASME_MD) to obtain the purpose.
  • the environmental features that match the above are picked up, and from the data of the latest time included in the work space information DB (ASME_SD), the area showing the state closest to the picked up environmental features is displayed as a recommendation on the display (CLOD). To do.
  • FIG. 2A, FIG. 2B System configuration diagram of learning phase> 2A and 2B are block diagrams showing an example of configurations of an analysis server (SS), an environment measuring device (EM), a wearable sensor (TR), and a surveillance camera (SC) in a learning phase according to the embodiment of the present invention. is there.
  • SS analysis server
  • EM environment measuring device
  • TR wearable sensor
  • SC surveillance camera
  • the environment measuring machine is a device including a group of sensors for measuring an indoor or outdoor environment, and includes a sensor unit (EMSE), a storage unit (EMME), a battery (EMBT), a control unit (EMCO) and It has a transceiver unit (EMSR).
  • EM sensor unit
  • EMME storage unit
  • EMBT battery
  • EMCO control unit
  • MSR transceiver unit
  • sensors included in the sensor unit include a temperature sensor (EMSE_T), a humidity sensor (EMSE_H), and a noise measuring device (EMSE_S) that measures environmental sounds.
  • a sensor (not shown) for measuring the CO2 concentration in the air may be included.
  • the sensor unit may include a group of outdoor environment measuring instruments (EMSE_O) for measuring the amount of rainfall and the amount of sunlight.
  • the storage unit (EMME) also stores a clock (EMCK) that holds time information, terminal ID information (EMID) that identifies the environment measuring machine (EM), and sensing data (EMME_S) that is the measurement result. Further, the environment measuring machine (EM) has a battery (EMBT) for securing a power source.
  • EMCK clock
  • EMID terminal ID information
  • EME_S sensing data
  • control unit controls sensing and transmission / reception. Specifically, the control unit (EMCO) controls the sensor of the sensor unit (EMSE) by time synchronization (EMCO_T) that synchronizes the time information in the clock (EMCK) with the standard time, acquires the data related to the environment, and acquires the time information. Sensing control (EMCO_S) to be given and data transmission (EMSD) for transmitting the data to the analysis server (SS) via the transmission / reception unit (EMSR) are performed.
  • EEMCO_T time synchronization
  • ESD data transmission
  • SS analysis server
  • MSR transmission / reception unit
  • the wearable sensor is a sensor for measuring human behavior and state, and includes a sensor unit (TRSE), an input / output unit (TRIO), a storage unit (TRME), a battery (TRBT), and a control unit (TRCO). And a transceiver (TRSR).
  • TRSE sensor unit
  • TEO input / output unit
  • TRME storage unit
  • TRBT battery
  • TRCO control unit
  • TRSR transceiver
  • it is described as wearable, and it is assumed that it is worn on the body, but if it is a sensor that can measure the equivalent of movement and communication of the human body, it is not worn on the body,
  • a camera, a vibration sensor, a thermometer or the like may be used.
  • an acceleration sensor (TRSE_A) for measuring the movement of the body and a wearable sensor (TR) are used to communicate with each other to detect a face-to-face state or a proximity state between wearers.
  • TRSE_IR infrared transceiver
  • TRSE_L illumination sensor
  • TRSE_H heart rate monitor
  • the wearable sensor (TR) may have an input / output unit (TRIO) for presenting a questionnaire to the user (US) and receiving a response as needed.
  • the function for inputting the questionnaire may be provided in a terminal other than the wearable sensor (TR), such as a PC or a smartphone (not shown).
  • the input / output unit has a screen (TRIO_D) for displaying the questionnaire question and the time, a button (TRIO_B) for the user (US) to input an answer and switch the screen, and a specific It has a speaker (TRIO_S) for prompting the user (US) to answer at the time.
  • the storage unit stores a clock (TRCK) that holds time information, terminal ID information (TRID) that identifies the wearable sensor (TR), sensing data (TRME_S) that is the measurement result, and questionnaire response result data.
  • TRME_Q terminal ID information
  • the wearable sensor has a battery (TRBT) for securing a power source.
  • the control unit controls sensing and transmission / reception. Specifically, the control unit (TRCO) acquires time data (TRCO_T) that synchronizes the time information in the clock (TRCK) with the standard time, controls the sensor of the sensor unit (EMSE), and obtains data on human behavior and state. Sensing control (TRCO_S) that gives time information, questionnaire control (TRCO_Q) that controls the display of questionnaires and input of answers, and data that sends those data to the analysis server (SS) via the transmission / reception unit (TRSR). Perform transmission (TRSD).
  • a surveillance camera is a camera attached to a wall, ceiling, or PC, and is used to record the number and movements of people staying in a space as moving images or still images.
  • the surveillance camera (SC) has a sensor unit (SCSE), a storage unit (SCME), a battery (not shown), a control unit (SCCO), and a transmission / reception unit (SCSR).
  • SCSE sensor unit
  • SCME storage unit
  • SCCO control unit
  • SCSR transmission / reception unit
  • the sensor unit (SCSE) has a camera (SCSE_C).
  • the storage unit (SCME) also stores a clock (SCCK) that holds time information, terminal ID information (SCID) that identifies the surveillance camera (SC), and moving image data (SCME_M) that is the recorded result.
  • SCCK clock
  • SCID terminal ID information
  • SCME_M moving image data
  • the surveillance camera (SC) has a battery (not shown) for securing a power source.
  • control unit controls shooting and transmission / reception, controls time synchronization (SCCO_T) that synchronizes time information in the clock (SCCK) with standard time, and controls camera (SCSE_C) to shoot space ( SCCO_R), and further data transmission (SCSD) of transmitting the captured data to the analysis server (SS) via the transmission / reception unit (SCSR).
  • SCCO control unit
  • SCCO_T time synchronization
  • SCSE_C camera
  • SCSD further data transmission
  • the analysis server (SS) has the role of analyzing the collected data on human behavior and environment and generating a mathematical model of human business performance and environmental conditions.
  • the analysis server (SS) has a transmission / reception unit (SSSR), a storage unit (SSME), and a control unit (SSCO).
  • the storage unit stores terminal management information (SSME_T) that manages terminal IDs and types of environment measuring machines (EM), wearable sensors (TR), surveillance cameras (SC), and the type of space in which they are installed.
  • Area definition information (SSME_A) shown, a program group (SSME_P) for performing feature amount extraction (SSCO_FE), a sensing DB (SSME_SD) that stores the collected sensing data, and a feature amount DB (SSME_FD) that stores the extracted feature amount.
  • SSME_MD mathematical model DB
  • the control unit receives various types of data (SSRD) from the transmission / reception unit (SSSR) via the network (NW), and uses the feature amount extraction program (SSME_P) to set the feature amount according to each data type. Is extracted (SSCO_FE).
  • SSRD transmission / reception unit
  • SSME_P feature amount extraction program
  • Specific examples of the feature amount include those calculated from data obtained from a wearable sensor (TR), such as the number of steps, the average heart rate, the face-to-face time with another person or the number of face-to-face persons, the degree of interaction during conversation, and the acceleration
  • TR wearable sensor
  • An example of the feature amount calculated from the data obtained from the environment measuring machine (EM) is an average room temperature in 5 or 10 minutes, or a discomfort index calculated from temperature and humidity.
  • Examples of the feature amount calculated from the data obtained from the surveillance camera (SC) include the number of people staying in the area where the camera is placed, the ratio of the number of people by attribute of the visitor, and the activity status of the walker or stillness of the visitor. There is.
  • a series of terminals such as environment measuring equipment (EM), wearable sensors (TR), and surveillance cameras (SC) are time-synchronized, data of the same time zone acquired from multiple types of terminals should be combined. Then, for example, a combination feature amount such as “60 steps / minute or more under an area of room temperature of 25 to 28 degrees” may be generated.
  • EM environment measuring equipment
  • TR wearable sensors
  • SC surveillance cameras
  • ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇
  • FIG. 3A and FIG. 3B are block diagrams showing an example of configurations of a client (CL), an application server (AS), an environment measuring machine (EM), and a surveillance camera (SC) in an operation phase according to the embodiment of the present invention. ..
  • the operation phase is a phase for operating the work space utilization recommendation system using the mathematical model generated in the learning phase.
  • the mathematical model DB (ASME_MD) is a copy or integration of the mathematical model DB (SSME_MD) created by the learning phase analysis server (SS), but the workplace to be applied needs to be the same in the learning phase and the operation phase. There is no. In other words, the workplace that collects the data for creating the mathematical model and the workplace that uses the work space utilization recommendation system may be different.
  • the environment measurement device (EM) and the surveillance camera (SC) have the same configuration as the learning phase, so explanations are omitted.
  • the type and model of the sensor need not be exactly the same as in the learning phase, but it is preferable that the range of error and the criteria of the installation location are similar to those used in the learning phase.
  • the destination of the sensing data (EMME_S) and the moving image data (SCME_M) acquired by the environment measuring machine (EM) and the monitoring camera (SC) in the operation phase is the application server (AS), which is different from the learning phase.
  • the application server (AS) has a role of utilizing a mathematical model and performing processing for recommending an area in the work space suitable for the business purpose of the user (US).
  • the application server (AS) has a transmission / reception unit (ASSR), a storage unit (ASME), an environment data processing unit (ASCE), and a recommendation processing unit (ASCO).
  • ASSR transmission / reception unit
  • ASME storage unit
  • ASCE environment data processing unit
  • ASCO recommendation processing unit
  • the storage unit includes terminal management information (ASME_T) that manages terminal IDs and types of environment measuring machines (EM) and surveillance cameras (SC), and area definition information (ASME_A) that indicates the type of space in which they are installed. ), A group of programs (not shown) for performing feature amount extraction (ASCE_FE), a sensing DB (not shown) that stores the collected sensing data, and an office space information DB that manages the latest office space data that is sequentially updated. (ASME_SD) and a mathematical model DB (ASME_MD) copied or partially extracted from the analysis server (SS).
  • ASME_T terminal management information
  • EM environment measuring machines
  • SC surveillance cameras
  • ASME_A area definition information
  • 12A to 12C show an example of the configuration of tables included in the mathematical model DB (ASME_MD) or (SSME_MD).
  • FIG. 12A is an explanatory diagram showing an example of the configuration of objective variable tables (SSME_MD_O) and (ASME_MD_O) included in the mathematical model DBs (ASME_MD) and (SSME_MD) according to the embodiment of this invention.
  • FIG. 12B is an explanatory diagram showing an example of the configuration of the mathematical model table tables (SSME_MD_T1) and (ASME_MD_T1) included in the mathematical model DBs (ASME_MD) and (SSME_MD) according to the embodiment of this invention.
  • FIG. 12A is an explanatory diagram showing an example of the configuration of objective variable tables (SSME_MD_O) and (ASME_MD_O) included in the mathematical model DBs (ASME_MD) and (SSME_MD) according to the embodiment of this invention.
  • FIG. 12B is an explanatory diagram showing an example of the configuration of the mathematical model table tables (SSME_MD_T1) and (ASME_MD_T1) included in the mathematical model DBs (
  • 12C is an explanatory diagram showing an example of a configuration of commentary tables (SSME_MD_E) and (ASME_MD_E) included in the mathematical model DBs (ASME_MD) and (SSME_MD) according to the embodiment of this invention.
  • FIG. 12A shows an example of the structure of the tables (SSME_MD_O) and (ASME_MD_O) that define the objective variables.
  • This is a table in which behavior characteristic quantities and questionnaire items related to human work performance that can be used as objective variables are specified in advance.
  • SSCO_SA statistical analysis
  • FIG. 12B shows an example of the structure of the mathematical model tables (SSME_MD_T1) and (ASME_MD_T1).
  • # 1 is selected as the objective variable
  • ASME_MD_T1 is explanatory variables that are confirmed to be statistically related to the selected objective variable.
  • the environment is in the range of “temperature 23 to 25 ° C.” and the environmental sound is “50 to 60 dB”, and “the speed of thinking by the questionnaire response is 4 to 5”.
  • the intensive duration time is high when “Deskwork_30 minutes or more” is performed in the “high” state.
  • the combination feature amount of the feature amount relating to the environment and the feature amount relating to the human behavior or state is used as the explanatory variable, and the statistical relationship with the specific objective variable is clearly indicated.
  • Statistic amount r in the table is a statistic amount indicating the strength of the relation, and for example, multiple regression coefficient is described. Also, when statistical analysis is performed, the way of interpreting the analysis result changes if attention is paid to the time of the feature amount. It is shown that the objective variable improves while the explanatory variable is in the state of the explanatory variable when the objective variable and the explanatory variable have the same time zone. This is described as During in the analysis type column.
  • the objective variable is selected to come after the explanatory variable, it indicates that the objective variable improves after the explanatory variable state. This is described as After in the analysis type column. Furthermore, when the time division is divided into one day and the data of the objective variable and the explanatory variable of the same date are used, it is shown that the objective variable goes up on the day when there is the state of the explanatory variable. This is described as Day in the analysis type column.
  • a comment sentence table (SSME_MD_E) for storing comment sentences automatically generated based on the values of the table and (SSME_MD_E) is also preferable.
  • FIG. 13 is an explanatory diagram showing an example of the configuration of the office space information DB (ASME_SD) according to the embodiment of this invention.
  • the work space information DB (ASME_SD) is a database for managing the data obtained by the environment measuring device (EM) and the surveillance camera (SC) and the feature amount thereof in association with the time data.
  • the work space information DB (ASME_SD) is associated with the information included in the terminal management information (ASME_T), and the RoomID and time indicating the room or area. It is a table with the key.
  • the work space information DB (ASME_SD) includes temperature, humidity, and volume obtained from an indoor environment measuring instrument (EM), sunshine and rain amounts obtained from an outdoor environment measuring instrument (EM), and a monitoring camera (SC). ) Is a table showing the data of the characteristic amount such as the number of stays obtained from FIG.
  • the work space information DB may further include data indicating the reservation status of a room or area that requires a reservation to use.
  • the reservation system for managing the reservation status of the room or area is operating independently of the real-time office space utilization recommendation system. May store data indicating the reservation status read from the reservation system in the work space information DB (ASME_SD), or the work space information DB (ASME_SD) may not store the data indicating the reservation status.
  • the reservation system may be referred to as necessary.
  • a room or area in which the time zone that the user wants to use has already been reserved may be excluded from the target presented to the user.
  • FIG. 14 is an explanatory diagram showing an example of the configuration of the area definition information (SSME_A) and (ASME_A) according to the embodiment of this invention.
  • Area definition information is a table for managing information about the characteristics of the area and room in the workplace where the measurement is performed.
  • a room and an area other than the room may be collectively referred to simply as “area”.
  • the area definition information (SSME_A) has a RoomID indicating each area or room as a key, and stores the name, type, closed / open, coordinates on the map, necessity of reservation, and the like.
  • the name and type indicate the name and type of each area or room. Closed / Open indicates whether each area or room is an open space in which a person can freely enter or leave, or not.
  • the real-time office space utilization recommendation system holds an image of a map of the entire workplace, and the coordinates on the map indicate the coordinates of each area or room in the image.
  • the necessity of reservation indicates whether or not a reservation is necessary to use each area or room.
  • 15A to 15C show terminal management information (SSME_T) and (ASME_T). This is an ID indicating the individual terminal that is measuring, its model, RoomID of the installed area, the type of sensor included in the terminal, and information indicating the attribute of the installation location (for example, whether the installation location is outdoors). Is to manage.
  • FIG. 15A is an explanatory diagram showing an example of a configuration of terminal management information (SSME_T_EM) and (ASME_T_EM) that stores information measured by the environment measuring instrument (EM) according to the embodiment of this invention.
  • SSME_T_EM terminal management information
  • ASME_T_EM environment measuring instrument
  • a terminal ID for identifying each environmental measuring instrument (EM), a model of each environmental measuring instrument (EM), and each environmental measuring instrument (EM) are installed.
  • FIG. 15B is an explanatory diagram showing an example of the configuration of the terminal management information (SSME_T_TR) which stores information measured by the wearable sensor (TR) according to the embodiment of this invention.
  • SSME_T_TR terminal management information
  • the terminal management information (SSME_T_TR) shown in FIG. 15B is a terminal ID for identifying each wearable sensor (TR), a type of each wearable sensor (TR) (for example, whether the name tag is another terminal or a bracelet type terminal, etc.), A model of each wearable sensor (TR), a user ID for identifying a user (US) wearing each wearable sensor (TR), whether each wearable sensor (TR) includes an acceleration sensor, an infrared transmitter / receiver, and a heart rate meter Information such as whether or not it is included.
  • the terminal management information need only be that of the type of terminal that is being measured at the workplace, so in the example of the present embodiment, the terminal management information regarding the wearable sensor (TR) is unnecessary in the learning phase. ..
  • FIG. 15C is an explanatory diagram showing an example of the configuration of the terminal management information (SSME_T_SC) and (ASME_T_SC) that stores information measured by the surveillance camera (SC) according to the embodiment of this invention.
  • SSME_T_SC terminal management information
  • ASME_T_SC surveillance camera
  • the terminal management information (SSME_T_SC) and (ASME_T_SC) shown in FIG. 15C is a terminal ID for identifying each surveillance camera (SC), a model of each surveillance camera (SC), a room or area in which each surveillance camera (SC) is installed.
  • RoomID for identifying each, the resolution of each surveillance camera (SC), the frame rate of the video imaged by each surveillance camera (SC), the angle of view of each surveillance camera (SC) (for example, whether it is wide-angle), and each surveillance It includes information such as whether the camera (SC) is installed outdoors or indoors.
  • the application server (AS) has an environmental data processing unit (ASCE), and periodically updates the data obtained from the environmental measuring instrument (EM) and the surveillance camera (SC).
  • the environmental data processing unit (ASCE) receives data (ASRD) through the network (NW) through the transmission / reception unit (ASSR), and extracts feature quantities (ASCE_FE) from the data by a method equivalent to that of the analysis server (SS).
  • the extracted feature amount is added to the work space information DB (ASME_SD) together with the time information (ASCE_SO).
  • the recommendation processing unit (ASCO) is a process that provides a recommendation of the work space at that time, starting from an inquiry from the user (US) received via the input / output function of the client (CL).
  • the user (US) inputs a business goal (CLCO_I) using an input function of the client (CL), for example, a keyboard (CLIK) or a touch panel (CLIT)
  • the client (CL) sends it to the application server (AS).
  • AS application server
  • the recommendation processing unit (ASCO) receives the business objectives via the transmission / reception unit (ASSR) (ASCO_R), retrieves the record having the business objective selected as the objective variable from the mathematical model DB (ASME_MD), and applies the corresponding explanation. Get a list of variables (ASCO_SM). Next, the recommendation processing unit (ASCO) searches the work space information DB (ASME_SD) and acquires a list of rooms / areas in a state similar to the list of explanatory variables with the latest data (ASCO_SS).
  • ASSR transmission / reception unit
  • ASME_MD mathematical model DB
  • ASCO_SM work space information DB
  • the recommendation processing unit calculates the priority by a value indicating the difference between the range of the explanatory variables and the actual state of the work space (ASCO_CP), ranks the recommendations, and determines the recommended items ( (ASCO_DR), a screen to be displayed together with a map image, etc. is generated and sent to the client (CL) (ASCO_OD).
  • the client (CL) receives the screen (CLCO_R) and displays it (CLCO_D) on an output device such as a display (CLOD).
  • CLCC input / output control
  • AS application server
  • US user
  • the accuracy of the mathematical model improves as the data is accumulated. Therefore, when the learning phase is being carried out in parallel in other workplaces or the same workplace, the mathematical model that reflects the new data obtained in the learning phase is updated manually or automatically on a regular basis, and the mathematical model is updated. It is also possible to add or change to DB (ASME_MD) (ASCO_RM). Moreover, not only recommending the optimum area extracted from the work space information as a recommendation, but also providing a function (ASCO_IU) that cooperates with an external system such as a conference room reservation system to continue after the user (US) receives the recommendation. The client (CL) may be used to make a reservation for the recommended area.
  • a feature of the present invention is that the mathematical model DB (ASME_MD) that stores the statistical analysis results using the past accumulated data and the office space information DB (ASME_SD) are separately configured.
  • the mathematical model DBs (ASME_MD) and (SSME_MD) handle only general-purpose behavioral features and environmental features that are common to multiple workplaces, and the work space information DB (ASME_SD) is used for specific workplaces that are implementing the operation phase. Divided to handle only useful information about individual rooms and areas. By distinguishing these, the mathematical model DB generated from the data of another workplace can be diverted to the operation of another workplace. It is also possible to create a mathematical model DB by integrating data obtained at a plurality of workplaces.
  • the knowledge obtained from them is a general theory, which is difficult for users (US) to understand and of low value. Therefore, by using the work space information DB (ASME_SD) and converting the information into the information reflecting the real-time data of the workplace to which the user (US) belongs, and providing the recommendation, the user (US) should specifically go. I can understand the place.
  • the user is asked in the order of searching the mathematical model DB (ASME_MD) for data that accumulates general-purpose knowledge, and then searching the office space information DB (ASME_SD) for information for a specific workplace. To answer.
  • ASME_MD mathematical model DB
  • ASME_SD office space information DB
  • FIG. 4A to FIG. 6B Client display screen example> 4A to 6B are explanatory diagrams showing an example of screens displayed on the display (CLOD) of the client (CL) according to the embodiment of the present invention.
  • These screens are generated in the application server (AS) (ASCO_OD) and displayed by the client input / output control (CLCC), but may be generated in the client (CL).
  • AS application server
  • ASCO_OD client input / output control
  • 4A to 6B are illustrated assuming a large touch panel or a Web browser of a PC as the client (CL), other means such as a smartphone or a tablet may be used.
  • Screen example 1 (CLOD_1) in FIG. 4A is an example of a screen that is automatically displayed during a time period when the user (US) is not operating. This screen visualizes the index regarding the environment at the latest time obtained by the environment measuring device (EM). Specifically, the screen example 1 (CLOD_1) displays the date and time (D11), the type of index to be visualized (D12), and the visualization data (D13) associated with the map of the workplace. This is a screen generated by combining the information of the office space information DB (ASME_SD), the terminal management information (ASME_T), and the area definition information (ASME_A). When the user (US) presses button 1 (CLIO_B1), the screen transitions to the search mode of screen example 2 (CLOD_2).
  • FIG. 4 shows (in FIG. 4) a screen example 2 (CLOD_2) for allowing the user (US) to input a business goal (CLCO_I).
  • the notification field (D21) is a field for writing a question to the user (US), For example, "How do you want to work now?" Is displayed, etc.
  • the options of the business goals such as “concentrate desk work” and “idea generation” correspond to the items in the objective variable table (ASME_MD_O).
  • Screen example 3 (CLOD_3) in FIG. 5A is an example of a screen for inquiring about the state of the user (US). This screen may be skipped if the state is not used for analysis. For items such as “mood”, “physical condition”, and “thinking”, the degree (for example, how good the mood is, how good the physical condition is, how fast the thinking is) is set in the range of 1 to 5 by the user. (US) to select. When the user (US) presses button 3 (CLIO_B3), the screen transitions to screen example 4 (CLOD_4).
  • FIG. 5B Screen example 4 (CLOD_4) in FIG. 5B is an example of a screen displaying the recommendation calculated based on the information of the business goal and the status input so far. Areas with high priority (three in this example) extracted by the recommendation item determination (ASCO_DR) are displayed. The notification column (D41) presents that this page is a recommended result, and the comment column (D42) is populated with the relevant sentence selected from the comment sentence table (ASME_MD_E).
  • the name of each area registered in the area definition information (ASME_A) and the video (eg, real-time) taken by the surveillance camera (SC) of the area are displayed. Is also good.
  • such an image is displayed in the image display field (D43).
  • the reason for displaying the image is that the user (US) understands the situation such as the congestion degree of the area, and therefore, the process of making it difficult to identify the person in the image by blurring or converting to CG is performed. You may add.
  • the recommendation processing unit estimates the current number of people staying in each area from real-time video obtained from the surveillance camera (SC), and as a result, for example, the user is already full and cannot be used, or the degree of congestion is determined. Areas that are determined not to be suitable for the user's work (for example, a decrease in productivity is expected) may be excluded from the target of recommendation to the user.
  • the reason display column (D44) illustrates the information of the mathematical model table (ASME_MD) so that the user (US) can understand the reason for recommendation and the characteristics of each area.
  • ASME_MD mathematical model table
  • the information that “environmental sound is 50 to 60 dB” and “temperature is 23 to 25 ° C.”, which are effective explanatory variables for the objective variable of concentration, is displayed in two stages, and the current environmental sound of each area is displayed. And how close the temperature is to the range is expressed by the number of stars.
  • button 4 (CLIO_B4) to select one of the presented options, the screen transitions to screen example 6 (CLOD_6).
  • the screen example 6 (CLOD_6) in FIG. 6B is a route (D61) from the position of the display (CLOD) displaying the screen referred to when the user (US) selects the area to the selected area. Is displayed.
  • the screen example 6 (CLOD_6) is closed and the screen example 1 (CLOD_1) is displayed. This completes the process of recommending the work place to the user (US).
  • the client (CL) connects to the conference room reservation system (not shown) through the external system cooperation control (ASCO_IU) of the application server (AS).
  • ASCO_IU external system cooperation control
  • the screen example 5 (CLOD_5) shown in FIG. 6A may be continuously transitioned to make a reservation.
  • the client (CL) causes the user (US) to input the end time (D51) of the reservation and the employee number (D52), for example, and secures the conference room from the current time to the desired end time.
  • FIG. 7 is an explanatory diagram showing an example of a screen (TRIO_D) when a questionnaire is given to the user (US) by the wearable sensor (TR) according to the embodiment of the present invention.
  • the wearable sensor (TR) sounds an alarm on the speaker (TRIO_S) at a predetermined or random time, and prompts the user (US) for an answer.
  • a question (TRIO_D1) and a legend (TRIO_D2) corresponding to the answer number are displayed on the screen (TRIO_D).
  • the user (US) completes the answer by pressing one of the buttons (TRIO_B) corresponding to the legend.
  • FIG. 8 shows the procedure of sensing performed by the wearable sensor (TR), the environment measuring device (EM) and the surveillance camera (SC) and the data thereof in the analysis server (SS) in the learning phase of the embodiment of the present invention. It is a sequence diagram which shows the procedure until it stores.
  • the wearable sensor (TR) is activated (TR81) when the user (US) switches it on or picks it up from the charger (US81) and synchronizes the time (TRCO_T). Subsequently, the wearable sensor (TR) starts sensing (TR82) and transmits sensing data (TRSD) at regular time intervals. Further, the environment measuring instrument (EM) performs time synchronization (EMCO_T) after starting, performs sensing (EM82), and transmits sensing data (EMSD) at regular time intervals. Similarly, the surveillance camera (SC) also performs time synchronization (SCCO_T) after starting (SC81), performs shooting (SC82), and transmits moving image data at regular time intervals (SCSD).
  • the wearable sensor when conducting a questionnaire with a wearable sensor (TR), it is activated at a predetermined or random time by a timer (TR83), and the speaker (TRIO_S) notifies the user (TR84). Then, the wearable sensor (TR) displays the questionnaire items (TR85) on the screen (TRIO_D), and when the user (US) answers (US82), sends the answer data to the analysis server (SS) (TR86).
  • This process is controlled by the questionnaire control (TRCO_Q), but it may be performed by using another terminal such as a smartphone or a PC instead of the wearable sensor (TR).
  • the analysis server receives the sensing data and the questionnaire data (SSRD) and stores the data in the sensing DB (SSME_SD) (SS81).
  • FIG. 9 shows a procedure for generating a mathematical model performed in the analysis server (SS) and a mathematical model DB (SSME_MD) of the analysis server (SS) copied, extracted or integrated in the learning phase of the embodiment of the present invention. It is a sequence diagram which shows the procedure of updating the mathematical model DB (ASME_MD) of the application server (AS).
  • the analysis server (SS) is activated at a predetermined time at a predetermined frequency (SS81), for example, once a week, issues a request to the storage unit (SSME), and stores a predetermined date and target sensing data in the sensing DB. Acquire (SS82).
  • the analysis server (SS) performs feature quantity extraction (SSCO_FE) from the data and stores it in the feature quantity DB. Since the method of performing the feature amount extraction differs depending on the type of data, the analysis server (SS) repeats these processes until the calculation of all types of sensing data is completed (SS83).
  • the analysis server (SS) designates one objective variable (SSCO_SO) from a predetermined objective variable table (SSME_MD_O), performs statistical analysis (SSCO_SA), and extracts an explanatory variable associated with the objective variable. Then, the result is stored in the mathematical model DB as a mathematical model (SSCO_MD). The analysis server (SS) repeats this until the calculation is completed for all the objective variables in the objective variable table (SS84), and ends (SS85).
  • the analysis server (SS) periodically applies the mathematical model DB (SSME_MD) to the application server. It is manually or automatically copied and updated in the mathematical model DB (ASME_MD) of (AS) (ASCO_RM).
  • the analysis server (SS) may send a part of the mathematical model DB (SSME_MD) extracted to the application server (AS), or integrate a plurality of mathematical model DBs (SSME_MD) by a plurality of workplaces. Then, it may be used as the mathematical model DB (ASME_MD) of the application server (AS).
  • FIG. 10 is a sequence diagram showing a procedure for processing and updating the environmental data measured by the application server (AS) in the operation phase of the embodiment of the present invention.
  • the application server receives the sensing data (ASRD), extracts the feature amount from them (ASCO_FE), inputs the latest environmental feature amount into the office space information DB (ASME_SD), and updates (ASCO_SO).
  • FIG. 11 shows that, in the operation phase of the embodiment of the present invention, the application server (AS) generates a recommendation and presents it on the screen with respect to the business goal input by the user (US) operating the client (CL). It is a sequence diagram which shows the procedure to do.
  • the client (CL) When the client (CL) is started (CL11) by turning on the power, it acquires the latest working space information from the application server (AS) through the network (NW), and the initial screen (the example is shown in FIG. 4A). Screen example 1 (CLOD_1)) is automatically displayed (CL12). Next, when the search screen is activated (US11) to decide where the user (US) works, the search screen (screen example 2 (CLOD_2) shown in FIG. 4B) is displayed (CL13).
  • the user (US) inputs a business goal from what perspective the user wants to improve performance in response to the question on the screen (US12) (CLCO_I)
  • the client (CL) sends it to the application server (AS). Send (COCO_S).
  • the application server (AS) receives the business goal (ASCO_R), retrieves a record having the goal as an objective variable from the mathematical model DB (ASME_MD) (ASCO_SM), and then becomes an environment close to the condition of the explanatory variable.
  • the working area information DB (ASME_SD) is searched for the existing area (ASCO_SS).
  • the application server (AS) calculates the priority based on the similarity and the statistical reliability among the candidates narrowed down by the condition (ASCO_CP), for example, determines the top three recommended items (ASCO_DR), and And a screen integrated with the commentary is generated (ASCO_OD).
  • the client displays the received recommendation screen (screen example 5 (CLOD_4) of which the example is shown in FIG. 5B) (CL14), and when the user further selects one of the recommended items (US13), Finally, a map of a route from the current location to the selected area (the example is the screen example 6 (CLOD_6) shown in FIG. 6B) and the like are displayed to complete (CL15).
  • the data analysis system for example, the system shown in FIG. 1 to FIG. 3B which is one embodiment of the present invention
  • the target index for example, the target variable shown in FIG. 12A
  • the storage unit for example, the storage unit (ASME) of the application server (AS)
  • the mathematical model for example, the mathematical model table (ASME_MD_T1) shown in FIG.
  • ASCO_SM mathematical model search
  • ASCO_SS office space information search
  • ASCO_OD screen generation
  • the storage unit holds a first database (for example, a mathematical model DB (ASME_MD)) that stores a mathematical model and a second database (for example, a work space information DB (ASME_SD)) that stores environmental data.
  • the recommendation processing unit refers to the first database to search for a condition of the environmental index suitable for increasing the productivity of the person (for example, mathematical model search (ASCO_SM)), and then refers to the second database. Then, information regarding an activity place suitable for increasing the productivity of the person is searched (for example, office space information search (ASCO_SS)).
  • ASCO_SM mathematical model search
  • ASCO_SS office space information search
  • the environmental index in the mathematical model includes at least one of temperature, humidity and noise of the activity place (for example, at least one of temperature, humidity and sound included in the mathematical model table (ASME_MD_T1) of FIG. 12B), and environmental data Is a value of an index included in the mathematical model (for example, a temperature value measured by a temperature sensor (EMSE_T), obtained from the sensors installed in a plurality of activity places where a person may perform an activity from now on, It may include the humidity value measured by the humidity sensor (EMSE_H) and the noise value measured by the noise measuring device (EMSE_S).
  • the recommendation processing unit searches for a condition of the environmental index suitable for increasing the productivity of the person based on the relationship between the objective index corresponding to the work target data and the environmental index (for example, shown in the screen of FIG. 4B).
  • a mathematical model showing a relationship between the objective variable "concentration duration" (FIG. 12A) and the environmental index for example, the mathematical model table of FIG.
  • the information may be searched for as information about activity sites suitable for increasing a person's productivity.
  • the objective index, the environmental index, and the state of the person are associated with each other, and the recommendation processing unit causes the state of the person input by the person (for example, the user's mood, physical condition, thinking state, etc.) input via the screen of FIG. 5A are further accepted, and the person production is performed based on the input person's state, business goal data, and mathematical model.
  • the condition of the environmental index suitable for improving the property may be searched.
  • the recommendation processing unit acquires information indicating the current or future state of the activity place obtained by the search, and based on the current or future state of the activity place, determines information regarding the activity place to be output. Good.
  • the information indicating the current or future state of the activity place is information indicating the number of people staying at the activity place based on information (for example, a video of the surveillance camera (SC)) acquired from the sensor, or a reservation system for the activity place. It may be the reservation status of the activity place obtained from.
  • information for example, a video of the surveillance camera (SC)
  • SC surveillance camera
  • the present invention is not limited to the above-described embodiments, but includes various modified examples.
  • the above-described embodiments have been described in detail for better understanding of the present invention, and are not necessarily limited to those including all the configurations of the description.
  • each of the above-mentioned configurations, functions, processing units, processing means, etc. may be realized in hardware by designing a part or all of them with, for example, an integrated circuit. Further, each of the above-described configurations, functions and the like may be realized by software by a processor interpreting and executing a program for realizing each function. Information such as programs, tables, and files that realize each function is stored in a nonvolatile semiconductor memory, hard disk drive, storage device such as SSD (Solid State Drive), or computer-readable non-readable such as IC card, SD card, or DVD. It can be stored on a temporary data storage medium.
  • SSD Solid State Drive
  • control lines and information lines are shown to be necessary for explanation, and not all control lines and information lines are shown on the product. In practice, it may be considered that almost all configurations are connected to each other.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Educational Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A data analysis system comprising a storage unit which retains a mathematical model representing the relationship between a target indicator relating to a person's productivity and an environmental indicator relating to the environment of the person's place of activity, and also comprising a recommendation processing unit which: receives environmental data that relates to an environment of a person's place of activity and that has been acquired from a sensor, and business goal data that includes a goal relating to the person's activity and that has been input by the person; searches for environmental indicator conditions suitable for enhancing the person's productivity, on the basis of the business goal data and the mathematical model; searches for information relating to a place of activity suitable for enhancing the person's productivity, on the basis of the environmental indicator conditions and the environmental data; and outputs the found information relating to the place of activity.

