JP6594512B2 - Psychological state measurement system - Google Patents

Description

  The present invention relates to a psychological state measurement system that measures a person's psychological state. More specifically, the present invention relates to a technique for measuring a person's psychological state using a device attached to the human body.

  In recent years, big data has been attracting attention, and by analyzing the data acquired by the business system, we discovered the factors that affect the company's KPI (for example, profit, manufacturing time, cost, etc.) through quantitative statistical analysis, Attempts to use for decision-making are spreading. It is already known that human psychological state (for example, well-being) is related to productivity, and Non-Patent Document 1 divides it into a group of people who are in a healthy psychological state and a group of people in a depressed state. In some cases, a difference appears in the shape of the distribution.

  In Patent Document 1, an acceleration list is created by using a sensor node having a triaxial acceleration sensor, and an operator's activity is determined based on whether or not the acceleration list exceeds a certain threshold. A technique for creating an activity list is described. Here, when this active list is data in units of seconds, the number of seconds that have been active in one minute is counted, and if it is equal to or greater than a threshold value, that one minute is regarded as active. The effect is also described.

WO2012 / 169003

Nakamura, Toru et al., “Universal Scaling Law in Human Behavioral Organization”, Physical review letters, pp. 138103-1-4, 2007

  When the worker's psychological state is digitized, it is desirable that the worker's motivation becomes easier. For example, in order to encourage the worker to take action to achieve a desirable psychological state, it should be examined in particular what kind of index is more appropriate for quantification. Specifically, it is easy to grasp the current achievement status with respect to a more desirable psychological state, and a quantification that makes it easier to motivate to continue the action for promoting the above is useful. In addition, it is useful to make a numerical value for allowing the worker himself to understand what kind of work tends to take an undesirable action and what kind of work tends to take a desirable action.

  In light of the above, an object of the present invention is to provide a psychological state analysis system for quantifying a person's psychological state so as to facilitate motivation of the person.

A representative example of the present invention is a psychological state analysis system for analyzing a person's psychological state,
A storage unit for storing time-series data and threshold values of acceleration of the movement of the person's body;
A process for determining whether each acceleration frequency value calculated from the time series data is in a first state that is equal to or greater than the threshold value or a second state that is less than the threshold value, and a time during which the first state continues A processing unit that performs a process of determining a certain duration, and a process that quantifies the psychological state of the person based on the duration.
The plurality of regions in which the duration is in a predetermined range includes a first region in which the duration is a first range and a second region in which the duration is a second range,
The upper limit of the second range is greater than the upper limit of the first range,
The processing unit is a first term including a first appearance frequency that is an appearance frequency of the duration included in the first area, and an appearance frequency of the duration included in the second area. The psychological state is quantified by the sum of the second terms including the second appearance frequency.

  According to the present invention, it is possible to digitize a psychological state that makes it easier to motivate a person.

It is an example of the figure which shows the structure and utilization scene of a psychological state measuring device. It is an example of the figure which shows the structure of a terminal. It is an example of the figure which shows the structure of a sensor network server and a base station. It is an example of the figure which shows the structure of the apparatus connected to an application server from a client, an application server, and others. It is an example of the sequence diagram of the psychological index calculation in a terminal. It is an example of the sequence diagram of the process which synchronizes a setting file. It is an example of the flowchart of a psychological state analysis process. It is a figure explaining the procedure of a psychological state analysis. It is an example of the figure which shows a setting file. It is an example of the figure explaining the display screen of a terminal. It is an example of the figure which shows the screen of the Web application which displays a psychological parameter | index. It is an example of the figure which shows the screen of the web application which displays the correlation analysis result of a psychological parameter | index and another parameter | index. It is an example of the figure which shows a parameter | index storage table. It is an example of the figure which shows a user attribute list. It is an example of the figure which shows a sensing database (acceleration data). It is an example of the figure which shows a sensing database (meeting data). It is an example of the figure which shows a sensing database (meeting data). It is an example of the figure which shows an acceleration frequency table. It is a figure which shows the background knowledge of psychological index calculation. It is a figure which shows the background knowledge of psychological index calculation. It is a figure which shows the background knowledge of psychological index calculation. It is a figure which shows the background knowledge of psychological index calculation.

  The present invention is an apparatus for measuring a human psychological state, and is characterized by using a statistical distribution characteristic of frequency of duration of an active state acquired by a sensor terminal attached to a human body. Hereinafter, description will be made with reference to the drawings.

  First, a first embodiment of the present invention will be described with reference to the drawings.

  <Figure 1: System overview>

  FIG. 1 shows a system outline of the first embodiment. In the first embodiment, a sensor terminal (TR, TR2-3: hereinafter referred to as TR when no individual is identified) is designated as a user (US, US2-3: hereinafter, when an individual is not identified, all as US). The sensor (not shown) in the terminal (TR) acquires sensing data relating to the movement of the wearer and the face-to-face state (interaction) with other wearers. As for the interaction, when the users (US) face each other, the face-to-face is detected by transmitting and receiving infrared rays between the terminals (TR).

  The terminal (TR) processes sensing data relating to body movement (hereinafter referred to as triaxial acceleration data, but other groups may be used) in an in-terminal processing unit (not shown), and a program stored in advance Is used to calculate an index related to the psychological state (for example, the happiness level), and a numerical value related to the value or an argument thereof (for example, the frequency of the duration of the active state in a specific range) is connected to the terminal or wirelessly or by wired communication Output to the display device (LCDD).

  On the other hand, the acquired sensing data and basic indicators (calculated psychological indicators and their arguments) are connected wirelessly or by wire, transmitted to the base station (GW), and stored in the sensor network server (SS) through the network (NW). Is done. Moreover, the index regarding the psychological state is calculated by a program using the same coefficient as that of the terminal (TR) in the sensor network server (SS). The application server (AS) periodically acquires a psychological index related to a specific individual or group from the sensor network server (SS), and acquires it from an external data server (OS) such as another behavior index calculated from sensing data or a business database. The correlation analysis with the index is performed, and the psychological index and the result of the analysis are sent to the client (CL) and displayed on the screen (OD).

  Furthermore, the application server (AS) is connected to an external device (CM) that can affect the attributes of the environment, such as an air conditioner, and an external sensor (CS) that measures the attributes, and the values and psychological indicators are statistically linked. It is also possible to control an external device (CM) to maximize the psychological index of an individual or group in the environment by analyzing such associations.

  The psychological state quantified by the present invention targets a desirable state for the person and the group including the person such as happiness, employee satisfaction, fulfillment, and engagement. Conversely, a desirable state may be indirectly measured by measuring a state that is undesirable for the person and the group including the person, such as depression.

<FIGS. 2 to 4: Block diagram of the entire system>
2 to 4 are block diagrams illustrating the entire configuration of a sensor network system that implements the sensing data display device according to the embodiment of the present invention. Although shown separately for the sake of illustration, the respective processes shown are executed in cooperation with each other. Each function in the figure is realized by cooperation of hardware and software. Each of these components has a control part, a memory | storage part, and a transmission / reception part so that FIGS. The control unit is configured by a central processing unit (CPU, not shown), which is a processing unit such as an ordinary computer, and the storage unit is configured by a memory device such as a semiconductor storage device or a magnetic storage device, and a transmission / reception unit Consists of a network interface such as wired or wireless. In addition, a clock or the like is provided as necessary.

