JP2019041811A - Determination device, determination method, and determination program - Google Patents

Abstract

To realize efficient determination of identity of sensor information acquired from a plurality of terminals and a reduction of an information holding amount.SOLUTION: A determination device 20 includes: a motion determination part 252 for acquiring time-series sensor information at a plurality of terminals, and determining motion of an owner having the plurality of terminals based on the acquired sensor information; a storage determination part 253 for storing the acquired sensor information when the motion of the owner is the motion of a preset information storage object, and discarding the acquired sensor information when the motion of the owner is not the motion of the information storage object; and a same person determination part 254 for determining whether or not the plurality of terminals are owned by the same person based on the stored sensor information, and, when the plurality of terminals are determined to be owned by the same person, storing work trail information of the owner owning the plurality of terminals in a storage part.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a determination apparatus, a determination method, and a determination program.

  In recent years, the majority of consumers have come to possess a smartphone. In addition, with the spread of IoT (Internet of Things) devices as represented by wristband-type wearable devices, there are an increasing number of cases where a single person possesses a plurality of devices. Along with this, in order to improve the convenience of the user, a technology is proposed that authenticates the user based on the presence of a specific wearable device in the vicinity of the smartphone (in the communication range of Bluetooth (registered trademark)). It is done.

  For example, if the registered smartphone is in the vicinity of the wearable device, the technology for performing authentication (for example, refer to Non-Patent Document 1) or the technology for performing authentication when wearing the wearable device and detecting the detachment of the wearable device (For example, refer to nonpatent literature 2) and the technology (for example, refer to nonpatent literature 3) which authenticates using an electrocardiogram at the time of wearing of a wearable device is proposed.

Everykey, [online], [August 18, 2017 search], Internet <URL: https://everykey.com/> Hideez Key, [online], [August 18, 2017 search], Internet <URL: http://hideez.com/> nymi, [online], [August 18, 2017 search], Internet <URL: https://nymi.com/>

  Thus, conventionally, there has been proposed a technology for performing access control of a terminal existing in a range where proximity communication is possible, using biological information continuously measured by possession of a specific terminal or attachment of a device as a base of trust There is. However, in contrast to these conventional techniques, there is a problem in that products that authenticate within the communication range of Bluetooth allow other users in a short distance to use their own smartphones. Moreover, although the above-mentioned subject is solvable by incorporating the detection mechanism of biometrics or attachment or detachment in a wearable device, a special sensor is required and it is difficult to introduce in the conventional commercial product.

  Therefore, in recent years, a technology for ensuring that the same human being is in possession of a device is considered using the sensors of the smartphone and the wearable device. Specifically, in this assurance technology, when the match of the sensor information of a plurality of terminals is determined and the match is determined, the worker wearing the wearable device does not spoof or replace balls and perform specific work. Generate work trail information that guarantees that you are engaged.

  Here, since it is necessary to save work trail information for guaranteeing, it is essential to store sensor information which is the original data of work trail determination. However, in the prior art, in order to generate a work trail using sensor information constantly generated, a vast amount of storage is required, and it is assumed that it becomes a major issue for practical use.

  With regard to this problem, for example, in the field of surveillance cameras, there has been proposed a technique for controlling the photographing timing by performing moving object detection in order to reduce the storage amount of image data of the surveillance cameras. However, although this moving body detection technology is useful for sensors such as cameras that capture a fixed point or a fixed range, it is applied to sensors of wearable terminals that are possessed and worn by people and sensor information constantly changes. It is difficult to do.

  Further, in the prior art, the same person determination is performed for all sensor information acquired from a smartphone or a wearable device, which is not efficient, and the calculation cost required for the determination process is also large.

  The present invention has been made in view of the above, and provides a determination apparatus, determination method, and determination that realize reduction of information holding amount and efficient determination of the identity of sensor information acquired from a plurality of terminals. The purpose is to provide a program.

  In order to solve the problems described above and achieve the object, the determination apparatus according to the present invention ensures that an owner possessing a plurality of terminals each provided with a sensor is engaged in a specific task A storage unit that stores information; an operation determination unit that acquires time-series sensor information of a plurality of terminals; and determines an operation of an owner who possesses the plurality of terminals based on the acquired sensor information; Save determination to save the acquired sensor information if the operation is a preset information save target operation, and discard the acquired sensor information if the owner's action is not the information save target operation It is determined whether or not a plurality of terminals are possessed by the same person based on the unit and the stored sensor information, and if it is determined that the plurality of terminals are possessed by the same person, the plurality Owner who owns the terminal of The same person determination section for storing working trail information in the storage unit, and having a.