Description

データ分析システム及びデータ分析方法Data analysis system and data analysis method
　本発明は、人と環境のセンサデータに基づき業務目的に効果的な執務空間を推薦する技術に関する。 The present invention relates to a technique for recommending an effective work space for a business purpose based on sensor data of people and the environment.
　近年、執務空間は多様化し、従業員は自由に働く場所を選択できるようになりつつある。しかしながら場所を選択する基準は本人の好みか空き状況程度しかなかった。一方、これまでにウェアラブルセンサで人間の歩行、睡眠などの行動を定量的に計測する技術が広がってきている。さらに、それらのデータを用い、業務の生産性と関連する行動指標を高めるための働き方アドバイスを提供する技術が特許文献１に開示されている。 _ Recently, work spaces have become diversified, and employees are becoming able to freely choose where to work. However, the only criteria for choosing a place were their own preference or availability. On the other hand, techniques for quantitatively measuring human behavior such as walking and sleeping with wearable sensors have been spreading. Further, Patent Document 1 discloses a technique of using such data to provide work style advice for increasing a behavior index related to productivity of work.
　　特許文献１：特開２０１７－２０８００５号公報 Patent Document 1: JP-A-2017-200805
　オフィスワーカーは状況によって多様な業務目的、例えば執筆に集中したい、同僚と会話してアイディアを出したい、などを持っている。しかし目的によって適した執務空間は異なる。例えば執筆に集中するためには静かな空間が好ましく、アイディアを出すためには騒がしい空間や屋外の方が好ましいこともありえる。しかしながらオフィスの環境、具体的には室温、照度、環境音、及び人の数などはリアルタイムに変動する。また、人の個性及び状態によって効果を得やすい空間の特性は異なる。そのため、特定のエリアに滞在すれば常に同じ生産性が得られるものではない。よって、人と執務空間はその時々の状況を反映して動的にマッチングすることが有用である。 Office workers have various business purposes depending on the situation, such as wanting to concentrate on writing and talking with colleagues to come up with ideas. However, the work space suitable for each purpose is different. For example, a quiet space may be preferable to concentrate on writing, and a noisy space or an outdoor space may be preferable to generate an idea. However, the environment of the office, specifically, room temperature, illuminance, environmental sound, and the number of people change in real time. In addition, the characteristics of the space where it is easy to obtain an effect differ depending on the personality and state of the person. Therefore, staying in a specific area does not always provide the same productivity. Therefore, it is useful to dynamically match people and work spaces by reflecting the situation at each moment.
　以上を踏まえ、本発明の目的は、人と環境のセンサデータに基づき業務目的に効果的な執務空間を推薦するシステムを提供することにある。 Based on the above, an object of the present invention is to provide a system that recommends an effective work space for a business purpose based on sensor data of people and the environment.
　本願発明による課題を解決する手段のうち、代表的なものを例示すれば、データ分析システムであって、人物の生産性に関する目的指標と人物の活動場所の環境に関する環境指標との関連を示す数理モデルを保持する記憶部と、センサから取得した人物の活動場所の環境に関するデータである環境データと、前記人物によって入力された前記人物の活動に関する目標を含む業務目標データとを受け付け、前記業務目標データと前記数理モデルとに基づいて、前記人物の生産性を高めるのに適した前記環境指標の条件を探索し、前記環境指標の条件と前記環境データとに基づいて、前記人物の生産性を高めるのに適した活動場所に関する情報を探索し、探索によって得られた前記活動場所に関する情報を出力する推奨処理部と、を有する。 A typical example of the means for solving the problems according to the present invention is a data analysis system, which is a mathematical expression showing the relationship between a target index related to the productivity of a person and an environmental index related to the environment of the activity place of the person. A storage unit that holds a model, environment data that is data about the environment of a person's activity place acquired from a sensor, and business goal data including a goal related to the activity of the person input by the person are accepted, and the business goal is received. Based on the data and the mathematical model, to search the conditions of the environmental index suitable for increasing the productivity of the person, based on the environmental index conditions and the environmental data, the productivity of the person A recommendation processing unit that searches for information about an activity place suitable for enhancing and outputs information about the activity place obtained by the search.
　本発明の一態様によれば、人と環境に関する時間連続的なセンサデータを分析して、業務における人のパフォーマンスを高めるために効果的な職場空間をリアルタイムにマッチングすることが可能となる。なお、上記した以外の課題、構成、及び効果は、以下の実施形態の説明によって明らかにされる。 According to one aspect of the present invention, it is possible to analyze time-continuous sensor data relating to people and the environment, and match an effective work space in real time to improve the performance of people in work. The problems, configurations, and effects other than those described above will be clarified by the following description of the embodiments.
本発明の実施の形態のリアルタイム執務空間活用レコメンドシステムの概要を示す説明図である。It is explanatory drawing which shows the outline | summary of the real-time office space utilization recommendation system of embodiment of this invention. 本発明の実施の形態の学習フェーズにおける分析サーバおよび環境測定機の構成の一例を示すブロック図である。It is a block diagram showing an example of composition of an analysis server and an environment measuring machine in a learning phase of an embodiment of the invention. 本発明の実施の形態の学習フェーズにおけるウェアラブルセンサおよび監視カメラの構成の一例を示すブロック図である。It is a block diagram showing an example of composition of a wearable sensor and a surveillance camera in a learning phase of an embodiment of the invention. 本発明の実施の形態の運用フェーズにおけるクライアントおよびアプリケーションサーバの構成の一例を示すブロック図である。It is a block diagram showing an example of composition of a client and an application server in an operation phase of an embodiment of the invention. 本発明の実施の形態の運用フェーズにおける環境測定機および監視カメラの構成の一例を示すブロック図である。It is a block diagram showing an example of composition of an environment measuring machine and a surveillance camera in an operation phase of an embodiment of the invention. 本発明の実施の形態のクライアントのディスプレイに表示される画面の一例を示す説明図である。It is explanatory drawing which shows an example of the screen displayed on the display of the client of embodiment of this invention. 本発明の実施の形態のクライアントのディスプレイに表示される画面の一例を示す説明図である。It is explanatory drawing which shows an example of the screen displayed on the display of the client of embodiment of this invention. 本発明の実施の形態のクライアントのディスプレイに表示される画面の一例を示す説明図である。It is explanatory drawing which shows an example of the screen displayed on the display of the client of embodiment of this invention. 本発明の実施の形態のクライアントのディスプレイに表示される画面の一例を示す説明図である。It is explanatory drawing which shows an example of the screen displayed on the display of the client of embodiment of this invention. 本発明の実施の形態のクライアントのディスプレイに表示される画面の一例を示す説明図である。It is explanatory drawing which shows an example of the screen displayed on the display of the client of embodiment of this invention. 本発明の実施の形態のクライアントのディスプレイに表示される画面の一例を示す説明図である。It is explanatory drawing which shows an example of the screen displayed on the display of the client of embodiment of this invention. 本発明の実施の形態のウェアラブルセンサにてユーザにアンケートを行う場合の画面の一例を示す説明図である。It is an explanatory view showing an example of a screen when a user is surveyed with a wearable sensor of an embodiment of the invention. 本発明の実施の形態の学習フェーズにおいて、ウェアラブルセンサ、環境測定機および監視カメラにおいて行われるセンシングの手順と、そのデータを分析サーバに格納するまでの手順とを示すシーケンス図である。It is a sequence diagram which shows the procedure of the sensing performed in a wearable sensor, an environment measuring device, and a surveillance camera in the learning phase of embodiment of this invention, and the procedure until it stores the data in an analysis server. 本発明の実施の形態の学習フェーズにおいて、分析サーバにおいて行われる数理モデルを生成する手順と、分析サーバの数理モデルＤＢをコピー、抜粋または統合してアプリケーションサーバの数理モデルＤＢを更新する手順とを示すシーケンス図である。In the learning phase of the embodiment of the present invention, the procedure of generating a mathematical model performed in the analysis server and the procedure of copying, extracting or integrating the mathematical model DB of the analysis server to update the mathematical model DB of the application server are described. It is a sequence diagram shown. 本発明の実施の形態の運用フェーズにおいて、アプリケーションサーバにおいて計測された環境データを処理し更新する手順を示すシーケンス図である。It is a sequence diagram which shows the procedure which processes and updates the environmental data measured in the application server in the operation phase of embodiment of this invention. 本発明の実施の形態の運用フェーズにおいて、ユーザがクライアントを操作して入力した業務目標に対して、アプリケーションサーバがレコメンドを生成して画面に提示する手順を示すシーケンス図である。FIG. 9 is a sequence diagram showing a procedure in which an application server generates a recommendation and presents it on a screen with respect to a business goal input by a user operating a client in the operation phase of the exemplary embodiment of the present invention. 本発明の実施の形態の数理モデルＤＢに含まれる目的変数テーブルの構成の一例を示す説明図である。It is explanatory drawing which shows an example of a structure of the objective variable table contained in mathematical model DB of embodiment of this invention. 本発明の実施の形態の数理モデルＤＢに含まれる数理モデルテーブルテーブルの構成の一例を示す説明図である。It is explanatory drawing which shows an example of a structure of the mathematical model table table contained in mathematical model DB of embodiment of this invention. 本発明の実施の形態の数理モデルＤＢに含まれる解説文テーブルの構成の一例を示す説明図である。It is explanatory drawing which shows an example of a structure of the explanatory note table contained in mathematical model DB of embodiment of this invention. 本発明の実施の形態の執務空間情報ＤＢの構成の一例を示す説明図である。It is explanatory drawing which shows an example of a structure of office space information DB of embodiment of this invention. 本発明の実施の形態のエリア定義情報の構成の一例を示す説明図である。It is explanatory drawing which shows an example of a structure of the area definition information of embodiment of this invention. 本発明の実施の形態の環境計測器によって計測された情報を格納する端末管理情報の構成の一例を示す説明図である。It is explanatory drawing which shows an example of a structure of the terminal management information which stores the information measured by the environment measuring device of embodiment of this invention. 本発明の実施の形態のウェアラブルセンサによって計測された情報を格納する端末管理情報の構成の一例を示す説明図である。It is explanatory drawing which shows an example of a structure of the terminal management information which stores the information measured by the wearable sensor of embodiment of this invention. 本発明の実施の形態の監視カメラによって計測された情報を格納する端末管理情報の構成の一例を示す説明図である。It is explanatory drawing which shows an example of a structure of the terminal management information which stores the information measured by the surveillance camera of embodiment of this invention.
　本発明は、業務目的に効果的な執務空間をリアルタイムに推薦するシステムであり、人と環境の状況を計測したセンサデータを用いることを特徴とする。以下、図面を用いて説明を行う。 The present invention is a system that recommends an effective work space in real time for business purposes, and is characterized by using sensor data that measures the situation of people and the environment. Hereinafter, description will be given with reference to the drawings.
　最初に、本発明の実施の形態について図面を参照して説明する。 First, an embodiment of the present invention will be described with reference to the drawings.
　＜図１：システム概要＞
　図１は、本発明の実施の形態のリアルタイム執務空間活用レコメンドシステムの概要を示す説明図である。 <Figure 1: System overview>
FIG. 1 is an explanatory diagram showing an outline of a real-time office space utilization recommendation system according to an embodiment of the present invention.
　本発明の実施の形態では、数理モデルを作るための学習フェーズと、数理モデルを用いて執務空間活用レコメンドシステムを運用する運用フェーズの二種類が存在する。 In the embodiment of the present invention, there are two types: a learning phase for creating a mathematical model and an operating phase for operating the office space utilization recommendation system using the mathematical model.
　まず、学習フェーズについて述べる。 First, describe the learning phase.
　学習フェーズは、ウェアラブルセンサ（ＩＲ）、環境測定機（ＥＭ）、監視カメラ（ＳＣ）及び分析サーバ（ＳＳ）から構成される。ただし、監視カメラ（ＳＣ）は必須の構成ではない。 The learning phase consists of a wearable sensor (IR), environment measuring device (EM), surveillance camera (SC) and analysis server (SS). However, the surveillance camera (SC) is not an essential component.
　ウェアラブルセンサ（ＴＲ）をユーザ（ＵＳ）が装着する。ウェアラブルセンサ（ＴＲ）内の、物理量を計測するセンサ（図示省略）が、装着者の動きに関するセンシングデータ及び他の装着者とのインタラクション（例えば対面または近接状態）に関するセンシングデータを取得する。以下の説明ではウェアラブルセンサ（ＴＲ）が３軸加速度センサ（図示省略）を有し、それが計測した３軸加速度データを装着者の動きに関するセンシングデータとして用いるが、他の種類のセンサが計測した他の物理量を用いてもよい。 User (US) wears wearable sensor (TR). A sensor (not shown) that measures a physical quantity in the wearable sensor (TR) acquires sensing data regarding the movement of the wearer and sensing data regarding interaction with another wearer (for example, face-to-face or proximity state). In the following description, the wearable sensor (TR) has a triaxial acceleration sensor (not shown), and the triaxial acceleration data measured by the wearable sensor (TR) is used as sensing data relating to the motion of the wearer, but other types of sensors measure it. Other physical quantities may be used.
　インタラクションは、例えば、ユーザ（ＵＳ）同士が対面した際に各ウェアラブルセンサ（ＴＲ）間で赤外線信号又はその他の無線信号等を送受信することで検知される。また、机上などに設置された赤外線ビーコン（ＩＢ）とウェアラブルセンサ（ＴＲ）とが通信することで、ユーザ（ＵＳ）が滞在した場所と時刻に関するセンシングデータを取得できる。取得されたこれらのセンシングデータは、無線または有線のネットワーク（ＮＷ）を通じて分析サーバ（ＳＳ）に格納される。 The interaction is detected, for example, by transmitting and receiving an infrared signal or another wireless signal between the wearable sensors (TR) when the users (US) face each other. Further, the infrared beacon (IB) installed on the desk or the like and the wearable sensor (TR) communicate with each other, so that the sensing data regarding the place and time when the user (US) stays can be acquired. These acquired sensing data are stored in the analysis server (SS) through a wireless or wired network (NW).
　さらに、職務空間には所定のタイミングで（例えば一定の間隔で）主に屋内（屋外も含んでもよい）の環境を計測する環境測定機（ＥＭ）が設置される。環境測定機（ＥＭ）は、空間の状態を計測するセンサ群（例えば温度センサ、湿度センサ、及び騒音測定機などとするが、他の手段を用いても良い）を有し、それらを用いて職務空間の状況に関するセンシングデータを取得する。取得されたセンシングデータは、無線または有線のネットワーク（ＮＷ）を通じて分析サーバ（ＳＳ）に格納される。 Furthermore, in the work space, an environment measuring machine (EM) that mainly measures the environment of the indoor (outdoor may be included) at a predetermined timing (for example, at regular intervals) is installed. The environment measuring machine (EM) has a sensor group (for example, a temperature sensor, a humidity sensor, a noise measuring machine, etc., but other means may be used) for measuring the state of the space, and uses them. Obtain sensing data about the status of work space. The acquired sensing data is stored in the analysis server (SS) through a wireless or wired network (NW).
　また、職務空間の壁面または天井に設置された監視カメラ（ＳＣ）によって空間の状況を示す動画または静止画が記録され、無線または有線のネットワーク（ＮＷ）を通じて分析サーバ（ＳＳ）に格納される。 A video or still image showing the space situation is recorded by a surveillance camera (SC) installed on the wall or ceiling of the work space, and stored in the analysis server (SS) via a wireless or wired network (NW).
　分析サーバ（ＳＳ）は、ウェアラブルセンサ（ＴＲ）からのデータから行動に関する特徴量を抽出し、環境測定機（ＥＭ）からのデータと監視カメラ（ＳＣ）からのデータから環境に関する特徴量を生成し、組み合わせて統計分析を行う。分析サーバ（ＳＳ）は、統計分析において、人間の業務のパフォーマンスに関する行動特徴量、例えば集中継続時間または会話時双方向度を目的変数として、統計的に関連のある他の行動特徴量および環境特徴量を見つけ出す。分析サーバ（ＳＳ）は、それらの特徴量間の組み合わせを数理モデルＤＢ（ＳＳＭＥ＿ＭＤ）に格納する。 The analysis server (SS) extracts the feature amount related to the behavior from the data from the wearable sensor (TR), and generates the feature amount related to the environment from the data from the environment measuring device (EM) and the data from the monitoring camera (SC). , Combine and perform statistical analysis. In the statistical analysis, the analysis server (SS) uses behavior characteristic quantities related to human work performance, for example, other characteristic characteristic quantities and environmental characteristics that are statistically related to the objective variable such as the concentration duration or the conversation interactivity. Figure out the amount. The analysis server (SS) stores the combination between the feature quantities in the mathematical model DB (SSME_MD).
　次に、運用フェーズについて述べる。 Next, the operation phase will be described.
　運用フェーズは、アプリケーションサーバ（ＡＳ）、クライアント（ＣＬ）、環境測定機（ＥＭ）及び監視カメラ（ＳＣ）によって構成される。ただし、監視カメラ（ＳＣ）は必須の構成ではない。また、運用フェーズはさらにウェアラブルセンサ（ＴＲ）を含んでもよいが、簡単のため本発明では含まない構成において説明を行う。 The operation phase is composed of application server (AS), client (CL), environment measuring machine (EM) and surveillance camera (SC). However, the surveillance camera (SC) is not an essential component. Further, the operation phase may further include a wearable sensor (TR), but for the sake of simplicity, the explanation will be given with a configuration not included in the present invention.
　特定のタイミングで分析サーバ（ＳＳ）内の数理モデルＤＢ（ＳＳＭＥ＿ＭＤ）はアプリケーションサーバ（ＡＳ）内の数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）に手動または自動でコピーされる。さらに、環境測定機（ＥＭ）及び監視カメラ（ＳＣ）のセンシングデータがリアルタイムにアプリケーションサーバ（ＡＳ）内の執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）に格納される。 Mathematical model DB (SSME_MD) in the analysis server (SS) is manually or automatically copied to the mathematical model DB (ASME_MD) in the application server (AS) at a specific timing. Further, the sensing data of the environment measuring machine (EM) and the monitoring camera (SC) are stored in real time in the work space information DB (ASME_SD) in the application server (AS).
　今自分の業務目的に適した場所を探しているユーザ（ＵＳ）が、クライアント（ＣＬ）を操作して業務目的を入力すると、アプリケーションサーバ（ＡＳ）は数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）を検索して目的に合致する環境特徴量をピックアップし、さらに執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）に含まれる直近の時刻のデータから、ピックアップされた環境特徴量に最も近い状態を示すエリアをおすすめとしてディスプレイ（ＣＬＯＤ）に表示する。 When a user (US) who is now searching for a place suitable for his / her business purpose operates the client (CL) and inputs the business purpose, the application server (AS) searches the mathematical model DB (ASME_MD) to obtain the purpose. The environmental features that match the above are picked up, and from the data of the latest time included in the work space information DB (ASME_SD), the area showing the state closest to the picked up environmental features is displayed as a recommendation on the display (CLOD). To do.