  The six types of arrows having different shapes in FIGS. 2 to 4 respectively indicate time synchronization, associate, storage of acquired sensing data, analysis of sensing data, firmware update, and data or signal flow for control signals. Represents.

<Figure 2: Overall system 1 (TR)>
FIG. 2 shows a configuration of a terminal (TR) which is an embodiment of the sensor node. Here, the terminal (TR) has a name tag type shape and is assumed to hang from a person's neck. However, this is an example, and other shapes may be used. In many cases, a plurality of terminals (TR) exist in this series of systems, and each of them is worn by a plurality of persons. The terminal (TR) detects multiple human face-to-face infrared transmission / reception units (AB), a triaxial acceleration sensor (AC) to detect the wearer's movement, and detects the wearer's speech and surrounding sounds. Various sensors such as a microphone (AD) for detecting the light, an illuminance sensor (LS1F, LS1B) for detecting the front and back of the terminal, and a temperature sensor (AE) are mounted. The sensor to be mounted is an example, and other sensors may be used to detect the face-to-face condition and movement of the wearer.

  In this embodiment, four sets of infrared transmission / reception units are mounted. The infrared transmitter / receiver (AB) continues to periodically transmit terminal information (TRMT), which is unique identification information of the terminal (TR), in the front direction. When the person wearing the other terminal (TR) is located substantially in front (for example, front or diagonally front), the terminal (TR) and the other terminal (TR) mutually exchange their terminal information (TRMT) with infrared rays. Interact with. For this reason, it is possible to record who is facing who. It also detects which user (US) stayed in the area by transmitting and receiving terminal information (TRMT) and position information between a position detector (not shown) installed in the external environment and the terminal (TR). can do.

  Each infrared transmission / reception unit is generally composed of a combination of an infrared light emitting diode for infrared transmission and an infrared phototransistor. The infrared ID transmitter (IrID) generates terminal information (TRMT) that is its own ID and transfers it to the infrared light emitting diode of the infrared transceiver module. In this embodiment, all the infrared light emitting diodes are turned on simultaneously by transmitting the same data to a plurality of infrared transmission / reception modules. Of course, independent data may be output at different timings.

  The data received by the infrared phototransistor of the infrared transmission / reception unit (AB) is ORed by an OR circuit (IROR). That is, if the ID is received by at least one infrared receiving unit, the terminal recognizes the ID. Of course, a configuration having a plurality of ID receiving circuits independently may be employed. In this case, since the transmission / reception state can be grasped with respect to each infrared transmission / reception module, for example, it is also possible to obtain additional information such as in which direction a different terminal is facing.

  Sensing data (SENSD) detected by the sensor is stored in the storage unit (STRG) by the sensing data storage control unit (SDCNT). The sensing data (SENSD) is processed into a transmission packet by the communication control unit (TRCC) and transmitted to the base station (GW) by the transmission / reception unit (TRSR).

  At this time, it is the communication timing control unit (TRTMG) that takes out the sensing data (SENSD) from the storage unit (STRG) and determines the timing of wireless or wired transmission. The communication timing control unit (TRTMG) has a plurality of time bases (TB1, TB2) for determining a plurality of timings.

  The data stored in the storage unit includes not only sensing data (SENSD) detected by the sensor immediately before, but also batch data (CMBD) accumulated in the past and firmware for updating the terminal operation program firmware. There is firmware update data (FMUD).

  The terminal (TR) of this embodiment detects that the external power supply (EPOW) is connected by the external power supply connection detection circuit (PDET), and generates an external power supply detection signal (PDETS). The time base switching unit (TMGSEL) that switches the transmission timing generated by the timing control unit (TRTMG) or the data switching unit (TRDSEL) that switches data to be wirelessly communicated by the external power supply detection signal (PDETS) is the terminal (TR). It is a unique configuration. As an example, FIG. 2 illustrates a configuration in which the time base switching unit (TMGSEL) switches the transmission timing from two time bases of time base 1 (TB1) and time base (TB2) by an external power supply detection signal (PDETS). ing. In addition, the data switching unit uses the external power supply detection signal (PDETS) from the sensing data (SENSD) obtained from the sensor, the batch sending data (CMBD) accumulated in the past, and the firmware update data (FMUD). A configuration in which (TRDSEL) is switched is illustrated.

  The illuminance sensors (LS1F, LS1B) are mounted on the front surface and the back surface of the terminal (TR), respectively. Data acquired by the illuminance sensors (LS1F, LS1B) is stored in the storage unit (STRG) by the sensing data storage control unit (SDCNT), and at the same time is compared by the turnover detection unit (FBDET). When the name tag is correctly worn, the illuminance sensor (LS1F) mounted on the front surface receives external light, and the illuminance sensor (LS1B) mounted on the back surface is sandwiched between the terminal body and the wearer. Therefore, it does not receive extraneous light. At this time, the illuminance detected by the illuminance sensor (LS1F) takes a larger value than the illuminance detected by the illuminance sensor (LS1B). On the other hand, when the terminal (TR) is turned over, the illuminance sensor (LS1B) receives extraneous light and the illuminance sensor (LS1F) faces the wearer. The illuminance detected by the sensor (LS1B) is larger.

  Here, when the illuminance detected by the illuminance sensor (LS1F) and the illuminance detected by the illuminance sensor (LS1B) are compared by the turnover detection unit (FBDET), the name tag node may be turned over and not correctly mounted. It can be detected. When turning over is detected by the turn over detection unit (FBDET), a warning sound is generated from the speaker (SP) to notify the wearer.

  The microphone (AD) acquires audio information. The surrounding information such as “noisy” or “quiet” can be known from the sound information. Furthermore, by acquiring and analyzing the voices of people, whether communication is active or stagnant, whether they are communicating with each other equally or unilaterally, whether they are angry or laughing, It is possible to generate an action index related to face-to-face communication. Furthermore, the face-to-face state that the infrared transmitter / receiver (AB) cannot detect due to the standing position of a person can be supplemented by voice information and acceleration information.

  The voice acquired by the microphone (AD) acquires both a voice waveform and a signal obtained by integrating the voice waveform by an integration circuit (AVG). The integrated signal represents the energy of the acquired speech.

  The triaxial acceleration sensor (AC) detects the acceleration of the node, that is, the movement of the node. For this reason, from the acceleration data, it is possible to analyze the intensity of movement of the person wearing the terminal (TR) and behavior such as walking. Furthermore, by comparing the acceleration values detected by a plurality of terminals in the same time zone, the communication activity level, mutual rhythm, mutual correlation, etc. between persons wearing these terminals can be analyzed.

  In the terminal (TR) of the present embodiment, data acquired by the triaxial acceleration sensor (AC) is stored in the storage unit (STRG) by the sensing data storage control unit (SDCNT).

  Psychological state analysis (ANA) reads the setting file (TRSF) stored in advance in the storage unit (STRG), uses the program to calculate the frequency of the duration of the active state within a specific range, and specifies the same By calculating a linear sum of frequencies using the calculated coefficients, a psychological index is calculated for them. Thereafter, the value (psychological index, duration frequency) in the basic index (TRIF) in the storage unit (STRG) is updated in association with the update time, and the display value is also updated and displayed in the display control (DISP). Redisplay on the device (LCDD). The display content may be switched by pressing a button (BTN1 to 3).