  According to the present invention, reduction of the amount of information holding and efficient determination of the identity of sensor information acquired from a plurality of terminals are realized.

FIG. 1 is a diagram showing a schematic configuration of a determination system according to the embodiment. FIG. 2 is a view showing an example of the data configuration of the storage target operation information shown in FIG. FIG. 3 is a diagram showing an example of sensor information acquired from the terminal shown in FIG. FIG. 4 is a flowchart showing the procedure of the determination process performed by the determination apparatus shown in FIG. FIG. 5 is a diagram for explaining the determination processing by the conventional determination device. FIG. 6 is a diagram for explaining the determination process by the determination apparatus shown in FIG. FIG. 7 is a diagram illustrating an example of a computer in which the determination device is realized by execution of a program.

  Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. The present invention is not limited by the embodiment. Further, in the description of the drawings, the same portions are denoted by the same reference numerals.

Embodiment
First, with regard to the determination apparatus according to the embodiment, a schematic configuration of a determination system having the determination apparatus, a schematic configuration of the determination apparatus, and a flow of processing in the determination apparatus will be described.

[Configuration of judgment system]
First, the determination system in the present embodiment will be described with reference to FIG. FIG. 1 is a diagram showing a schematic configuration of a determination system according to the embodiment. As exemplified in FIG. 1, the determination system 1 in the present embodiment has a plurality of terminals 10 and a determination device 20.

  The terminal 10 is a smartphone, a wearable terminal, or the like. The terminal 10 includes, for example, a close proximity communication function such as a Bluetooth function. For example, of the terminals 10, the terminal 10A is a wristband type wearable terminal, and the terminal 10B is a smartphone.

  The determination apparatus 20 determines the terminals 10 (for example, the terminals 10A and 10B) possessed by the same person among the plurality of terminals 10 by a determination process described later. Terminals determined to be possessed by the same person by the determination apparatus 20 (for example, the terminals 10A and 10B) are connected by the Bluetooth function or the like, and the terminals 10A and 10B are unlocked and made usable Perform authentication mutually.

  The determination device 20 holds only the sensor information corresponding to a certain operation, and performs the sameness determination as to whether or not the same person holds only the held sensor information. In other words, the determination device 20 realizes reduction of the information holding amount and efficiency improvement of the identity determination by discarding sensor information other than the sensor information corresponding to a certain operation.

[Terminal configuration]
First, the configuration of the terminal 10 will be described. As illustrated in FIG. 1, the terminal 10 includes an input / output unit 11, a proximity communication unit 12, a communication unit 13, a storage unit 14, a control unit 15, and a sensor 16 unit.

  The input / output unit 11 is realized by a touch panel or the like, and inputs various instruction information to the control unit 15 in response to the input operation by the operator, or the result of the authentication process described later, etc. Output.

  The close proximity communication unit 12 connects the terminals 10 within the communication range of close proximity communication such as Bluetooth, for example, to be able to mutually communicate information by the close proximity communication.

  The communication unit 13 is realized by an NIC (Network Interface Card) or the like, and communicates between the control unit 15 and an external device such as the determination apparatus 20 via a telecommunication line such as a LAN (Local Area Network) or the Internet. Run.

  The storage unit 14 is realized by a storage device such as a semiconductor memory element such as a random access memory (RAM) or a flash memory. For example, the storage unit 14 stores information of other terminals capable of proximity communication such as Bluetooth.

  The close proximity communication unit 12 connects the terminals 10 within the communication range of close proximity communication such as Bluetooth, for example, to be able to mutually communicate information by the close proximity communication.

  The control unit 15 has a program defining various processing procedures and the like, and an internal memory for storing required data, and executes various processing by these. For example, the control unit 15 is an electronic circuit such as a central processing unit (CPU) or a micro processing unit (MPU). The control unit 15 transmits sensor information by the sensor unit 16 (described later) of the own device to the determination device 20 via the communication unit 13, and requests the same user determination of the own device and the other terminal 10. Terminals determined to be possessed by the same person by the determination apparatus 20 are connected by the function of the proximity communication unit 12 and authentication of the other terminal 10 (for example, authentication by pattern lock or PIN code) is performed. Without this, the other terminal 10 can be used conveniently.

