JP6813456B2 - Judgment device, judgment method, and judgment program - Google Patents

Description

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

There are concerns about fraud such as spoofing applications and replacement ball exams using online services such as qualification tests conducted on the electronic administration and the Web. Authentication methods for preventing spoofing and replacement balls include memory authentication (for example, password authentication), property authentication (for example, IC card authentication), and physical feature authentication (for example, fingerprint and vein authentication). Etc. are known.

However, in these authentication methods, authentication is often performed only once at the start of using the service, and there is a possibility that an illegal operation may be performed by replacing the user with another person when the key is input after the authentication. As a countermeasure against such replacement with another person, authentication using the habit of the person such as the keystroke at the time of key input of the person to be authenticated (authentication by behavioral characteristics) has also been proposed (see Non-Patent Document 1). For example, in the above authentication using keystrokes, the subject and the key inputter to the data input device are the same by using features such as the pattern, speed, and rhythm when the subject strikes the key. It is also conceivable to judge the personality.

Japanese Unexamined Patent Publication No. 2013-025491 Japanese Unexamined Patent Publication No. 2010-177998

Toshiharu Samura et al., "Keystroke Dynamics Identification in Atypical Japanese Sentence Input", Journal of the Society of System Control and Information Technology, Vol.22, No.4, pp.145-153, 2009

However, for example, in the determination using the above keystrokes, if the feature amount of the key input (keystroke) changes, the determination accuracy may decrease. For example, if the feature amount of the user's key input (keystroke) changes due to a change in the user's key input proficiency level, mental state such as tension, injury to the arm or hand, use of an unfamiliar keyboard, etc., the judgment accuracy will be improved. May decrease.

Further, when the data input device is a tablet terminal, a smartphone, or the like, operations other than key input such as swiping and tapping on the touch screen are often performed. However, conventionally, for operations other than key input, a technique for determining whether or not the operator of the data input device is the same person as the regular user has not been studied.

Therefore, it is an object of the present invention to accurately determine whether or not the operator of the data input device is the same person as the regular user, even if the data input device accepts operations other than key input.

In order to solve the above-mentioned problems, the present invention comprises a sensor data acquisition unit that acquires sensor data indicating the movement of the wearer's hand or arm of the wearable device, and the wearable device based on the acquired center data at each time. Estimated by the estimation unit, an estimation unit that estimates an input event on the screen of the data input device by the wearer, an input event acquisition unit that acquires an input event by a touch operation on the screen of the data input device, and an estimation unit. A first time-series data showing the input event by the wearer of the wearable device in time series, and a second time-series showing the input event in the data input device acquired by the input event acquisition unit. When the time-series data is collated and the matching rate between the series of input events in the first time-series data and the series of input events in the second time-series data is equal to or more than a predetermined value, the data input device The operator is provided with a determination unit that determines that the wearer of the wearable device is the same person.

According to the present invention, even in a data input device that accepts operations other than key input, it is possible to accurately determine whether or not the operator of the data input device is the same person as a regular user.

FIG. 1 is a diagram for explaining an outline of the present embodiment. FIG. 2 is a diagram for explaining an outline of the same personness determination in the present embodiment. FIG. 3 is a diagram showing a configuration example of the determination system of the present embodiment. FIG. 4 is a diagram showing an example of the touch operation log of FIG. FIG. 5 is a diagram for explaining the types of touch operations. FIG. 6 is a diagram for explaining an input event estimation method in the present embodiment. FIG. 7 is a diagram for explaining collation of time-series data of each of the touch operation log and the sensor data in the present embodiment. FIG. 8 is a diagram for explaining collation of time-series data of each of the touch operation log and the sensor data in the present embodiment. FIG. 9 is a graph showing the acceleration data of the wearable device and the down touch operation of the data input device 20 at each time after the time synchronization. FIG. 10 is a sequence diagram showing an example of the processing procedure of the determination system. FIG. 11 is a diagram showing a computer that executes the determination program.

Hereinafter, embodiments (embodiments) for carrying out the present invention will be described with reference to the drawings. The present invention is not limited to the embodiments described below.