  Whether the terminal (TR) has faced another terminal (TR) by exchanging infrared rays between nodes by the infrared transmission / reception unit (AB), that is, the person wearing the terminal (TR) It is detected whether or not the person wearing TR) is faced. For this reason, it is desirable that the terminal (TR) is attached to the front part of the person. As described above, the terminal (TR) further includes a sensor such as a triaxial acceleration sensor (AC). The sensing process in the terminal (TR) corresponds to sensing (TRSS1) in FIG.

  In many cases, there are a plurality of terminals. When terminals and base stations are wirelessly connected, each terminal is connected to a nearby base station (GW) to form a personal area network (PAN).

  The temperature sensor (AE) of the terminal (TR) acquires the temperature of the place where the terminal is located, and the illuminance sensor (LS1F) acquires the illuminance such as the front direction of the terminal (TR). As a result, the surrounding environment can be recorded. For example, it is also possible to know that the terminal (TR) has moved from one place to another based on temperature and illuminance.

  As input / output devices corresponding to the worn person, buttons 1 to 3 (BTN1 to 3), a display device (LCDD), a speaker (SP) and the like are provided.

  The storage unit (STRG) is specifically composed of a nonvolatile storage device such as a hard disk or a flash memory, and includes terminal information (TRMT) that is a unique identification number of the terminal (TR), sensing interval, and output to the display. Operation settings (TRMA) such as contents are recorded. In addition, the storage unit (STRG) can temporarily record data and is used to record sensed data.

  The clock (TRCK) is a clock that holds time information (GWCSD) and updates the time information (GWCSD) at regular intervals. In order to prevent the time information (GWCSD) from deviating from other terminals (TR), the time information periodically corrects the time based on the time information (GWCSD) transmitted from the base station (GW).

  The sensing data storage control unit (SDCNT) controls the sensing interval of each sensor according to the operation setting (TRMA) recorded in the storage unit (STRG) and manages the acquired data.

  Time synchronization is performed by acquiring time information from the base station (GW) and correcting the clock (TRCK). Time synchronization may be executed immediately after an associate described later, or may be executed in accordance with a time synchronization command transmitted from the base station (GW).

  The communication control unit (TRCC) performs transmission interval control and conversion to a data format compatible with wireless transmission and reception when transmitting and receiving data. The communication control unit (TRCC) may have a wired communication function instead of wireless if necessary. The communication control unit (TRCC) may perform congestion control so that transmission timing does not overlap with other terminals (TR).

  The associate (TRTA) transmits / receives an associate request (TRTAQ) and an associate response (TRTAR) to form a personal area network (PAN) with the base station (GW), and transmits a base station (GW) to which data is to be transmitted. decide. Associate (TRTA) is executed when the power of the terminal (TR) is turned on and when transmission / reception with the base station (GW) is interrupted as a result of movement of the terminal (TR). In the case of wired connection, it is executed when it is detected that the terminal (TR) is connected to the base station (GW) by wire. As a result of the associate (TRTA), the terminal (TR) is associated with one base station (GW) in a near range where a radio signal from the terminal (TR) can reach.

  The transmission / reception unit (TRSR) includes an antenna and transmits and receives radio signals. If necessary, the transmission / reception unit (TRSR) can perform transmission / reception using a connector for wired communication. Sensing data / basic index (SENSD) transmitted / received by the transceiver unit (TRSR) is transferred to / from the base station (GW) via the personal area network (PAN).

<Figure 3: Overall system 2 (GW / SS)>
FIG. 3 shows the configuration of an embodiment of the sensor network server (SS) and the base station (GW).

<Base station (GW)>
The base station (GW) has a role of mediating between the terminal (TR) and the sensor network server (SS). When a terminal (TR) and a base station (GW) are connected by radio, a plurality of base stations (GW) are arranged so as to cover areas such as living rooms and workplaces in consideration of radio reachable distance. The When connecting by wire, an upper limit of the number of terminals (TR) to be managed is set in accordance with the processing capability of the base station (GW).

  The base station (GW) includes a transmission / reception unit (GWSR), a storage unit (GWME), and a control unit (GWCO).

  The transmission / reception unit (GWSR) receives data from the terminal (TR) wirelessly or by wire, and performs wired or wireless transmission to the sensor network server (SS). When radio is used for transmission / reception, the transmission / reception unit (GWSR) includes an antenna for receiving radio. Further, as necessary, congestion control, that is, communication timing control is performed so that data is not lost during transmission and reception of sensing data. Also, the type of received data is distinguished. Specifically, the received data is identified as general sensing data, associate data, or time-synchronized response, etc., from the header part of the data, and these data are respectively appropriate. To pass the function.

  The storage unit (GWME) includes an external recording device (not shown) such as a hard disk, a memory, or an SD card. The storage unit (GWME) stores operation settings (GWMA), data format information (GWMF), terminal management table (GWTT), base station information (GWMG), and terminal firmware (GWTFD). The operation setting (GWMA) includes information indicating an operation method of the base station (GW). The data format information (GWMF) includes information indicating a data format for communication and information necessary for tagging the sensing data. The terminal management table (GWTT) includes terminal information (TRMT) of the subordinate terminals (TR) currently associated with each other and local IDs distributed to manage those terminals (TR). If the terminal (TR) is connected by wire and it is not necessary to keep track of the terminal (TR) under its control, the terminal management table (GWTT) may be omitted. The base station information (GWMG) includes information such as the address of the base station (GW) itself. The terminal firmware (GWTFD) stores a program for operating the terminal. When an instruction and new terminal firmware are received from the sensor network server (SS), the firmware update data (TRDFW) is personalized. It transmits to the terminal (TR) through the area network (PAN) (GWCFW). The storage unit (GWME) may further store a program executed by a CPU (not shown) of the control unit (GWCO).

  The control unit (GWCO) includes a CPU (not shown). When the CPU executes a program stored in the storage unit (GWME), the timing at which sensing data is received from the terminal (TR), the processing of the sensing data, and the transmission / reception to the terminal (TR) or the sensor network server (SS) And the timing of time synchronization are managed. Specifically, processing such as data reception control (GWCSR), data transmission (GWCSS), associate (GWCTA), terminal management information correction (GWCTF), terminal firmware update (GWCFW), and time synchronization (GWCS) is executed.

  The clock (GWCK) holds time information. The time information is updated at regular intervals. Specifically, the time information of the clock (GWCK) is corrected by the time information acquired from an NTP (Network Time Protocol) server (TS) at regular intervals.

  Time synchronization (GWCS) transmits time information to a subordinate terminal (TR) at a fixed interval or when a terminal (TR) is connected to a base station (GW) as a trigger. Thereby, the time of the clock (GWCK) of the plurality of terminals (TR) and the base station (GW) is synchronized.

  In response to the associate request (TRTAQ) sent from the terminal (TR), the associate (GWCTA) performs an associate response (TRTAR) that transmits the assigned local ID to each terminal (TR). When the associate is established, the associate (GWTA) performs terminal management information correction (GWCTF) for correcting the terminal management table (GWTT).