  The sensor unit 16 is a sensor that acquires behavior information of the own device, surrounding sound information, a biological signal of the owner, and the like. For example, the sensor unit 16 is an acceleration sensor or an angular velocity sensor, and measures the acceleration or the angular velocity of the terminal 10. Of course, the sensor unit 16 may acquire the action information of the terminal 10 as well as the acceleration or the angular velocity. Also, the sensor unit 16 may be a microphone or the like that collects surrounding sound information. Further, the sensor unit 16 may be a biological sensor that acquires biological signals such as an electrocardiogram, a heart rate, and an electromyography. In addition, the sensor unit 16 may be a touch sensor, a geomagnetic sensor, or the like. Of course, the sensor unit 16 may have a plurality of types of sensors. The sensor information by the sensor unit 16 is transmitted to the determination device 20 through the communication unit 13 under the control of the control unit 15 together with the owner identification information (for example, owner ID (IDentifier)).

[Configuration of judgment device]
Next, the configuration of the determination device 20 will be described. The determination device 20 is realized by a general-purpose computer such as a workstation or a personal computer. As shown in FIG. 1, the determination device 20 includes an input unit 21, an output unit 22, a communication unit 23, a storage unit 24, and a control unit 25.

  The input unit 21 is an input interface that receives various operations from the operator of the determination device 20. For example, the input unit 21 is configured of an input device such as a touch panel, a voice input device, a keyboard, or a mouse.

  The output unit 22 is realized by a display device such as a liquid crystal display, a printing device such as a printer, an information communication device, and the like. The output unit 22 outputs an authentication result and the like described later to the operator.

  The communication unit 23 is a communication interface that transmits and receives various information to and from another device connected via a network or the like. The communication unit 13 is realized by an NIC or the like, and performs communication between another device (for example, the terminal 10) and the control unit 25 via a telecommunication line such as a LAN or the Internet.

  The storage unit 24 is realized by a storage device such as a RAM, a semiconductor memory device such as a flash memory, or a hard disk or an optical disk, and a processing program for operating the determination device 20, data used during execution of the processing program, etc. It is memorized. In addition, the storage unit 24 may be configured to communicate with the control unit 25 via the communication unit 23. The storage unit 24 stores an authentication database (DB) 241, a template DB 242, storage target operation information 243, and work trail information 244.

  The authentication DB 241 holds authentication information required for authentication of the terminal 10. The authentication DB 241 stores, for example, the name of each terminal 10, the ID of each terminal 10, the ID of the registered owner, and the like.

  The template DB 242 stores an operation template and a mounting position template. The operation template is a template of time-series sensor information from the terminal 10 according to the operation of the owner who holds the terminal. The operation template is generated based on time-series sensor information in the terminal 10 obtained in advance for each operation of the owner who holds the terminal 10. Specifically, time-series sensor information in the terminal 10 is acquired in advance for each operation of the owner of the terminal 10. The operation template is a template indicating predetermined feature quantities generated from the sensor information, and is set according to each operation. Alternatively, the operation position template may be generated using time-series sensor information at each mounting position of each terminal 10 calculated using simulation or the like.

  The mounting position template is a mounting position template of time-series sensor information from the terminal 10 according to the mounting position. The mounting position template is generated based on time-series sensor information in the terminal 10 obtained in advance for each mounting position of the terminal 10. Specifically, time-series sensor information in the terminal 10 is acquired in advance for each mounting position for the owner of the terminal 10. The mounting position template is a template indicating a predetermined feature amount generated from the sensor information, and is set according to various mounting positions. Alternatively, the operation position template may be generated using time-series sensor information at each mounting position of each terminal 10 calculated using simulation or the like.

  The storage target operation information 243 is information indicating the operation of the owner who holds the terminal 10 that is the storage target of the sensor information. That is, sensor information corresponding to the operation indicated in the storage target operation information 243 is held in the determination device 20. The storage target operation information 243 is set in advance.

  FIG. 2 is a view showing an example of the data configuration of the storage target operation information 243 shown in FIG. As shown in FIG. 2, in the storage target operation information 243, the operation of the owner having the terminal 10 is associated with the necessity of storage.