　＜図２Ａ、図２Ｂ：学習フェーズのシステム構成図＞
　図２Ａおよび図２Ｂは、本発明の実施の形態の学習フェーズにおける分析サーバ（ＳＳ）、環境測定機（ＥＭ）、ウェアラブルセンサ（ＴＲ）および監視カメラ（ＳＣ）の構成の一例を示すブロック図である。 <FIG. 2A, FIG. 2B: System configuration diagram of learning phase>
2A and 2B are block diagrams showing an example of configurations of an analysis server (SS), an environment measuring device (EM), a wearable sensor (TR), and a surveillance camera (SC) in a learning phase according to the embodiment of the present invention. is there.
　環境測定機（ＥＭ）は、屋内または屋外の環境を計測するための一群のセンサを含む機器であり、センサ部（ＥＭＳＥ）、記憶部（ＥＭＭＥ）、電池（ＥＭＢＴ）、制御部（ＥＭＣＯ）および送受信部（ＥＭＳＲ）を有する。 The environment measuring machine (EM) is a device including a group of sensors for measuring an indoor or outdoor environment, and includes a sensor unit (EMSE), a storage unit (EMME), a battery (EMBT), a control unit (EMCO) and It has a transceiver unit (EMSR).
　センサ部（ＥＭＳＥ）が有するセンサの例としては、温度センサ（ＥＭＳＥ＿Ｔ）、湿度センサ（ＥＭＳＥ＿Ｈ）、および環境音を測る騒音測定機（ＥＭＳＥ＿Ｓ）がある。ほかに空気中のＣＯ２濃度を測るセンサ（図示省略）などを含んでも良い。また環境測定機（ＥＭ）を屋外に設置する場合には、センサ部（ＥＭＳＥ）は、雨量および日照量などを測るための屋外環境用計測機器群（ＥＭＳＥ＿Ｏ）を含んでも良い。 Examples of sensors included in the sensor unit (EMSE) include a temperature sensor (EMSE_T), a humidity sensor (EMSE_H), and a noise measuring device (EMSE_S) that measures environmental sounds. In addition, a sensor (not shown) for measuring the CO2 concentration in the air may be included. Further, when the environment measuring machine (EM) is installed outdoors, the sensor unit (EMSE) may include a group of outdoor environment measuring instruments (EMSE_O) for measuring the amount of rainfall and the amount of sunlight.
　また、記憶部（ＥＭＭＥ）には時刻情報を保持する時計（ＥＭＣＫ）、環境測定機（ＥＭ）を識別する端末ＩＤ情報（ＥＭＩＤ）、および計測した結果であるセンシングデータ（ＥＭＭＥ＿Ｓ）を格納する。また、環境測定機（ＥＭ）は、電源を確保するための電池（ＥＭＢＴ）を有する。 The storage unit (EMME) also stores a clock (EMCK) that holds time information, terminal ID information (EMID) that identifies the environment measuring machine (EM), and sensing data (EMME_S) that is the measurement result. Further, the environment measuring machine (EM) has a battery (EMBT) for securing a power source.
　さらに、制御部（ＥＭＣＯ）は、センシングおよび送受信の制御を行う。具体的には、制御部（ＥＭＣＯ）は、時計（ＥＭＣＫ）内の時刻情報を標準時と同期させる時刻同期（ＥＭＣＯ＿Ｔ）、センサ部（ＥＭＳＥ）のセンサを制御し環境に関するデータを取得し時刻情報を付与するセンシング制御（ＥＭＣＯ＿Ｓ）、さらにそれらのデータを送受信部（ＥＭＳＲ）を介して分析サーバ（ＳＳ）に送信するデータ送信（ＥＭＳＤ）を実施する。 Furthermore, the control unit (EMCO) controls sensing and transmission / reception. Specifically, the control unit (EMCO) controls the sensor of the sensor unit (EMSE) by time synchronization (EMCO_T) that synchronizes the time information in the clock (EMCK) with the standard time, acquires the data related to the environment, and acquires the time information. Sensing control (EMCO_S) to be given and data transmission (EMSD) for transmitting the data to the analysis server (SS) via the transmission / reception unit (EMSR) are performed.
　ウェアラブルセンサ（ＴＲ）は、人間の行動および状態を計測する目的のセンサであり、センサ部（ＴＲＳＥ）、入出力部（ＴＲＩＯ）、記憶部（ＴＲＭＥ）、電池（ＴＲＢＴ）、制御部（ＴＲＣＯ）および送受信部（ＴＲＳＲ）を有する。なお、本発明ではウェアラブルと記載しており、身体に装着されることを想定しているが、人間の身体の運動およびコミュニケーションなど同等のものが計測できるセンサであれば、身体に装着しないもの、例えばカメラや振動センサ、サーモメータなどを用いても良い。 The wearable sensor (TR) is a sensor for measuring human behavior and state, and includes a sensor unit (TRSE), an input / output unit (TRIO), a storage unit (TRME), a battery (TRBT), and a control unit (TRCO). And a transceiver (TRSR). In the present invention, it is described as wearable, and it is assumed that it is worn on the body, but if it is a sensor that can measure the equivalent of movement and communication of the human body, it is not worn on the body, For example, a camera, a vibration sensor, a thermometer or the like may be used.
　センサ部（ＴＲＳＥ）に含むセンサの一例としては、身体の動きを計測するための加速度センサ（ＴＲＳＥ＿Ａ）、ウェアラブルセンサ（ＴＲ）間で通信し装着者同士の対面状態や近接状態を検知するための赤外線送受信機（ＴＲＳＥ＿ＩＲ）、照度センサ（ＴＲＳＥ＿Ｌ）および心拍計（ＴＲＳＥ＿Ｈ）がある。 As an example of a sensor included in the sensor unit (TRSE), an acceleration sensor (TRSE_A) for measuring the movement of the body and a wearable sensor (TR) are used to communicate with each other to detect a face-to-face state or a proximity state between wearers. There is an infrared transceiver (TRSE_IR), an illumination sensor (TRSE_L) and a heart rate monitor (TRSE_H).
　また、ウェアラブルセンサ（ＴＲ）は、必要に応じてユーザ（ＵＳ）にアンケートを提示し回答を受け取るための入出力部（ＴＲＩＯ）を有しても良い。アンケート入力のための機能はウェアラブルセンサ（ＴＲ）とは別の端末、たとえばＰＣまたはスマートフォン（図示省略）に持たせてもよい。 Also, the wearable sensor (TR) may have an input / output unit (TRIO) for presenting a questionnaire to the user (US) and receiving a response as needed. The function for inputting the questionnaire may be provided in a terminal other than the wearable sensor (TR), such as a PC or a smartphone (not shown).
　入出力部（ＴＲＩＯ）は、アンケート設問および時刻を表示するための画面（ＴＲＩＯ＿Ｄ）、ユーザ（ＵＳ）が回答を入力したり画面を切り替えたりする操作を行うためのボタン（ＴＲＩＯ＿Ｂ）、および、特定の時刻にユーザ（ＵＳ）に回答を促すためのスピーカー（ＴＲＩＯ＿Ｓ）を有する。 The input / output unit (TRIO) has a screen (TRIO_D) for displaying the questionnaire question and the time, a button (TRIO_B) for the user (US) to input an answer and switch the screen, and a specific It has a speaker (TRIO_S) for prompting the user (US) to answer at the time.
　記憶部（ＴＲＭＥ）は、時刻情報を保持する時計（ＴＲＣＫ）、ウェアラブルセンサ（ＴＲ）を識別する端末ＩＤ情報（ＴＲＩＤ）、計測した結果であるセンシングデータ（ＴＲＭＥ＿Ｓ）、および、アンケート回答結果のデータ（ＴＲＭＥ＿Ｑ）を格納する。また、ウェアラブルセンサ（ＴＲ）は、電源を確保するための電池（ＴＲＢＴ）を有する。 The storage unit (TRME) stores a clock (TRCK) that holds time information, terminal ID information (TRID) that identifies the wearable sensor (TR), sensing data (TRME_S) that is the measurement result, and questionnaire response result data. Store (TRME_Q). Further, the wearable sensor (TR) has a battery (TRBT) for securing a power source.
　制御部（ＴＲＣＯ）は、センシングおよび送受信の制御を行う。具体的には、制御部（ＴＲＣＯ）は、時計（ＴＲＣＫ）内の時刻情報を標準時と同期させる時刻同期（ＴＲＣＯ＿Ｔ）、センサ部（ＥＭＳＥ）のセンサを制御し人間の行動や状態に関するデータを取得し時刻情報を付与するセンシング制御（ＴＲＣＯ＿Ｓ）、アンケートの表示や回答の入力を制御するアンケート制御（ＴＲＣＯ＿Ｑ）、さらにそれらのデータを送受信部（ＴＲＳＲ）を介して分析サーバ（ＳＳ）に送信するデータ送信（ＴＲＳＤ）を実施する。 The control unit (TRCO) controls sensing and transmission / reception. Specifically, the control unit (TRCO) acquires time data (TRCO_T) that synchronizes the time information in the clock (TRCK) with the standard time, controls the sensor of the sensor unit (EMSE), and obtains data on human behavior and state. Sensing control (TRCO_S) that gives time information, questionnaire control (TRCO_Q) that controls the display of questionnaires and input of answers, and data that sends those data to the analysis server (SS) via the transmission / reception unit (TRSR). Perform transmission (TRSD).
　監視カメラ（ＳＣ）は、壁や天井またはＰＣに取り付けられたカメラであり、空間に滞在する人の数や動きなどを動画または静止画で記録するためのものである。監視カメラ（ＳＣ）は、センサ部（ＳＣＳＥ）、記憶部（ＳＣＭＥ）、電池（図示省略）、制御部（ＳＣＣＯ）および送受信部（ＳＣＳＲ）を有する。 A surveillance camera (SC) is a camera attached to a wall, ceiling, or PC, and is used to record the number and movements of people staying in a space as moving images or still images. The surveillance camera (SC) has a sensor unit (SCSE), a storage unit (SCME), a battery (not shown), a control unit (SCCO), and a transmission / reception unit (SCSR).
　センサ部（ＳＣＳＥ）は、カメラ（ＳＣＳＥ＿Ｃ）を有する。また、記憶部（ＳＣＭＥ）は、時刻情報を保持する時計（ＳＣＣＫ）、監視カメラ（ＳＣ）を識別する端末ＩＤ情報（ＳＣＩＤ）や記録した結果である動画データ（ＳＣＭＥ＿Ｍ）を格納する。また、監視カメラ（ＳＣ）は、電源を確保するための電池（図示省略）を有する。 The sensor unit (SCSE) has a camera (SCSE_C). The storage unit (SCME) also stores a clock (SCCK) that holds time information, terminal ID information (SCID) that identifies the surveillance camera (SC), and moving image data (SCME_M) that is the recorded result. Further, the surveillance camera (SC) has a battery (not shown) for securing a power source.
　さらに、制御部（ＳＣＣＯ）は、撮影や送受信の制御を行い、時計（ＳＣＣＫ）内の時刻情報を標準時と同期させる時刻同期（ＳＣＣＯ＿Ｔ）、カメラ（ＳＣＳＥ＿Ｃ）を制御し空間を撮影する撮影制御（ＳＣＣＯ＿Ｒ）、さらにその撮影データを送受信部（ＳＣＳＲ）を介して分析サーバ（ＳＳ）に送信するデータ送信（ＳＣＳＤ）を実施する。 Furthermore, the control unit (SCCO) controls shooting and transmission / reception, controls time synchronization (SCCO_T) that synchronizes time information in the clock (SCCK) with standard time, and controls camera (SCSE_C) to shoot space ( SCCO_R), and further data transmission (SCSD) of transmitting the captured data to the analysis server (SS) via the transmission / reception unit (SCSR).
　分析サーバ（ＳＳ）は、収集した人間の行動や環境に関するデータを分析し、人間の業務のパフォーマンスと環境状況に関する数理モデルを生成する役目を持つ。分析サーバ（ＳＳ）は、送受信部（ＳＳＳＲ）、記憶部（ＳＳＭＥ）および制御部（ＳＳＣＯ）を有する。 The analysis server (SS) has the role of analyzing the collected data on human behavior and environment and generating a mathematical model of human business performance and environmental conditions. The analysis server (SS) has a transmission / reception unit (SSSR), a storage unit (SSME), and a control unit (SSCO).
　記憶部（ＳＳＭＥ）は、環境測定機（ＥＭ）、ウェアラブルセンサ（ＴＲ）及び監視カメラ（ＳＣ）などの端末ＩＤ及び種類を管理する端末管理情報（ＳＳＭＥ＿Ｔ）、それらが設置された空間の種類を示すエリア定義情報（ＳＳＭＥ＿Ａ）、特徴量抽出（ＳＳＣＯ＿ＦＥ）を行うためのプログラム群（ＳＳＭＥ＿Ｐ）、収集したセンシングデータを格納するセンシングＤＢ（ＳＳＭＥ＿ＳＤ）、抽出された特徴量を格納する特徴量ＤＢ（ＳＳＭＥ＿ＦＤ）、及び、算出した数理モデルを格納する数理モデルＤＢ（ＳＳＭＥ＿ＭＤ）を有する。 The storage unit (SSME) stores terminal management information (SSME_T) that manages terminal IDs and types of environment measuring machines (EM), wearable sensors (TR), surveillance cameras (SC), and the type of space in which they are installed. Area definition information (SSME_A) shown, a program group (SSME_P) for performing feature amount extraction (SSCO_FE), a sensing DB (SSME_SD) that stores the collected sensing data, and a feature amount DB (SSME_FD) that stores the extracted feature amount. ) And a mathematical model DB (SSME_MD) that stores the calculated mathematical model.
　制御部（ＳＳＣＯ）は、ネットワーク（ＮＷ）を介して送受信部（ＳＳＳＲ）から諸々のデータを受信（ＳＳＲＤ）し、特徴量抽出プログラム（ＳＳＭＥ＿Ｐ）を用いてそれぞれのデータの種類に合わせた特徴量を抽出する（ＳＳＣＯ＿ＦＥ）。特徴量の具体例としては、ウェアラブルセンサ（ＴＲ）から得られたデータから算出されるものとしては、歩数、平均心拍数、他者との対面時間や対面人数、会話時の双方向度、加速度センサデータを用いて職場や個人の活性状態を示すハピネス度、エリア別の滞在場所や滞在時間、及びアンケート回答結果などがある。環境測定機（ＥＭ）から得られたデータから算出する特徴量の例としては、５分または１０分単位の平均室温または温度と湿度から算出する不快指数などがある。監視カメラ（ＳＣ）から得られたデータから算出する特徴量の例としては、カメラが置かれたエリアの滞在人数、滞在者の属性別の人数比、滞在者の歩行または静止などの活動状態などがある。 The control unit (SSCO) receives various types of data (SSRD) from the transmission / reception unit (SSSR) via the network (NW), and uses the feature amount extraction program (SSME_P) to set the feature amount according to each data type. Is extracted (SSCO_FE). Specific examples of the feature amount include those calculated from data obtained from a wearable sensor (TR), such as the number of steps, the average heart rate, the face-to-face time with another person or the number of face-to-face persons, the degree of interaction during conversation, and the acceleration There are happiness levels that indicate the active state of the workplace and individuals using sensor data, the place and time of stay in each area, and the results of questionnaire responses. An example of the feature amount calculated from the data obtained from the environment measuring machine (EM) is an average room temperature in 5 or 10 minutes, or a discomfort index calculated from temperature and humidity. Examples of the feature amount calculated from the data obtained from the surveillance camera (SC) include the number of people staying in the area where the camera is placed, the ratio of the number of people by attribute of the visitor, and the activity status of the walker or stillness of the visitor. There is.
　また、環境測定機（ＥＭ）、ウェアラブルセンサ（ＴＲ）及び監視カメラ（ＳＣ）などの一連の端末は時刻同期されているため、複数の種類の端末から取得された同時間帯のデータを組み合わせることで、例えば「室温２５～２８度のエリア下で歩数６０歩／分以上」といった組み合わせ特徴量を生成しても良い。 In addition, since a series of terminals such as environment measuring equipment (EM), wearable sensors (TR), and surveillance cameras (SC) are time-synchronized, data of the same time zone acquired from multiple types of terminals should be combined. Then, for example, a combination feature amount such as “60 steps / minute or more under an area of room temperature of 25 to 28 degrees” may be generated.
　次に、事前に少なくとも１つ以上の目的変数として使える人間の行動または状態に関する特徴量（アンケートの回答結果も含む）を定義しておく。順に１つずつ目的変数を指定（ＳＳＣＯ＿ＳＯ）して、統計分析（ＳＳＣＯ＿ＳＡ）とそこから得られた数理モデル格納（ＳＳＣＯ＿ＭＤ）を行う。統計分析（ＳＳＣＰ＿ＳＡ）は、単回帰分析や重回帰分析、機械学習などを用いて、所定の目的変数と統計的有意に関連する説明変数（環境に関する特徴量や行動に関する特徴量またはそれらを組み合わせた特徴量）を見つけ出すものである。その目的変数と説明変数の組み合わせ群を、数理モデルと呼ぶ。数理モデルを生成することで学習フェーズが完了する。 Next, define in advance the characteristic quantities (including the questionnaire response results) related to human actions or states that can be used as at least one or more objective variables. Objective variables are designated one by one (SSCO_SO) in order, and statistical analysis (SSCO_SA) and mathematical model storage (SSCO_MD) obtained therefrom are performed. Statistical analysis (SSCP_SA) uses a single regression analysis, multiple regression analysis, machine learning, etc., and a predetermined objective variable and explanatory variables related to statistical significance (feature amount related to environment or feature amount related to behavior or a combination thereof). (Feature amount). The combination group of the objective variable and the explanatory variable is called a mathematical model. The learning phase is completed by generating a mathematical model.
＜図３Ａ、図３Ｂ：運用フェーズのシステム構成図＞
　図３Ａ及び図３Ｂは、本発明の実施の形態の運用フェーズにおけるクライアント（ＣＬ）、アプリケーションサーバ（ＡＳ）、環境測定機（ＥＭ）および監視カメラ（ＳＣ）の一例の構成を示すブロック図である。 <FIG. 3A, FIG. 3B: System configuration diagram of operation phase>
FIG. 3A and FIG. 3B are block diagrams showing an example of configurations of a client (CL), an application server (AS), an environment measuring machine (EM), and a surveillance camera (SC) in an operation phase according to the embodiment of the present invention. ..
　運用フェーズは、学習フェーズで生成した数理モデルを用いて、執務空間活用レコメンドシステムを運用するためのフェーズである。数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）は、学習フェーズの分析サーバ（ＳＳ）で作成した数理モデルＤＢ（ＳＳＭＥ＿ＭＤ）をコピーまたは統合したものであるが、適用する職場は学習フェーズと運用フェーズとで同じである必要はない。つまり、数理モデルを作るためのデータを収集する職場と、それを利用した執務空間活用レコメンドシステムを活用する職場とは異なっても良い。 The operation phase is a phase for operating the work space utilization recommendation system using the mathematical model generated in the learning phase. The mathematical model DB (ASME_MD) is a copy or integration of the mathematical model DB (SSME_MD) created by the learning phase analysis server (SS), but the workplace to be applied needs to be the same in the learning phase and the operation phase. There is no. In other words, the workplace that collects the data for creating the mathematical model and the workplace that uses the work space utilization recommendation system may be different.
　運用フェーズにおいて、環境測定機（ＥＭ）と監視カメラ（ＳＣ）は学習フェーズと同等の構成であるため説明を省略する。センサの種類および機種は学習フェーズと全く同一である必要はないが、誤差の範囲および設置場所の基準などについて、学習フェーズで用いたものと類似した性能である方が望ましい。また、運用フェーズの環境測定機（ＥＭ）および監視カメラ（ＳＣ）が取得したセンシングデータ（ＥＭＭＥ＿Ｓ）および動画データ（ＳＣＭＥ＿Ｍ）の送り先がアプリケーションサーバ（ＡＳ）である点は、学習フェーズとは異なる。 In the operation phase, the environment measurement device (EM) and the surveillance camera (SC) have the same configuration as the learning phase, so explanations are omitted. The type and model of the sensor need not be exactly the same as in the learning phase, but it is preferable that the range of error and the criteria of the installation location are similar to those used in the learning phase. Further, the destination of the sensing data (EMME_S) and the moving image data (SCME_M) acquired by the environment measuring machine (EM) and the monitoring camera (SC) in the operation phase is the application server (AS), which is different from the learning phase.
　アプリケーションサーバ（ＡＳ）は、数理モデルを活用し、ユーザ（ＵＳ）の業務目的に適した執務空間内のエリアを推薦するための処理を行う役目を持つ。アプリケーションサーバ（ＡＳ）は、送受信部（ＡＳＳＲ）、記憶部（ＡＳＭＥ）、環境データ処理部（ＡＳＣＥ）およびレコメンド処理部（ＡＳＣＯ）を有する。 The application server (AS) has a role of utilizing a mathematical model and performing processing for recommending an area in the work space suitable for the business purpose of the user (US). The application server (AS) has a transmission / reception unit (ASSR), a storage unit (ASME), an environment data processing unit (ASCE), and a recommendation processing unit (ASCO).
　記憶部（ＳＳＭＥ）は、環境測定機（ＥＭ）および監視カメラ（ＳＣ）などの端末ＩＤおよび種類を管理する端末管理情報（ＡＳＭＥ＿Ｔ）、それらが設置された空間の種類を示すエリア定義情報（ＡＳＭＥ＿Ａ）、特徴量抽出（ＡＳＣＥ＿ＦＥ）を行うためのプログラム群（図示省略）、収集したセンシングデータを格納するセンシングＤＢ（図示省略）、逐次更新される最新の執務空間のデータを管理する執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）、および、分析サーバ（ＳＳ）からコピーまたは部分的に抽出した数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）を有する。 The storage unit (SSME) includes terminal management information (ASME_T) that manages terminal IDs and types of environment measuring machines (EM) and surveillance cameras (SC), and area definition information (ASME_A) that indicates the type of space in which they are installed. ), A group of programs (not shown) for performing feature amount extraction (ASCE_FE), a sensing DB (not shown) that stores the collected sensing data, and an office space information DB that manages the latest office space data that is sequentially updated. (ASME_SD) and a mathematical model DB (ASME_MD) copied or partially extracted from the analysis server (SS).
　図１２Ａ～図１２Ｃに数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）または（ＳＳＭＥ＿ＭＤ）に含まれるテーブルの構成の一例を示す。 12A to 12C show an example of the configuration of tables included in the mathematical model DB (ASME_MD) or (SSME_MD).