[Overview]
First, the outline of the embodiment of the present invention will be described with reference to FIG. In the determination system of the present embodiment, the user of the data input device 20 shall wear a wearable device 10 including a sensor such as an acceleration sensor. That is, the determination system includes a wearable device 10 worn by the user and a data input device 20 in which the user performs various operations.

The determination system acquires sensor data (for example, acceleration data) indicating the movement of the hand or arm of the wearable device 10 wearer (user) at each time. Further, the determination system acquires data input device data from the data input device 20. This data input device data is a touch operation on the screen of the data input device 20 such as the type of user's touch operation at each time (for example, tap, double tap, left swipe, right swipe, up scroll, down scroll, etc.). It is the data which shows the input event by.

Then, the determination system determines whether or not the operator of the data input device 20 and the wearer of the wearable device 10 are the same person by collating the data input device data and the sensor data at each time (same). Perform personality judgment).

For example, as shown in FIG. 2, the determination system has an input event (for example, scrolling up → tapping → tapping → tapping → tapping → tapping → tapping → tapping → tapping → tapping → Right swipe) to estimate. The determination system also estimates the input event (for example, up scroll → tap → right swipe) generated in the wearable device 10 at each time from the sensor data of the wearable device 10. Then, the determination system collates the input events estimated to have occurred in both devices at each time, and if both match, the operator of the data input device 20 is the same person as the wearer of the wearable device 10. Is determined.

That is, in the determination system, if the time-series input event on the screen of the data input device 20 and the time-series input event indicated by the sensor data of the wearable device 10 match (or the match rate is predetermined). (If it is equal to or more than the value), the operator of the data input device 20 determines that the person is the same as the wearer of the wearable device 10.

According to such a determination system, even if there is a discrepancy between the time stamp value given by the data input device 20 and the time stamp value given by the wearable device 10 at the same time, the data input device 20 can be used. Using the acquired data (data input device data) and the data (sensor data) acquired from the wearable device 10, it is determined whether or not the operator of the data input device 20 is the same person as the wearer of the wearable device 10. can do.

As an example, a touch operation log indicating a series of touch operations on the data input device 20 is recorded on the data input device 20, and the value of the time stamp (time information) is stamped on the data input device 20. On the other hand, the sensor data is measured by the wearable device 10 and transmitted to the data input device 20. The time stamp of the sensor data is not always stamped by the data input device 20, and even if it is stamped by the data input device 20, there is a time lag with the time stamp of the touch operation log. In addition, there is a possibility that the time stamp will not be stamped on any device due to the specifications and configuration of the device.

Here, according to the determination system described above, if the series of input events on the screen of the data input device 20 and the series of input events indicated by the sensor data of the wearable device 10 match, the data input device 20 Is determined to be the same person as the wearer of the wearable device 10. Therefore, even if the time stamps of both devices are different or the time stamps are not stamped, the determination system determines whether the operator of the data input device 20 and the wearer of the wearable device 10 are the same person. Can be determined.

Next, a configuration example of the determination system will be described. As shown in FIG. 3, for example, the determination system includes a wearable device 10 and a data input device 20. The number of each device is not limited to the number shown in FIG.

The wearable device 10 includes a sensor data acquisition unit 11. The sensor data acquisition unit 11 acquires sensor data (for example, acceleration data, angular velocity data, geomagnetic data, etc.) indicating the movement of the wearer's hand or arm of the wearable device 10 at each time, and sends it to the data input device 20. Send. The wearable device 10 is attached to, for example, the arm on the side of performing the tap operation of the data input device 20.

It should be noted that whether or not the wearable device 10 is worn by an authorized user shall be confirmed in terms of operation. Further, the wearable device 10 has a function of monitoring the attachment / detachment state of the wearable device 10, and it is possible to confirm that the same person continues to wear the wearable device 10 by the function.

The data input device 20 is a device that accepts touch operations on the screen. The data input device 20 is, for example, a personal computer, a tablet terminal, a smartphone, or the like. The data input device 20 includes a storage unit 21, an input event acquisition unit 22, an input event estimation unit 23, and a determination unit 24.