  For example, the storage target operation information 243 illustrated in FIG. 2 indicates that the storage is “unnecessary” when the operation is “terminal rest”. When the terminal 10 is kept stationary, there may be no case where sensor information such as characteristic acceleration that is effective for the same person determination whether the terminal 10 and the other terminal 10 are owned by the same person is generated There are many. For this reason, when the terminal 10 is left standing, it becomes difficult to determine the same person, so the sensor information corresponding to this operation becomes unnecessary. In addition, when the operation is "I / O work to terminal", it is indicated that the storage is "necessary". This is because when the input / output operation is performed on the terminal 10, there is a high possibility that sensor information such as an acceleration associated with the operation on the terminal 10 is generated, so that the same person determination can be performed.

  The work trail information 244 is information that guarantees that an owner possessing a plurality of terminals is engaged in a specific work. The work trail information 244 is a period in which the owner is engaged in the specific work, sensor information in this period, and information indicating whether or not the owner has removed the terminal. Further, each period in the work trail information 244 corresponds to the presence or absence of execution of trail confirmation by the determination device 20 and information indicating the work content distributed by the work manager and the work performed by the owner It may be attached.

  The control unit 25 has a program defining various processing procedures and the like, and an internal memory for storing required data, and executes various processing by these. For example, the control unit 25 is an electronic circuit such as a CPU or an MPU. The control unit 25 includes a signal processing unit 251, an operation determination unit 252, a storage determination unit 253, and the same person determination unit 254.

  The signal processing unit 251 acquires time-series sensor information in the plurality of terminals 10, and converts the time-series sensor information into a predetermined feature amount. For example, when the signal processing unit 251 acquires acceleration information from the terminal 10 as sensor information, the signal processing unit 251 generates feature amounts such as frequency components such as power spectrum of acceleration for each fixed time, peak value of signal, average value, or variance. Output to the operation determination unit 252. Of course, the signal processing unit 251 may directly input the acquired time-series signal without converting it into the feature amount.

  The operation determination unit 252 acquires time-series sensor information of the plurality of terminals 10, and determines the operation of the owner who owns the plurality of terminals 10 based on the acquired sensor information. That is, the operation determination unit 252 determines the operation of the owner who owns each terminal 10 based on the feature amounts of the plurality of terminals 10 output from the signal processing unit 251. For example, the operation determination unit 252 determines the operation of the owner who owns the plurality of terminals 10 based on the acquired sensor information using machine learning. In addition, the operation determination unit 252 determines the operation of the owner who holds the plurality of terminals 10 and the mounting positions of the plurality of terminals 10 based on the operation template and the mounting position template in the template DB 242 of the storage unit 24.

  The storage determination unit 253 determines storage or discarding of the acquired sensor information in the storage unit 24. Specifically, the storage determination unit 253 stores the acquired sensor information in the storage unit 24 when the operation of the owner is a target information storage operation set in advance. On the other hand, when the operation of the owner is not the operation of the information storage target, the storage determination unit 253 discards the acquired sensor information. The storage determination unit 253 refers to the storage target operation information 243 in the storage unit 24 to determine whether or not storage of the feature amount information is possible.

  The same person determination unit 254 determines the same person based on the sensor information stored by the storage determination unit 253 and determines whether or not the plurality of terminals 10 are owned by the same person. When the same person determination unit 254 determines that the plurality of terminals 10 are owned by the same person, the same person determination unit 254 stores, in the storage unit 24, work trail information of the owner who possesses the plurality of terminals. Then, the same person determination unit 254 transmits the determination results to the plurality of terminals 10 determined to be possessed by the same person, and connection by the proximity communication unit 12 between these terminals 10 and the terminals 10 are performed. And simple use permission of

[Process of operation determination unit]
Next, among the functional units of the determination apparatus 20, the process of the operation determination unit 252 will be described. The operation determination unit 252 determines the owner's operation using machine learning.

  For example, the operation determination unit 252 compares the operation template registered in advance with the feature amount output from the signal processing unit 251, and determines what operation the owner of the terminal 10 has performed. Specifically, the operation determination unit 252 classifies the feature amount information output from the signal processing unit 251 into an operation corresponding to any one of the operation templates of the template DB 242 using machine learning. The operation determination unit 252 compares the mounting position template with the feature amount output from the signal processing unit 251, and determines at which position the owner has mounted the terminal 10. Specifically, the operation determination unit 252 classifies the feature amount information output from the signal processing unit 251 into a mounting position corresponding to one of the mounting position templates of the template DB 242 using machine learning.

