JP2019101742A - Data generation device, data generation method, and data generation program, and sensor device - Google Patents

Abstract

To provide a technique for generating virtual sensing data that describes operational state information of peripheral devices in the vicinity of a physical sensor.SOLUTION: A data generation device comprises: a selection unit configured to select a determination criterion corresponding to first virtual sensing data indicative of a first determination result about a state surrounding a physical sensor from a plurality of determination criteria defined for state items to be determined; and a determination unit configured to determine operating states of peripheral devices in the vicinity of the physical sensor for each of the state items on the basis of physical sensing data using the selected determination criterion, and generate second virtual sensing data indicative of the determination result about the states.SELECTED DRAWING: Figure 1

Description

  The present disclosure relates to a data generation device, a data generation method, a data generation program, and a sensor device.

  In addition to the sensors (physical sensors) actually arranged, one or more physical sensors analyze and process sensing data (physical sensing data) generated by observing the sensing target, and new sensing data A technology (program module) of a virtual sensor that generates (virtual sensing data) is known. By designing a virtual sensor that generates sensing data that matches the user's request, the user can use desired sensing data even if such a physical sensor does not actually exist.

  In Patent Document 1, “The voltage waveform, current waveform, voltage value, and current amount of the power supplied to the home appliance connected to the outlet or tap are required for each home appliance in real time (required by the home appliance) By measuring the required power, that is, the required power, inside the outlet or tap, and “calculating the measurement result in the outlet or the computing device in the tap, and recognizing and analyzing it as the voltage waveform and current waveform pattern” It has been disclosed that “identify the home appliance connected to the outlet or the tap, detect the operation status of each home appliance, occurrence of a problem, etc.” (0027).

JP, 2016-28545, A

  The technique of Patent Document 1 needs to use "smart tap which is a tap provided with power measurement means" ([0015]), which is expensive compared to many other sensing devices such as temperature sensors. It is. In addition, special construction is required when using this smart tap as an “embedded outlet to be embedded in a structure or facility such as a wall, pillar, ceiling, floor, or furniture of a building” (0029). , More expensive.

  Also, the situation consists of various elements. Therefore, when making a determination on an element of a situation based on physical sensing data, noise or the like from another element may be affected.

  An object of the present disclosure is to provide a technology for generating virtual sensing data that describes information on the operation status of a peripheral device around a physical sensor.

  A data generation device according to a first aspect of the present disclosure includes: a first acquisition unit that acquires physical sensing data obtained by observing a sensing target by a physical sensor; and determination of a situation around the physical sensor A second acquisition unit that acquires first virtual sensing data representing a result; a third acquisition unit that acquires a plurality of determination criteria defined for a status item to be determined; A selection unit that selects one determination criterion corresponding to the first virtual sensing data from the determination criteria, and the physical sensing data acquired using the selected determination criteria for each of the status items Based on the operation condition of the peripheral device around the physical sensor is determined, and second virtual sensing data representing the determination result of the operation condition of the peripheral device is generated ; And a that the determination unit.

  According to this data generation device, the determination criteria can be used in which the influence of noise or the like due to the condition indicated by the first virtual sensing data can be used, so that the operation condition of peripheral devices around the physical sensor can be accurately determined. It becomes possible.

  In the data generation device according to the first aspect, the determination criteria may include a raw data of the physical sensing data and a reference value for at least one of processed data of the raw data. Thereby, the operation state of the peripheral device can be determined by comparing the reference value included in the determination reference with the raw data of the physical sensing data corresponding to the reference value or the processed data thereof.

  In the data generation device according to the first aspect, the determination criterion is the operation status of the peripheral device from the learning physical sensing data generated under the condition indicated by the first virtual sensing data associated with the determination criterion. It may include a learned model created by performing machine learning to determine.

  Thus, by providing raw data of physical sensing data as input data or processed data thereof to a neural network in which a learned model is set, it is possible to determine the operation status of the peripheral device.

  In the data generation device according to the first aspect, the status item is a first item that handles information on the operation status of the illumination around the physical sensor that generates the physical sensing data, and a ventilation fan around the physical sensor Second item handling information on the operation status of the third item handling information on the operation status of the refrigerator around the physical sensor, and information on the operation status of the microwave oven around the physical sensor It may include at least one of the four items. According to this data generation device (hereinafter, referred to as a data generation device according to the second aspect of the present disclosure), it is possible to determine the first to fourth items.

  In the data generation device according to the second aspect, the status item includes the first item, the physical sensing data includes at least one of illuminance data and sound pressure data, and the determination unit The selected criterion is applied to at least one of raw data of each of the illuminance data and the sound pressure data and processed data of the raw data, and the determination is performed for the first item. Good. Thereby, for example, determination on the first item can be realized without the need for a smart tap.

  In the data generation device according to the second aspect, the status item includes the second item, the physical sensing data includes at least one of barometric pressure data and sound pressure data, and the determination unit The selected criterion is applied to at least one of the barometric pressure data, the raw data of the sound pressure data, and the processed data of the raw data, and the second item is judged Good. Thereby, for example, determination on the second item can be realized without the need for a smart tap.

  In the data generation device according to the second aspect, the status item includes the third item, the physical sensing data includes at least one of sound pressure data and temperature data, and the determination unit The selected criterion is applied to at least one of the sound pressure data, the raw data of each of the temperature data, and the processed data of the raw data, and the determination is performed for the third item. Good. Thereby, for example, the determination on the third item can be realized without the need for a smart tap.

  In the data generation device according to the second aspect, the status item includes the fourth item, and the physical sensing data includes at least one of sound pressure data, temperature data, and humidity data, and the determination The unit applies the selected determination criterion to at least one of raw data of each of the sound pressure data, the temperature data, and the humidity data, and processed data of the raw data, and the fourth The determination may be made on the item. Thereby, for example, the determination on the fourth item can be realized without the need for a smart tap.

  A sensor device according to a third aspect of the present disclosure includes the data generation device according to the first or second aspect, and the physical sensor. Thereby, in addition to physical sensing data, an intelligent sensor device can be provided that generates virtual sensing data indicating the determination result on the operation state of the peripheral device.

  In a data generation method according to a fourth aspect of the present disclosure, a computer acquires physical sensing data obtained by a physical sensor observing a sensing target, and a determination result of a situation around the physical sensor. Obtaining the first virtual sensing data representing H, obtaining a plurality of determination criteria defined for the status item to be determined, and the first virtual from the obtained plurality of determination criteria Peripheral device around the physical sensor based on the acquired physical sensing data using the selected criterion for selecting one criterion corresponding to the sensing data and using the selected criterion for each of the status items Determining a second operating condition of the peripheral device and generating second virtual sensing data representing a result of the determination of the operating condition of the peripheral device. Comprising.

  According to this data generation method, it is possible to use a determination criterion in which the influence of noise or the like due to the situation indicated by the first virtual sensing data is taken into consideration, so that the operation situation of peripheral devices around the physical sensor is accurately determined. It becomes possible.

  The data generation program according to the fifth aspect of the present disclosure is a computer that acquires physical sensing data obtained by a physical sensor observing a sensing target, and a determination result about a situation around the physical sensor. Obtaining the first virtual sensing data representing H, obtaining a plurality of determination criteria defined for the status item to be determined, and the first virtual from the obtained plurality of determination criteria Peripheral device around the physical sensor based on the acquired physical sensing data using the selected criterion for selecting one criterion corresponding to the sensing data and using the selected criterion for each of the status items The second virtual sensing data representing the determination result of the operation condition of the peripheral device is generated. Is a program for executing the Toto.

  According to this data generation program, it is possible to use a determination criterion in which the influence of noise or the like due to the condition indicated by the first virtual sensing data is taken into consideration, so that the operation condition of peripheral devices around the physical sensor is accurately determined. It becomes possible.

  According to the present disclosure, it is possible to provide a technique for generating virtual sensing data that describes information on the operation status of peripheral devices around a physical sensor.

FIG. 1 is a block diagram showing an application example of a data generation device according to an embodiment. The block diagram which illustrates the hardware constitutions of the data generation device concerning an embodiment. FIG. 1 is a block diagram illustrating a functional configuration of a data generation device according to an embodiment. FIG. 1 illustrates a data distribution system including a data generation apparatus according to an embodiment. FIG. 4 is a block diagram illustrating a first virtual sensing data generation unit of FIG. 3; The figure which illustrates the status item of virtual sensing data, and the physical sensing data used in order to judge about the said status item. The figure which illustrates the data chart used in order to judge about the status item "stove." The figure which illustrates the criterion used in order to judge about the status item "stove". FIG. 9 is a view showing a comparison result of the data chart of FIG. 7 and the determination reference of FIG. The graph which illustrates the raw data of the physical sensing data used in order to make a judgment about the status item "lighting", and its processed data. The figure which illustrates the data chart used in order to judge about the status item "lighting". The figure which illustrates the criterion used in order to judge about the status item "lighting". The figure which shows the comparison result of the data chart of FIG. 11, and the criterion of FIG. The graph which illustrates the raw data of the physical sensing data used in order to judge about the status item "ventilator", and its processed data. The figure which illustrates the data chart used in order to judge about the status item "ventilator". The figure which illustrates the criterion used in order to judge about the status item "ventilator". FIG. 18 is a view showing a comparison result of the data chart of FIG. 15 and the determination reference of FIG. 16; The graph which illustrates the raw data of the physical sensing data used in order to judge about the status item "fridge", and its processed data. The figure which illustrates the data chart used in order to judge about the status item "fridge." The figure which illustrates the criterion used in order to judge about status item "fridge." The figure which shows the comparison result of the data chart of FIG. 19, and the criterion of FIG. The graph which illustrates the physical sensing data used in order to judge about the status item "microwave oven." FIG. 4 is a block diagram illustrating a second virtual sensing data generation unit of FIG. 3; The figure which illustrates the condition item of 2nd virtual sensing data, the corresponding item in 1st virtual sensing data, and the physical sensing data used in order to supplement the said corresponding item. 7 is a flowchart illustrating the operation of the first virtual sensing data generation unit of FIG. 5; FIG. 24 is a flowchart illustrating the operation of a second virtual sensing data generation unit of FIG. 23; FIG. FIG. 4 is a block diagram illustrating a sensor device including the data generation device of FIG. 3; FIG. 4 is a block diagram illustrating a communication device including the data generation device of FIG. 3; FIG. 4 is a block diagram illustrating a server including the data generation device of FIG. 3;

  Hereinafter, embodiments according to one aspect of the present disclosure (hereinafter, also referred to as “this embodiment”) will be described based on the drawings.