　具体的には、図１２Ａは、本発明の実施の形態の数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）および（ＳＳＭＥ＿ＭＤ）に含まれる目的変数テーブル（ＳＳＭＥ＿ＭＤ＿Ｏ）および（ＡＳＭＥ＿ＭＤ＿Ｏ）の構成の一例を示す説明図である。図１２Ｂは、本発明の実施の形態の数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）および（ＳＳＭＥ＿ＭＤ）に含まれる数理モデルテーブルテーブル（ＳＳＭＥ＿ＭＤ＿Ｔ１）および（ＡＳＭＥ＿ＭＤ＿Ｔ１）の構成の一例を示す説明図である。図１２Ｃは、本発明の実施の形態の数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）および（ＳＳＭＥ＿ＭＤ）に含まれる解説文テーブル（ＳＳＭＥ＿ＭＤ＿Ｅ）および（ＡＳＭＥ＿ＭＤ＿Ｅ）の構成の一例を示す説明図である。 Specifically, FIG. 12A is an explanatory diagram showing an example of the configuration of objective variable tables (SSME_MD_O) and (ASME_MD_O) included in the mathematical model DBs (ASME_MD) and (SSME_MD) according to the embodiment of this invention. FIG. 12B is an explanatory diagram showing an example of the configuration of the mathematical model table tables (SSME_MD_T1) and (ASME_MD_T1) included in the mathematical model DBs (ASME_MD) and (SSME_MD) according to the embodiment of this invention. FIG. 12C is an explanatory diagram showing an example of a configuration of commentary tables (SSME_MD_E) and (ASME_MD_E) included in the mathematical model DBs (ASME_MD) and (SSME_MD) according to the embodiment of this invention.
　数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）および（ＳＳＭＥ＿ＭＤ）に含まれるテーブルの種類およびカラムの種類などの構造はほぼ同じである。図１２Ａには目的変数を定義するテーブル（ＳＳＭＥ＿ＭＤ＿Ｏ）および（ＡＳＭＥ＿ＭＤ＿Ｏ）の構造の一例を示す。これはあらかじめ目的変数として利用可能な人間の業務のパフォーマンスに関する行動特徴量やアンケート項目を指定したテーブルである。統計分析（ＳＳＣＯ＿ＳＡ）ではこれらを目的変数として分析が行われる。 The structures such as the types of tables and the types of columns included in the mathematical model DBs (ASME_MD) and (SSME_MD) are almost the same. FIG. 12A shows an example of the structure of the tables (SSME_MD_O) and (ASME_MD_O) that define the objective variables. This is a table in which behavior characteristic quantities and questionnaire items related to human work performance that can be used as objective variables are specified in advance. In the statistical analysis (SSCO_SA), analysis is performed using these as objective variables.
　図１２Ｂには、数理モデルテーブル（ＳＳＭＥ＿ＭＤ＿Ｔ１）および（ＡＳＭＥ＿ＭＤ＿Ｔ１）の構造の一例を示す。ここでは目的変数として＃１、つまり「集中継続時間」を選択した場合に絞り込まれた結果を表示している。数理モデルテーブル（ＳＳＭＥ＿ＭＤ＿Ｔ１）および（ＡＳＭＥ＿ＭＤ＿Ｔ１）に記載されるのは、選択された目的変数と統計的に関連することが確認された説明変数である。 FIG. 12B shows an example of the structure of the mathematical model tables (SSME_MD_T1) and (ASME_MD_T1). Here, the result narrowed down when # 1 is selected as the objective variable, that is, "concentration duration time" is displayed. Described in the mathematical model tables (SSME_MD_T1) and (ASME_MD_T1) are explanatory variables that are confirmed to be statistically related to the selected objective variable.
　たとえば図１２Ｂの数理モデルテーブルの１行目では、環境が「温度２３～２５℃」の範囲かつ環境音が「５０～６０ｄＢ」の中で、「アンケート回答による思考の速さが４～５と高い」状態で「デスクワーク＿３０分以上」行った場合に集中継続時間が高いということを示している。このように、環境に関する特徴量と人間の行動または状態に関する特徴量との組み合わせ特徴量を説明変数とし、特定の目的変数との統計的関連を明示する。 For example, in the first line of the mathematical model table of FIG. 12B, the environment is in the range of “temperature 23 to 25 ° C.” and the environmental sound is “50 to 60 dB”, and “the speed of thinking by the questionnaire response is 4 to 5”. This indicates that the intensive duration time is high when “Deskwork_30 minutes or more” is performed in the “high” state. In this way, the combination feature amount of the feature amount relating to the environment and the feature amount relating to the human behavior or state is used as the explanatory variable, and the statistical relationship with the specific objective variable is clearly indicated.
　テーブル内の統計量ｒはその関連の強さを示す統計量であり、たとえば重回帰係数などを記載する。また、統計分析を行う際に、特徴量の時刻に留意すると分析結果の解釈の仕方が変わる。目的変数と説明変数が同じ時間帯になるものを用いた場合には、説明変数の状態である間に目的変数が向上することを示す。これを分析種別カラムではＤｕｒｉｎｇと記載している。 Statistic amount r in the table is a statistic amount indicating the strength of the relation, and for example, multiple regression coefficient is described. Also, when statistical analysis is performed, the way of interpreting the analysis result changes if attention is paid to the time of the feature amount. It is shown that the objective variable improves while the explanatory variable is in the state of the explanatory variable when the objective variable and the explanatory variable have the same time zone. This is described as During in the analysis type column.
　また、目的変数が説明変数より後の時刻になるように選択した場合には、説明変数の状態の後に目的変数が向上することを示す。これを分析種別カラムではＡｆｔｅｒと記載している。さらに、時間の区切りを１日で区切り、同じ日付の目的変数と説明変数のデータを用いた場合には、説明変数の状態があった日には目的変数が上がることを示す。これを分析種別カラムではＤａｙと記載している。 Also, if the objective variable is selected to come after the explanatory variable, it indicates that the objective variable improves after the explanatory variable state. This is described as After in the analysis type column. Furthermore, when the time division is divided into one day and the data of the objective variable and the explanatory variable of the same date are used, it is shown that the objective variable goes up on the day when there is the state of the explanatory variable. This is described as Day in the analysis type column.
　さらに、上記のようなテーブルのままではユーザ（ＵＳ）が理解しにくいので、図１２Ｃに示すように、テーブルの値に基づいて自動的に生成した解説文を格納する解説文テーブル（ＳＳＭＥ＿ＭＤ＿Ｅ）および（ＳＳＭＥ＿ＭＤ＿Ｅ）もあるとよい。 Further, since it is difficult for the user (US) to understand with the above table as it is, as shown in FIG. 12C, a comment sentence table (SSME_MD_E) for storing comment sentences automatically generated based on the values of the table and (SSME_MD_E) is also preferable.
　図１３は、本発明の実施の形態の執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）の構成の一例を示す説明図である。 FIG. 13 is an explanatory diagram showing an example of the configuration of the office space information DB (ASME_SD) according to the embodiment of this invention.
　執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）は、環境測定機（ＥＭ）および監視カメラ（ＳＣ）で得たデータおよびその特徴量を、時刻データと関連付けて管理するためのデータベースである。１つの部屋またはエリアに複数の端末が設置されていることがありえるが、執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）は、端末管理情報（ＡＳＭＥ＿Ｔ）に含まれる情報と関連付けて、部屋またはエリアを示すＲｏｏｍＩＤと時刻をキーとしたテーブルになっている。執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）は、屋内の環境測定機（ＥＭ）から得た温度、湿度および音量など、屋外の環境測定機（ＥＭ）から得た日照量および雨量など、ならびに、監視カメラ（ＳＣ）から得た滞在人数などの特徴量のデータを、エリア別かつ時刻ごとに示すテーブルである。 The work space information DB (ASME_SD) is a database for managing the data obtained by the environment measuring device (EM) and the surveillance camera (SC) and the feature amount thereof in association with the time data. Although it is possible that multiple terminals are installed in one room or area, the work space information DB (ASME_SD) is associated with the information included in the terminal management information (ASME_T), and the RoomID and time indicating the room or area. It is a table with the key. The work space information DB (ASME_SD) includes temperature, humidity, and volume obtained from an indoor environment measuring instrument (EM), sunshine and rain amounts obtained from an outdoor environment measuring instrument (EM), and a monitoring camera (SC). ) Is a table showing the data of the characteristic amount such as the number of stays obtained from FIG.
　図１３では省略されているが、執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）は、使用するために予約が必要な部屋またはエリアに関しては、その予約状況を示すデータをさらに含んでもよい。本実施形態のリアルタイム執務空間活用レコメンドシステムの運用フェーズが適用される職場において、部屋またはエリアの予約状況を管理するための予約システムが当該リアルタイム執務空間活用レコメンドシステムとは独立に稼働している場合には、その予約システムから読み出された予約状況を示すデータが執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）に格納されてもよいし、執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）が予約状況を示すデータを保持せずに、必要に応じて予約システムが参照されてもよい。また、ユーザが使用したい時間帯が既に予約されている部屋またはエリアは、ユーザに提示する対象から除外してもよい。 Although omitted in FIG. 13, the work space information DB (ASME_SD) may further include data indicating the reservation status of a room or area that requires a reservation to use. In the workplace to which the operation phase of the real-time office space utilization recommendation system is applied, the reservation system for managing the reservation status of the room or area is operating independently of the real-time office space utilization recommendation system. May store data indicating the reservation status read from the reservation system in the work space information DB (ASME_SD), or the work space information DB (ASME_SD) may not store the data indicating the reservation status. The reservation system may be referred to as necessary. In addition, a room or area in which the time zone that the user wants to use has already been reserved may be excluded from the target presented to the user.
　図１４は、本発明の実施の形態のエリア定義情報（ＳＳＭＥ＿Ａ）および（ＡＳＭＥ＿Ａ）の構成の一例を示す説明図である。 FIG. 14 is an explanatory diagram showing an example of the configuration of the area definition information (SSME_A) and (ASME_A) according to the embodiment of this invention.
　エリア定義情報（ＳＳＭＥ＿Ａ）は、計測が行われる職場内のエリアおよび部屋の特性に関する情報を管理するためのテーブルである。なお、本実施の形態では、部屋と、部屋以外のエリア（例えば屋上庭園など）とを総称して単に「エリア」と記載する場合がある。 Area definition information (SSME_A) is a table for managing information about the characteristics of the area and room in the workplace where the measurement is performed. In the present embodiment, a room and an area other than the room (for example, a rooftop garden) may be collectively referred to simply as “area”.
　エリア定義情報（ＳＳＭＥ＿Ａ）には、それぞれのエリアまたは部屋を示すＲｏｏｍＩＤをキーとし、名称、種類、閉／開、マップ上座標および予約要否などが格納される。名称および種類は、それぞれのエリアまたは部屋の名称およびその種類を示す。閉／開は、それぞれのエリアまたは部屋が、人が自由に出入りできる開空間かそうではない閉空間かを示す。また、リアルタイム執務空間活用レコメンドシステムは職場全体のマップの画像を保持しており、マップ上座標は、その画像内の各エリアまたは部屋の座標を示す。予約要否は、それぞれのエリアまたは部屋を利用するために予約が必要であるか否かを示す。 The area definition information (SSME_A) has a RoomID indicating each area or room as a key, and stores the name, type, closed / open, coordinates on the map, necessity of reservation, and the like. The name and type indicate the name and type of each area or room. Closed / Open indicates whether each area or room is an open space in which a person can freely enter or leave, or not. Further, the real-time office space utilization recommendation system holds an image of a map of the entire workplace, and the coordinates on the map indicate the coordinates of each area or room in the image. The necessity of reservation indicates whether or not a reservation is necessary to use each area or room.
　図１５Ａ～図１５Ｃに端末管理情報（ＳＳＭＥ＿Ｔ）および（ＡＳＭＥ＿Ｔ）を示す。これは、計測している個別の端末を示すＩＤと、その機種、設置されたエリアのＲｏｏｍＩＤ、端末が含むセンサの種類、及び設置箇所の属性（例えば設置場所が屋外かどうか）を示す情報とを管理するものである。 15A to 15C show terminal management information (SSME_T) and (ASME_T). This is an ID indicating the individual terminal that is measuring, its model, RoomID of the installed area, the type of sensor included in the terminal, and information indicating the attribute of the installation location (for example, whether the installation location is outdoors). Is to manage.
　図１５Ａは、本発明の実施の形態の環境計測器（ＥＭ）によって計測された情報を格納する端末管理情報（ＳＳＭＥ＿Ｔ＿ＥＭ）及び（ＡＳＭＥ＿Ｔ＿ＥＭ）の構成の一例を示す説明図である。 FIG. 15A is an explanatory diagram showing an example of a configuration of terminal management information (SSME_T_EM) and (ASME_T_EM) that stores information measured by the environment measuring instrument (EM) according to the embodiment of this invention.
　図１５Ａに示す端末管理情報（ＳＳＭＥ＿Ｔ＿ＥＭ）及び（ＡＳＭＥ＿Ｔ＿ＥＭ）は、各環境計測器（ＥＭ）を識別する端末ＩＤ、各環境計測器（ＥＭ）の機種、各環境計測器（ＥＭ）が設置された部屋またはエリアを識別するＲｏｏｍＩＤ、各環境計測器（ＥＭ）が温度センサ、湿度センサおよび騒音測定器を含んでいるか否か、及び、各環境計測器（ＥＭ）が屋外または屋内のいずれに設置されているか、といった情報を含む。 In the terminal management information (SSME_T_EM) and (ASME_T_EM) shown in FIG. 15A, a terminal ID for identifying each environmental measuring instrument (EM), a model of each environmental measuring instrument (EM), and each environmental measuring instrument (EM) are installed. RoomID for identifying a room or area, whether each environmental measuring instrument (EM) includes a temperature sensor, a humidity sensor and a noise measuring instrument, and whether each environmental measuring instrument (EM) is installed outdoors or indoors. Information such as whether or not it is included.
　図１５Ｂは、本発明の実施の形態のウェアラブルセンサ（ＴＲ）によって計測された情報を格納する端末管理情報（ＳＳＭＥ＿Ｔ＿ＴＲ）の構成の一例を示す説明図である。 FIG. 15B is an explanatory diagram showing an example of the configuration of the terminal management information (SSME_T_TR) which stores information measured by the wearable sensor (TR) according to the embodiment of this invention.
　図１５Ｂに示す端末管理情報（ＳＳＭＥ＿Ｔ＿ＴＲ）は、各ウェアラブルセンサ（ＴＲ）を識別する端末ＩＤ、各ウェアラブルセンサ（ＴＲ）の種類（例えば名札が他端末であるか腕輪型端末であるかなど）、各ウェアラブルセンサ（ＴＲ）の機種、各ウェアラブルセンサ（ＴＲ）を装着しているユーザ（ＵＳ）を識別するユーザＩＤ、各ウェアラブルセンサ（ＴＲ）が加速度センサ、赤外線送受信機及び心拍計を含んでいるか否か、といった情報を含む。 The terminal management information (SSME_T_TR) shown in FIG. 15B is a terminal ID for identifying each wearable sensor (TR), a type of each wearable sensor (TR) (for example, whether the name tag is another terminal or a bracelet type terminal, etc.), A model of each wearable sensor (TR), a user ID for identifying a user (US) wearing each wearable sensor (TR), whether each wearable sensor (TR) includes an acceleration sensor, an infrared transmitter / receiver, and a heart rate meter Information such as whether or not it is included.
　なお、端末管理情報は、当該職場で計測している種類の端末のものだけがあればよいため、本実施例の形態の例では学習フェーズではウェアラブルセンサ（ＴＲ）に関する端末管理情報は不要である。 It should be noted that the terminal management information need only be that of the type of terminal that is being measured at the workplace, so in the example of the present embodiment, the terminal management information regarding the wearable sensor (TR) is unnecessary in the learning phase. ..
　図１５Ｃは、本発明の実施の形態の監視カメラ（ＳＣ）によって計測された情報を格納する端末管理情報（ＳＳＭＥ＿Ｔ＿ＳＣ）及び（ＡＳＭＥ＿Ｔ＿ＳＣ）の構成の一例を示す説明図である。 FIG. 15C is an explanatory diagram showing an example of the configuration of the terminal management information (SSME_T_SC) and (ASME_T_SC) that stores information measured by the surveillance camera (SC) according to the embodiment of this invention.
　図１５Ｃに示す端末管理情報（ＳＳＭＥ＿Ｔ＿ＳＣ）及び（ＡＳＭＥ＿Ｔ＿ＳＣ）は、各監視カメラ（ＳＣ）を識別する端末ＩＤ、各監視カメラ（ＳＣ）の機種、各監視カメラ（ＳＣ）が設置された部屋またはエリアを識別するＲｏｏｍＩＤ、各監視カメラ（ＳＣ）の解像度、各監視カメラ（ＳＣ）によって撮影される映像のフレームレート、各監視カメラ（ＳＣ）の画角（例えば広角か否か）、及び、各監視カメラ（ＳＣ）が屋外または屋内のいずれに設置されているか、といった情報を含む。 The terminal management information (SSME_T_SC) and (ASME_T_SC) shown in FIG. 15C is a terminal ID for identifying each surveillance camera (SC), a model of each surveillance camera (SC), a room or area in which each surveillance camera (SC) is installed. RoomID for identifying each, the resolution of each surveillance camera (SC), the frame rate of the video imaged by each surveillance camera (SC), the angle of view of each surveillance camera (SC) (for example, whether it is wide-angle), and each surveillance It includes information such as whether the camera (SC) is installed outdoors or indoors.
　次に、再び図３を参照して、アプリケーションサーバ（ＡＳ）について説明する。アプリケーションサーバ（ＡＳ）は、環境データ処理部（ＡＳＣＥ）を有し、環境測定機（ＥＭ）および監視カメラ（ＳＣ）から得たデータを定期的に更新する。環境データ処理部（ＡＳＣＥ）は、送受信部（ＡＳＳＲ）を通してネットワーク（ＮＷ）越しにデータを受信（ＡＳＲＤ）し、そのデータから分析サーバ（ＳＳ）と同等の方法で特徴量抽出（ＡＳＣＥ＿ＦＥ）し、抽出した特徴量を時刻情報と共に執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）に追加する（ＡＳＣＥ＿ＳＯ）。 Next, the application server (AS) will be described with reference to FIG. 3 again. The application server (AS) has an environmental data processing unit (ASCE), and periodically updates the data obtained from the environmental measuring instrument (EM) and the surveillance camera (SC). The environmental data processing unit (ASCE) receives data (ASRD) through the network (NW) through the transmission / reception unit (ASSR), and extracts feature quantities (ASCE_FE) from the data by a method equivalent to that of the analysis server (SS). The extracted feature amount is added to the work space information DB (ASME_SD) together with the time information (ASCE_SO).
　一方で、レコメンド処理部（ＡＳＣＯ）は、クライアント（ＣＬ）の入出力機能を介して受信したユーザ（ＵＳ）からの問い合わせを起点として、その時点の執務空間のレコメンドを提供する処理である。クライアント（ＣＬ）の入力機能、例えばキーボード（ＣＬＩＫ）またはタッチパネル（ＣＬＩＴ）を用いてユーザ（ＵＳ）が業務目標を入力すると（ＣＬＣＯ＿Ｉ）、クライアント（ＣＬ）はそれをアプリケーションサーバ（ＡＳ）に送信する（ＣＬＣＯ＿Ｓ）。 On the other hand, the recommendation processing unit (ASCO) is a process that provides a recommendation of the work space at that time, starting from an inquiry from the user (US) received via the input / output function of the client (CL). When the user (US) inputs a business goal (CLCO_I) using an input function of the client (CL), for example, a keyboard (CLIK) or a touch panel (CLIT), the client (CL) sends it to the application server (AS). (CLCO_S).
　レコメンド処理部（ＡＳＣＯ）は、送受信部（ＡＳＳＲ）を介して業務目標を受信し（ＡＳＣＯ＿Ｒ）、数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）から選択された業務目標を目的変数とするレコードを検索し、該当する説明変数のリストを取得する（ＡＳＣＯ＿ＳＭ）。その次に、レコメンド処理部（ＡＳＣＯ）は、執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）を検索し、最新のデータで説明変数のリストと類似する状態にある部屋・エリアのリストを取得する（ＡＳＣＯ＿ＳＳ）。 The recommendation processing unit (ASCO) receives the business objectives via the transmission / reception unit (ASSR) (ASCO_R), retrieves the record having the business objective selected as the objective variable from the mathematical model DB (ASME_MD), and applies the corresponding explanation. Get a list of variables (ASCO_SM). Next, the recommendation processing unit (ASCO) searches the work space information DB (ASME_SD) and acquires a list of rooms / areas in a state similar to the list of explanatory variables with the latest data (ASCO_SS).
　さらに、レコメンド処理部（ＡＳＣＯ）は、説明変数の範囲と実際の執務空間の状態との差を示す値によって優先度を算出し（ＡＳＣＯ＿ＣＰ）、レコメンドに順位付けをしてレコメンド項目を決定し（ＡＳＣＯ＿ＤＲ）、マップ画像などと合わせて表示する画面を生成し、クライアント（ＣＬ）に送る（ＡＳＣＯ＿ＯＤ）。 Furthermore, the recommendation processing unit (ASCO) calculates the priority by a value indicating the difference between the range of the explanatory variables and the actual state of the work space (ASCO_CP), ranks the recommendations, and determines the recommended items ( (ASCO_DR), a screen to be displayed together with a map image, etc. is generated and sent to the client (CL) (ASCO_OD).
　クライアント（ＣＬ）は、画面を受信し（ＣＬＣＯ＿Ｒ）、それをディスプレイ（ＣＬＯＤ）などの出力機器に表示（ＣＬＣＯ＿Ｄ）する。クライアント（ＣＬ）の制御部（ＣＬＣＯ）内にある入出力制御（ＣＬＣＣ）では、アプリケーションサーバ（ＡＳ）から送られた画面を表示したり、ユーザ（ＵＳ）の操作に基づく入力を受け付けてアプリケーションサーバ（ＡＳ）に送ったりする場面での制御を行う。 The client (CL) receives the screen (CLCO_R) and displays it (CLCO_D) on an output device such as a display (CLOD). In the input / output control (CLCC) in the control unit (CLCO) of the client (CL), the screen sent from the application server (AS) is displayed, and the input based on the operation of the user (US) is accepted to the application server. Controls the situation when sending to (AS).