The storage unit 21 stores a log of touch operations (touch operation log) on the screen of the data input device 20. The touch operation log is, for example, information recorded in association with an event (event type) of a touch operation on the data input device 20, an event occurrence time (time stamp), coordinates in which the event occurred, and the like (). (See FIG. 4). As illustrated in FIG. 4, this touch operation log may include the value of the pressure on the screen at each touch operation. The events of this touch operation are, for example, the "down event (finger touches the screen)", "up event (finger moves away from the screen)", and "move event (finger touches the screen)" shown in FIG. Moved) ”etc. It is assumed that this touch operation log is recorded by a touch operation recording unit (not shown) or the like that records the touch operation of the data input device 20.

The input event acquisition unit 22 of FIG. 3 acquires an input event (for example, tap, double tap, left swipe, right swipe, up scroll, down scroll, etc.) by a touch operation on the screen of the data input device 20. Specifically, the input event acquisition unit 22 determines an input event based on the event type of each touch operation in the touch operation log, the coordinates at which the event occurred, the pressure at the coordinates, and the like.

For example, in the touch operation, the input event acquisition unit 22 has a time when the screen is touched (time from down to up) is equal to or less than the threshold value, and the coordinate movement distance while touching the screen is equal to or less than the threshold value. If so, the input event is determined to be a tap. Further, the input event acquisition unit 22 determines that the input event is a double tap when the tap satisfying the above conditions is observed twice within a predetermined time in the touch operation.

Further, in the touch operation, when the movement distance of the coordinates while touching the screen is equal to or more than the threshold value and the movement is from right to left, the input event is swiped left (finger to the left). It is judged to be traced / repelled). Further, in the touch operation, when the movement distance of the coordinates is equal to or more than the threshold value and the movement is from left to right while touching the screen, the input event acquisition unit 22 swipes right (traces the finger to the right /). Repel).

Further, in the touch operation, when the movement distance of the coordinates is equal to or greater than the threshold value and the movement is from downward to upward while touching the screen, the input event acquisition unit 22 scrolls upward (traces the finger upward /). Repel). Further, in the touch operation, when the movement distance of the coordinates is equal to or more than the threshold value and the movement is from upward to downward while touching the screen, the input event acquisition unit 22 scrolls downward (traces the finger downward /). Repel).

The input event estimation unit 23 estimates the input event on the screen of the data input device 20 by the wearable device 10 at each time based on the center data of each time received from the wearable device 10.

For example, when the sensor data is three-dimensional acceleration data, the input event estimation unit 23 determines that the Z-axis has an acceleration change larger than the threshold value during a very short time width based on the acceleration data. , The input event is presumed to be a tap. Further, the input event estimation unit 23 estimates that the input event is a double tap when the tap satisfying the above conditions is observed twice within a predetermined time based on the acceleration data.

Further, the input event estimation unit 23 estimates that the input event is a left swipe when there is a large acceleration change or a continuous acceleration change on the X-axis based on the acceleration data and the movement is from right to left. Further, the input event estimation unit 23 estimates that the input event is a right swipe when the X-axis has a large acceleration change or a continuous acceleration change and the movement is from left to right based on the acceleration data.

Further, the input event estimation unit 23 estimates that the input event scrolls up when there is a large acceleration change or a continuous acceleration change on the Y-axis based on the acceleration data and the movement is from downward to upward. Further, based on the sensor data, the input event estimation unit 23 estimates that the input event scrolls down when there is a large acceleration change or a continuous acceleration change on the Y-axis and the movement is from upward to downward.

Here, the input event estimation unit 23 may estimate the input event by, for example, classification by the feature amount of the sensor data for each type of the input event, pattern matching of the waveform of the sensor data, or the like.

For example, the input event estimation unit 23 prepares a waveform pattern of the sensor data of the input event for each type of input event. Then, as shown in FIG. 6, the input event estimation unit 23 slides a window having a predetermined time width with respect to the acquired sensor data of the wearable device 10 at each time, and waveforms the sensor data of each input event. Search for a section that matches the pattern of.