  For example, the operation determination unit 252 classifies the values of the feature amounts of the terminals 10A and 10B output from the signal processing unit 251 with a classifier, and the terminal 10A which is a wearable terminal is mounted on the left wrist and a terminal which is a smartphone Determine that 10B was held on the same left hand.

  Here, the motion determination unit 252 performs motion estimation using behavior information such as acceleration as sensor information. Also, the motion determination unit 252 uses machine learning to classify various feature values such as the power spectrum of acceleration, peak value, average, variance, and waveform shape extracted by the signal processing unit 251. You may A large number of motion classification methods may be considered, but the motion determination unit 252 may determine the motion using any method.

  In addition, the motion determination unit 252 may use not only behavior information such as acceleration but also surrounding sound information as sensor information. For example, the motion determination unit 252 may adopt a method of estimating the work content by collecting the sounds of the outside world while estimating the state other than the walking or stationary state using the acceleration (for details, see Akihiro Chiba) , Takashi Isesaki, Naoki Asano, Kazuhiro Yoshida, Tomoki Watanabe, Osamu Mizuno, "A Study on High Accuracy Estimation of Physical Activity Intensity from Heart Rate Information by Selecting Learning Data," Research Report Consumer Device & System (CDS), vol. 2016-CDS-16, no. 3, pp. 1-7, May 2016. and Kazunari Ouchi, “Pattern Measurement Technology in Wearable / Ubiquitous Environment”, Measurement and Control, vol. 53, no. 7, pp. 579-585, 2014.). Thus, when the terminal 10 has a microphone, the operation determination unit 252 may perform operation classification using sound information.

  In addition, the motion determination unit 252 may acquire not only activity information such as acceleration but also biological signals such as an electrocardiogram, a heart rate, and an electromyogram as sensor information, and may use them for classification. For example, it is possible to adopt a method of estimating physical activity intensity from heart rate information using linear regression analysis (for details, Jun Ohashi, Takashi Sudo, Kazunari Ouchi, Tatsunori Saito, "Useable Wearable Terminals / Smartphones" "Distributed processing method of life action recognition", Research report Ubiquitous computing system (UBI), vol. 2014-UBI-44, no. 10, pp. 1-8, October 2014.). When the terminal 10, which is a wearable terminal, includes a living body sensor, the movement determining unit 252 may perform the movement classification using a living body signal. Of course, the motion determination unit 252 may apply a learning device other than the reported learning method to the biological signal to perform motion classification.

[Processing of storage judgment unit]
Next, among the functional units of the determination device 20, the process of the storage determination unit 253 will be described. When the storage determination unit 253 determines that the operation of the owner is the operation of the information storage target based on the operation of the owner determined by the operation determination unit 252 and the mounting position of the terminal 10, the acquired sensor To save the information. On the other hand, if the storage determination unit 253 determines that the owner's operation is not the information storage target operation based on the owner's operation determined by the operation determination unit 252 and the terminal installation position, the acquired sensor Discard information. The storage determination unit 253 refers to the storage target operation information 243 in the storage unit 24 to determine whether or not storage of the feature amount information is possible.

  For example, the case where the operation determination unit 252 determines that the terminal 10B which is a smartphone is stationary will be described. In this case, the storage determination unit 253 determines that an effective acceleration is not generated for the same person determination, and discards the sensor information and the feature amount information of the period obtained this time. In addition, a case where the operation determination unit 252 generates an input work or the like to the terminal 10B which is a smartphone will be described. In this case, the storage determination unit 253 determines that the acceleration due to the operation of the smartphone is likely to be generated, and the same person determination is valid, and the same person determination unit 254 obtains the period obtained this time. Sending feature quantity information of

[Process of same person determination unit]
Next, among the functional units of the determination apparatus 20, the process of the same person determination unit 254 will be described.

  The same person determination unit 254 determines, using the time-series feature amount transmitted from the storage determination unit 253, whether or not the feature amount is due to a signal generated due to the operation of the same person. At that time, the same person determination unit 254 performs correction according to the mounting position of the terminal 10 estimated by the operation determination unit 252.