  Hereinafter, elements which are the same as or similar to the already described elements are denoted by the same or similar reference numerals, and redundant descriptions will be basically omitted. For example, when there are a plurality of identical or similar elements, a common code may be used to explain each element without distinction, and the common code may be used to distinguish and describe each element. In addition, branch numbers may be used.

11 Application example
First, an application example of the present embodiment will be described using FIG. FIG. 1 schematically shows an application example of the data generation apparatus according to the present embodiment. The data generation apparatus 100 determines the operation statuses of peripheral devices around the physical sensor based on the physical sensing data for each of a plurality of status items predetermined as a determination target, and determines values corresponding to the determination results. Virtual sensing data (hereinafter, also referred to as second virtual sensing data for convenience) is generated. Here, peripheral devices may mean all devices installed around physical sensors, and neither physical connection nor functional coordination with physical sensors and / or virtual sensors is required. .

  In the following description, the condition around the physical sensor may include the condition of the sensing object of the virtual sensor, such as a person or other living or inanimate object in the space around the physical sensor. In addition, the environment of the physical sensor means the operating conditions (for example, accuracy, resolution, dynamic range, etc.) of the physical sensor that generates physical sensing data used directly or indirectly as a base of the input data of the virtual sensor It may be determined based on the characteristics of the sensing object of the sensor (e.g., light, sound, temperature, etc.) and the surrounding environment (e.g., in air, in water, in vacuum, etc.).

  The status item may be, for example, an item for segmenting and describing the status. Specifically, the status items are “human presence” that handles information on whether or not there is a person around the physical sensor, the operation status of the stove, air conditioning, microwave oven, and TV around the physical sensor. It may include "stove" handling information, "air conditioning", "microwave oven" and "TV", "cooking" handling information on whether or not a person is cooking around a physical sensor, and the like. Here, the status items include at least the items belonging to the operating status of the peripheral device (for example, the above-mentioned "stove", "air conditioning", "microwave" and "TV"). Specific examples of the items belonging to the operation status of the peripheral device will be described later.

  The data generation apparatus 100 includes a physical sensing data acquisition unit 101, a virtual sensing data acquisition unit 102, a determination reference acquisition unit 103, a determination reference selection unit 111, and a situation determination unit 112.

  The physical sensing data acquisition unit 101 acquires physical sensing data. Physical sensing data may include, for example, illuminance data, sound pressure data, acceleration data, gas data, barometric pressure data, temperature data, humidity data, and the like. When the data generation device 100 is built in a sensor device, the physical sensing data acquisition unit 101 may acquire physical sensing data from a sensor in the sensor device. Also, the physical sensing data acquisition unit 101 may receive physical sensing data generated by a physical sensor unit incorporated in the external device.

  The virtual sensing data acquisition unit 102 acquires first virtual sensing data representing a primary determination result about the situation. The first virtual sensing data may be generated by an external device such as, for example, a host system, or may be generated by the data generation apparatus 100.

  The determination criterion acquisition unit 103 acquires a predetermined determination criterion for the status item. The criterion is applied to generate second virtual sensing data representing a secondary determination result of the situation. Here, the condition indicated by the second virtual sensing data at least includes the operation condition of the peripheral device. Note that a plurality of determination criteria may be defined for the status item.

  Here, it has been stated that the first virtual sensing data indicates a primary determination result, and the second virtual sensing data indicates a secondary determination result, but the “primary” and “secondary” modifications Merely describes the order in which the determinations of the situation are made, and is not intended to define any relationship, including superiority or inferiority between the two.

  When a plurality of determination criteria are defined for a given situation item, the determination criteria selection unit 111 selects one determination criterion for the situation item. Specifically, the determination criterion selection unit 111 may select a determination criterion corresponding to the first virtual sensing data.

  Temporarily, the criterion 1 used when the condition item "person present" is true (people exist around the physical sensor) as the determination criteria for determining the condition item "stove", the condition item "air conditioning" Judgment criterion 2 used when is true (air conditioning around physical sensor is ON), when the status item “microwave” is true (microwave oven around physical sensor is ON) And the criterion 4 used when the status item “TV” is true (TV at the periphery of the physical sensor is ON). Here, the determination criterion selection unit 111 may select the determination criterion 1 when the first virtual sensing data indicates that a person is present around the physical sensor.

  Note that the status item included in the first virtual sensing data may not match the status item included in the second virtual sensing data. If the two do not match, the data generation apparatus 100 may include a data conversion unit for converting the value of the status item of the first virtual sensing data into the value of the corresponding item of the second virtual sensing data. . For example, when the first virtual sensing data includes the value of the status item "number of people" that handles information on the number of people present around the physical sensor, the data conversion unit uses the value of "number of people" It may be converted to the value of

  The determination criterion may include a reference value for at least one of raw data of physical sensing data to be referred to for determination of the status item and its processed data. For example, the reference value may be 200 lx for raw data of illuminance data, 50% for a time ratio in which the sound pressure exceeds 50 dB in 30 seconds, or the like. The reference value may be, for example, raw data of physical sensing data generated under a situation corresponding to a situation item targeted by the judgment standard, or of processed data of the physical sensing data and physical sensing data generated under a situation other than that. It can be designed by analyzing raw data or its processed data.

  In this case, the situation determination unit 112 prepares data necessary for applying the determination criteria, that is, raw data of physical sensing data for which a reference value is defined or processed data thereof. The processed data of the raw data of the physical sensing data may be included in the physical sensing data, may be calculated by another component included in the status determination unit 112 or the data generation apparatus 100, or may be an external device May calculate. The situation determination unit 112 compares the data thus prepared with the reference value, and sets the value of the situation item in the second virtual sensing data according to the comparison result.

  Alternatively, the criteria may include a trained model that is used to make a determination on the context item. This learned model may be created by performing machine learning that determines the situation from the learning physical sensing data. For example, in the learned model as the determination criterion 2, the raw data of each learning physical sensing data generated when the air conditioning is ON around the physical sensor and the stove is ON around the physical sensor and And / or can be created by performing supervised learning using the processed data as learning data with a correct answer label. In addition, the raw data and / or the processed data of each learning physical sensing data generated when the air conditioning is on around the physical sensor and the stove is off around the physical sensor, are labeled as incorrect solutions It may be used as attached learning data.

  In this case, the situation determination unit 112 uses raw data of physical sensing data or its processing for inputting data necessary for applying the determination criteria, that is, a neural network in which a learned model as the determination criteria is set. Prepare the completed data. The situation determination unit 112 gives the data prepared in this manner to the neural network in which the learned model as the determination standard is set, and sets the value of the situation item based on the output value. The learned model may be created through machine learning for acquiring the ability to make decisions on a plurality of situation items simultaneously. In this case, common judgment criteria are determined among the plurality of status items.

  As described above, the data generation apparatus 100 according to the application example uses the determination criteria used to determine the operating condition of the peripheral device based on the first virtual sensing data representing the primary determination result of the condition. Choose Therefore, according to this data generation apparatus 100, since the determination criteria in which the influence of noise etc. due to the situation indicated by the first virtual sensing data can be used can be used, the operation situation of the peripheral device around the physical sensor can be accurately determined. It is possible to determine

22 Configuration example
[Hardware configuration]
Next, an example of the hardware configuration of the data generation apparatus 200 according to the present embodiment will be described using FIG. FIG. 2 schematically illustrates an example of the hardware configuration of the data generation apparatus 200 according to the present embodiment.

  As exemplified in FIG. 2, the data generation apparatus 200 according to the present embodiment includes a control unit 211, a storage unit 212, a communication interface 213, an input device 214, an output device 215, an external interface 216, and a drive. 217 may be an electrically connected computer. In FIG. 2, the communication interface and the external interface are described as “communication I / F” and “external I / F”, respectively.

  The control unit 211 includes a central processing unit (CPU), a random access memory (RAM), a read only memory (ROM), and the like. The CPU develops the program stored in the storage unit 212 in the RAM. Then, the CPU interprets and executes this program, whereby the control unit 211 can execute various information processing, for example, processing or control of components described in the item of the functional configuration.