For example, the input event estimation unit 23 slides a window having a predetermined time width with respect to the sensor data of the wearable device 10 as shown in FIG. 6, and a section that matches the waveform pattern of the sensor data of each input event. To explore. For example, the input event estimation unit 23 searches for a section estimated to be a tap by sliding a window having a predetermined time width for (1) a waveform pattern of sensor data indicating a tap. Further, the input event estimation unit 23 also slides a window having a predetermined time width for the waveform pattern of the sensor data indicating (2) up scroll and (3) right swipe, and is estimated to be up scroll and right swipe. Search for a section.

By performing the above processing, the input event estimation unit 23 can estimate what kind of input event has occurred from the sensor data of the wearable device 10 at each time. As a result, for example, the input event estimation unit 23 can obtain an estimation result that an input event of scrolling up → tapping → swiping right has occurred on the wearable device 10 from the sensor data shown in FIG.

The input event estimation unit 23 defines an allowable range of the sensor data (for example, acceleration data) of the wearable device 10, such as the amplitude value and frequency of the data value, and the sensor data outside the allowable range. May be excluded. Further, the data input device 20 excludes sensor data other than the touch operation from the sensor data of the wearable device 10 by using the result of machine learning of the sensor data during the touch operation and the non-touch operation of the data input device 20. You may. By doing so, the input event estimation unit 23 can improve the accuracy of estimating the input event.

The determination unit 24 of FIG. 3 collates the time-series data of the input event on the screen of the data input device 20 with the time-series data of the input event estimated from the sensor data of the wearable device 10 to input data. It is determined whether or not the operator of the device 20 is the same person as the wearer of the wearable device 10.

Specifically, the determination unit 24 acquires the first time-series data which is the time-series data of the input event by the wearer of the wearable device 10 estimated by the input event estimation unit 23. Further, the determination unit 24 acquires the second time-series data which is the time-series data of the input event in the data input device 20 acquired by the input event acquisition unit 22.

Then, the determination unit 24 collates the first time series data with the second time series data, and determines the matching rate between the input event in the first time series data and the input event in the second time series data. If it is equal to or more than the value, it is determined that the operator of the data input device 20 is the same person as the wearer of the wearable device 10. On the other hand, when the matching rate is less than a predetermined value, the determination unit 24 determines that the operator of the data input device 20 is not the same person as the wearer of the wearable device 10.

For example, as shown in FIG. 7, the determination unit 24 swipes right → taps → scrolls up → left in the time series arrangement (second time series data) of the estimation results of the input events obtained from the touch operation log. The input events of swipe → tap → tap are grouped together, and the section in which the group appears from the time-series sequence of the estimation results of the input events by the wearer of the wearable device 10 (first time-series data). Explore.

Then, the determination unit 24 selects a section in which a group of right swipe → tap → up scroll → left swipe → tap → tap appears from the time series arrangement of the estimation result of the input event by the wearer of the wearable device 10. If found, the operator of the data input device 20 is determined to be the same person as the wearer of the wearable device 10. By doing so, the determination unit 24 collates the input events of both time series data and data even if there is a time lag between the first time series data and the second time series data. The operator of the input device 20 can determine whether or not he / she is the same person as the wearer of the wearable device 10.

It is also possible that the estimation accuracy of the input event in the first time series data is not very high. In such a case, the determination unit 24 associates the first time-series data with the second time-series data so that the matching rate of the input events in both time-series data is the highest, and then both. Time series data may be collated. That is, the determination unit 24 may collate both time series data after synchronizing the time between the first time series data and the second time series data. The match rate here is determined in consideration of, for example, the type of input event in the time series data, the arrangement of the input events, the time interval between the input events, and the like.

For example, as shown in FIG. 8, the time series arrangement (second time series data) of the estimation result of the input event obtained from the touch operation log is right swipe → tap → up scroll → left swipe → tap → It is a tap, and the time-series arrangement (first time-series data) of the estimation result of the input event of the sensor data is right swipe → right swipe → tap → tap → tap → tap → left swipe → tap → tap. Consider the case.

In this case, when there are two "right swipes" in the estimation result of the input event of the sensor data with respect to the estimation result "right swipe" of the input event in the touch operation log, the determination unit 24 determines both time series data. As a whole, the candidate with the highest matching rate between the estimation results of the input event is selected.