　また、数理モデルはデータが蓄積されるほど精度が向上する。そのため、他の職場または同一の職場で並行して学習フェーズを行っている場合には、学習フェーズで得られた新しいデータを反映した数理モデルを、定期的に手動または自動で更新し、数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）に追記または変更することも可能である（ＡＳＣＯ＿ＲＭ）。また、レコメンドとして執務空間情報から抽出した最適なエリアを推薦するだけでなく、会議室予約システムなどの外部システムと連携する機能（ＡＳＣＯ＿ＩＵ）を持たせ、ユーザ（ＵＳ）がレコメンドを受け取ったあと続けてクライアント（ＣＬ）を使ってレコメンドされたエリアの予約を取れるようにしても良い。 Moreover, the accuracy of the mathematical model improves as the data is accumulated. Therefore, when the learning phase is being carried out in parallel in other workplaces or the same workplace, the mathematical model that reflects the new data obtained in the learning phase is updated manually or automatically on a regular basis, and the mathematical model is updated. It is also possible to add or change to DB (ASME_MD) (ASCO_RM). Moreover, not only recommending the optimum area extracted from the work space information as a recommendation, but also providing a function (ASCO_IU) that cooperates with an external system such as a conference room reservation system to continue after the user (US) receives the recommendation. The client (CL) may be used to make a reservation for the recommended area.
　ここで本発明の特徴として、過去の蓄積データを用いて統計分析結果を格納する数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）と、執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）とを別のものに分けて構成したことがある。数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）および（ＳＳＭＥ＿ＭＤ）は複数の職場に共通の汎用的な行動特徴量および環境特徴量のみを扱い、執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）では運用フェーズを実施している特定の職場にのみ有用な個別の部屋およびエリアに関する情報を扱うように区分した。これらを区別することで他の職場のデータから生成した数理モデルＤＢを別の職場の運用に転用することが可能になる。また、複数の職場で得たデータを統合して数理モデルＤＢを作ることも可能になる。 A feature of the present invention is that the mathematical model DB (ASME_MD) that stores the statistical analysis results using the past accumulated data and the office space information DB (ASME_SD) are separately configured. The mathematical model DBs (ASME_MD) and (SSME_MD) handle only general-purpose behavioral features and environmental features that are common to multiple workplaces, and the work space information DB (ASME_SD) is used for specific workplaces that are implementing the operation phase. Divided to handle only useful information about individual rooms and areas. By distinguishing these, the mathematical model DB generated from the data of another workplace can be diverted to the operation of another workplace. It is also possible to create a mathematical model DB by integrating data obtained at a plurality of workplaces.
　一方で、それらから得られた知見は一般論であり、ユーザ（ＵＳ）にとっては理解が難しく価値の低いものである。そこで、執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）を用いてユーザ（ＵＳ）が所属する職場のリアルタイムデータを反映した情報に変換してレコメンドを提供することで、ユーザ（ＵＳ）は具体的に自分が行くべき場所を理解することができる。このように汎用的な知見を蓄積したデータを数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）で検索し、その次に特定の職場のための情報を執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）で検索するという順序でユーザの問いに回答する。これによって、バックボーンとなるデータの母数を増やすことで知見の信頼性を高め、合わせてユーザ（ＵＳ）の利便性の向上を両立することができる。 On the other hand, the knowledge obtained from them is a general theory, which is difficult for users (US) to understand and of low value. Therefore, by using the work space information DB (ASME_SD) and converting the information into the information reflecting the real-time data of the workplace to which the user (US) belongs, and providing the recommendation, the user (US) should specifically go. I can understand the place. In this order, the user is asked in the order of searching the mathematical model DB (ASME_MD) for data that accumulates general-purpose knowledge, and then searching the office space information DB (ASME_SD) for information for a specific workplace. To answer. As a result, the reliability of the knowledge can be increased by increasing the parameter of the data serving as the backbone, and the convenience of the user (US) can be improved at the same time.
　＜図４Ａ～図６Ｂ：クライアントの表示画面例＞
　図４Ａ～図６Ｂは、本発明の実施の形態のクライアント（ＣＬ）のディスプレイ（ＣＬＯＤ）に表示される画面の一例を示す説明図である。 <FIG. 4A to FIG. 6B: Client display screen example>
4A to 6B are explanatory diagrams showing an example of screens displayed on the display (CLOD) of the client (CL) according to the embodiment of the present invention.
　これらの画面はアプリケーションサーバ（ＡＳ）において生成され（ＡＳＣＯ＿ＯＤ）、クライアントの入出力制御（ＣＬＣＣ）によって表示されるが、クライアント（ＣＬ）内で画面生成されてもよい。また、図４Ａ～図６Ｂにおいてはクライアント（ＣＬ）として大型タッチパネルまたはＰＣのＷｅｂブラウザなどを想定して図示しているが、スマートフォンまたはタブレットなどの別の手段を用いてもよい。 These screens are generated in the application server (AS) (ASCO_OD) and displayed by the client input / output control (CLCC), but may be generated in the client (CL). 4A to 6B are illustrated assuming a large touch panel or a Web browser of a PC as the client (CL), other means such as a smartphone or a tablet may be used.
　図４Ａの画面例１（ＣＬＯＤ＿１）は、ユーザ（ＵＳ）が操作していない時間帯に自動で表示される画面の例である。この画面は、環境測定機（ＥＭ）によって得られた最新時刻の環境に関する指標を可視化する。具体的には、画面例１（ＣＬＯＤ＿１）は、日付と時刻（Ｄ１１）、可視化する指標の種類（Ｄ１２）、および、職場のマップに対応付けた可視化データ（Ｄ１３）を表示する。これは、執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）、端末管理情報（ＡＳＭＥ＿Ｔ）およびエリア定義情報（ＡＳＭＥ＿Ａ）の情報を組み合わせて生成される画面である。ユーザ（ＵＳ）がボタン１（ＣＬＩＯ＿Ｂ１）を押すと画面例２（ＣＬＯＤ＿２）の検索モードに遷移する。 Screen example 1 (CLOD_1) in FIG. 4A is an example of a screen that is automatically displayed during a time period when the user (US) is not operating. This screen visualizes the index regarding the environment at the latest time obtained by the environment measuring device (EM). Specifically, the screen example 1 (CLOD_1) displays the date and time (D11), the type of index to be visualized (D12), and the visualization data (D13) associated with the map of the workplace. This is a screen generated by combining the information of the office space information DB (ASME_SD), the terminal management information (ASME_T), and the area definition information (ASME_A). When the user (US) presses button 1 (CLIO_B1), the screen transitions to the search mode of screen example 2 (CLOD_2).
　図４（に、ユーザ（ＵＳ）に業務目標入力（ＣＬＣＯ＿Ｉ）をさせるための画面例２（ＣＬＯＤ＿２）を示す。通知欄（Ｄ２１）は、ユーザ（ＵＳ）への問いを記載する欄であり、例えば「今からどのように働きたいですか？」などを表示する。また、入力させる項目の例としては何人で仕事をするのか、またどのような業務目標をもっているのかを人数によって選択肢を絞りこんで表示する。「集中してデスクワーク」および「アイディア生成」などの業務目標の選択肢は、目的変数テーブル（ＡＳＭＥ＿ＭＤ＿Ｏ）の項目と対応したものになっている。ユーザ（ＵＳ）が人数および業務目標を選択し、ボタン２（ＣＬＩＯ＿Ｂ２）を押すと次の画面例３（ＣＬＯＤ＿３）に遷移する。 4 shows (in FIG. 4) a screen example 2 (CLOD_2) for allowing the user (US) to input a business goal (CLCO_I). The notification field (D21) is a field for writing a question to the user (US), For example, "How do you want to work now?" Is displayed, etc. Also, as an example of the items to be input, narrow down the choices by the number of people to work and what kind of work goals they have. The options of the business goals such as “concentrate desk work” and “idea generation” correspond to the items in the objective variable table (ASME_MD_O). When selected and button 2 (CLIO_B2) is pressed, the screen transitions to the next screen example 3 (CLOD_3).
　図５Ａの画面例３（ＣＬＯＤ＿３）は、ユーザ（ＵＳ）の状態を尋ねる画面の一例である。状態を分析に用いない場合は、この画面はスキップしても良い。例えば「気分」「体調」「思考」などの項目については、その程度（例えば気分がどの程度よいか、体調がどの程度よいか、思考がどの程度速いか）を、１～５の範囲でユーザ（ＵＳ）に選択させる。ユーザ（ＵＳ）がボタン３（ＣＬＩＯ＿Ｂ３）を押すと画面例４（ＣＬＯＤ＿４）に遷移する。 Screen example 3 (CLOD_3) in FIG. 5A is an example of a screen for inquiring about the state of the user (US). This screen may be skipped if the state is not used for analysis. For items such as “mood”, “physical condition”, and “thinking”, the degree (for example, how good the mood is, how good the physical condition is, how fast the thinking is) is set in the range of 1 to 5 by the user. (US) to select. When the user (US) presses button 3 (CLIO_B3), the screen transitions to screen example 4 (CLOD_4).
　図５Ｂの画面例４（ＣＬＯＤ＿４）は、ここまでに入力された業務目標と状態の情報を踏まえて計算されたレコメンドを表示する画面の一例である。レコメンド項目決定（ＡＳＣＯ＿ＤＲ）で抽出された優先度の高いエリア（この例では３件）が表示される。通知欄（Ｄ４１）に、このページがおすすめ結果であることを提示し、解説欄（Ｄ４２）には解説文テーブル（ＡＳＭＥ＿ＭＤ＿Ｅ）から選ばれた該当する文章が差し込まれる。 Screen example 4 (CLOD_4) in FIG. 5B is an example of a screen displaying the recommendation calculated based on the information of the business goal and the status input so far. Areas with high priority (three in this example) extracted by the recommendation item determination (ASCO_DR) are displayed. The notification column (D41) presents that this page is a recommended result, and the comment column (D42) is populated with the relevant sentence selected from the comment sentence table (ASME_MD_E).
　また、レコメンドされた３つのエリアについては、エリア定義情報（ＡＳＭＥ＿Ａ）に登録されている各エリアの名称と共に、そのエリアの監視カメラ（ＳＣ）によって撮影された（例えばリアルタイムの）映像が表示されても良い。図５Ｂの例では、映像表示欄（Ｄ４３）にこのような映像が表示される。映像を表示する理由は当該エリアの混雑度などの状況をユーザ（ＵＳ）が把握するためであるので、ぼかしをかけたりＣＧに変換したりして映っている人物が特定できないようにする処理を加えても良い。 For the three recommended areas, the name of each area registered in the area definition information (ASME_A) and the video (eg, real-time) taken by the surveillance camera (SC) of the area are displayed. Is also good. In the example of FIG. 5B, such an image is displayed in the image display field (D43). The reason for displaying the image is that the user (US) understands the situation such as the congestion degree of the area, and therefore, the process of making it difficult to identify the person in the image by blurring or converting to CG is performed. You may add.
　なお、レコメンド処理部は、監視カメラ（ＳＣ）から得られたリアルタイムの映像から、各エリアの現在の滞在人数を推定し、その結果、例えば既に満員でユーザが使用できない、または、混雑の程度がユーザの業務に適切でない（例えば生産性の低下が予想される）、などと判断したエリアを、ユーザにレコメンドする対象から除外してもよい。 Note that the recommendation processing unit estimates the current number of people staying in each area from real-time video obtained from the surveillance camera (SC), and as a result, for example, the user is already full and cannot be used, or the degree of congestion is determined. Areas that are determined not to be suitable for the user's work (for example, a decrease in productivity is expected) may be excluded from the target of recommendation to the user.
　また、レコメンドの根拠と各エリアの特徴をユーザ（ＵＳ）が理解できるように、数理モデルテーブル（ＡＳＭＥ＿ＭＤ）の情報を図示しているのが根拠表示欄（Ｄ４４）である。ここでは、集中という目的変数に対して有効な説明変数であった「環境音が５０～６０ｄＢ」かつ「温度が２３～２５℃」という情報を２段で表示し、各エリアの現在の環境音と温度がその範囲にどれだけ近いかを星の数で表現している。ユーザ（ＵＳ）がボタン４（ＣＬＩＯ＿Ｂ４）を押すことで提示された選択肢から１つを選ぶと、画面例６（ＣＬＯＤ＿６）に遷移する。 Also, the reason display column (D44) illustrates the information of the mathematical model table (ASME_MD) so that the user (US) can understand the reason for recommendation and the characteristics of each area. Here, the information that “environmental sound is 50 to 60 dB” and “temperature is 23 to 25 ° C.”, which are effective explanatory variables for the objective variable of concentration, is displayed in two stages, and the current environmental sound of each area is displayed. And how close the temperature is to the range is expressed by the number of stars. When the user (US) presses button 4 (CLIO_B4) to select one of the presented options, the screen transitions to screen example 6 (CLOD_6).
　図６Ｂの画面例６（ＣＬＯＤ＿６）は、ユーザ（ＵＳ）がエリアを選択したときに参照している画面を表示しているディスプレイ（ＣＬＯＤ）の位置から、選択されたエリアまでの経路（Ｄ６１）を表示する。ユーザが表示内容を確認して、画面を閉じるためのボタン６（ＣＬＩＯ＿Ｂ６）を操作すると、画面例６（ＣＬＯＤ＿６）が閉じ、画面例１（ＣＬＯＤ＿１）に遷移する。これで、ユーザ（ＵＳ）に対する執務場所のレコメンドの処理は終了する。 The screen example 6 (CLOD_6) in FIG. 6B is a route (D61) from the position of the display (CLOD) displaying the screen referred to when the user (US) selects the area to the selected area. Is displayed. When the user confirms the display content and operates the button 6 (CLIO_B6) for closing the screen, the screen example 6 (CLOD_6) is closed and the screen example 1 (CLOD_1) is displayed. This completes the process of recommending the work place to the user (US).
　ただし、ユーザ（ＵＳ）が予約の必要なエリアを選択した場合には、クライアント（ＣＬ）がアプリケーションサーバ（ＡＳ）の外部システム連携制御（ＡＳＣＯ＿ＩＵ）を通して会議室予約システム（図示省略）などに接続し、連続的に図６Ａに示す画面例５（ＣＬＯＤ＿５）に遷移して予約を行えるようにして良い。このときクライアント（ＣＬ）は例えば予約の終了時刻（Ｄ５１）と社員番号（Ｄ５２）をユーザ（ＵＳ）に入力させ、現在時刻から所望の終了時刻までの会議室を確保する。 However, when the user (US) selects an area requiring reservation, the client (CL) connects to the conference room reservation system (not shown) through the external system cooperation control (ASCO_IU) of the application server (AS). , The screen example 5 (CLOD_5) shown in FIG. 6A may be continuously transitioned to make a reservation. At this time, the client (CL) causes the user (US) to input the end time (D51) of the reservation and the employee number (D52), for example, and secures the conference room from the current time to the desired end time.
　＜図７：端末の表示画面例＞
　図７は、本発明の実施の形態のウェアラブルセンサ（ＴＲ）にてユーザ（ＵＳ）にアンケートを行う場合の画面（ＴＲＩＯ＿Ｄ）の一例を示す説明図である。 <Figure 7: Terminal display screen example>
FIG. 7 is an explanatory diagram showing an example of a screen (TRIO_D) when a questionnaire is given to the user (US) by the wearable sensor (TR) according to the embodiment of the present invention.
　ウェアラブルセンサ（ＴＲ）は、スピーカー（ＴＲＩＯ＿Ｓ）で所定のまたはランダムな時刻にアラームを鳴らし、ユーザ（ＵＳ）に回答を促す。画面（ＴＲＩＯ＿Ｄ）に設問（ＴＲＩＯ＿Ｄ１）と回答の番号と対応する凡例（ＴＲＩＯ＿Ｄ２）を表示する。ユーザ（ＵＳ）は凡例に対応する複数のボタン（ＴＲＩＯ＿Ｂ）のうち１つを押すことで回答が完了する。 The wearable sensor (TR) sounds an alarm on the speaker (TRIO_S) at a predetermined or random time, and prompts the user (US) for an answer. A question (TRIO_D1) and a legend (TRIO_D2) corresponding to the answer number are displayed on the screen (TRIO_D). The user (US) completes the answer by pressing one of the buttons (TRIO_B) corresponding to the legend.
　＜図８：学習フェーズ　センシングのシーケンス＞
　図８は、本発明の実施の形態の学習フェーズにおいて、ウェアラブルセンサ（ＴＲ）、環境測定機（ＥＭ）および監視カメラ（ＳＣ）において行われるセンシングの手順と、そのデータを分析サーバ（ＳＳ）に格納するまでの手順とを示すシーケンス図である。 <Figure 8: Learning phase Sensing sequence>
FIG. 8 shows the procedure of sensing performed by the wearable sensor (TR), the environment measuring device (EM) and the surveillance camera (SC) and the data thereof in the analysis server (SS) in the learning phase of the embodiment of the present invention. It is a sequence diagram which shows the procedure until it stores.
　ウェアラブルセンサ（ＴＲ）は、ユーザ（ＵＳ）がスイッチを入れたり充電器から取り上げたりした際（ＵＳ８１）に起動（ＴＲ８１）し、時刻を同期（ＴＲＣＯ＿Ｔ）する。続けて、ウェアラブルセンサ（ＴＲ）はセンシング（ＴＲ８２）を開始し、一定の時刻ごとにセンシングデータを送信（ＴＲＳＤ）する。また、環境測定機（ＥＭ）は、起動後に時刻同期（ＥＭＣＯ＿Ｔ）し、センシングを行い（ＥＭ８２）、一定の時刻ごとにセンシングデータを送信（ＥＭＳＤ）する。監視カメラ（ＳＣ）も同様に、起動（ＳＣ８１）後、時刻同期（ＳＣＣＯ＿Ｔ）し、撮影を行い（ＳＣ８２）、一定の時刻ごとに動画データを送信する（ＳＣＳＤ）。 The wearable sensor (TR) is activated (TR81) when the user (US) switches it on or picks it up from the charger (US81) and synchronizes the time (TRCO_T). Subsequently, the wearable sensor (TR) starts sensing (TR82) and transmits sensing data (TRSD) at regular time intervals. Further, the environment measuring instrument (EM) performs time synchronization (EMCO_T) after starting, performs sensing (EM82), and transmits sensing data (EMSD) at regular time intervals. Similarly, the surveillance camera (SC) also performs time synchronization (SCCO_T) after starting (SC81), performs shooting (SC82), and transmits moving image data at regular time intervals (SCSD).
　また、ウェアラブルセンサ（ＴＲ）でアンケートを行う場合は、タイマによって所定のまたはランダムな時刻に起動し（ＴＲ８３）、それをスピーカー（ＴＲＩＯ＿Ｓ）でユーザに通知（ＴＲ８４）する。そして、ウェアラブルセンサ（ＴＲ）は、画面（ＴＲＩＯ＿Ｄ）にアンケート項目を表示（ＴＲ８５）し、ユーザ（ＵＳ）が回答（ＵＳ８２）するとその回答データを分析サーバ（ＳＳ）に送信（ＴＲ８６）する。このプロセスはアンケート制御（ＴＲＣＯ＿Ｑ）によって制御されるが、ウェアラブルセンサ（ＴＲ）ではなくスマートフォンまたはＰＣなど別の端末を用いて実施しても良い。 Also, when conducting a questionnaire with a wearable sensor (TR), it is activated at a predetermined or random time by a timer (TR83), and the speaker (TRIO_S) notifies the user (TR84). Then, the wearable sensor (TR) displays the questionnaire items (TR85) on the screen (TRIO_D), and when the user (US) answers (US82), sends the answer data to the analysis server (SS) (TR86). This process is controlled by the questionnaire control (TRCO_Q), but it may be performed by using another terminal such as a smartphone or a PC instead of the wearable sensor (TR).
　最後に、分析サーバ（ＳＳ）は、センシングデータおよびアンケートデータを受信（ＳＳＲＤ）し、データをセンシングＤＢ（ＳＳＭＥ＿ＳＤ）に格納（ＳＳ８１）する。 Finally, the analysis server (SS) receives the sensing data and the questionnaire data (SSRD) and stores the data in the sensing DB (SSME_SD) (SS81).
　＜図９：学習フェーズ　数理モデル生成のシーケンス＞
　図９は、本発明の実施の形態の学習フェーズにおいて、分析サーバ（ＳＳ）において行われる数理モデルを生成する手順と、分析サーバ（ＳＳ）の数理モデルＤＢ（ＳＳＭＥ＿ＭＤ）をコピー、抜粋または統合してアプリケーションサーバ（ＡＳ）の数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）を更新する手順とを示すシーケンス図である。 <Figure 9: Learning phase Sequence of mathematical model generation>
FIG. 9 shows a procedure for generating a mathematical model performed in the analysis server (SS) and a mathematical model DB (SSME_MD) of the analysis server (SS) copied, extracted or integrated in the learning phase of the embodiment of the present invention. It is a sequence diagram which shows the procedure of updating the mathematical model DB (ASME_MD) of the application server (AS).
　分析サーバ（ＳＳ）は、例えば週に一度など、所定の頻度で所定の時刻に起動し（ＳＳ８１）、記憶部（ＳＳＭＥ）にリクエストを出し、センシングＤＢ内の所定の日付および対象のセンシングデータを取得する（ＳＳ８２）。次に、分析サーバ（ＳＳ）は、そのデータから特徴量抽出（ＳＳＣＯ＿ＦＥ）を行い、特徴量ＤＢに格納する。特徴量抽出の実施方法はデータの種類によって異なるため、分析サーバ（ＳＳ）は全種類のセンシングデータの計算が完了するまでそれらの処理を繰り返す（ＳＳ８３）。 The analysis server (SS) is activated at a predetermined time at a predetermined frequency (SS81), for example, once a week, issues a request to the storage unit (SSME), and stores a predetermined date and target sensing data in the sensing DB. Acquire (SS82). Next, the analysis server (SS) performs feature quantity extraction (SSCO_FE) from the data and stores it in the feature quantity DB. Since the method of performing the feature amount extraction differs depending on the type of data, the analysis server (SS) repeats these processes until the calculation of all types of sensing data is completed (SS83).