  Data reception control (GWCSR) receives a packet of sensing data (SENSD) sent from a terminal (TR). The header of the data packet is read to determine the type of data, and at the same time, congestion control is performed so that data from a large number of terminals (TR) is not concentrated.

  Data transmission (GWCSS) assigns the ID of the base station through which the data has passed and its time data, and transmits the sensing data to the sensor network server (SS).

<Sensor network server (SS)>
The sensor network server (SS) includes a transmission / reception unit (SSSR), a storage unit (SSME), and a control unit (SSCO).

  The sensor network server (SS) manages data collected from all terminals (TR). Specifically, the sensor network server (SS) stores the sensing data sent from the base station (GW) in the sensing database (SSDB), and stores the basic index in the index storage table (SSDTB) (SSCDB). . Further, data in the index storage table (SSDT) is searched based on a request from the application server (AS) and transmitted to the application server (AS) (SSDG).

  Further, the sensor network server (SS) manages information on the base station (GW) and the terminal (TR) under its management as needed. Also, this is the starting point of a control command for updating the firmware of the terminal (TR). When the setting file (SSSF) is modified because the psychological index calculation program stored in the setting file (SSSF) and some of the coefficients for calculating the index are preferably synchronized with the terminal (TR) In this case, the setting file (TRSF) in the terminal (TR) is updated using the terminal firmware update (SSCFW) path.

  The transmission / reception unit (SSSR) transmits and receives data to and from the base station (GW), application server (AS), personal client (CP), and client (CL), and performs communication control at that time .

  The storage unit (SSME) is configured by a data storage device such as a hard disk, and includes at least a sensing database (SSDB), an index storage table (SSDT), a data format information (SSMF), a terminal management table (SSTT), and a terminal firmware (SSFW). ). Furthermore, the storage unit (SSME) stores a program executed by a CPU (not shown) of the control unit (SSCO).

  The sensing database (SSDB) includes sensing data acquired by each terminal (TR), information on the terminal (TR), information on a base station (GW) through which the sensing data transmitted from each terminal (TR) has passed, and the like. It is a database for recording. A column is created for each data element such as acceleration and temperature, and the data is managed. A table may be created for each data element. In either case, all data is managed in association with terminal information (TRMT), which is the ID of the acquired terminal (TR), and information regarding the sensed time. An example of an acceleration data table held in the sensing database (SSDB) is shown in FIG. 15 (SSDB_ACC — 1002), and an example of two infrared data tables is shown in FIG. 16 (SSDB_IR — 1002) (SSDB_IR — 1003). FIG. 17 (SSDB_ACCTP — 1 min) shows an example of a table of acceleration frequencies (or behavior rhythms) in the case of.

  The data format information (SSMF) includes a data format for communication, a method of separating sensing data tagged with a base station (GW) and recording it in a database, information indicating how to respond to a data request, and the like. ing. This data format information (SSMF) is referred to after data reception and before data transmission to perform data format conversion and data distribution.

  The terminal management table (SSTT) is a table that records which terminal (TR) is currently managed by which base station (GW). When a new terminal (TR) is added under the management of the base station (GW), the terminal management table (SSTT) is updated. Further, when the base station (GW) and the terminal (TR) are connected by wire, the terminal management information may not always be monitored.

  The terminal firmware (SSFW) stores a program for operating the terminal, and when the terminal firmware update (SSCFW) is performed, the terminal firmware (SSFW) is updated and the network (NW) This is sent to the base station (GW) through the network, and further sent to the terminal (TR) through the personal area network (PAN) to update the firmware in the terminal (TR) (FMUD).

  The control unit (SSCO) includes a CPU (not shown) and controls transmission / reception of sensing data and recording / retrieving to / from a database. Specifically, when the CPU executes a program stored in the storage unit (SSME), data storage (SSCDB), terminal management information correction (SSCTF), terminal firmware update (SSCFW), psychological state analysis (SSCDT) And processing such as behavior discrimination (SSCAD).

  Data storage (SSCDB) is processing for receiving sensing data sent from a base station (GW) and storing it in a sensing database (SSDB). Additional information such as time information, terminal ID, and time via the base station is combined and stored in the database as one record.

  The clock (SSCK) maintains a standard time by periodically connecting to the external NTP server (TS). When the clock (SSCK) satisfies a predetermined time or a specific condition, the sensing data processing (SSCDT) is activated (SSTK).

  Psychological state analysis (SSCDT) acquires the basic index (frequency for each active duration) sent from the sensing data stored in the sensing database (SSDB) or the terminal (TR) stored in the index storage table, A psychological index for each predetermined time is calculated using the program and coefficient stored in the setting file (SSSF), and the result is stored in the index storage table (SSDT).

  Behavior discrimination (SSCAD) acquires sensing data acquired by a terminal (TR) from a sensing database (SSDB), and uses a program (not shown) in a storage unit (SSME) to perform actions such as walking, desk work, and a meeting. Are stored in the index storage table (SSDT) in association with the time information.

  The terminal management information correction (SSCTTF) updates the terminal management table (SSTT) when receiving a command for correcting the terminal management information from the base station (GW). This is for constantly grasping a list of terminals (TR) under the control of each base station (GW).

  The terminal firmware update (SSCFW) updates the terminal firmware (SSFW) in the storage unit (SSME) when it becomes necessary to update the firmware of the terminal (TR) manually or automatically. GW) is instructed to update the firmware of the terminal (TR) under its control. In addition, a response that the firmware update is completed at each terminal (TR) is received, and the process is continued until the update of all the terminals (TR) is completed.

<Figure 4: Overall system 3 (CL / AS)>
FIG. 4 shows a configuration of an embodiment of a client (CL), an application server (AS), and devices connected from the outside.

<About client (CL)>
The client (CL) inputs and outputs data as a contact point with the user (US). The client (CL) includes an input / output unit (CLIO), a transmission / reception unit (CLSR), a storage unit (not shown), and a control unit (CLCO).

  The input / output unit (CLIO) serves as an interface with the user (US). The input / output unit (CLIO) includes a display (CLOD), a touch panel (CLIT), a keyboard (CLIK), a mouse (CLIM), and the like. Other input / output devices can be connected to an external input / output (CLIU) as required.

  The display (CLOD) is an image display device such as a CRT (Cathode-Ray Tube) or a liquid crystal display. The display (CLOD) may include a printer or the like. When the touch panel (CLIT) is used to support the input by the user, the touch panel (CLIT) is installed so as to overlap the screen (OD) of the display (CLOD), and output and input are performed on the same screen. You can also show it.

  The transmission / reception unit (CLSR) transmits / receives data and commands to / from an application server (AS) or a device connected to another network. Specifically, the transmission / reception unit (CLSR) transmits a request for a screen to be displayed to the application server (AS), and receives an image corresponding to the request.

  The storage unit (not shown) is configured by an external recording device such as a hard disk, a memory, or an SD card. The storage unit (not shown) may store a display history, a user (US) login ID, and the like.

  The control unit (CLCO) includes a CPU (not shown) and controls the screen (CLCOD) for output to a display (CLOD) or the like, and the user (US) notifies the application server (AS) of a change in analysis conditions. Process such as analysis condition setting (CLCS).