That is, as shown in FIG. 8, when the estimation result “right swipe” of the input event obtained from the touch operation log and the “right swipe” (candidate A) of the sensor data are combined so as to correspond to each other, both time series data The match rate between the estimation results of input events other than "right swipe" (candidate A) is low.

On the other hand, when the estimation results "right swipe" and "right swipe" (candidate B) of the input event obtained from the touch operation log are combined so as to correspond to each other, the two time series data are compared with the case of candidate A. The match rate between the estimation results of the input events other than candidate B is higher.

Therefore, the determination unit 24 has both time series so as to correspond the estimation result "right swipe" of the input event obtained from the touch operation log and the estimation result "right swipe" (candidate B) of the input event of the sensor data. After matching the data (that is, after synchronizing the time of both time series data), the two time series data are collated.

By synchronizing the time of both time series data as described above, the determination unit 24 allows the operator of the data input device 20 to perform the wearable device 10 even if the estimation accuracy of the input event indicated by the sensor data of the wearable device 10 is low. It is possible to accurately determine whether or not the person is the same person as the wearer of.

The determination unit 24 describes, for example, the acceleration data of the X-axis, the Y-axis, and the Z-axis at each time of the wearable device 10 and the data extracted only for the down touch operation at each time of the data input device 20. When the time is synchronized by the method of FIG. 9, the graph shown in FIG. 9 is obtained. As shown in FIG. 9, by synchronizing the time of both time series data by the above method, the timing at which the down touch operation is performed on the screen of the data input device 20 and the X-axis and Y of the wearable device 10 It can be seen that the timing at which the acceleration data of the axis and the Z axis fluctuate greatly can be substantially matched.

Next, an example of the processing procedure of the authentication process using the above-mentioned determination system will be described with reference to FIG. In the following description, the data input device 20 releases the operation lock when the PIN code is input to the data input device 20, and the operator of the data input device 20 and the wearer of the wearable device 10 are the same person. If it is determined that there is no such operation, the operation lock shall be performed again. In addition, the wearable device 10 is a function of confirming that the wearable device 10 is worn by a legitimate user by biometric authentication or the like, and confirming whether or not the wearable device 10 is continuously worn by the user (regular user) (same person wearing continuation confirmation function). Shall be provided.

Further, the data input device 20 shall be paired with the wearable device 10 after inputting the PIN code. The wearable device 10 to be paired here is a biometrically authenticated wearable device 10 within a range in which wireless communication with the data input device 20 is possible. Then, the data input device 20 acquires acceleration data as sensor data from the paired wearable device 10, and based on this acceleration data, the same person as the operator of the data input device 20 and the wearer of the wearable device 10. Gender determination processing shall be performed.

First, when it is detected that the wearable device 10 is worn by the user (S1) (S2: wearing state detection), the same person wearing continuation confirmation function for confirming whether or not the wearing is continued by the same person is turned on. (S3).

Then, after the operation lock state (S10), the data input device 20 accepts the PIN code input from the user (S11), releases the lock (S12) if the authentication is OK, and detects the wearable device 10 (S10). S13). That is, the data input device 20 detects the wearable device 10 within the range in which wireless communication is possible from the data input device 20. Then, when the data input device 20 requests the detected wearable device 10 for pairing (S14) and receives the pairing permission notification from the wearable device 10 (S15), the data input device 20 is the wearable. Pairing with the device 10 is performed (S16).

The wearable device 10 transmits, for example, a notification of pairing permission to the data input device 20 when it is confirmed that the same person is continuously worn after the biometric authentication of the user in the wearable device 10. Then, the data input device 20 registers the wearable device 10 that is the transmission source of the pairing permission notification as the pairing partner (the target of the identity determination based on the acceleration data).

After S16, the data input device 20 displays the pairing result on the screen and gives an instruction to start the touch operation (S17). The user who sees such a display starts a touch operation on the screen of the data input device 20 (S21), and the data input device 20 acquires the log of the user's touch operation and stores it in the storage unit 21. (S22: Touch operation log acquisition). In addition, the wearable device 10 acquires acceleration data indicating the movement of the user's hand or arm (S23). Further, the data input device 20 requests the wearable device 10 to transmit acceleration data (S24), and receives the time-stamped acceleration data from the wearable device 10 and the device signature of the wearable device 10 (S24). S25).