  The storage unit 212 is a so-called auxiliary storage device, and is, for example, a built-in or external semiconductor memory such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory. obtain. The storage unit 212 is a program executed by the control unit 211 (for example, a program for causing the control unit 211 to execute data generation processing), data used by the control unit 211 (for example, various physical sensing data, various virtual sensing Store data, judgment criteria, etc.

  The communication interface 213 is, for example, various wireless communication modules for BLE (Bluetooth (registered trademark) Low Energy), mobile communication (3G, 4G, etc.), WLAN (Wireless Local Area Network), etc. It may be an interface for performing wireless communication. The communication interface 213 may further include a wired communication module such as a wired LAN module in addition to or instead of the wireless communication module.

  The input device 214 may include a device for receiving user input, such as a touch screen, a keyboard, a mouse, and the like. The input device 214 may also include a sensor that measures a predetermined physical quantity and generates and inputs physical sensing data. The output device 215 is, for example, a device for performing an output such as a display or a speaker.

  The external interface 216 is a USB (Universal Serial Bus) port, a memory card slot, or the like, and is an interface for connecting to an external device.

  The drive 217 is, for example, a CD (Compact Disc) drive, a DVD (Digital Versatile Disc) drive, a BD (Blu-ray (registered trademark) Disc) drive, or the like. The drive 217 reads a program and / or data stored in the storage medium 218 and passes it to the control unit 211. Note that part or all of the programs and data described to be stored in the storage unit 212 described above may be read from the storage medium 218 by the drive 217.

  The storage medium 218 is a medium that stores programs and / or data electrically, magnetically, optically, mechanically or chemically in a machine-readable form including a computer. The storage medium 218 is, for example, a removable disk medium such as a CD, a DVD, and a BD, but is not limited thereto, and may be a flash memory or another semiconductor memory.

  In addition, regarding the specific hardware configuration of the data generation apparatus 200, omission, replacement, and addition of components can be appropriately made according to the embodiment. For example, the control unit 211 may include a plurality of processors. The data generation device 200 may be an information processing device designed specifically for the service to be provided, or a general-purpose information processing device such as a smartphone, a tablet PC (Personal Computer), a laptop PC, a desktop PC, etc. It may be. Also, the data generation device 200 may be configured of a plurality of information processing devices or the like.

[Function configuration]
Next, an example of a functional configuration of the data generation apparatus 200 according to the present embodiment will be described using FIG. 3. FIG. 3 schematically illustrates an example of a functional configuration of the data generation apparatus 200.

  As shown in FIG. 3, the data generation apparatus 200 includes a physical sensing data acquisition unit 301, a virtual sensing data acquisition unit 302, a determination reference acquisition unit 303, a first virtual sensing data generation unit 310, and a second. It includes a virtual sensing data generation unit 320 and a data output unit 330.

  The data generation apparatus 200 generates virtual sensing data 11 and virtual sensing data 12 (corresponding to the above-described second virtual sensing data), and outputs these.

  Note that the data generation apparatus 200 may not generate part of the virtual sensing data 11 and the virtual sensing data 12. When the virtual sensing data 11 is not generated, the first virtual sensing data generation unit 310 can be omitted. When the virtual sensing data 12 is not generated, the second virtual sensing data generation unit 320 can be omitted. The virtual sensing data 11 and the virtual sensing data 12 can be used, for example, in various business areas such as marketing activities.

  The virtual sensing data 11 and the virtual sensing data 12 may be provided directly to the use side from the data generation apparatus 200 or may be provided to the use side through a data distribution system described below. In any case, the data generation device 200 may be incorporated in a (physical) sensor device, a server, an application device or the like, or may be configured as an information processing device independent of these.

  As mentioned above, this data generation device 200 may be incorporated into any of the various devices that form the data distribution market. That is, the data generation device 200 may be incorporated in a sensor device that generates physical sensing data, or a communication device (for example, a smart phone, which relays physical sensing data to a platform server, a matching server, or an application device on the use side). Or the like, or may be incorporated in a platform server, a matching server, or an application device. In this case, the data generation device 200 can use the hardware of the device in which the data generation device 200 is incorporated. Alternatively, the data generation device 200 may be configured as an information processing device independent of these devices.

  FIG. 4 schematically illustrates an example of a data distribution system in which the data generation apparatus 200 is included. The data distribution system includes the sensor devices 400-1, ..., 400-5, the communication devices 410-1, ..., 410-3, the server 420, and the application devices 430-1, ..., 430. And -3. In addition, the number of each apparatus illustrated by FIG. 4 is only an illustration. Therefore, the branch numbers assigned to the reference numerals of the respective devices will be described without particular distinction.

  The sensor device 400 includes a sensor that measures a physical quantity, a communication I / F that transmits physical sensing data obtained by digitizing a measurement value of the sensor, and a control unit that controls the sensor and the communication I / F. The sensor device 400 is connected to the communication device 410 using, for example, a communication technology such as wireless body area network (WBAN) or wireless personal area network (WPAN). Sensor device 400 transmits physical sensing data (and virtual sensing data, if any) to communication device 410.

  The communication device 410 may be, for example, a smartphone or various PCs. The communication device 410 includes a communication I / F that transmits and receives data, and a control unit that controls the communication I / F. The communication device 410 receives physical sensing data from the sensor device 400. Then, the communication device 410 transmits physical sensing data (and, if any, to the server 420 via the gateway or base station using a communication technology such as WLAN, Wireless Metropolitan Area Network (WMAN), Wireless Wide Area Network (WWAN), etc. Send virtual sensing data). In addition, the communication device 410 may transmit to the server 420 a provider-side data catalog (DC) for performing trading matching of sensing data.

  The provider-side data catalog includes, for example, the number of data catalog, provider of sensing data, name of sensing data, measurement date / time and location of sensing data, observation target / characteristic, event data specification, provision period of sensing data, transaction conditions , Various items such as data trading conditions can be included.

  The application device 430 may be, for example, a smartphone, various PCs, or a server. The application device 430 includes a communication I / F that transmits and receives data, and a control unit that controls the communication I / F. The application device 430 may transmit, to the server 420, a user-side data catalog (DC) for performing trading matching of sensing data.

  Here, the user-side data catalog includes, for example, identification information of data catalog, user of sensing data, name of sensing data, measurement date / time and location of sensing data, observation target / characteristic, event data specification, use of sensing data It can include various items such as terms, trading conditions, data trading conditions, and the like.

  The application device 430 receives from the server 420 physical sensing data (and virtual sensing data, if any) purchased through trading matching. Then, the application device 430 processes physical sensing data (and virtual sensing data, if any) in accordance with the purpose of each use.

  The server 420 includes a communication I / F that transmits and receives data, a storage unit that stores data, and a control unit that controls the storage unit and the communication I / F and performs trading matching described later. The server 420 receives physical sensing data from the communication device 410. The server 420 then accumulates this physical sensing data (and virtual sensing data, if any).

  In addition, the server 420 obtains and stores the provider-side data catalog and the user-side data catalog, respectively, and compares the two to perform trade matching. The provider data catalog and the user data catalog may be acquired by receiving from the communication device 410, the application device 430, or another communication device, or may be acquired by other means such as direct input. When the server 420 finds a provider data catalog that matches the user data catalog, the server 420 provides the user with physical sensing data (and virtual sensing data, if any) corresponding to the provider data catalog. That is, the server 420 sends physical sensing data (and virtual sensing data, if any) to the application device 430.

  The form of the data distribution system is not limited to the example of FIG. For example, the sensor device 400 directly transmits physical sensing data and / or data to the server 420 or the application device 430 via the gateway or base station without using the communication device 410, for example, using a communication technology such as WLAN, WMAN, WWAN, etc. Alternatively, virtual sensing data may be transmitted.

  In addition, the server 420 may not transmit physical sensing data and / or virtual sensing data to the application apparatus 430 immediately after establishment of trading matching, and may once request the providing side or the using side for approval of trading. Also, the server 420 may perform data flow control without transmitting physical sensing data and / or virtual sensing data to the application device 430. For example, the server 420 may instruct the sensor device 400 or the communication device 410 to transmit the physical sensing data and / or virtual sensing data to the application device 430 that has purchased the physical sensing data and / or virtual sensing data. . Alternatively, the server 420 may be divided into a server performing trading matching and a server storing physical sensing data and / or virtual sensing data.

  Furthermore, the server 420 may delegate trading matching to a matching server (not shown) without directly performing trading matching. The matching server may realize a distribution market that does not distinguish between platforms by performing trading matching across multiple platforms, or physical sensing data and / or virtual sensing data (provided without using a platform). For example, a secondary market that does not distinguish the source of the data may be realized by adding the data collected from the sensor device 400 installed personally to the target of the trade matching.

Hereinafter, individual components of the data generation apparatus 200 illustrated in FIG. 3 will be described.
The physical sensing data acquisition unit 301 acquires physical sensing data, and sends the physical sensing data to the first virtual sensing data generation unit 310 and the second virtual sensing data generation unit 320. Physical sensing data may include, for example, illuminance data, sound pressure data, acceleration data, gas data, barometric pressure data, temperature data, humidity data, and the like. The physical sensing data may be raw data, processed raw data, or a combination thereof.