　次に、分析サーバ（ＳＳ）は、あらかじめ決められた目的変数テーブル（ＳＳＭＥ＿ＭＤ＿Ｏ）から１つの目的変数を指定（ＳＳＣＯ＿ＳＯ）し、統計分析（ＳＳＣＯ＿ＳＡ）を行って目的変数と関連のある説明変数を抽出し、その結果を数理モデルとして数理モデルＤＢに格納する（ＳＳＣＯ＿ＭＤ）。分析サーバ（ＳＳ）はこれを目的変数テーブルの全ての目的変数に関して計算が終了するまで繰り返し（ＳＳ８４）、終了となる（ＳＳ８５）。 Next, the analysis server (SS) designates one objective variable (SSCO_SO) from a predetermined objective variable table (SSME_MD_O), performs statistical analysis (SSCO_SA), and extracts an explanatory variable associated with the objective variable. Then, the result is stored in the mathematical model DB as a mathematical model (SSCO_MD). The analysis server (SS) repeats this until the calculation is completed for all the objective variables in the objective variable table (SS84), and ends (SS85).
　さらに、運用フェーズを開始する際、または学習フェーズと運用フェーズとを並行して別の職場で進めている際には、分析サーバ（ＳＳ）は、定期的に数理モデルＤＢ（ＳＳＭＥ＿ＭＤ）をアプリケーションサーバ（ＡＳ）の数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）に手動または自動でコピーし、更新する（ＡＳＣＯ＿ＲＭ）。このとき、分析サーバ（ＳＳ）は、数理モデルＤＢ（ＳＳＭＥ＿ＭＤ）から一部分を抜き出したものをアプリケーションサーバ（ＡＳ）に送ってもよいし、複数の職場による複数種類の数理モデルＤＢ（ＳＳＭＥ＿ＭＤ）を統合してそれをアプリケーションサーバ（ＡＳ）の数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）としても良い。また、常に数理モデルＤＢ（ＳＳＭＥ＿ＭＤ）と数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）の内容が一致するように、数理モデルＤＢ（ＳＳＭＥ＿ＭＤ）が更新される都度、その差分のみを数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）に反映しても良い。 Furthermore, when starting the operation phase or advancing the learning phase and the operation phase in parallel at different workplaces, the analysis server (SS) periodically applies the mathematical model DB (SSME_MD) to the application server. It is manually or automatically copied and updated in the mathematical model DB (ASME_MD) of (AS) (ASCO_RM). At this time, the analysis server (SS) may send a part of the mathematical model DB (SSME_MD) extracted to the application server (AS), or integrate a plurality of mathematical model DBs (SSME_MD) by a plurality of workplaces. Then, it may be used as the mathematical model DB (ASME_MD) of the application server (AS). Also, each time the mathematical model DB (SSME_MD) is updated, only the difference is reflected in the mathematical model DB (ASME_MD) so that the contents of the mathematical model DB (SSME_MD) and the mathematical model DB (ASME_MD) always match. Is also good.
　＜図１０：運用フェーズ　環境データ更新のシーケンス＞
　図１０は、本発明の実施の形態の運用フェーズにおいて、アプリケーションサーバ（ＡＳ）において計測された環境データを処理し更新する手順を示すシーケンス図である。 <Figure 10: Operation phase environment data update sequence>
FIG. 10 is a sequence diagram showing a procedure for processing and updating the environmental data measured by the application server (AS) in the operation phase of the embodiment of the present invention.
　環境測定機（ＥＭ）および監視カメラ（ＳＣ）が起動してからセンシングデータを送信するまでのフローは図８の学習フェーズと同様である。 The flow from the activation of the environmental measuring device (EM) and the surveillance camera (SC) to the transmission of sensing data is the same as in the learning phase of FIG.
　アプリケーションサーバ（ＡＳ）は、センシングデータを受け取り（ＡＳＲＤ）、それらから特徴量を抽出して（ＡＳＣＯ＿ＦＥ）、執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）に最新の環境特徴量を入力し、更新する（ＡＳＣＯ＿ＳＯ）。 The application server (AS) receives the sensing data (ASRD), extracts the feature amount from them (ASCO_FE), inputs the latest environmental feature amount into the office space information DB (ASME_SD), and updates (ASCO_SO).
　＜図１１：運用フェーズ　レコメンド提供のシーケンス＞
　図１１は、本発明の実施の形態の運用フェーズにおいて、ユーザ（ＵＳ）がクライアント（ＣＬ）を操作して入力した業務目標に対して、アプリケーションサーバ（ＡＳ）がレコメンドを生成して画面に提示する手順を示すシーケンス図である。 <Figure 11: Sequence of operation phase recommendation provision>
FIG. 11 shows that, in the operation phase of the embodiment of the present invention, the application server (AS) generates a recommendation and presents it on the screen with respect to the business goal input by the user (US) operating the client (CL). It is a sequence diagram which shows the procedure to do.
　クライアント（ＣＬ）は、電源を入れるなどして起動（ＣＬ１１）されたら、ネットワーク（ＮＷ）を通じてアプリケーションサーバ（ＡＳ）から最新時刻の執務空間情報を取得し、初期画面（その例が図４Ａに示した画面例１（ＣＬＯＤ＿１））を自動的に表示する（ＣＬ１２）。次に、ユーザ（ＵＳ）が働く場所を決めたいと検索画面を起動した（ＵＳ１１）ら、検索画面（その例が図４Ｂに示した画面例２（ＣＬＯＤ＿２））が表示される（ＣＬ１３）。画面の問いに答えてユーザ（ＵＳ）が今からどのような観点でパフォーマンスを上げたいかという業務目標を入力すると（ＵＳ１２）（ＣＬＣＯ＿Ｉ）、クライアント（ＣＬ）は、それをアプリケーションサーバ（ＡＳ）に送信する（ＣＯＣＯ＿Ｓ）。 When the client (CL) is started (CL11) by turning on the power, it acquires the latest working space information from the application server (AS) through the network (NW), and the initial screen (the example is shown in FIG. 4A). Screen example 1 (CLOD_1)) is automatically displayed (CL12). Next, when the search screen is activated (US11) to decide where the user (US) works, the search screen (screen example 2 (CLOD_2) shown in FIG. 4B) is displayed (CL13). When the user (US) inputs a business goal from what perspective the user wants to improve performance in response to the question on the screen (US12) (CLCO_I), the client (CL) sends it to the application server (AS). Send (COCO_S).
　アプリケーションサーバ（ＡＳ）は、業務目標を受信し（ＡＳＣＯ＿Ｒ）、数理モデルＤＢ（ＡＳＭＥ＿ＭＤ）からその目標を目的変数とするレコードを検索し（ＡＳＣＯ＿ＳＭ）、次にその説明変数の条件と近い環境になっているエリアを執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ）から検索する（ＡＳＣＯ＿ＳＳ）。アプリケーションサーバ（ＡＳ）は、その条件によって絞り込まれた候補の中で類似度および統計的信頼性に基づいて優先度を計算し（ＡＳＣＯ＿ＣＰ）、たとえば上位３つのレコメンド項目を決定し（ＡＳＣＯ＿ＤＲ）、データおよび解説文と統合した画面を生成（ＡＳＣＯ＿ＯＤ）する。 The application server (AS) receives the business goal (ASCO_R), retrieves a record having the goal as an objective variable from the mathematical model DB (ASME_MD) (ASCO_SM), and then becomes an environment close to the condition of the explanatory variable. The working area information DB (ASME_SD) is searched for the existing area (ASCO_SS). The application server (AS) calculates the priority based on the similarity and the statistical reliability among the candidates narrowed down by the condition (ASCO_CP), for example, determines the top three recommended items (ASCO_DR), and And a screen integrated with the commentary is generated (ASCO_OD).
　クライアント（ＣＬ）は、受信したレコメンド画面（その例が図５Ｂに示した画面例５（ＣＬＯＤ＿４））を表示（ＣＬ１４）し、さらにユーザがレコメンド項目の中から１つを選択（ＵＳ１３）すると、最後に現在地から選んだエリアまでの経路の地図（その例が図６Ｂに示した画面例６（ＣＬＯＤ＿６））などを表示して完了（ＣＬ１５）となる。 The client (CL) displays the received recommendation screen (screen example 5 (CLOD_4) of which the example is shown in FIG. 5B) (CL14), and when the user further selects one of the recommended items (US13), Finally, a map of a route from the current location to the selected area (the example is the screen example 6 (CLOD_6) shown in FIG. 6B) and the like are displayed to complete (CL15).
　以上に説明した本発明の代表的な実施形態をまとめると、次の通りとなる。 The representative embodiments of the present invention described above are summarized as follows.
　すなわち、本発明の一実施形態であるデータ分析システム（例えば図１～図３Ｂに示すシステム）は、人物の生産性に関する目的指標（例えば図１２Ａに示す目的変数）と人物の活動場所（執務空間）の環境に関する環境指標との関連を示す数理モデル（例えば図１２Ｂに示す数理モデルテーブル（ＡＳＭＥ＿ＭＤ＿Ｔ１））を保持する記憶部（例えばアプリケーションサーバ（ＡＳ）の記憶部（ＡＳＭＥ））と、センサ（例えば環境測定機（ＥＭ）のセンサ部（ＥＭＳＥ）又は監視カメラ（ＳＣ）のセンサ部（ＳＣＳＥ））から取得した人物の活動場所の環境に関するデータである環境データと、人物によって入力された人物の活動に関する目標を含む業務目標データ（例えば図４Ｂの画面を介して入力されるデータ）とを受け付け、業務目標データと数理モデルとに基づいて、人物の生産性を高めるのに適した環境指標の条件を探索し（例えば数理モデル探索（ＡＳＣＯ＿ＳＭ））、環境指標の条件と環境データとに基づいて、人物の生産性を高めるのに適した活動場所に関する情報を探索し（例えば執務空間情報検索（ＡＳＣＯ＿ＳＳ））、探索によって得られた活動場所に関する情報を出力（例えば画面生成（ＡＳＣＯ＿ＯＤ））する推奨処理部（例えばレコメンド処理部（ＡＳＣＯ））と、を有する。 That is, the data analysis system (for example, the system shown in FIG. 1 to FIG. 3B) which is one embodiment of the present invention, the target index (for example, the target variable shown in FIG. 12A) relating to the productivity of the person and the activity place (work space) of the person. ), The storage unit (for example, the storage unit (ASME) of the application server (AS)) holding the mathematical model (for example, the mathematical model table (ASME_MD_T1) shown in FIG. 12B) and the sensor (for example, Environmental data that is data about the environment of the activity place of the person acquired from the sensor unit (EMSE) of the environment measuring machine (EM) or the sensor unit (SCSE) of the surveillance camera (SC), and the activity of the person input by the person Acceptance of business goal data (for example, data input via the screen of FIG. 4B) including a goal relating to the environmental goal conditions suitable for increasing the productivity of a person based on the business goal data and the mathematical model. (For example, mathematical model search (ASCO_SM)), and based on the condition of the environmental index and the environmental data, information regarding an activity place suitable for enhancing the productivity of the person is searched (for example, the office space information search (ASCO_SS). )), And a recommended processing unit (for example, a recommendation processing unit (ASCO)) that outputs (for example, screen generation (ASCO_OD)) information about the activity place obtained by the search.
　これによって、人と環境に関する時間連続的なセンサデータを分析して、業務における人のパフォーマンスを高めるために効果的な職場空間をリアルタイムにマッチングすることが可能となる。 By doing this, it becomes possible to analyze time-continuous sensor data related to people and the environment, and match in real time an effective workplace space to improve the performance of people in work.
　ここで、記憶部は、数理モデルを格納する第１のデータベース（例えば数理モデルＤＢ（ＡＳＭＥ＿ＭＤ））と、環境データを格納する第２のデータベース（例えば執務空間情報ＤＢ（ＡＳＭＥ＿ＳＤ））とを保持し、推奨処理部は、第１のデータベースを参照して人物の生産性を高めるのに適した環境指標の条件を探索し（例えば数理モデル探索（ＡＳＣＯ＿ＳＭ））、その後、第２のデータベースを参照して、人物の生産性を高めるのに適した活動場所に関する情報を探索する（例えば執務空間情報検索（ＡＳＣＯ＿ＳＳ））。 Here, the storage unit holds a first database (for example, a mathematical model DB (ASME_MD)) that stores a mathematical model and a second database (for example, a work space information DB (ASME_SD)) that stores environmental data. The recommendation processing unit refers to the first database to search for a condition of the environmental index suitable for increasing the productivity of the person (for example, mathematical model search (ASCO_SM)), and then refers to the second database. Then, information regarding an activity place suitable for increasing the productivity of the person is searched (for example, office space information search (ASCO_SS)).
　このように、組織を限定せずに適用できる汎用の第１のデータベースと、各組織専用の第２のデータベースとを分けることによって、他の組織で取得したデータによる知見を用い、自組織のエリア名称及び特性を反映した具体的な方法で推薦を提示することが可能になる。 In this way, by dividing the general-purpose first database that can be applied without limiting the organization and the second database dedicated to each organization, the knowledge of the data obtained by other organizations is used, and the area of the own organization is used. It becomes possible to present the recommendation in a concrete method that reflects the name and characteristics.
　また、数理モデルにおける環境指標は、活動場所の温度、湿度及び騒音の少なくとも一つ（例えば図１２Ｂの数理モデルテーブル（ＡＳＭＥ＿ＭＤ＿Ｔ１）に含まれる温度、湿度及び音の少なくともいずれか）を含み、環境データは、人物がこれから活動を行う可能性がある複数の活動場所に設置された前記センサから取得された、数理モデルに含まれる指標の値（例えば温度センサ（ＥＭＳＥ＿Ｔ）によって計測された温度の値、湿度センサ（ＥＭＳＥ＿Ｈ）によって計測された湿度の値、及び騒音測定機（ＥＭＳＥ＿Ｓ）によって計測された騒音の値）を含んでもよい。 In addition, the environmental index in the mathematical model includes at least one of temperature, humidity and noise of the activity place (for example, at least one of temperature, humidity and sound included in the mathematical model table (ASME_MD_T1) of FIG. 12B), and environmental data Is a value of an index included in the mathematical model (for example, a temperature value measured by a temperature sensor (EMSE_T), obtained from the sensors installed in a plurality of activity places where a person may perform an activity from now on, It may include the humidity value measured by the humidity sensor (EMSE_H) and the noise value measured by the noise measuring device (EMSE_S).
　このように、どのような場所でも計測可能な一般的な環境の指標を用いることによって、ある組織で取得したデータによる知見を他の組織において利用することが可能になる。 In this way, by using a general environmental index that can be measured at any place, it is possible to use the knowledge obtained by the data of one organization in other organizations.
　また、推奨処理部は、業務目標データに対応する目的指標と環境指標との関連に基づいて、人物の生産性を高めるのに適した環境指標の条件を探索し（例えば図４Ｂの画面に示すように「集中してデスクワーク」が選択された場合に、それに対応する目的変数である「集中継続時間」（図１２Ａ）と環境指標との関連を示す数理モデル（例えば図１２Ｂの数理モデルテーブル（ＡＳＭＥ＿ＭＤ＿Ｔ１））から、生産性を高めるのに適した環境指標の条件を探索し）、環境指標の条件と環境データとの関係が所定の条件を満たす（例えば両者の類似度が高い）活動場所に関する情報を、人物の生産性を高めるのに適した活動場所に関する情報として探索してもよい。 Further, the recommendation processing unit searches for a condition of the environmental index suitable for increasing the productivity of the person based on the relationship between the objective index corresponding to the work target data and the environmental index (for example, shown in the screen of FIG. 4B). When "concentrated deskwork" is selected as described above, a mathematical model showing a relationship between the objective variable "concentration duration" (FIG. 12A) and the environmental index (for example, the mathematical model table of FIG. 12B ( ASME_MD_T1)) to search for a condition of an environmental index suitable for improving productivity), and a relationship between the condition of the environmental index and the environmental data satisfies a predetermined condition (for example, the degree of similarity between the two is high) The information may be searched for as information about activity sites suitable for increasing a person's productivity.
　これによって、これから行おうとする業務の目的に適した活動場所を、その組織に存在する具体的な場所（例えば部屋又はエリア）として提示することができる。 By doing this, it is possible to present an activity place suitable for the purpose of the business you are going to do as a concrete place (for example, a room or area) existing in the organization.
　また、数理モデルにおいて、目的指標と環境指標と人物の状態（例えば図１２Ｂの数理モデルテーブル（ＡＳＭＥ＿ＭＤ＿Ｔ１）における「状態」）とが関連づけられ、推奨処理部は、人物によって入力された人物の状態（例えば図５Ａの画面を介して入力されたユーザの気分、体調、思考の状態等）をさらに受け付け、入力された人物の状態と、業務目標データと、数理モデルと、に基づいて、人物の生産性を高めるのに適した環境指標の条件を探索してもよい。 Further, in the mathematical model, the objective index, the environmental index, and the state of the person (for example, “state” in the mathematical model table (ASME_MD_T1) of FIG. 12B) are associated with each other, and the recommendation processing unit causes the state of the person input by the person ( For example, the user's mood, physical condition, thinking state, etc.) input via the screen of FIG. 5A are further accepted, and the person production is performed based on the input person's state, business goal data, and mathematical model. The condition of the environmental index suitable for improving the property may be searched.
　これによって、人物の状態も考慮して、業務に適した活動場所を提示することができる。 With this, it is possible to present the activity place suitable for the work, considering the person's state.
　また、推奨処理部は、探索によって得られた活動場所の現在又は未来の状態を示す情報を取得し、活動場所の現在又は未来の状態に基づいて、出力する活動場所に関する情報を決定してもよい。 In addition, the recommendation processing unit acquires information indicating the current or future state of the activity place obtained by the search, and based on the current or future state of the activity place, determines information regarding the activity place to be output. Good.
　ここで、活動場所の現在又は未来の状態を示す情報は、センサから取得された情報（例えば監視カメラ（ＳＣ）の映像）に基づく活動場所の滞在人数を示す情報、又は、活動場所の予約システムから得られた活動場所の予約状況であってもよい。 Here, the information indicating the current or future state of the activity place is information indicating the number of people staying at the activity place based on information (for example, a video of the surveillance camera (SC)) acquired from the sensor, or a reservation system for the activity place. It may be the reservation status of the activity place obtained from.
　これによって、実際に利用可能な活動場所を提示することができる。 With this, it is possible to present the actual available activity locations.
　以上、本発明の実施形態について説明したが、本発明は上記実施形態に限定されるものではなく、種々変形実施可能であり、上述した各実施形態を適宜組み合わせることが可能であることは、当業者に理解されよう。 Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, various modifications can be made, and it is possible to appropriately combine the above-described embodiments. It will be understood by the vendor.
　具体的には、本発明は上記した実施例に限定されるものではなく、様々な変形例が含まれる。例えば、上記した実施例は本発明のより良い理解のために詳細に説明したのであり、必ずしも説明の全ての構成を備えるものに限定されるものではない。 Specifically, the present invention is not limited to the above-described embodiments, but includes various modified examples. For example, the above-described embodiments have been described in detail for better understanding of the present invention, and are not necessarily limited to those including all the configurations of the description.
　また、上記の各構成、機能、処理部、処理手段等は、それらの一部又は全部を、例えば集積回路で設計する等によってハードウェアで実現してもよい。また、上記の各構成、機能等は、プロセッサがそれぞれの機能を実現するプログラムを解釈し、実行することによってソフトウェアで実現してもよい。各機能を実現するプログラム、テーブル、ファイル等の情報は、不揮発性半導体メモリ、ハードディスクドライブ、ＳＳＤ（Ｓｏｌｉｄ　Ｓｔａｔｅ　Ｄｒｉｖｅ）等の記憶デバイス、または、ＩＣカード、ＳＤカード、ＤＶＤ等の計算機読み取り可能な非一時的データ記憶媒体に格納することができる。 Also, each of the above-mentioned configurations, functions, processing units, processing means, etc. may be realized in hardware by designing a part or all of them with, for example, an integrated circuit. Further, each of the above-described configurations, functions and the like may be realized by software by a processor interpreting and executing a program for realizing each function. Information such as programs, tables, and files that realize each function is stored in a nonvolatile semiconductor memory, hard disk drive, storage device such as SSD (Solid State Drive), or computer-readable non-readable such as IC card, SD card, or DVD. It can be stored on a temporary data storage medium.
　また、制御線及び情報線は説明上必要と考えられるものを示しており、製品上必ずしも全ての制御線及び情報線を示しているとは限らない。実際にはほとんど全ての構成が相互に接続されていると考えてもよい。 Also, the control lines and information lines are shown to be necessary for explanation, and not all control lines and information lines are shown on the product. In practice, it may be considered that almost all configurations are connected to each other.