After S25, when the data input device 20 confirms the identity of the wearable device 10 by the device signature, the data input device 20 collates the acceleration data at each time received from the wearable device 10 with the touch operation log acquired in S22. , It is determined whether or not the operator (user) of the data input device 20 and the wearer of the wearable device 10 are the same person (S26: same person identity determination process). Here, when the data input device 20 determines that the operator of the data input device 20 and the wearer of the wearable device 10 are not the same person (No in S27), the operation of the data input device 20 is locked (S10). ). On the other hand, when the data input device 20 determines that the operator of the data input device 20 and the wearer of the wearable device 10 are the same person (Yes in S27), the operation lock is not performed and the operation is continued (S28).

By doing so, after the PIN code of the data input device 20 is authenticated, the determination system can accept operations from a legitimate user, but cannot accept (lock) operations from anyone other than the legitimate user.

In the pairing of S16 in FIG. 10, the data input device 20 may automatically detect the wearable device 10 from the radio wave intensity of BLE (Bluetooth Low Energy) or the like, or may be a candidate for the wearable device 10 in the vicinity. May be displayed on the screen and the user may select. In either case, even if the data input device 20 is accidentally paired with another wearable device 10, the operation cannot be continued unless the identity determination process to be performed later is successful (operation lock is performed). ). As a result, the determination system can prevent the data input device 20 from being illegally operated by a third party.

Further, in S26 of FIG. 10, the data input device 20 may perform the same personality determination process for each predetermined number of touch operations or operation times. In that case, if the determination result is continuously NG a predetermined number of times, the data input device 20 may determine that the operation is performed by another person and lock the operation.

[Other Embodiments]
The data input device 20 uses the above-mentioned first time-series data (arrangement of the estimation results of input events by the wearer of the wearable device 10 in time series) and second time-series data (obtained from the touch operation log). In order to synchronize the time of both time series data when collating with the time series of the estimation result of the input event), the calibration may be performed at the time of data acquisition.

Specifically, the data input device 20 further includes a calibration unit 25 shown in FIG. The calibration unit 25 displays on the screen of the data input device 20 or the like to urge the user to perform a predetermined touch operation for calibration. The above-mentioned predetermined touch operation is preferably a characteristic touch operation so that calibration can be easily performed. Then, when the input event indicating the predetermined touch operation appears in the first time series data and the second time series data, the determination unit 24 assumes that the time when the input event occurs is the same time. , The time synchronization of the first time series data and the second time series data.

In this way, in the data input device 20, by synchronizing the time of the first time series data and the second time series data, the same person identity determination process based on the first time series data and the second time series data is performed. Can be performed accurately.

Further, in the above-described embodiment, the data input device 20 performs the above-mentioned identity determination process and the estimation of the input event indicated by the sensor data of the wearable device 10, but a device other than the data input device 20 ( For example, a determination device or a determination server) may perform the operation.

[program]
Further, it can be implemented by installing a program that realizes the function of the data input device 20 described in the above embodiment on a desired information processing device (computer). For example, the information processing device can function as the data input device 20 by causing the information processing device to execute the above program provided as package software or online software. The information processing device referred to here includes a desktop type or notebook type personal computer. In addition, the information processing device includes smartphones, mobile phones, mobile communication terminals such as PHS (Personal Handyphone System), and PDA (Personal Digital Assistant). Further, the data input device 20 may be mounted on the cloud server.

An example of a computer that executes the above program (determination program) will be described with reference to FIG. As shown in FIG. 11, the computer 1000 has, for example, a memory 1010, a CPU 1020, 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. Each of these parts is connected by a bus 1080.

The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM (Random Access Memory) 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. The disk drive interface 1040 is connected to the disk drive 1100. A removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100. For example, a mouse 1110 and a keyboard 1120 are connected to the serial port interface 1050. A display 1130 is connected to the video adapter 1060, for example.

Here, as shown in FIG. 11, the hard disk drive 1090 stores, for example, the OS 1091, the application program 1092, the program module 1093, and the program data 1094. Various data and information described in each of the above-described embodiments are stored in, for example, a hard disk drive 1090 or a memory 1010.