  Here, as a method applied to the same person determination processing, a correlation analysis with respect to time-series signals, a method of viewing statistical consistency such as DTW (Dynamic Time Warping), and a method using machine learning can be considered. The unit 254 may use any method. Furthermore, when the result of the same person determination is guaranteed by another authenticity assurance technology, the same person determination unit 254 updates the correction method and the determination threshold using the feature amount to improve the determination accuracy. May be

  FIG. 3 is a view showing an example of sensor information acquired from the terminals 10A and 10B shown in FIG. (A) of FIG. 3 shows a signal waveform Xa which is sensor information of the terminal 10A, and (b) of FIG. 3 shows a signal waveform Xb which is sensor information of the terminal 10B.

  The same person determination unit 254 appropriately divides each sensor signal of time series obtained as shown in FIG. 3 and averages the amplitude, standard deviation, variance, peak-to-peak distance of amplitude, feature conversion such as frequency conversion, or Feature quantification is performed on the waveform of the sensor signal using a method such as DTW or correlation coefficient. Then, the same person determining unit 254 sets a threshold value and compares the feature amounts of the signal waveforms Xa and Xb to determine whether the feature amounts of the signal waveforms Xa and Xb match. When the feature quantities of the signal waveforms Xa and Xb match, the identical person determination unit 254 determines that the two terminals 10A and 10B are owned by the same person. On the other hand, when the feature quantities of the signal waveforms Xa and Xb do not match, the same person determination unit 254 determines that the two terminals 10A and 10B are not possessed by the same person.

  Further, the same person determination unit 254 may perform the same person determination on the feature amount using a learning method such as supervised machine learning, unsupervised machine learning, reinforcement learning, and the like. Then, the same person determination unit 254 may determine by applying a technique such as deep learning to time series signals obtained from the respective sensor units 16 of the plurality of terminals 10 without performing feature amount extraction.

[Process procedure of judgment processing]
Next, the determination process of the determination device 20 will be described. FIG. 4 is a flowchart showing the procedure of the determination process performed by the determination apparatus 20 shown in FIG.

  First, in the determination device 20, the signal processing unit 251 acquires sensor information of a plurality of terminal 10 time series via the communication unit 13 (step S1), and converts the sensor information into a predetermined feature amount. A process is performed (step S2).

  Subsequently, the operation determination unit 252 refers to the operation template and the mounting position template of the template DB 242 (step S3). The operation determination unit 252 performs an operation determination process of determining the operation of the owner of the terminal 10 by comparing each feature amount of the plurality of terminals 10 output from the signal processing unit 251 with each template (step S4). ).

  The storage determination unit 253 refers to the storage target operation information 243 (step S5), and determines storage or discarding of the acquired sensor information according to the operation determination result by the operation determination unit 252. Specifically, the storage determination unit 253 determines whether the operation of the owner determined by the operation determination unit 252 is a preset storage target operation (step S6).

  If the storage determination unit 253 determines that the operation of the owner determined by the operation determination unit 252 is not a preset storage target operation (step S6: No), the sensor information used for this operation determination is discarded ((step S6: Step S7). Then, in the determination apparatus 20, the process returns to step S1, and newly performs a determination process on sensor information of a plurality of terminals 10.

  On the other hand, when the storage determination unit 253 determines that the operation of the owner determined by the operation determination unit 252 is a preset storage target operation (step S6: Yes), the sensor information used for this operation determination is Save (step S8). Then, the same person determination unit 254 performs the same person determination process of determining whether the plurality of terminals 10 are owned by the same person based on the sensor information stored by the storage determination unit 253 (step S9). .

  Then, in the determination apparatus 20, it is determined whether the determination processing result by the same person determination unit 254 is possessed by the same person (step S10). In the determination device 20, when the determination processing result is not possessed by the same person (step S10: No), the same person determination unit 254 does not generate a work trail based on this sensor information, and the determination device 20 proceeds to step S1. Returning to this, determination processing on sensor information of a plurality of terminals 10 is newly performed.

  On the other hand, in the determination apparatus 20, when the determination processing result is possessed by the same person (step S10: Yes), work trail information of the owner who possesses the plurality of terminals 10 is generated (step S11), Store in section 24.