  When the data generation device 200 is incorporated in the sensor device 400, the physical sensing data acquisition unit 301 may acquire physical sensing data from a sensor included in the sensor device 400. On the other hand, when the data generation device 200 is not incorporated in the sensor device 400, the physical sensing data acquisition unit 301 receives physical sensing data from the external device using the sensor device 400 as a transmission source to obtain physical sensing data. You can get Note that it is not necessary for all of the physical sensing data to be acquired from the same sensor device 400. For example, one physical sensing data and another physical sensing data may be acquired from different sensor devices 400.

  The virtual sensing data acquisition unit 302 acquires virtual sensing data 13 (that is, first virtual sensing data) indicating a primary determination result about the situation, and sends the virtual sensing data 13 to the second virtual sensing data generation unit 320. The virtual sensing data 13 may be generated by an external device such as, for example, the upper system, the sensor device 400, the communication device 410, the server 420, and the application device 430, or may be generated by the first virtual sensing data generation unit 310. It may be the virtual sensing data 11 that has been sent.

  Alternatively, the virtual sensing data acquisition unit 302 may acquire the virtual sensing data 12 generated by the second virtual sensing data generation unit 320 as the virtual sensing data 13. For example, when the second virtual sensing data generation unit 320 repeatedly determines a given situation, it is also assumed that the generated virtual sensing data 12 is repeatedly used. Specifically, second virtual sensing data generation unit 320 repeatedly uses virtual sensing data 12 to determine the status stepwise from a simple or general status item to a complex or detailed status item. It is also good.

  The determination criterion acquisition unit 303 acquires a predetermined determination criterion for the status item. The determination criteria are applied to generate virtual sensing data 11 (hereinafter also referred to as a first determination criterion) and applied to generate virtual sensing data 12 (hereinafter referred to as a second determination) (Also referred to as a reference). A determination criterion acquisition unit may be individually provided for each of the first determination criterion and the second determination criterion. The first determination criterion and the second determination criterion may be partially common or completely different. The determination reference acquisition unit 303 sends the first determination reference to the first virtual sensing data generation unit 310, and sends the second determination reference to the second virtual sensing data generation unit 320.

  The determination criterion acquiring unit 303 may acquire the determination criterion by reading out the determination criterion stored in the determination criterion storage unit (not shown in FIG. 3) incorporated in the data generation device 200, or from the external device The determination criteria may be acquired by receiving the transmitted determination criteria.

  The first virtual sensing data generation unit 310 receives physical sensing data from the physical sensing data acquisition unit 301, and receives a determination criterion (first determination criterion) from the determination criterion acquisition unit 303. The first virtual sensing data generation unit 310 determines the situation based on the physical sensing data using the determination criteria, and generates the virtual sensing data 11. The virtual sensing data 11 may indicate, for example, the determination result of the situation for each situation item. The first virtual sensing data generation unit 310 sends the virtual sensing data 11 to the data output unit 330.

  Although a specific generation method of the virtual sensing data 11 will be described later, for example, when the determination standard determined for a certain situation item includes raw data of physical sensing data or a reference value for its processed data, The first virtual sensing data generation unit 310 may prepare raw data of physical sensing data corresponding to a reference value or processed data thereof, and compare the two to make a determination on the status item. Alternatively, if the determination criterion is a learned model for making a determination on one or more status items, the first virtual sensing data generation unit 310 sets the learned model in a neural network, and the neural network Raw data or physical processed data of physical sensing data defined as the input data of may be prepared, and the prepared data may be given to the neural network to make a determination.

  The second virtual sensing data generation unit 320 receives physical sensing data from the physical sensing data acquisition unit 301, receives the virtual sensing data 13 from the virtual sensing data acquisition unit 302, and receives the determination criteria (second Receive judgment criteria). When a plurality of determination criteria are defined for a given situation item, the second virtual sensing data generation unit 320 selects one corresponding to the virtual sensing data 13 from the plurality of determination criteria. Then, the second virtual sensing data generation unit 320 determines the situation based on the physical sensing data using the selected determination criterion, and generates the virtual sensing data 12. The virtual sensing data 12 may indicate, for example, the determination result of the situation for each situation item. The second virtual sensing data generation unit 320 sends the virtual sensing data 12 to the data output unit 330.

  Although a specific generation method of the virtual sensing data 12 will be described later, for example, if the criterion selected for a certain situation item includes physical sensing data or a reference value for the processed data, the second virtual The sensing data generation unit 320 may prepare the physical sensing data corresponding to the reference value or the processed data thereof, and compare the two to determine the situation item. Alternatively, if the determination criterion is a learned model for making a determination on one or more status items, the second virtual sensing data generation unit 320 sets the learned model in a neural network, and the neural network Raw data or physical processed data of physical sensing data defined as the input data of may be prepared, and the prepared data may be given to the neural network to make a determination.

  The data output unit 330 receives the virtual sensing data 11 from the first virtual sensing data generation unit 310, and receives the virtual sensing data 12 from the second virtual sensing data generation unit 320. The data output unit 330 outputs the received virtual sensing data to the outside of the data generation apparatus 200. Further, the data output unit 330 may shape virtual sensing data or control output timing of the virtual sensing data.

Hereinafter, the first virtual sensing data generation unit 310 will be further described with reference to FIGS. 5 to 22.
As illustrated in FIG. 5, the first virtual sensing data generation unit 310 includes a situation determination unit 311. The status determination unit 311 receives physical sensing data from the physical sensing data acquisition unit 301, and receives a determination criterion (first determination criterion) from the determination criterion acquisition unit 303. The situation determination unit 311 determines the situation based on the physical sensing data using the determination criteria, and generates virtual sensing data 11. The situation determination unit 311 sends the virtual sensing data 11 to the data output unit 330.

  The status item included in the virtual sensing data 11 may belong to “operation status of peripheral device”, for example, as shown in FIG. The status items shown in FIG. 6 are merely examples, and status items different from this may be used. In addition, virtual sensing data 11 may include status items that do not belong to the “operation status of the peripheral device” illustrated in FIG. 6, and the status items listed in FIG. There is also room for interpretation. FIG. 6 exemplifies status items belonging to “operation status of peripheral device” and physical sensing data used to make a determination on the status items.

  In FIG. 6, physical sensing data listed in the column of physical sensing data is not limited to raw data, but may include processed data. Here, as an example of processed data, in addition to statistics of raw data, heat stroke risk calculated from raw data of temperature spectrum and temperature data and humidity data generated by applying Fourier transform to raw data, acceleration, acceleration There may be a seismic intensity calculated from the raw data of Similarly, physical sensing data listed in the column of physical sensing data is merely illustrative.

  For example, it is assumed that the situation determination unit 311 acquires the determination chart illustrated in FIG. 8 as a determination standard for the situation item “stove”. Here, the determination chart is, for example, a list of reference values used for determination. The reference value may be, for example, raw data of physical sensing data generated under the situation corresponding to the condition item targeted by the judgment criteria or raw data of the processed data and physical sensing data generated under the situation other than that. It can be designed by analyzing the data or its processed data.

  The situation determination unit 311 exemplifies the raw data of the physical sensing data or the processed data thereof at least for which the reference value is determined in FIG. May be prepared as a data chart. Here, the data chart is, for example, a list of raw data of physical sensing data used for determination and processed data thereof. When the physical sensing data does not include the processed data of the raw data, the situation determination unit 311 may generate necessary processed data.

  The situation determination unit 311 compares the data chart of FIG. 7 with the determination chart of FIG. 8 to obtain the comparison result illustrated in FIG. In FIG. 9, “○” is determined in the determination chart when the value in the corresponding column of the data chart is greater than or equal to the reference value defined in the determination chart, and “×” when the value is below the reference value. When there is no reference value, "-" is attached respectively.

  The situation determination unit 311 converts, for example, “o” and “x” as “1 (true)” or “0 (false)” or vice versa, respectively, and is a logical expression defined as a part of the determination criteria. Or set the value of the status item by substituting it into a relational expression. The value of the status item may be defined as a binary value, eg, “1 (true)” or “0 (false)”, or may be defined as three or more multivalues, eg, probability value, percentage, score, etc. .

  As described above, the determination criteria may include a learned model. When the determination criterion includes a learned model, the situation determination unit 311 sets the learned model in a neural network, and raw data of physical sensing data defined as input data of the neural network or the processed data thereof. And the prepared data may be given to the neural network to make a determination.

  This learned model may be created by performing machine learning that determines the situation from the learning physical sensing data. For example, a learned model for making a determination on the status item “stove” may be raw data and / or processed data of each of the learning physical sensing data generated when the stove is on around the physical sensor, It can be created by performing supervised learning using it as learning data with a correct answer label. Also, raw data and / or processed data of each learning physical sensing data generated when the stove is off around the physical sensor may be used as learning data with an incorrect answer label.

  Hereinafter, specific examples of determination regarding various status items will be described with reference to FIGS. 10 to 22. Although all of the specific examples described here make the determination using the reference value, the determination using the learned model may be made as appropriate as described above.

  FIG. 10 shows raw data and physical processed data of physical sensing data "illuminance" and "sound pressure" used to make a determination on the status item "lighting". The status item "lighting" can handle information on the lighting operation status around the physical sensor.

  If the illumination is in the ON state around the physical sensor, the illumination light may increase raw data of the physical sensing data “illuminance”. Therefore, for raw data of the physical sensing data "illuminance", a value for distinguishing ON / OFF of the illumination, for example, "200 [lx]" may be set as the reference value.