Then, the CPU 1020 reads the program module 1093 and the program data 1094 stored in the hard disk drive 1090 into the RAM 1012 as needed, and executes each of the above-described procedures.

The program module 1093 and program data 1094 related to the above determination program are not limited to the case where they are stored in the hard disk drive 1090, for example, are stored in a removable storage medium and are stored by the CPU 1020 via the disk drive 1100 or the like. It may be read out. Alternatively, the program module 1093 and the program data 1094 related to the above program are stored in another computer connected via a network such as LAN (Local Area Network) or WAN (Wide Area Network), and are stored via the network interface 1070. It may be read by the CPU 1020.

10 Wearable device 11 Sensor data acquisition unit 20 Data input device 21 Storage unit 22 Input event acquisition unit 23 Input event estimation unit 24 Judgment unit 25 Calibration unit

Claims (6)

A sensor data acquisition unit that acquires sensor data indicating the movement of the wearable device's hand or arm, and a sensor data acquisition unit.
An estimation unit that estimates an input event is the type of touch operation on the screen of the data input device according to the wearer of the wearable device based on the sensor data at each time and the acquired,
An input event acquisition unit that acquires an input event by touch operation on the screen of the data input device,
A series of the in the data input device and the first time series data, acquired by the input event acquiring section showing a series of said input event by the wearer of the wearable device estimated by the estimation unit in chronological collating the second time series data shown in chronological input events, the rate of matching with the sequence of the input event in a series of the input event and the second time series data in the first time series data A determination device including a determination unit that determines that the operator of the data input device is the same person as the wearer of the wearable device when is equal to or greater than a predetermined value. The determination unit
When collating the first time series data with the second time series data, the matching rate between the series of input events in the first time series data and the series of input events in the second time series data. The determination device according to claim 1, wherein the time-synchronization of the first time-series data and the second time-series data is performed so that the value is the highest. The determination device
The data input device is further provided with a calibration unit that prompts the user to perform a predetermined touch operation for calibration.
The determination unit
When an input event indicating a predetermined touch operation for the calibration appears in the first time series data and the second time series data, it is assumed that the time when the input event occurs is the same time. , The first time-series data and the second time-series data are time-synchronized, and then the first time-series data and the second time-series data are collated. Item 1. The determination device according to item 1. The estimation unit
The time from the occurrence of the down event that the finger touches on the screen of the data input device to the occurrence of the up event that the finger separates from the screen, and the move that the finger touches and moves on the screen. The input event is estimated using the distance traveled in the event.
The determination unit
At the timing when the down event occurs in the wearable device and the data input device, the time synchronization between the first time series data and the second time series data is performed, and the first time series data and the first time series data are synchronized. Collate with 2 time series data
The determination device according to claim 1, wherein the determination device is characterized by the above. Judgment device
Steps to acquire sensor data indicating the movement of the wearable device wearer's hand or arm, and
Estimating an input event on the screen of the data input device according to the wearer of the wearable device based on the sensor data at each time and the acquired,
A step of acquiring an input event, which is a type of touch operation on the screen of the data input device, and
A first time series data shown in a time series sequence of the input events by the wearer of the estimated the wearable device, showing a series of the input events in the acquired the data input device in time series second time collates the series data, when the rate of matching with the sequence of the input event in a series of the input event and the second time series data in the first time series data is a predetermined value or more, A determination method comprising the step of determining that the operator of the data input device is the same person as the wearer of the wearable device. Steps to acquire sensor data indicating the movement of the wearable device wearer's hand or arm, and
Estimating an input event on the screen of the data input device according to the wearer of the wearable device based on the sensor data at each time and the acquired,
A step of acquiring an input event, which is a type of touch operation on the screen of the data input device, and
A first time series data shown in a time series sequence of the input events by the wearer of the estimated the wearable device, showing a series of the input events in the acquired the data input device in time series second time collates the series data, when the rate of matching with the sequence of the input event in a series of the input event and the second time series data in the first time series data is a predetermined value or more, A determination program characterized in that an operator of the data input device causes a computer to perform a step of determining that the operator is the same person as the wearer of the wearable device.

Images