<Application server (AS)>
Application Server (AS) is a client that analyzes the correlation between psychological indicators and other behavioral indicators / performance indicators (ASCA), optimal control of external devices (ASMC), psychological indicators and correlation analysis results, external device status, etc. Screen generation (ASCD) for presentation to (CL) is performed.

  The application server (AS) includes a transmission / reception unit (ASSR), a storage unit (ASME), and a control unit (ASCO).

  The transmission / reception unit (ASSR) is connected to the sensor network server (SS), the NTP server (TS), the client (CL), the external device (CM), the external sensor (CS), and the external data server (OS) through the network (NW). Data is transmitted to and received from the network, and communication control for that is performed.

  The storage unit (ASME) is configured by an external recording device such as a hard disk, a memory, or an SD card. The storage unit (ASME) stores the created content information, a program for creating content, and other data related to content creation. Specifically, the storage unit (ASME) stores a user attribute list (ASUL), a display setting file (ASDF), an external data table (ASDT), and a control target value (ASCT).

  The user attribute list (ASUL) is a comparison table of the ID of the terminal (TR) and the name / user ID / affiliation, mail address, attribute, etc. of the user (US) wearing the terminal. Reference is made when the ID received from the other party at the time of meeting between persons is linked to the name, the psychological index is aggregated for each department, or the display content is changed according to the ID logged in to the Web. FIG. 14 shows a specific example.

  The control unit (ASCO) includes a CPU (not shown) and executes processes such as data analysis and screen generation. The application server (AS) has a clock (ASCK) and is connected to an external NTP server (TS) to maintain an accurate time. When the time set in advance for each program is reached, the timer is started (ASTK) and the program in the control unit (ASCO) is executed. The program can be started manually or when an instruction from the client (CL) is received, or triggered by the fact that the index transmitted from the sensor network server (SS) is a specific pattern. Also good.

  Display screen generation (ASCD) sends a request to the sensor network server (SS) to acquire necessary data, and also includes the results of correlation analysis (ASCA) and user attribute list (ASUL) and display settings. The screen is drawn with reference to the file (ASDF) and transmitted to the client (CL).

  Correlation analysis (ASCA) performs statistical analysis using data obtained from external data tables (ASDT) such as psychological indicators and data after behavior discrimination in the sensor network server (SS), business / financial data, etc., and maximizes Extract the index that is statistically related to the index you want. Based on the analysis result, a control variable and its target value in external device control (ASMC) are defined and recorded in the control target value (ASCT). Furthermore, when a psychological index is obtained from a questionnaire, an estimation formula for calculating the psychological index may be updated by a correlation analysis with the behavior index.

  Further, the correlation analysis (ASCA) performs an analysis for quantifying the influence of other indexes on the psychological index. Specifically, by analyzing the correlation between the psychological index in the first and second time zones and other sensor information in the first and second time zones, the influence of the sensor information on the psychological index. Can be quantified.

  The analysis condition update determination (ASJR) checks whether there is a change in the estimation formula of the psychological index, its coefficient, and the type of argument to be used, and if an update is necessary, sends an update request to the sensor network server (SS). Then, the setting file (SSSF) is updated, and the terminal firmware update (SSCFW) is activated to update the setting file (TRSF) in the terminal (TR).

  External data storage (ASCS) acquires data from operation logs of external devices (CM) connected to the application server (AS), logs of external sensors (CS), business / financial data in the external data server (OS), etc. In this process, time information is adjusted, converted into a format suitable for correlation analysis (ASCA), and stored in an external data table (ASDT).

  The external device control (ASMC) is a mechanism for controlling the external device (CM) connected to the application server (AS), and appropriately controls the external device (CM) according to the control algorithm stored in the control target value (ASCT). Send control commands to get into the state. If necessary, information on the external sensor (CS) that senses an object that the external device (CM) has an effect on is acquired sequentially, and the sensor value is optimized (that is, the psychological index H described later is maximized). The driving device (CMAA) may be controlled so as to obtain a sensor value. For example, if the external device (CM) is an air conditioner, a room temperature meter is installed as an external sensor (CS), and the room temperature at which the psychological index of the indoor occupant is optimal is specified and controlled in correlation analysis (ASCA). A control command is sent to the air conditioner as the target value. Similarly, control to optimize human psychological indicators in environmental BGM control (volume control and music selection), how to assign passengers to be placed on elevators and vehicles, and how to present information in driving a car. Can do.

<Figure 5: Sequence of psychological index calculation at terminal>
FIG. 5 is a sequence diagram showing a procedure of psychological index calculation centered on the terminal (TR), which is executed in the embodiment of the present invention.

  First, when the terminal (TR) is turned on and the terminal (TR) is not associated with the base station (GW), the terminal (TR) periodically associates with the timer activation (TRST1) (TRTA1). )I do. Associate is to define that the terminal (TR) has a relationship of communicating with a certain base station (GW). When an associate response is received from the base station (GW) and the associate is successful, the terminal (TR) next performs time synchronization (TRCS). In time synchronization (TRCS), a terminal (TR) receives time information from a base station (GW) and sets a clock (TRCK) in the terminal (TR). The base station (GW) periodically connects to the NTP server (TS) to correct the time. For this reason, time is synchronized in all the terminals (TR). This makes it possible to compare and analyze data at the same time between persons by comparing the time information attached to the sensing data when analyzing later.

  Various sensors such as the triaxial acceleration sensor (AC) and temperature sensor (AE) of the terminal (TR) start a timer (TRST2) at a constant cycle, for example, every 10 seconds, and sense acceleration, sound, temperature, illuminance, and the like. (TRSS1). The terminal (TR) detects the facing state by transmitting / receiving a terminal ID, which is one of terminal information (TRMT), to / from another terminal (TR) using infrared rays. Various sensors of the terminal (TR) may always perform sensing without starting the timer (TRST). However, it is possible to use the power source efficiently by starting up at a constant cycle, and it is possible to continue using the terminal (TR) for a long time without charging.

  The terminal (TR) attaches time information of the clock (TRCK) and terminal information (TRMT) to the sensed data (TRCT1). When data is later analyzed in the sensor network server (SS) or application server (AS), the person wearing the terminal (TR) is identified by the terminal information (TRMT).

  In the data format conversion (TRDF1), the terminal (TR) attaches tag information such as sensing conditions to the sensing data, converts it to a determined transmission format, and records it in the in-terminal storage unit (STRG). This format is stored in common with the data format information (GWMF) in the base station (GW) and the data format information (SSMF) in the sensor network server (SS). The converted data is then transmitted to the base station (GW).

  Psychological state analysis (ANA) is activated periodically (TRST3), determines whether it is in an active state (inactive state) from acceleration data according to the read setting file (TRSF), and counts the active duration time. . For example, when calculating the frequency count and the psychological index every day, the frequency count for the previous day is stored with a date at the time of a day specified in advance in the setting file (TRSF) (for example, 2:00 am). (STRG) and the frequency count memory is reset (ANA1). Thereafter, acceleration data is read in every predetermined time unit (for example, 1 minute), an acceleration rhythm is calculated, and it is determined whether or not it is in an active state. When it is determined that the active state continues from the previous time unit (ANA2), the duration is counted up and the value of the active duration displayed on the display device (LCDD) is updated (ANA3) (LCDD1) ). Furthermore, the frequency data in the basic index (TRIF) is overwritten (ANA4) in the applicable duration range. Further, the psychological index is recalculated using a predetermined function (ANA5), and the value of the psychological index is also overwritten. This function is a prediction formula with the frequency of a specific activity duration as an argument, as shown in FIG. The updated frequency data and psychological index are displayed on the display device (LCDD) (ANA6) (LCDD2).