[Effect of this embodiment]
As described above, the determination device 20 according to the present embodiment realizes reduction of the amount of information holding and efficiency improvement of the determination of identity by discarding sensor information other than sensor information corresponding to a certain operation. There is.

  Here, the determination processing by the conventional determination device will be described. FIG. 5 is a diagram for explaining the determination processing by the conventional determination device. As shown in FIG. 5, when the worker U possesses the terminal 10A as a smartphone and the terminal 10B as a wearable terminal, each sensor information is transmitted as a time-series signal from each of the terminals 10A and 10B. (See (1) in FIG. 5). When the conventional determination device 20P receives this sensor information, it accumulates all the sensor information (see (2) in FIG. 5), and the owner of each of the terminals 10A and 10B is the same person for all the sensor information (See (3) in FIG. 5).

  Therefore, in the conventional determination device 20P, all the sensor information which is the original data of the work trail determination is accumulated, and the same person determination is performed for all the sensor information. Therefore, in the conventional determination device 20P, there is a problem that a vast amount of storage is required in order to accumulate sensor information that is constantly generated. Further, in the conventional determination device 20P, since the same person determination is performed for all the sensor information, the calculation cost required for the determination process also becomes large.

  And the determination processing by the determination apparatus 20 which concerns on this Embodiment is demonstrated. FIG. 6 is a diagram for explaining the determination process by the determination device 20 shown in FIG. As shown in FIG. 6, in the present embodiment, it is assumed that each piece of sensor information is transmitted as a time-series signal from the terminal 10A and the terminal 10B possessed by the worker U (see (1) in FIG. 6). First, the operation determination unit 252 determines the operation of the terminals 10A and 10B (see (2) in FIG. 6). Subsequently, based on the determination result by the operation determination unit 252, the storage determination unit 253 automatically discriminates and discards unnecessary sensor information such as during non-operation (see (3) in FIG. 6).

  For example, the storage determination unit 253 determines that “9: 35-9: 37”, “10: 45-10: 55”, “11: 55-13: 05”, and 13: 37-13: 38 ”and discard the sensor information. Accordingly, as shown in the table Ti, the work trail information includes "9: 35-9: 37", "10: 45-10: 55", "11: 55-13: 05", and "13:37. The description between -13: 38 "is omitted. Therefore, in the determination apparatus 20, it is possible to reduce the information holding amount and the calculation cost required for the later stage identity determination.

  Then, the same person determination unit 254 determines whether the owner is the same person only for the stored sensor information, not all the sensor information (see FIG. 6 (4)). Therefore, the determination device 20 can reduce the number of identical person determination processes compared to the case of all the sensor information, and can reduce the calculation cost by the determination process. In addition, the determination device 20 appropriately generates work trail information (for example, the table Ti) which guarantees that the worker U is engaged in the specific work without actually spoofing or replacement balls as in the table Ti. can do.

  Therefore, in the determination apparatus 20, according to the operation determination result, the sensor information is discarded for a period in which the owner's work does not occur, and the sensor information acquired from the plurality of terminals is omitted by omitting the execution of the same person determination process. Reduce the amount of As a result, according to this embodiment, it is not necessary to use a vast amount of storage for holding sensor information.

  In addition, in the determination apparatus 20, the sensor information is stored for a period in which the owner's work occurs, and the same person determination process is executed to reduce the number of identical person determination processes compared to the case of all sensor information. The same person determination can be performed efficiently.

[System configuration etc.]
The components of the illustrated devices are functionally conceptual and do not necessarily have to be physically configured as illustrated. That is, the specific form of the dispersion and integration of each device is not limited to that shown in the drawings, and all or a part thereof is functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured. Furthermore, all or any part of each processing function performed by each device may be realized by a CPU and a program analyzed and executed by the CPU, or may be realized as wired logic hardware.

  Further, among the processes described in the present embodiment, all or part of the process described as being automatically performed may be manually performed, or the process described as being manually performed. All or part of them can be automatically performed by a known method. In addition to the above, the processing procedures, control procedures, specific names, and information including various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified.

[program]
FIG. 7 is a diagram illustrating an example of a computer in which the determination device 20 is realized by executing a program. The computer 1000 includes, for example, a memory 1010 and a CPU 1020. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These units are connected by a bus 1080.

  The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1090. Disk drive interface 1040 is connected to disk drive 1100. For example, a removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120. The video adapter 1060 is connected to, for example, the display 1130.