  In addition, if the illumination is switched from the OFF state to the ON state around the physical sensor, there is a possibility that an abrupt increase in illuminance may occur. Therefore, the situation determination unit 311 can also use changes in the raw data of the physical sensing data “illuminance” (here, for example, maximum change for one second) for determination. For example, “50 [lx]” may be set as the reference value for the change of the raw data of the physical sensing data “illuminance”.

  If a switch operation noise is generated when the illumination is switched from the OFF state to the ON state around the physical sensor, significant sound pressure may be detected. Therefore, the situation determination unit 311 searches for a peak exceeding “± 15 [dB]” for changes in raw data of the physical sensing data “sound pressure” for a predetermined analysis period, for example, for the last 30 seconds, and the 30 Processed data (hereinafter, also simply referred to as “the number of changes”) may be prepared in which the maximum number of peaks falling in an area of any one second in a second is calculated. For the number of changes in sound pressure, a value for distinguishing between when there is a switch operation of the illumination and when it is not so, for example, “1 [time]” may be set as the reference value. Here, one second is an example of a time domain for capturing the up and down movement of the impulse-like sound pressure accompanying the switch operation sound, and can be changed.

  It is assumed that the situation determination unit 311 acquires the determination chart illustrated in FIG. 12 as a determination standard for the situation item “lighting”. The situation determination unit 311 prepares raw data of physical sensing data for which a reference value is determined at least in FIG. 12 or processed data thereof as a data chart illustrated in FIG.

  The situation determination unit 311 compares the data chart of FIG. 11 with the determination chart of FIG. 12 to obtain the comparison result illustrated in FIG. In FIG. 13, “定 め” is determined in the determination chart when the value in the corresponding column of the data chart is greater than or equal to the reference value defined in the determination chart, and “×” when the value is below the reference value. When there is no reference value, "-" is attached respectively.

  In this example, both the raw data and change of the illuminance and the number of changes of the sound pressure are above the reference value. Therefore, the situation determination unit 311 sets the value of the status item “lighting”, for example, that the lighting is in the on state around the physical sensor, or that the lighting is switched from the off state to the on state in the last 30 seconds. It is possible to set “1 (true)” indicating

  FIG. 14 shows raw data and physical processed data of physical sensing data "atmospheric pressure" and "sound pressure" used to make a determination on the status item "ventilating fan". The status item "ventilating fan" can handle information on the operating status of the ventilating fan around the physical sensor.

  If the ventilation fan is in the ON state around the physical sensor, the raw data of the physical sensing data "pressure" may change due to the operation of the ventilation fan. For example, if the air supply type ventilation fan is operated, the inflow of air into the room may be increased and the raw data of the physical sensing data "pressure" may be increased. On the other hand, if the exhaust ventilation fan operates, the outflow of air to the outside may increase and the raw data of the physical sensing data "pressure" may decrease. Therefore, the situation determination unit 311 can also use the change in the raw data of the physical sensing data “pressure” (here, for example, the difference from the value 5 seconds before) for the determination. For example, “0.02 hPa” may be set as the reference value for the change of the raw data of the physical sensing data “atmospheric pressure”.

  If the ventilation fan is in the ON state around the physical sensor, the raw sound of the physical sensing data "sound pressure" may increase due to the operation noise. Therefore, the situation determination unit 311 can also use changes in raw data of the physical sensing data “sound pressure” for determination. For changes in raw data of the physical sensing data "sound pressure", for example, "10 [dB]" may be set as a reference value.

  It is assumed that the situation determination unit 311 acquires the determination chart illustrated in FIG. 16 as a determination standard for the situation item “ventilating fan”. The situation determination unit 311 prepares raw data of physical sensing data for which a reference value is determined at least in FIG. 16 or processed data thereof as a data chart illustrated in FIG.

  The situation determination unit 311 compares the data chart of FIG. 15 with the determination chart of FIG. 16 to obtain the comparison result illustrated in FIG. In FIG. 17, “定 め” is determined in the determination chart when the value in the corresponding column of the data chart is greater than or equal to the reference value defined in the determination chart, and “×” when the value is below the reference value. When there is no reference value, "-" is attached respectively.

  In this example, both the change in barometric pressure and the change in sound pressure are above the reference value. Therefore, the situation determination unit 311 determines that the value of the status item “ventilating fan” is, for example, that the ventilating fan is in the on state around the physical sensor or that the ventilating fan is switched from the off state to the on state in the last 30 seconds It is possible to set “1 (true)” indicating

  FIG. 18 shows raw data of physical sensing data “sound pressure” used to make a determination on the status item “refrigerator” and processed data thereof. The status item “fridge” can handle information about the operation status of the refrigerator around the physical sensor, for example, whether or not the door of the refrigerator has been opened or closed for the last 30 seconds around the physical sensor.

  If the refrigerator door is opened and closed around the physical sensor, significant sound pressure may be detected when the refrigerator door is opened and closed, respectively. Therefore, the situation determination unit 311 searches for a peak exceeding “50 [dB]” for the raw data of the physical sensing data “sound pressure” for, for example, the last 30 seconds, and arbitrary 10 seconds of the 30 seconds Processed data (hereinafter, also simply referred to as “raw value number”) may be prepared by calculating the maximum number of peaks falling into the region of. As the raw value of this sound pressure, a value for distinguishing between when there is opening and closing of the refrigerator door and when it is not so, for example, “2 [times]” may be set as the reference value. Here, the area length of 10 seconds is an estimated required time from opening to closing of the refrigerator door, and can be changed as appropriate.

  Similarly, changes in raw data of physical sensing data "sound pressure" can be used for determination. Specifically, the situation determination unit 311 determines the number of times the change in the raw data of the physical sensing data "sound pressure" exceeds "+10 dB" and falls below "-10 [dB]" within 10 seconds from that. It is also possible to prepare processed data that has been counted (hereinafter, also simply referred to as “number of changes”). For the number of changes in the sound pressure, a value, for example, “2 [times]” may be set as a reference value to distinguish between the case where the door of the refrigerator is opened and the case where the door is not opened.

  It is assumed that the situation determination unit 311 acquires the determination chart illustrated in FIG. 20 as a determination standard for the situation item “fridge”. The situation determination unit 311 prepares raw data of physical sensing data for which a reference value is determined at least in FIG. 20 or processed data thereof as a data chart illustrated in FIG.

  In addition to this, for example, there is a possibility that the situation item "refrigerator" can be more accurately determined by capturing a drop in temperature due to leakage of cold air in the refrigerator based on the physical sensing data "temperature".

  The situation determination unit 311 compares the data chart of FIG. 19 with the determination chart of FIG. 20, and obtains the comparison result exemplified in FIG. In FIG. 21, “21” is determined in the determination chart when the value in the corresponding column of the data chart is greater than or equal to the reference value defined in the determination chart, and “×” when the value is below the reference value. When there is no reference value, "-" is attached respectively.

  In this example, both the raw value number and the change number of the sound pressure are equal to or greater than the reference value. Therefore, the situation determination unit 311 may set, for example, “1 (true)” indicating that the door of the refrigerator has been opened and closed around the physical sensor, to the value of the situation item “fridge”.

  FIG. 22 shows raw data of physical sensing data “sound pressure” used to make a determination on the status item “microwave range”. The status item “microwave oven” can handle information on the operation status of the microwave oven around the physical sensor.

  As the change in sound pressure caused by the operating condition of the microwave, there is a rapid change in sound pressure when the door is opened or closed (for example, around time [0:00:04] and around [0:00:07] in FIG. 22). ), Sound pressure generated continuously by using, for example, a magnetron as a noise source during operation (around [0:00:09] and [around 0:00:24] of time in FIG. 22), and abruptness due to the end of operation There is a change in sound pressure (for example, around time [0:00:24] in FIG. 22) and the like. For example, the reference value can be designed in consideration of some or all of these factors.

  In addition to this, for example, based on the physical sensing data “temperature” and “humidity”, the status item “electronic” is captured by capturing an increase in temperature and humidity due to the vapor leaking from the inside when taking out the warmed food etc. There is a possibility that it can be judged more accurately about "range".

The second virtual sensing data generation unit 320 will be further described below with reference to FIGS. 23 and 24.
As illustrated in FIG. 23, the second virtual sensing data generation unit 320 includes a determination criterion selection unit 321 and a situation determination unit 322.

  The determination criteria selection unit 321 receives the virtual sensing data 13 from the virtual sensing data acquisition unit 302, and receives the determination criteria (second determination criteria) from the determination criteria acquisition unit 303. When a plurality of determination criteria are defined for a given situation item, the determination criteria selection unit 321 selects one of the plurality of determination criteria corresponding to the virtual sensing data 13, and the selected determination criteria Are sent to the situation determination unit 322.

  The situation determination unit 322 receives physical sensing data from the physical sensing data acquisition unit 301, and receives the determination criteria selected from the determination criteria selection unit 321. The situation determination unit 322 determines the situation based on the physical sensing data using the selected determination criteria, and generates virtual sensing data 12. The situation determination unit 322 sends the virtual sensing data 12 to the data output unit 330.