  As for the screen display of the terminal (TR), as shown in the example of FIG. 10, the display screen may be switched (LCDD4) by pressing any button (BTN) (LCDD3).

  Furthermore, a timer is started at a predetermined time (TRST4), and after establishing an associate (TRTA2) with the base station (GW), the sensing data and the basic index of the difference from the previous transmission are transmitted to the base station (GW), respectively. (TRSE1) (TRSE2) The base station (GW) receives it (GWSE1) (GWSE2).

<Figure 6: Configuration file synchronization sequence>
Since it is desirable that the value confirmed by the user (US) on the display device (LCDD) while wearing the terminal (TR) and the value confirmed later on the screen (OD) of the client (CL) are the same, the sensor network The psychological index obtained as a result of the psychological state analysis (SSCDT) in the server (SS) needs to coincide with the psychological index obtained as a result of the psychological state analysis (ANA) in the terminal (TR). For that purpose, the setting value of the function for calculating the psychological index needs to be synchronized in the setting file (SSSF) in the sensor network server (SS) and the setting file (TRSF) in the terminal (TR). . FIG. 9 shows an example of setting values whose values should be synchronized in the two setting files (SSSF) (TRSF). For example, a range definition (LD) for classifying the duration of the active state, an acceleration frequency threshold value (SF_TH) for determining the active state, and a time for updating the date when the psychological index is calculated every day (SF_RE) ), And a mathematical formula (SF_EQ) for calculating a psychological index.

  FIG. 6 shows a sequence diagram of processing when the setting file (SSSF) in the sensor network server (SS) and the setting file (TRSF) in the terminal (TR) are synchronized.

  In the application server (AS), the analysis condition update determination (ASJR) is performed by the timer activation (ASF1), and when the analysis condition is changed from the client (CL) or a correlation analysis with a psychological index by a regular questionnaire ( As a result of ASCD, when it is determined that a more appropriate value can be obtained by changing the setting value of the setting file (SSSF) (TRSF) (ASF2), a setting file update request (ASF3) is transmitted. The sensor network server (SS) receives the request, updates the corresponding part of the setting file (SSSF) in itself (SSF1), and further activates the terminal firmware update (SSCFW) to update the setting file of the terminal (TR). Is sent to the base station (GW). The base station (GW) activates terminal firmware update (GWCFW) and sends an update command to all or specified terminals (TR) under management. The terminal (TR) that has received the command rewrites the corresponding part of the setting file (TRSF) (TRF1).

<FIG. 7: Psychological state analysis flowchart>
FIG. 7 shows a flowchart of psychological state analysis. Further, FIG. 8 shows a table for explaining the calculation procedure by an example.

  This is a flow common to psychological state analysis (ANA) performed in the terminal (TR) and psychological state analysis (SSCDT) performed in the sensor network server (SS), and the basic index calculated in the terminal (TR) is used as an index. When stored in the storage table (SSDT) and used for display screen generation (ASCD) or correlation analysis (ASCA), the psychological state analysis (SSCDT) in the sensor network server (SS) can be omitted. Alternatively, using the value of the appearance frequency for each specific period (for example, every day) output in the psychological state analysis (ANA) in the terminal (TR), only the procedure after the procedure (AN06) is performed on the sensor network server (SS). It is also possible to recalculate as a psychological index of a group including a plurality of periods or a plurality of persons in the psychological state analysis (SSCDT).

  As an analysis procedure, first, time series data of acceleration is input (AN01), and an acceleration frequency for a predetermined time unit, for example, every minute is calculated (AN02). At this time, in the case of a three-axis acceleration sensor, a geometric average of the three-axis values for each sensing time Δt (for example, 0.01 seconds) is obtained as one positive value, and the frequency is calculated from the time-series data F (t). Ask. As a method for obtaining the frequency, an existing method such as a fast Fourier transform may be used. As a method for saving the calculation amount in the terminal (TR), the time series data F (t) is blurred by a width of n × Δt, and a difference between the value of the time t and the value of the time t + Δt is newly determined. The frequency may be calculated for convenience by counting time series data (G (t)) and counting the number of peaks of F (t) for convenience. In the example of the column (t0804) in FIG. 8, the frequency value is multiplied by 100 and indicated by an integer.

  Next, it is determined whether or not the acceleration frequency is greater than or equal to a predetermined threshold (SF_TH) every unit time (for example, 1 minute). If it is greater than or equal to the threshold, it is determined that the state is active (AN03) (t0805). When it is in the active state at time T1, the time during which it is in the active state is counted continuously (t0806), and the active duration L is calculated (AN04) (t0807). Next, a range (any one of L0 to Ln) to which the active duration L is applied is determined according to the range definition (LD) specified in the setting file (SSSF) or (TRSF), and the corresponding appearance frequency (e0 to en 1) is added to the count (AN05).

  Then, a daily psychological index H is calculated using a calculation formula (SF_EQ) including predetermined arguments (for example, e1 and e3) specified in the setting file (SSSF) or (TRSF). Finally, as the basic index, the psychological index H and the value of the appearance frequency (e0 to en) are output or transmitted to the next step as needed (AN07). When this analysis is performed at the terminal (TR), it is stored in the basic index (TRIF) and then transmitted to the base station (GW). When it is performed at the sensor network server (SS), the index Store in the storage table (SSDT).

<Figure 18: Knowledge about psychological index calculation>
FIGS. 18A to 18D are diagrams illustrating the inventors' findings that confirm that human happiness or depression tends to appear in the duration of physical exercise.

  FIG. 18A is a diagram for explaining the active duration L, and the vertical axis shows the active state as a binary value determined by whether or not the acceleration frequency is equal to or higher than a threshold value.

  FIG. 18B illustrates the distribution of the active duration from the frequency of the acceleration data obtained with an actual wearable sensor. Based on a stress questionnaire, the low stress person data and the high stress person data are separated. It is shown. From this result, it was confirmed that the distribution of human activity duration has a certain tendency, and that the slope of the distribution varies depending on the stress level. In addition, we collect psychological indices of multiple persons using questionnaires such as CES-D, which are commonly used in psychology, in order to search for areas L1 and L2 where the difference in activity duration is particularly significant. It was confirmed that the index value H0 was sufficiently predictable by the linear sum of the frequencies of the two types of activity durations (FIG. 18 (c)). FIG. 18C is a distribution of the average value of the questionnaire for each group and the value H predicted by the calculation formula shown in FIG. As a result, it was confirmed that the prediction can be made well.