  The hard disk drive 1090 stores, for example, an OS (Operating System) 1091, an application program 1092, a program module 1093, and program data 1094. That is, a program defining each process of the determination device 20 is implemented as a program module 1093 in which a computer-executable code is described. The program module 1093 is stored, for example, in the hard disk drive 1090. For example, a program module 1093 for executing the same process as the functional configuration of the determination device 20 is stored in the hard disk drive 1090. The hard disk drive 1090 may be replaced by a solid state drive (SSD).

  The setting data used in the process of the above-described embodiment is stored as program data 1094 in, for example, the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads out the program module 1093 and the program data 1094 stored in the memory 1010 and the hard disk drive 1090 to the RAM 1012 as needed, and executes them.

  The program module 1093 and the program data 1094 are not limited to being stored in the hard disk drive 1090, and may be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and the program data 1094 may be stored in another computer connected via a network (LAN, WAN (Wide Area Network), etc.). The program module 1093 and the program data 1094 may be read by the CPU 1020 from another computer via the network interface 1070.

  Although the embodiment to which the invention made by the inventor is applied has been described above, the present invention is not limited by the description and the drawings that form a part of the disclosure of the present invention according to the present embodiment. That is, other embodiments, examples, operation techniques and the like made by those skilled in the art based on the present embodiment are all included in the scope of the present invention.

DESCRIPTION OF SYMBOLS 1 Judgment system 10, 10A, 10B Terminal 11 I / O unit 12 Proximity communication unit 13, 23 Communication unit 14, 24 Memory unit 15, 25 Control unit 16 Sensor unit 20, 20P Judgment device 21 Input unit 22 Output unit 241 Authentication database ( DB)
242 Template DB
243 operation target information for storing 244 operation trail information 251 signal processing unit 252 operation determining unit 253 storage determining unit 254 same person determining unit

Claims (5)

A storage unit that stores work trail information that guarantees that an owner possessing a plurality of terminals each provided with a sensor is engaged in a specific task;
An operation determination unit that acquires time-series sensor information in the plurality of terminals and determines an operation of an owner who holds the plurality of terminals based on the acquired sensor information;
The acquired sensor information is stored in the storage unit when the operation of the owner is an operation of an information storage target set in advance, and the operation of the owner is not the operation of an information storage target. A storage determination unit that discards the acquired sensor information;
It is determined based on the stored sensor information whether or not the plurality of terminals are possessed by the same person, and when it is determined that the plurality of terminals are possessed by the same person, the plurality The same person determination unit which stores in the storage unit work trail information of an owner who holds the terminal of
The determination apparatus characterized by having.   The determination apparatus according to claim 1, wherein the operation determination unit determines an operation of an owner possessing the plurality of terminals based on the acquired sensor information using machine learning. The storage unit is an operation template of time-series sensor information from the terminal according to an operation of an owner possessing the terminal, and a mounting position of time-series sensor information from the terminal according to the mounting position of the terminal Memorize template attachment position template,
The operation determination unit determines, based on the operation template and the mounting position template, an operation of an owner who holds the plurality of terminals and each mounting position of the plurality of terminals.
The storage determining unit is acquired when it is determined that the owner's operation is an information storage target operation based on the owner's operation determined by the operation determining unit and the mounting position of the terminal. The determination apparatus according to claim 1, wherein the sensor information is stored, and the acquired sensor information is discarded when it is determined that the operation of the owner is not the operation of the information storage target. A determination method executed by the determination device,
The determination apparatus includes a storage unit that stores work trail information that guarantees that an owner possessing a plurality of terminals provided with a sensor is engaged in a specific task, respectively.
Acquiring time-series sensor information in the plurality of terminals, and determining an operation of an owner possessing the plurality of terminals based on the acquired sensor information;
The acquired sensor information is stored when the operation of the owner is an operation for storing information set in advance, and the acquired sensor is stored when the operation of the owner is not an operation for storing information. Discarding the information;
It is determined whether or not the plurality of terminals are possessed by the same person, and when it is determined that the plurality of terminals are possessed by the same person, based on the stored sensor information, Storing work trail information of an owner possessing a plurality of terminals in the storage unit;
A determination method comprising:   The determination program for functioning a computer as a determination apparatus as described in any one of Claims 1-3.

Images