  Similar to the virtual sensing data 11, the status item included in the virtual sensing data 12 can belong to "the operating status of the peripheral device", for example, as shown in FIG. The status items shown in FIG. 6 are merely examples, and status items different from this may be used. In addition, virtual sensing data 11 may include status items that do not belong to the “operation status of the peripheral device” illustrated in FIG. 6, and the status items listed in FIG. There is also room for interpretation.

  In FIG. 6, physical sensing data listed in the column of physical sensing data is not limited to raw data, but may include processed data. Similarly, physical sensing data listed in the column of physical sensing data is merely illustrative.

  For example, for the condition item "stove", the determination criterion selection unit 321 determines the determination criterion 1 used when the condition item "personal presence" is true, and the determination criterion 2 used when the condition item "air conditioning" is true. It is assumed that determination criterion 3 used when the status item “microwave range” is true and determination criterion 4 used when the status item “TV” indicates true are acquired as determination charts. Here, the determination chart is, for example, a list of reference values used for determination. The reference value included in the determination criteria is, for example, (1) a condition that matches the condition (indicated by the virtual sensing data 13) to which the determination criterion is associated and that corresponds to the condition item targeted by the determination criterion Under the situation that matches the situation where the raw data of the physical sensing data generated below or its processed data and (2) the judgment criteria are matched, but it does not correspond to the situation item targeted by the judgment standards It is possible to design by analyzing the raw data of the physical sensing data generated by or the processed data thereof. The determination criterion selection unit 321 may select the determination criterion 1 when the first virtual sensing data indicates that a person is present around the physical sensor.

  The situation determination unit 322 may prepare, as a data chart, raw data of physical sensing data for which at least a reference value is determined in the determination chart selected by the determination criteria selection unit 321 or processed data thereof. Here, the data chart is, for example, a list of raw data of physical sensing data used for determination and processed data thereof. When the physical sensing data does not include processed data of the raw data, the situation determination unit 322 may generate necessary processed data.

  The situation determination unit 322 compares the data chart with the determination chart to obtain a comparison result. The situation determination unit 322 converts the comparison results of the respective reference values as “1 (true)” or “0 (false)” or vice versa, respectively, and is a logical expression defined as a part of the determination criteria or Set the value of the status item by substituting it into a relational expression. The value of the status item may be defined as a binary value, eg, “1 (true)” or “0 (false)”, or may be defined as three or more multivalues, eg, probability value, percentage, score, etc. .

  As described above, the determination criteria may include a learned model. When the determination criterion includes a learned model, the situation determination unit 322 sets the learned model in a neural network, and raw data of physical sensing data defined as input data of the neural network or its processed data And the prepared data may be given to the neural network to make a determination.

  This learned model may be created by performing machine learning that determines the situation from the learning physical sensing data. For example, if the value of the status item “TV” in the virtual sensing data 13 is true (TV at the periphery of the physical sensor is ON), the learned model for determining the status item “stove” is physically The raw data and / or the processed data of each of the learning physical sensing data generated when the TV is on around the sensor and the stove is on around the physical sensor are labeled with a correct answer label It can be created by performing supervised learning using it as data. Also, the raw data and / or the processed data of each of the learning physical sensing data generated when the TV is on around the physical sensor and the stove is off around the physical sensor are labeled as incorrect solutions It may be used as attached learning data.

  The situation determination unit 322 may not perform the determination using the determination criteria for part or all of the situation items included in the virtual sensing data 12. Specifically, the situation determination unit 322 may perform the determination based on the virtual sensing data 13 acquired from the virtual sensing data acquisition unit 302 for part or all.

  For example, the situation determination unit 322 may use the value of the virtual sensing data 13 as it is or as a value of a specific situation item included in the virtual sensing data 12. In addition, the situation determination unit 322 may determine the situation items included in the virtual sensing data 12 by supplementing the corresponding items in the virtual sensing data 13 based on the physical sensing data.

  FIG. 24 exemplifies a status item belonging to the middle item “operation status of peripheral device”, an item of virtual sensing data 13 corresponding to the status item, and physical sensing data used to supplement the item.

<Others>
Each function of the data generation apparatus 200 will be described in detail in an operation example described later. In the present embodiment, an example is described in which each function of the data generation apparatus 200 is realized by a general-purpose CPU. However, some or all of the above functions may be realized by one or more dedicated processors. In addition, regarding the functional configuration of the data generation device 200, omission, replacement, and addition of functions may be performed as appropriate according to the embodiment.

3 3 Operation example
Next, an operation example of the data generation apparatus 200 will be described using FIGS. 25 and 26. FIG. In addition, the process sequence demonstrated below is only an example, and each process may be changed as much as possible. In addition, according to the embodiment, steps may be omitted, replaced, or added as appropriate, according to the embodiment.

FIG. 25 is a flowchart showing an example of the operation of the first virtual sensing data generation unit 310.
First, the physical sensing data acquisition unit 301 acquires physical sensing data, and the determination criterion acquisition unit 303 acquires a determination criterion (first determination criterion) (step S501). The situation determination unit 311 receives the physical sensing data and the determination criteria, and the process proceeds to step S502.

  In step S502, the situation determination unit 311 selects an unselected item among the situation items (for example, the items illustrated in FIG. 6) included in the virtual sensing data 11. Note that depending on the judgment criteria, judgments can be made simultaneously for a plurality of status items. For example, the criteria may include a learned model created by machine learning that makes decisions on multiple status items simultaneously. In such a case, a plurality of items may be selected in step S502.

  The situation determination unit 311 prepares raw data of physical sensing data and its processed data necessary to apply the determination criteria defined for the situation item (here, referred to simply as the selection item) selected in step S502. (Step S503). Here, the physical sensing data required to apply the determination criteria may be, for example, raw data of the physical sensing data for which the reference value included in the determination criteria is defined or the processed data thereof, or the determination criteria It may be raw data of physical sensing data defined as input data of a neural network in which a learned model included in the set is set or processed data thereof.

  The situation determination unit 311 determines whether the situation corresponds to the selection item by applying the determination criteria set for the selection item to the data prepared in step S503 (step S504). Applying the determination criteria to the data may be comparing the reference value included in the determination criteria with the corresponding data, or the data may be input to the set neural network of the learned model included in the determination criteria. It may be giving.

  The situation determination unit 311 sets the value of the selection item in the virtual sensing data 11 according to the determination result of step S504 (step S505). If the process for all status items is completed at the end of step S505, the operation of FIG. 25 is ended, otherwise the process returns to step S502 (step S506).

FIG. 26 is a flowchart illustrating an example of the operation of the second virtual sensing data generation unit 320.
First, the physical sensing data acquisition unit 301 acquires physical sensing data, the virtual sensing data acquisition unit 302 acquires the virtual sensing data 13, and the determination criterion acquisition unit 303 acquires a determination criterion (second determination criterion) (see FIG. Step S511). The determination criteria selection unit 321 receives the virtual sensing data 13 and the determination criteria, the situation determination unit 322 receives the physical sensing data, and the process proceeds to step S512.

  In step S512, the determination criterion selection unit 321 selects an unselected item among the status items (for example, the items illustrated in FIG. 6) included in the virtual sensing data 12. Note that depending on the judgment criteria, judgments can be made simultaneously for a plurality of status items. For example, the criteria may include a learned model created by machine learning that makes decisions on multiple status items simultaneously. In such a case, a plurality of items may be selected in step S512.

  In the case where a plurality of determination criteria are defined for the status item selected in step S512 (here, simply referred to as a selection item), the determination criteria selection unit 321 uses the virtual sensing data 13 acquired in step S511. A corresponding one is selected (step S513). In addition, step S513 may be skipped when only one determination criterion is defined with respect to a selection item.

  The situation determination unit 322 prepares raw data of physical sensing data necessary for applying the determination criteria selected in step S513 and the processed data thereof (step S514). Here, the physical sensing data required to apply the determination criteria may be, for example, raw data of the physical sensing data for which the reference value included in the determination criteria is defined or the processed data thereof, or the determination criteria It may be raw data of physical sensing data defined as input data of a neural network in which a learned model included in the set is set or processed data thereof.

  The situation determination unit 322 applies the determination criteria selected in step S513 to the data prepared in step S514 to determine whether the situation corresponds to the selection item (step S515). Applying the determination criteria to the data may be comparing the reference value included in the determination criteria with the corresponding data, or the data may be input to the set neural network of the learned model included in the determination criteria. It may be giving.

  The situation determination unit 322 sets the value of the selection item in the virtual sensing data 12 according to the determination result of step S515 (step S516). If the process for all status items is completed at the end of step S516, the operation of FIG. 26 is ended, otherwise the process returns to step S512 (step S517).

[Operation / effect]
As described above, in the present embodiment, the data generation apparatus determines the operation status of the peripheral device based on the physical sensing data using the determination reference. Therefore, according to this data generation device, it is possible to generate virtual sensing data indicating the determination result of the operation state of the peripheral device.

  Also, in order to determine the operation status of the peripheral device based on the first virtual sensing data representing the primary determination result of the status generated by the data generation device itself or generated by the external device. You may select the criterion to be used. As a result, it is possible to use a determination criterion in which the influence of noise or the like due to the situation indicated by the first virtual sensing data is taken into consideration, so that it is possible to accurately determine the operation situation of peripheral devices around the physical sensor. .

  According to this data device, it is possible to flexibly provide virtual sensing data that matches the requirements of the user. Therefore, according to this virtual sensing data, utilization of sensing data on the user side may be promoted.