Claims (14)

  1. 　人物の生産性に関する目的指標と人物の活動場所の環境に関する環境指標との関連を示す数理モデルを保持する記憶部と、
    　センサから取得した人物の活動場所の環境に関するデータである環境データと、前記人物によって入力された前記人物の活動に関する目標を含む業務目標データとを受け付け、
    　前記業務目標データと前記数理モデルとに基づいて、前記人物の生産性を高めるのに適した前記環境指標の条件を探索し、
    　前記環境指標の条件と前記環境データとに基づいて、前記人物の生産性を高めるのに適した活動場所に関する情報を探索し、
    　探索によって得られた前記活動場所に関する情報を出力する推奨処理部と、を有することを特徴とするデータ分析システム。     A storage unit that holds a mathematical model showing the relationship between the target index related to the productivity of the person and the environmental index related to the environment of the activity place of the person,
    Accepting environmental data, which is data related to the environment of a person's activity place acquired from a sensor, and business goal data including a goal related to the activity of the person input by the person
    Based on the work target data and the mathematical model, search for conditions of the environmental index suitable for increasing the productivity of the person,
    Based on the conditions of the environmental index and the environmental data, search for information on an activity place suitable for enhancing the productivity of the person,
    A recommendation processing unit that outputs information about the activity place obtained by the search, and a data analysis system.
  2. 　請求項１に記載のデータ分析システムであって、
    　前記記憶部は、前記数理モデルを格納する第１のデータベースと、前記環境データを格納する第２のデータベースとを保持し、
    　前記推奨処理部は、前記第１のデータベースを参照して前記人物の生産性を高めるのに適した前記環境指標の条件を探索し、その後、前記第２のデータベースを参照して、前記人物の生産性を高めるのに適した活動場所に関する情報を探索することを特徴とするデータ分析システム。     The data analysis system according to claim 1, wherein
    The storage unit holds a first database that stores the mathematical model and a second database that stores the environment data,
    The recommendation processing unit refers to the first database to search for a condition of the environmental index suitable for increasing the productivity of the person, and then refers to the second database to search for the person. A data analysis system characterized by searching for information on an activity place suitable for increasing productivity.
  3. 　請求項２に記載のデータ分析システムであって、
    　前記数理モデルにおける前記環境指標は、前記活動場所の温度、湿度及び騒音の少なくとも一つを含み、
    　前記環境データは、前記人物がこれから活動を行う可能性がある複数の活動場所に設置された前記センサから取得された、前記数理モデルに含まれる前記環境指標の値を含むことを特徴とするデータ分析システム。     The data analysis system according to claim 2, wherein
    The environmental indicator in the mathematical model includes at least one of temperature, humidity and noise of the activity place,
    The environmental data includes a value of the environmental index included in the mathematical model, obtained from the sensors installed at a plurality of activity locations where the person may perform an activity. Analysis system.
  4. 　請求項１に記載のデータ分析システムであって、
    　前記推奨処理部は、
    　前記業務目標データに対応する前記目的指標と前記環境指標との関連に基づいて、前記人物の生産性を高めるのに適した前記環境指標の条件を探索し、
    　前記環境指標の条件と前記環境データとの関係が所定の条件を満たす前記活動場所に関する情報を、前記人物の生産性を高めるのに適した活動場所に関する情報として探索することを特徴とするデータ分析システム。     The data analysis system according to claim 1, wherein
    The recommended processing unit is
    Based on the relationship between the objective index and the environmental index corresponding to the business goal data, search for conditions of the environmental index suitable for increasing the productivity of the person,
    Data analysis characterized in that information about the activity place satisfying a predetermined condition of the relationship between the condition of the environmental index and the environmental data is searched as information about the activity place suitable for enhancing the productivity of the person. system.
  5. 　請求項１に記載のデータ分析システムであって、
    　前記数理モデルにおいて、前記目的指標と前記環境指標と前記人物の状態とが関連づけられ、
    　前記推奨処理部は、
    　前記人物によって入力された前記人物の状態をさらに受け付け、
    　前記入力された前記人物の状態と、前記業務目標データと、前記数理モデルと、に基づいて、前記人物の生産性を高めるのに適した前記環境指標の条件を探索することを特徴とするデータ分析システム。     The data analysis system according to claim 1, wherein
    In the mathematical model, the objective index, the environmental index, and the state of the person are associated,
    The recommended processing unit is
    Further accepting the status of the person entered by the person,
    Data characterized by searching for conditions of the environmental index suitable for increasing the productivity of the person based on the input state of the person, the work goal data, and the mathematical model. Analysis system.
  6. 　請求項１に記載のデータ分析システムであって、
    　前記推奨処理部は、
    　前記探索によって得られた前記活動場所の現在又は未来の状態を示す情報を取得し、
    　前記活動場所の現在又は未来の状態に基づいて、出力する前記活動場所に関する情報を決定することを特徴とするデータ分析システム。     The data analysis system according to claim 1, wherein
    The recommended processing unit is
    Obtaining information indicating the current or future state of the activity place obtained by the search,
    A data analysis system, characterized in that information on the activity place to be output is determined based on a current or future state of the activity place.
  7. 　請求項６に記載のデータ分析システムであって、
    　前記活動場所の現在又は未来の状態を示す情報は、前記センサから取得された情報に基づく前記活動場所の滞在人数を示す情報、又は、前記活動場所の予約システムから得られた前記活動場所の予約状況であることを特徴とするデータ分析システム。     The data analysis system according to claim 6,
    The information indicating the current or future state of the activity place is information indicating the number of people staying in the activity place based on the information acquired from the sensor, or the reservation of the activity place obtained from the activity place reservation system. Data analysis system characterized by the situation.
  8. 　記憶部と、推奨処理部と、を有するデータ分析システムが実行するデータ分析方法であって、
    　前記記憶部は、人物の生産性に関する目的指標と人物の活動場所の環境に関する環境指標との関連を示す数理モデルを保持し、
    　前記データ分析方法は、
    　前記推奨処理部が、センサから取得した人物の活動場所の環境に関するデータである環境データと、前記人物によって入力された前記人物の活動に関する目標を含む業務目標データとを受け付ける第１手順と、
    　前記推奨処理部が、前記業務目標データと前記数理モデルとに基づいて、前記人物の生産性を高めるのに適した前記環境指標の条件を探索する第２手順と、
    　前記推奨処理部が、前記環境指標の条件と前記環境データとに基づいて、前記人物の生産性を高めるのに適した活動場所に関する情報を探索する第３手順と、
    　前記推奨処理部が、探索によって得られた前記活動場所に関する情報を出力する第４手順と、を含むことを特徴とするデータ分析方法。     A data analysis method executed by a data analysis system having a storage unit and a recommended processing unit,
    The storage unit holds a mathematical model showing a relationship between a target index related to the productivity of a person and an environment index related to the environment of the activity place of the person,
    The data analysis method is
    A first procedure in which the recommendation processing unit receives environmental data, which is data related to the environment of a person's activity place acquired from a sensor, and business goal data including a goal related to the person's activity input by the person,
    A second step in which the recommendation processing unit searches for a condition of the environmental index suitable for increasing the productivity of the person based on the work target data and the mathematical model;
    A third step in which the recommended processing unit searches for information on an activity place suitable for increasing the productivity of the person based on the condition of the environmental index and the environmental data;
    The recommendation processing unit includes a fourth step of outputting information on the activity place obtained by the search, and a data analysis method.
  9. 　請求項８に記載のデータ分析方法であって、
    　前記記憶部は、前記数理モデルを格納する第１のデータベースと、前記環境データを格納する第２のデータベースとを保持し、
    　前記推奨処理部は、前記第２手順において、前記第１のデータベースを参照して前記人物の生産性を高めるのに適した前記環境指標の条件を探索し、その後、前記第３手順において、前記第２のデータベースを参照して、前記人物の生産性を高めるのに適した活動場所に関する情報を探索することを特徴とするデータ分析方法。     The data analysis method according to claim 8, wherein
    The storage unit holds a first database that stores the mathematical model and a second database that stores the environment data,
    In the second procedure, the recommendation processing unit refers to the first database to search for a condition of the environmental index suitable for increasing the productivity of the person, and then in the third procedure, A data analysis method, which refers to a second database to search for information on an activity place suitable for increasing the productivity of the person.
  10. 　請求項９に記載のデータ分析方法であって、
    　前記数理モデルにおける前記環境指標は、前記活動場所の温度、湿度及び騒音の少なくとも一つを含み、
    　前記環境データは、前記人物がこれから活動を行う可能性がある複数の活動場所に設置された前記センサから取得された、前記数理モデルに含まれる前記環境指標の値を含むことを特徴とするデータ分析方法。     The data analysis method according to claim 9, wherein
    The environmental indicator in the mathematical model includes at least one of temperature, humidity and noise of the activity place,
    The environmental data includes a value of the environmental index included in the mathematical model, obtained from the sensors installed at a plurality of activity locations where the person may perform an activity. Analysis method.
  11. 　請求項８に記載のデータ分析方法であって、
    　前記第２手順において、前記推奨処理部は、前記業務目標データに対応する前記目的指標と前記環境指標との関連に基づいて、前記人物の生産性を高めるのに適した前記環境指標の条件を探索し、
    　前記第３手順において、前記推奨処理部は、前記環境指標の条件と前記環境データとの関係が所定の条件を満たす前記活動場所に関する情報を、前記人物の生産性を高めるのに適した活動場所に関する情報として探索することを特徴とするデータ分析方法。     The data analysis method according to claim 8, wherein
    In the second procedure, the recommendation processing unit determines a condition of the environmental index suitable for increasing the productivity of the person based on the relationship between the purpose index corresponding to the business goal data and the environmental index. Explore,
    In the third step, the recommendation processing unit provides information about the activity place where the relationship between the environmental index condition and the environmental data satisfies a predetermined condition, to the activity place suitable for increasing the productivity of the person. A data analysis method, characterized by searching as information about.
  12. 　請求項８に記載のデータ分析方法であって、
    　前記数理モデルにおいて、前記目的指標と前記環境指標と前記人物の状態とが関連づけられ、
    　前記第１手順において、前記推奨処理部は、前記人物によって入力された前記人物の状態をさらに受け付け、
    　前記第２手順において、前記推奨処理部は、前記入力された前記人物の状態と、前記業務目標データと、前記数理モデルと、に基づいて、前記人物の生産性を高めるのに適した前記環境指標の条件を探索することを特徴とするデータ分析方法。     The data analysis method according to claim 8, wherein
    In the mathematical model, the objective index, the environmental index, and the state of the person are associated,
    In the first procedure, the recommendation processing unit further accepts the state of the person input by the person,
    In the second procedure, the recommendation processing unit, based on the input state of the person, the business goal data, and the mathematical model, the environment suitable for increasing the productivity of the person. A data analysis method characterized by searching the condition of an index.
  13. 　請求項８に記載のデータ分析方法であって、
    　前記第３手順において、前記推奨処理部は、
    　前記探索によって得られた前記活動場所の現在又は未来の状態を示す情報を取得し、
    　前記活動場所の現在又は未来の状態に基づいて、出力する前記活動場所に関する情報を決定することを特徴とするデータ分析方法。     The data analysis method according to claim 8, wherein
    In the third procedure, the recommended processing unit
    Obtaining information indicating the current or future state of the activity place obtained by the search,
    A data analysis method, comprising: determining information about the activity place to be output based on a current or future state of the activity place.
  14. 　請求項１３に記載のデータ分析方法であって、
    　前記活動場所の現在又は未来の状態を示す情報は、前記センサから取得された情報に基づく前記活動場所の滞在人数を示す情報、又は、前記活動場所の予約システムから得られた前記活動場所の予約状況であることを特徴とするデータ分析方法。     The data analysis method according to claim 13, wherein
    The information indicating the current or future state of the activity place is information indicating the number of people staying in the activity place based on the information acquired from the sensor, or the reservation of the activity place obtained from the activity place reservation system. A data analysis method characterized by being a situation.
PCT/JP2018/043053 2018-11-21 2018-11-21 Data analysis system and data analysis method WO2020105154A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2020557089A JPWO2020105154A1 (en) 2018-11-21 2018-11-21 Data analysis system and data analysis method
PCT/JP2018/043053 WO2020105154A1 (en) 2018-11-21 2018-11-21 Data analysis system and data analysis method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2018/043053 WO2020105154A1 (en) 2018-11-21 2018-11-21 Data analysis system and data analysis method