  FIG. 18D discloses a calculation formula for predicting a psychological index (a value indicating happiness, a happiness level). The psychological index H is expressed by a linear sum of frequencies of activity durations in at least two types of ranges. The constants a, b1, and b2 are determined so as to maximize the fit with the value of the questionnaire result. Further, as a feature, one coefficient of the term including the frequency becomes a negative value, and the other coefficient becomes positive. This can be interpreted as allocation being a trade-off, while the upper limit of the daily activity time is limited. Furthermore, the result is that the duration range L1 of the term having a negative coefficient is smaller than the duration range L2 of the term having a positive coefficient, and the number of times that the active state lasts long without interruption is short. In many cases, the stress was found to be light. The measurement time T is the number of measurement data in one day. By dividing the frequency e by T, each term is regarded as the occurrence probability of the duration in each range, and the psychological index is calculated by the linear sum of the occurrence probabilities.

  In summary, the psychological state analysis system for analyzing the psychological state of a person according to the present embodiment includes a terminal (TR) worn on the person's body. The terminal (TR) includes an acceleration sensor (AC) that measures acceleration of body motion, a storage unit (STRG) that stores acceleration time-series data (SENSD) and a threshold value (SF_TH), and time-series data (SENSD). Processing (AN03) for determining whether each value (t0804) included in the first state (active state) equal to or greater than a threshold value is a second state (inactive state) less than the threshold value, A processing unit (ANA) that performs a process (AN04) for determining a duration (L), which is a continuous time of the state, and a process (AN06) for quantifying a person's psychological state based on the duration (L); It is characterized by having. Due to such characteristics, the psychological state analysis system according to the present embodiment can present the duration of the active state desirable for the psychological state of the worker, and the worker increases the behavior that becomes the duration. It is possible to change the code of conduct in consideration of self-behavior. Alternatively, it is possible to indirectly change the code of conduct by presenting an undesirable duration and avoiding that duration.

  More specifically, the processing unit (ANA), for a plurality of regions (L1, L2) whose duration is in a predetermined range, the appearance frequency (e1 / T, e2 / T) of the duration included in each region. ) Based on the psychological state. As a result, it is possible to present a range of desirable duration and a range of undesirable duration for the psychological state, and it becomes easier to revise the behavioral code. Here, the plurality of regions include a first region (L1) whose duration is the first range and a second region (L2) whose duration is the second range, and the second region The upper limit of the range is preferably larger than the upper limit of the first range. This is because the range in the trade-off relationship described above can be clarified.

  More specifically, the processing unit (ANA) includes the first term including the first appearance frequency (e1 / T) that is the appearance frequency of the duration included in the first region, and the second region. The psychological state may be quantified by the sum of the second term including the second appearance frequency (e2 / T) which is the appearance frequency of the included duration. Furthermore, in the first appearance frequency and the second appearance frequency, one is a sum of terms having a negative coefficient and the other one having a positive coefficient. This is based on the knowledge described with reference to FIG. 18. With such a configuration, it is possible to calculate a distribution that fits well with the average value of the questionnaire, and to reproduce the psychological state of the person with higher accuracy.

  Further, the psychological state measurement system includes an external sensor (CS) that measures sensor information related to an environment where a person exists, an external device (CM) that has a function of changing sensor information, and an application server (AS). The application server (AS) further includes a process (ASCA) for analyzing the correlation between the psychological state quantified by the processing unit (ANA) and the sensor information, and the psychological state value based on the correlation analysis result. It is preferable to perform processing (ASMC) for causing an external device to perform control for changing sensor information so as to increase the sensor information. With this configuration, it is possible to control an external device that optimizes a person's psychological index.

If it demonstrates from another viewpoint, the psychological state analysis system which analyzes the mental state of the person based on a present Example will be equipped with the terminal (TR) with which a person's body is equipped, and a terminal (TR) will be the acceleration of a motion of a body. A first psychological index, which is an index indicating a person's psychological state in the first time zone, and a person in the second time zone, based on an acceleration sensor (AC) that measures the time and acceleration time-series data (SENSD) And a processing unit (ANA) that calculates a second psychological index that is an index indicating the psychological state of the patient. The processing unit (ANA) includes the first and second psychological indexes (H) and the behavior of the person. Sensor information (for example, information on the number of steps obtained from the triaxial acceleration sensor (AC)) or sensor information related to the environment where the person exists (for example, various information obtained from the external sensor (CS), infrared transmission / reception) (The face information obtained from (AB), the voice information obtained from the microphone (AD), the temperature information obtained from the temperature sensor (AE), etc.) in the first time zone and in the second time zone. Based on the value of 2, it can be interpreted that the influence of the sensor information on the psychological state of the person is quantified. Here, the method of calculating the psychological index (H) is the one described in FIG. 18, but is not limited thereto, and includes the one calculated by other calculation methods. By such a method, it is possible to quantify the influence of changes in sensor information on the psychological state, and it is possible to control the sensor information to a value optimal for a person using the numerical value.

<Figure 10: Display screen example of terminal>
An example of the screen of the display device (LCDD) of the terminal (TR) that measures the psychological state, invented based on the knowledge shown in FIG. 18, is shown in FIG. The terminal (TR) calculates and displays a psychological index (TROD20) using an acceleration frequency from a predetermined time (for example, 2:00 am) to the present time in the terminal (TR). The screen can be switched (LCDD3) by pressing some buttons (BTN1 to 3). When it is not desirable that the psychological index (TROD20) is always visible from another person when the terminal (TR) is worn, usually another screen 1 (TROD1) is displayed and the psychological state only for a predetermined time after the button is pressed. It is also possible to display (TROD20) (TROD2).

  For example, it is possible to display the duration of the active state at normal times. Thereby, the motivation to continue the active state can be performed. For example, in the case of the setting file (SSSF) (TRSF) shown in FIG. 9, if the duration is 5 minutes or more and less than 10 minutes, the psychological state is negatively affected (undesirable influence), and 15 minutes or more and 20 minutes. If the duration of less than is satisfied, it can be interpreted as having a positive influence (desirable influence) on the psychological state. The frequency of appearance in one day in this range is displayed together with explanations of “Oops!” And “Success!” (TRODe1) (TRODe3). Furthermore, it may be set with the goal of maintaining the activity for 15 minutes, and the duration of the active state from the time when the active state is once interrupted to the present time may be displayed together (TRODe).

  As described above, the display unit (LCDD) according to the present embodiment has a duration (TRODe), a frequency of occurrence of a duration (TRODe1, TRODe3) included in a certain region where the duration is in a predetermined range, or The psychological value (TROD20) that has been digitized is displayed. Such a display mode makes it possible to motivate the worker more appropriately. In particular, the first appearance frequency (TRODe1) which is the appearance frequency of the duration included in the first area (L1) and the second appearance frequency of the duration included in the second area (L2). It is preferable to display the appearance frequency (TRODe3). Furthermore, the upper limit of the second range is preferably larger than the upper limit of the first range. Such a display mode makes it easier for the worker to grasp the desired behavior and the undesirable behavior identified based on the knowledge described in FIG. 18, and motivates the worker more accurately. .

<FIGS. 11, 12, and 13: Web Application Display Screen Examples>
11 and 12 are examples of the display screen (OD) of the Web application generated by the display screen generation (ASCD).