4 4 variations
The embodiments of the present disclosure have been described above in detail, but the above description is merely illustrative of the present disclosure in all respects. It goes without saying that various improvements and modifications can be made without departing from the scope of the present disclosure. For example, the following changes are possible. In the following, the same reference numerals are used for the same constituent elements as the above embodiment, and the description of the same parts as the above embodiment is appropriately omitted. The following modifications may be combined as appropriate.

<4.1>
For example, data generator 200 may be incorporated into a sensor device. FIG. 27 schematically illustrates an example of a functional configuration of a sensor device in which the data generation device 200 is incorporated. The hardware configuration of this sensor device may be the same as or similar to the configuration example shown in FIG.

The sensor device of FIG. 27 includes a data generation device 200, a physical sensor control unit 601, a physical sensor unit 610, a transmission unit 621, a determination reference storage unit 622, and a reception unit 623.
The physical sensor control unit 601 controls the operation of the physical sensor unit 610.

  The physical sensor unit 610 is controlled by the physical sensor control unit 601, measures one or more types of physical quantities, and generates physical sensing data representing the physical quantities. The physical sensor unit 610 sends physical sensing data to the transmission unit 621 and the data generation apparatus 200.

The physical sensor unit 610 measures, for example, an illuminance sensor 611 that measures illuminance, a sound pressure sensor 612 that measures sound pressure, an acceleration sensor 613 that measures acceleration, and gas concentrations such as volatile organic compounds (VOCs) or CO ₂ Gas sensor 614, a barometric pressure sensor 615 for measuring the barometric pressure, and the like. However, the various physical sensors listed here are merely examples, and the physical sensor unit 610 may include sensors different from these sensors, or may not include some or all of these sensors.

  The transmission unit 621 receives physical sensing data from the physical sensor unit 610, and receives virtual sensing data from the data generation apparatus 200. The transmission unit 621 transmits the physical sensing data and the virtual sensing data to the upper communication device or server or the application device. Note that the transmission unit 621 may combine physical sensing data and virtual sensing data and then transmit the combined data, or may transmit separate data. Also, the transmission unit 621 may make the destinations and / or paths of the physical sensing data and the virtual sensing data different.

  The determination criteria storage unit 622 stores the determination criteria used by the data generation apparatus 200. The determination criteria stored in the determination criteria storage unit 622 are read out by the data generation apparatus 200 (a determination criteria acquisition unit 303 included therein) as necessary. The determination criteria may be preset in the determination criteria storage unit 622, may be created inside the sensor device of FIG. 27, or created by an external device (for example, a server) and received by the receiving unit 623. It is also good.

  The receiving unit 623 sends, for example, the determination criteria created by the external device (for example, a server) to the determination criteria storage unit 622. The determination criteria are stored in the determination criteria storage unit 622. In addition, the reception unit 623 may receive virtual sensing data from an external device (for example, a higher-level communication device or a server), and send the virtual sensing data to the data generation device 200. This virtual sensing data can also be used as virtual sensing data 13, for example.

  The data generation apparatus 200 acquires physical sensing data from the physical sensor unit 610, and acquires a determination reference from the determination reference storage unit 622. Furthermore, the data generation device 200 can acquire, from the reception unit 623, virtual sensing data generated by the external device. The data generation apparatus 200 operates as described above to generate part or all of the virtual sensing data 11 and the virtual sensing data 12, and sends the part to the transmission unit 621.

  As described above, in the modified example <4.1>, the data generation device 200 according to the embodiment is incorporated in the sensor device. Therefore, according to this modification, it is possible to provide an intelligent sensor device that generates virtual sensing data in addition to physical sensing data. Moreover, according to this modification, the data generation device 200 can be realized using hardware resources such as a processor and a memory of the sensor device.

<4.2>
For example, data generator 200 may be incorporated into a communication device. FIG. 28 schematically illustrates an example of a functional configuration of a communication device in which the data generation device 200 is incorporated. The hardware configuration of this communication apparatus may be the same as or similar to the configuration example shown in FIG.

  The communication device in FIG. 28 may be, for example, a smartphone or various PCs. The communication device includes a data generation device 200, a reception unit 701, a determination reference storage unit 702, and a transmission unit 703.

  The receiving unit 701 receives physical sensing data from an external device (for example, a sensor device), and sends the data to the data generating device 200 and the transmitting unit 703. Also, the receiving unit 701 can receive virtual sensing data from an external device (for example, a higher-level communication device or server), and can send this to the data generation device 200. This virtual sensing data can also be used as virtual sensing data 13, for example. Similarly, the receiving unit 701 can receive the determination criteria from an external device (for example, a server) and send the determination criteria to the determination criteria storage unit 702. The determination criteria are stored in the determination criteria storage unit 702.

  The determination criteria storage unit 702 stores the determination criteria used by the data generation apparatus 200. The determination criteria stored in the determination criteria storage unit 702 are read out by the data generation apparatus 200 (a determination criteria acquisition unit 303 included therein) as necessary. The determination criteria may be preset in the determination criteria storage unit 702, may be created inside the communication device of FIG. 28, or may be created by an external device (for example, a server) and received by the receiving unit 701. It is also good.

  The transmission unit 703 receives physical sensing data from the reception unit 701, and receives virtual sensing data from the data generation apparatus 200. The transmitting unit 703 transmits the physical sensing data and the virtual sensing data to the upper communication apparatus or server or the application apparatus. Note that the transmission unit 703 may combine physical sensing data and virtual sensing data before transmission, or may transmit separate data. In addition, the transmission unit 703 may make the destinations and / or paths of the physical sensing data and the virtual sensing data different.

  The data generation apparatus 200 acquires physical sensing data from the reception unit 701, and acquires the determination criteria from the determination criteria storage unit 702. Furthermore, the data generation device 200 can acquire, from the reception unit 701, virtual sensing data generated by the external device. The data generation apparatus 200 operates as described above to generate part or all of the virtual sensing data 11 and the virtual sensing data 12 and sends the part to the transmission unit 703.

  As described above, in the modification <4.2>, the data generation apparatus 200 according to the embodiment is incorporated in the communication apparatus. Therefore, according to this modification, even when the sensor device can not generate at least a part of the virtual sensing data 11 and the virtual sensing data 12 described above, necessary virtual sensing data can be replenished. Further, according to this modification, the data generation device 200 can be realized using hardware resources such as a processor and a memory of the communication device.

<4.3>
For example, data generator 200 may be incorporated into a server. FIG. 29 schematically illustrates an example of a functional configuration of a server incorporating the data generation device 200. The hardware configuration of this server may be the same as or similar to the configuration example shown in FIG.

  The server in FIG. 29 uses the data generation apparatus 200, the reception unit 801, the determination reference storage unit 802, the virtual sensing data storage unit 803, the physical sensing data storage unit 804, the provider data catalog storage unit 805, and It includes a side data catalog storage unit 806, a matching unit 807, a data management unit 808, and a transmission unit 809.

  The reception unit 801 receives physical sensing data from an external device (for example, a sensor device), and sends the data to the data generation device 200 and the physical sensing data storage unit 804. Also, the receiving unit 801 can receive virtual sensing data from an external device and can send this to the data generation device 200. This virtual sensing data can also be used as virtual sensing data 13, for example. Similarly, the receiving unit 801 can receive the determination reference from the external device and send it to the determination reference storage unit 802. The determination criteria are stored in the determination criteria storage unit 802.

  The receiving unit 801 can receive a provider data catalog used for matching from an external device (for example, a communication device), and can send this to the provider data catalog storage unit 805. The provider data catalog is stored in the provider data catalog storage unit 805. Similarly, the receiving unit 801 can receive a use side data catalog used for matching from an external device (for example, an application device), and can send this to the use side data catalog storage unit 806. The use-side data catalog is stored in the use-side data catalog storage unit 806.

  The determination criteria storage unit 802 stores the determination criteria used by the data generation apparatus 200. The determination criteria stored in the determination criteria storage unit 802 are read out by the data generation apparatus 200 (the determination criteria acquisition unit 303 included therein) as necessary. The determination criteria may be preset in the determination criteria storage unit 802, may be created inside the server of FIG. 29, or may be created by an external device and received by the receiving unit 801.

  The virtual sensing data storage unit 803 stores virtual sensing data generated by the data generation device 200. The virtual sensing data stored in the virtual sensing data storage unit 803 is read by the data management unit 808 as necessary.

  The physical sensing data storage unit 804 stores physical sensing data received by the receiving unit 801. The physical sensing data stored in the physical sensing data storage unit 804 is read by the data management unit 808 as necessary.

  The provider data catalog storage unit 805 stores, for example, a provider data catalog received by the receiver 801 or directly input. The providing side data catalog stored in the providing side data catalog storage unit 805 is read by the matching unit 807 as required.

  The use-side data catalog storage unit 806 stores, for example, a use-side data catalog received by the reception unit 801 or directly input. The usage-side data catalog stored in the usage-side data catalog storage unit 806 is read by the matching unit 807 as necessary.