Publications (1)

Publication Number Publication Date
WO2020105154A1 true WO2020105154A1 (en) 2020-05-28

Family

ID=70774463

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/043053 WO2020105154A1 (en) 2018-11-21 2018-11-21 Data analysis system and data analysis method

Country Status (2)

Country Link
JP (1) JPWO2020105154A1 (en)
WO (1) WO2020105154A1 (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018198948A1 (en) * 2017-04-24 2018-11-01 パナソニックＩｐマネジメント株式会社 Intellectual productivity evaluation device and intellectual productivity evaluation method
JP2018181245A (en) * 2017-04-21 2018-11-15 株式会社デンソー Productivity determination device, productivity determination program, and productivity determination method

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63279370A (en) * 1987-05-11 1988-11-16 Kokuyo Kk Office planning method and map used to said method
JP5778470B2 (en) * 2011-04-28 2015-09-16 株式会社竹中工務店 Action incentive device
US10325102B2 (en) * 2013-05-23 2019-06-18 yTrre, Inc. Real-time customer experience management systems and methods
JP6212474B2 (en) * 2014-12-11 2017-10-11 株式会社Ｎｔｔファシリティーズ Office activity analysis system, office activity analysis method, and program
JP6675266B2 (en) * 2016-05-20 2020-04-01 株式会社日立製作所 Sensor data analysis system and sensor data analysis method
JP2018073333A (en) * 2016-11-04 2018-05-10 株式会社イトーキ Business activity analysis device, business activity analysis method, and program
JP6688723B2 (en) * 2016-12-09 2020-04-28 株式会社日立製作所 Action recommendation system and action recommendation method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018181245A (en) * 2017-04-21 2018-11-15 株式会社デンソー Productivity determination device, productivity determination program, and productivity determination method
WO2018198948A1 (en) * 2017-04-24 2018-11-01 パナソニックＩｐマネジメント株式会社 Intellectual productivity evaluation device and intellectual productivity evaluation method

Also Published As

Publication number Publication date
JPWO2020105154A1 (en) 2021-09-27

Similar Documents

Publication Publication Date Title
US10062163B2 (en) Health information service system
JP6423017B2 (en) Psychological state measurement system
JP6677167B2 (en) Matching system, information processing device, matching method, and program
CN106537927A (en) Control and modification of live presentation
JP2004289828A (en) Control method for information transmission and computer-readable storage medium
JP2013105471A (en) Event data processor
JP2008287690A (en) Group visualization system and sensor-network system
CN107656938A (en) It is a kind of to recommend method and apparatus, a kind of device for being used to recommend
US10275915B2 (en) Method and system for visualization of position data
CN105009114B (en) Search capability is predictably presented
Monti et al. Iot and data visualization to enhance hyperlocal data in a smart campus context
US20120131477A1 (en) Social Network Device
JP6738655B2 (en) Guide display system, guide display method, and guide display program
WO2017195440A1 (en) Information processing device, information processing method, and program
WO2020105154A1 (en) Data analysis system and data analysis method
US20180316972A1 (en) Information processing device, method, and program
Thoring et al. Technology-supported design research
Pattath et al. Interactive visualization and analysis of network and sensor data on mobile devices
US20220405689A1 (en) Information processing apparatus, information processing method, and program
Simpson et al. A Platform for the Analysis of Qualitative and Quantitative Data about the Built Environment and its Users
JP6594512B2 (en) Psychological state measurement system
KR20220010941A (en) Bigdata-based residential model recommendation system for users and a method for recommending a residential model using the same
JPWO2020032239A1 (en) Information output device, design support system, information output method and information output program
Vongkunkij et al. Soundscape: Sensing and visualizing acoustic landscape on campus
García et al. Determining and locating the closest available resources to mobile collaborators

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18940861

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020557089

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18940861

Country of ref document: EP

Kind code of ref document: A1