  FIG. 12 shows an example of a screen for the user (US) to check the psychological index of himself or his / her organization. For example, the graph (HG) displays time-series changes in psychological indices such as the person and the organization to which he belongs. In addition, the activity duration distribution (HV), which is an argument of the psychological index, may be displayed in a graph to confirm the appearance frequency of the desired range and the range that is not. In this way, it is possible to confirm what causes the high and low days of the psychological index, and to examine the measures for improving the psychological state by linking with the events of the day.

  Furthermore, FIG. 12 is an example of a screen (OD) showing the result of correlation analysis (ASCA). Statistical analysis is performed using the calculated psychological index as an objective variable, and an index or behavior index related to the environment or device operation as an explanatory variable, and a highly related explanatory variable is extracted and displayed. In that case, you may distinguish and describe the analysis result (AP) regarding an individual, and the analysis result (AS) regarding an organization.

  FIG. 13 is an example of an index storage table (SSDT) for one user (US). Reading the values of the index storage table (SSDT), the screens illustrated in FIGS. 10, 11, and 12 are generated. The basic index (TRIF) in the terminal (TR) has the same items, but when the storage capacity is small, the specification may hold data for only a few days. The index storage table (SSDT) stores the frequency (e0 to e4) for each designated range L, the total number of hours T measured, and the predicted value (H) of the psychological index. In addition to this, data such as behavior discrimination (SSCAD) results may be stored, but is omitted in FIG.

<FIG. 14: Example of User Attribute List (ASUL)>
FIG. 14 is an example of the format of the user attribute list (ASUL) stored in the storage unit (ASME) of the application server (AS). In the user attribute list (AUL), a user number (ASUIT1), a user name (ASUIT2), a terminal ID (ASUIT3), and a part to which the user belongs (ASUIT4) and a section (ASUIT5) are recorded in association with each other. The user number (ASUIT1) indicates a serial number of an existing user. The user name (ASUIT2) is a notation of the name or nickname of the user (US) used when generating the display screen or content, and the terminal ID (ASUIT3) indicates terminal information of the terminal (TR) owned by the user (US). Is. The user (US) and the terminal ID (ASUIT3) basically correspond one to one. Also, the department (ASUIT4) and section (ASUIT5) to which the user belongs is information on the organization to which the user (US) belongs. For example, when creating basic content in organizational units, the members included in the data are based on this information. Identify.

  In FIG. 14, the information on the user and the organization to which the user belongs is defined in the form of a table, but this may be shown hierarchically using XML or the like. In such a case, it is possible to indicate in accordance with the organizational hierarchy such that A part exists under Company A and A1 section exists under A part. And terminal ID can be described. Note that since the same person may concurrently serve as a plurality of organizations, a plurality of organizations may correspond to one user.

<FIG. 15: Sensing Database (SSDB) Example: Acceleration Data Table>
FIG. 15 shows an example of an acceleration data table (SSDB_ACC — 1002) as an example of sensing data stored in the sensing database (SSDB) in the sensor network server (SS). This is basically the sensing data acquired by the terminal (TR) as it is, and is the data that has not undergone down-processing. A table is created for each individual, and is associated with time information (DBTM) every sampling period (for example, 0.02 seconds), and each of the three axis directions of the X axis (DBAX), Y axis (DBAY), and Z axis (DBAZ) Acceleration data is stored. In addition, you may store the raw numerical value which the acceleration sensor detected, and may store the value after converting a unit into gravity constant [G]. Such an acceleration data table is created for each member, and stored in association with the sensed time information. If a column indicating the user ID is added, the tables may be integrated without being divided for each individual.

<FIG. 16: Example of sensing database (SSDB): meeting table>
A plurality of types of sensing data of a plurality of members are recorded in the sensing database (SSDB). An example of a table in which meeting data by infrared transmission / reception is collected is shown in FIGS. (A) of FIG. 16 is a meeting table (SSDB_IR_1002), and is assumed to be a table in which data acquired by a terminal (TR) having a terminal ID of 1002 is collected. Similarly, (B) of FIG. 16 is a meeting table (SSDB_IR_1003), which is a table in which data acquired by a terminal (TR) having a terminal ID of 1003 is collected. If the infrared receiver ID is added to the column, the table need not be divided for each acquired terminal (TR). Also, other data such as acceleration and temperature may be included in the same table.

  16 (A) and 16 (B), 10 sets of the time (DBTM) when the terminal (TR) transmitted data, the infrared transmission side ID (DBR1), and the number of receptions from the ID (DBN1) ( DBR1 to DBR10, DBN1 to DBN10). When data transmission is performed once every 10 seconds, this table shows how many infrared rays are received from which terminal (TR) in 10 seconds after the previous transmission. Even when facing a plurality of terminals (TR) in 10 seconds, up to 10 sets can be stored. The number of sets can be freely set. If there is no meeting, that is, there is no reception of infrared rays, the table value is null. In FIGS. 16A and 16B, the time is expressed up to milliseconds, but any time format may be used.

<FIG. 17: Example of sensing database (SSDB): behavior rhythm table>
The result of acceleration frequency calculation (AN02) in psychological state analysis (ANA) (SSCDT) may be output to the sensing database (SSDB) as time series data. An example of the acceleration frequency table (SSDB_ACCTP_1min) is shown in FIG. The acceleration frequency table (SSDB_ACCTP_1min) is calculated based on the acceleration data table (SSDB_ACC) for each user (US) at a certain frequency (for example, 1 minute). This is stored in the table in association with the ID. In addition to the table, the data may be stored in another method such as a CSV file.

  Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and various modifications can be made, and it is possible to appropriately combine the above-described embodiments. It will be understood by the contractor.

TR, TR2-3 Terminal GW Base station US, US2-3 User NW Network PAN Personal area network SS Sensor network server AS Application server CL Client OS External data server CM External device CS External sensor.

Claims (4)

A psychological state analysis system for analyzing a person's psychological state,
A storage unit for storing time-series data and threshold values of acceleration of the movement of the person's body;
A process for determining whether each acceleration frequency value calculated from the time series data is in a first state that is equal to or greater than the threshold value or a second state that is less than the threshold value, and a time during which the first state continues A processing unit that performs a process of determining a certain duration, and a process that quantifies the psychological state of the person based on the duration.
The plurality of regions in which the duration is in a predetermined range includes a first region in which the duration is a first range and a second region in which the duration is a second range,
The upper limit of the second range is greater than the upper limit of the first range,
The processing unit is a first term including a first appearance frequency that is an appearance frequency of the duration included in the first area, and an appearance frequency of the duration included in the second area. A psychological state analysis system characterized in that the psychological state is quantified by a sum of second terms including a second appearance frequency. In claim 1,
In the first appearance frequency and the second appearance frequency, the processing unit quantifies the psychological state by a sum of terms having one negative coefficient and the other one having a positive coefficient. Psychological state analysis system. In claim 1,
The psychological state analysis system further comprising a display unit that displays the duration, the first appearance frequency, the second appearance frequency, or the numerical value of the psychological state. In claim 1,
The psychological state analysis system is
An external sensor for measuring sensor information related to the environment in which the person exists;
An external device having a function of changing the sensor information;
An application server,
The application server is
Processing for analyzing the correlation between the digitized psychological state and the sensor information;
A psychological state analysis system that performs a process of causing the external device to perform control to change the sensor information so as to increase the value of the psychological state based on the analysis result of the correlation.

Images