  The matching unit 807 reads the provider data catalog from the provider data catalog storage unit 805, and reads the user data catalog from the user data catalog storage unit 806. The matching unit 807 performs trade matching between the provider data catalog and the user data catalog. For example, the matching unit 807 compares at least a part of items included in the user-side data catalog with corresponding items included in the provider-side data catalog, and extracts a provider-side data catalog that matches the request of the user. The matching unit 807 notifies the data management unit 808 to that effect when the transaction matching is established. In addition, when the providing side data catalog meeting the request of the user side is found, the matching unit 807 asks the user and / or the provider side for approval of the data exchange, and then manages the establishment of the transaction matching. It may be notified to the part 808.

  When notified by the matching unit 807 that trading matching has been established, the data management unit 808 receives physical sensing data and / or virtual sensing data on the provider side from the physical sensing data storage unit 804 and / or virtual sensing data storage unit 803. Are sent to the transmission unit 809.

  The transmission unit 809 receives physical sensing data and / or virtual sensing data from the data management unit 808, and transmits this to the application device. Note that the transmission unit 809 may combine physical sensing data and virtual sensing data before transmission, or may transmit separate data. Also, the transmission unit 809 may make the destinations and / or paths of the physical sensing data and the virtual sensing data different.

  The data generation apparatus 200 acquires physical sensing data from the reception unit 801, and acquires a determination criterion from the determination criterion storage unit 802. Furthermore, the data generation device 200 can acquire virtual sensing data generated by the external device from the reception unit 801. The data generation apparatus 200 operates as described above to generate a part or all of the virtual sensing data 11 and the virtual sensing data 12, and sends the virtual sensing data 11 and the virtual sensing data 12 to the virtual sensing data storage unit 803. The virtual sensing data is stored in the virtual sensing data storage unit 803.

  As described above, in the modified example <4.3>, the data generation apparatus 200 according to the embodiment is incorporated in the server. Therefore, according to this modification, it is possible to supplement necessary virtual sensing data even when a lower device such as a sensor device can not generate at least a part of the virtual sensing data 11 and virtual sensing data 12 described above. it can. Also, according to this modification, the data generation device 200 can be realized using hardware resources such as a processor and memory of the server.

  Note that the server according to the modification <4.3> may delegate trading matching to a matching server (not shown) without directly performing trading matching. In this case, components relating to trading matching, for example, the providing side data catalog storage unit 805, the use side data catalog storage unit 806, and the matching unit 807 can be omitted.

<4.4>
For example, data generator 200 may be incorporated into an application device. The functional configuration of this application device may correspond to, for example, one in which the transmission unit 703 in the communication device shown in FIG. 28 is replaced with a component for utilizing physical sensing data and / or virtual sensing data.

  According to the application apparatus of the modification <4.4>, necessary virtual sensing data is supplemented even when data not including at least a part of the virtual sensing data 11 and virtual sensing data 12 described above is provided. Can be used. Further, according to this modification, the data generation device 200 can be realized using hardware resources such as a processor and a memory of the application device.

<4.5>
The virtual sensing data 11 and / or the virtual sensing data 12 can also be treated as metadata indicating a measurement environment of physical sensing data and / or virtual sensing data. Such metadata can be used to facilitate pre-processing for utilization of physical sensing data and / or virtual sensing data. Also, by using metadata, it is easy to organize physical sensing data and / or virtual sensing data, for example, to generate a table. Furthermore, detection of an event is also possible by using metadata.

<4.6>
In the description of the embodiment, an example in which situation determination and / or reliability calculation is realized using a neural network in which a learned model is set is introduced. In such an approach using artificial intelligence (AI), a causal relationship model, a decision tree, a support vector machine (SVM), etc. can also be used.

  However, all the embodiments described so far are merely illustrative of the present disclosure in all respects. It goes without saying that various improvements and modifications can be made without departing from the scope of the present disclosure. That is, in the implementation of the present disclosure, a specific configuration according to the embodiment may be appropriately adopted. Although data appearing in each embodiment is described in natural language, more specifically, it is specified by a pseudo language, a command, a parameter, a machine language or the like that can be recognized by a computer.

  Part or all of the above-described embodiments can be described as well as the claims below, but is not limited thereto.

A first acquisition unit (101) for acquiring physical sensing data obtained by the physical sensor observing a sensing target;
A second acquisition unit (102) for acquiring first virtual sensing data representing a determination result about a situation around the physical sensor;
A third acquisition unit (103) for acquiring a plurality of determination criteria defined for the status item to be determined;
A selection unit (111) which selects one determination criterion corresponding to the first virtual sensing data from the plurality of acquired determination criteria;
For each of the status items, the operation status of the peripheral device around the physical sensor is determined based on the acquired physical sensing data using the selected determination criteria, and the operation status of the peripheral device is determined. A data generation device comprising: a determination unit (112) that generates second virtual sensing data representing a determination result.

11, 12, 13, ... virtual sensing data 100, 200 ... data generation device 101, 301 ... physical sensing data acquisition unit 102, 302 ... virtual sensing data acquisition unit 103, 303 ... judgment criteria Acquisition unit 111, 321 ... judgment criteria selection unit 112, 311, 322 ... situation judgment unit 211 ... control unit 212 ... storage unit 213 ... communication interface 214 ... input device 215 · · · Output device 216 External interface 217 Drive 218 Storage medium 310 First virtual sensing data generator 320 Second virtual sensing data generator 330 Data output Section 400 ... sensor device 410 ... communication device 420 ... server 430 ... application device 601 ... physical sensor control unit 610 ... physical sensor unit 611 ... illuminance sensor 612 ... sound pressure sensor 613 ... acceleration sensor 614 ... gas sensor 615 ... atmospheric pressure sensor 621, 703, 809 ... Transmission section 622, 702, 802 ... Judgment storage section 623, 701, 801 ... Reception section 803 ... Virtual sensing data storage section 804 ... Physical sensing data storage section 805 ... Provision Side DC storage unit 806: Use side DC storage unit 807: Matching unit 808: Data management unit

Claims (11)

A first acquisition unit that acquires physical sensing data obtained by the physical sensor observing a sensing target;
A second acquisition unit configured to acquire first virtual sensing data representing a determination result of a situation around the physical sensor;
A third acquisition unit that acquires a plurality of determination criteria defined for the status item to be determined;
A selection unit that selects one determination criterion corresponding to the first virtual sensing data from the plurality of acquired determination criteria;
For each of the status items, the operation status of the peripheral device around the physical sensor is determined based on the acquired physical sensing data using the selected determination criteria, and the operation status of the peripheral device is determined. A determination unit that generates second virtual sensing data representing a determination result.   The data generation device according to claim 1, wherein the determination standard includes a reference value for at least one of raw data of the physical sensing data and processed data of the raw data.   The determination criterion is created by performing machine learning to determine the operating condition of the peripheral device from the learning physical sensing data generated under the condition indicated by the first virtual sensing data associated with the determination criterion. The data generation device according to claim 1, comprising a learned model.   The status item is a first item that handles information on the operating status of the illumination around the physical sensor that generates the physical sensing data, and a second item that handles the information on the operating status of the ventilation fan around the physical sensor The third item handling information on the operating condition of the refrigerator around the physical sensor, and the fourth item handling information on the operating condition of the microwave oven around the physical sensor, The data generation device according to any one of claims 1 to 3. The status item includes the first item,
The physical sensing data includes at least one of illuminance data and sound pressure data,
The determination unit applies the selected determination criterion to at least one of raw data of each of the illuminance data and the sound pressure data and processed data of the raw data, and the first item Make a decision,
The data generation device according to claim 4. The status item includes the second item,
The physical sensing data includes at least one of barometric pressure data and sound pressure data,
The determination unit applies the selected determination criterion to at least one of raw data of each of the barometric pressure data and the sound pressure data and processed data of the raw data, and the second item Make a decision,
The data generation device according to claim 4. The status item includes the third item,
The physical sensing data includes at least one of sound pressure data and temperature data,
The determination unit applies the selected determination criterion to at least one of raw data of each of the sound pressure data and the temperature data and processed data of the raw data, and the third item Make a decision,
The data generation device according to claim 4. The status item includes the fourth item,
The physical sensing data includes at least one of sound pressure data, temperature data, and humidity data,
The determination unit applies the selected determination criterion to at least one of raw data of each of the sound pressure data, the temperature data, and the humidity data, and processed data of the raw data; Make a decision on item 4
The data generation device according to claim 4. A data generation apparatus according to any one of claims 1 to 8.
A sensor device comprising the physical sensor. The computer is
Obtaining physical sensing data obtained by the physical sensor observing a sensing target;
Acquiring first virtual sensing data representing a determination result about a situation around the physical sensor;
Obtaining a plurality of determination criteria defined for the status item to be determined;
Selecting one determination criterion corresponding to the first virtual sensing data from the plurality of acquired determination criteria;
For each of the status items, the operation status of the peripheral device around the physical sensor is determined based on the acquired physical sensing data using the selected determination criteria, and the operation status of the peripheral device is determined. Generating second virtual sensing data representing a determination result. On the computer
Obtaining physical sensing data obtained by the physical sensor observing a sensing target;
Acquiring first virtual sensing data representing a determination result about a situation around the physical sensor;
Obtaining a plurality of determination criteria defined for the status item to be determined;
Selecting one determination criterion corresponding to the first virtual sensing data from the plurality of acquired determination criteria;
For each of the status items, the operation status of the peripheral device around the physical sensor is determined based on the acquired physical sensing data using the selected determination criteria, and the operation status of the peripheral device is determined. And generating second virtual sensing data representing a determination result.