WO2018116434A1 - Estimation device, estimation method, program, and non-transitory computer-readable information recording medium - Google Patents

Estimation device, estimation method, program, and non-transitory computer-readable information recording medium Download PDF

Info

Publication number
WO2018116434A1
WO2018116434A1 PCT/JP2016/088306 JP2016088306W WO2018116434A1 WO 2018116434 A1 WO2018116434 A1 WO 2018116434A1 JP 2016088306 W JP2016088306 W JP 2016088306W WO 2018116434 A1 WO2018116434 A1 WO 2018116434A1
Authority
WO
WIPO (PCT)
Prior art keywords
time
predetermined operation
terminal
estimation
unit
Prior art date
Application number
PCT/JP2016/088306
Other languages
French (fr)
Japanese (ja)
Inventor
睦美 福田
Original Assignee
楽天株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 楽天株式会社 filed Critical 楽天株式会社
Priority to PCT/JP2016/088306 priority Critical patent/WO2018116434A1/en
Priority to JP2017516789A priority patent/JP6139814B1/en
Publication of WO2018116434A1 publication Critical patent/WO2018116434A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units

Definitions

  • the present invention relates to an estimation device, an estimation method, a program, and a non-transitory computer-readable information recording medium, and particularly relates to estimation of an event experience state.
  • Patent Document 1 discloses a technology for confirming that a broadcast advertisement is viewed regardless of whether the broadcast advertisement is viewed in real time, recorded or viewed on demand. ing.
  • the broadcast seconds from the start to the end of the advertisement are embedded in the broadcast advertisement in advance, and the number of seconds that the broadcast advertisement is played is measured at the user terminal that has played the broadcast advertisement. It is determined whether or not the advertisement has been viewed by comparing the broadcast seconds and the reproduced seconds.
  • the present invention solves the above-described problems, and is an estimation device, an estimation method, a program, and a non-optimum suitable for estimating whether or not the user has experienced a predetermined event from a user's operation. It is an object to provide a temporary computer-readable information recording medium.
  • An estimation apparatus is: A reception unit that receives the time at which the user performs a predetermined operation on the terminal used by each of the plurality of users from each of the terminals; An acquisition unit for acquiring a first time distribution of the predetermined operation from the received time; A calculating unit that calculates the degree of coincidence between the acquired first time distribution and the time received from each terminal; An estimation unit that estimates whether each of the plurality of users has experienced a predetermined event associated with the predetermined operation based on the degree of coincidence; It is characterized by providing.
  • the predetermined event occurs a plurality of times
  • the reception unit receives time of the predetermined operation performed by each of the plurality of users from each terminal,
  • the acquisition unit acquires a second time distribution of the predetermined operation performed by the user for each of the plurality of users.
  • the calculating unit calculates a similarity between the acquired first time distribution and the acquired second time distribution;
  • the estimation unit estimates, based on the similarity, whether or not the user who has acquired the second time distribution related to the similarity has experienced the experience target in which the predetermined event occurs.
  • An allocation unit that randomly allocates each terminal with a margin time from the time when the predetermined operation is performed until the terminal reports the fact that the predetermined operation has been performed to the estimation device;
  • the reception unit receives a report that the predetermined operation reported after the allowance time has elapsed from each terminal,
  • the acquisition unit from the time when the report indicating that the predetermined operation has been received is received, a third time distribution of the report indicating that the predetermined operation has been performed, and the degree of concentration of access to the estimation device, Get the The allocating unit adjusts the margin time so as to reduce a difference between the first time distribution and the third time distribution while suppressing the access concentration to a threshold value or less.
  • the time when the predetermined operation received from each terminal is performed is the time measured by the clock of each terminal
  • the calculating unit obtains a difference between the time of the predetermined operation measured at each terminal and the time when a report indicating that the predetermined operation has been received is received.
  • the estimation method is: An estimation method executed by an estimation device, An accepting step for accepting, from each of the terminals, the time when the user performed a predetermined operation on the terminal used by each of the plurality of users by the estimation device; An obtaining step in which the estimation device obtains a first time distribution of the predetermined operation from the accepted time; A calculation step in which the estimation device calculates a degree of coincidence between the acquired first time distribution and the time received from each terminal; An estimation step in which the estimation device estimates whether each of the plurality of users has experienced a predetermined event previously associated with the predetermined operation based on the degree of coincidence; It is characterized by providing.
  • the program according to the third aspect of the present invention is: Computer A receiving unit that receives, from each terminal, a time at which the user performs a predetermined operation in a terminal used by each of a plurality of users; An acquisition unit for acquiring a first time distribution of the predetermined operation from the received time; A calculation unit that calculates the degree of coincidence between the acquired first time distribution and the time received from each terminal; An estimation unit that estimates whether each of the plurality of users has experienced a predetermined event previously associated with the predetermined operation based on the degree of coincidence, It is made to function as.
  • a non-transitory computer-readable information recording medium is provided.
  • Computer A receiving unit that receives, from each terminal, a time at which the user performs a predetermined operation in a terminal used by each of a plurality of users; An acquisition unit for acquiring a first time distribution of the predetermined operation from the received time; A calculation unit that calculates the degree of coincidence between the acquired first time distribution and the time received from each terminal; An estimation unit that estimates whether each of the plurality of users has experienced a predetermined event previously associated with the predetermined operation based on the degree of coincidence, A program characterized by functioning as a program is recorded.
  • the non-transitory computer-readable information recording medium can be distributed and sold independently of the computer.
  • the non-transitory information recording medium refers to a tangible information recording medium.
  • Non-temporary information recording media are, for example, compact disks, flexible disks, hard disks, magneto-optical disks, digital video disks, magnetic tapes, semiconductor memories, and the like.
  • the transitory information recording medium refers to the transmission medium (propagation signal) itself.
  • the temporary information recording medium is, for example, an electric signal, an optical signal, an electromagnetic wave, or the like.
  • the temporary storage area is an area for temporarily storing data and programs, and is, for example, a volatile memory such as a RAM (Random Access Memory).
  • an estimation device an estimation method, a program, and a non-transitory computer-readable information record suitable for estimating whether or not the user has experienced a predetermined event from the user's operation A medium can be provided.
  • FIG. It is a figure which shows the relationship between the estimation apparatus which concerns on embodiment of this invention, and a terminal. It is a figure which shows schematic structure of the typical information processing apparatus with which the estimation apparatus which concerns on embodiment of this invention is implement
  • FIG. It is a figure for demonstrating the operation history table. It is a figure which shows the example of 1st time distribution. It is a figure for demonstrating the operation history table. It is a figure for demonstrating the relationship between the 1st time distribution acquired about the some event, and the 2nd time distribution acquired about the user a-1. 6 is a flowchart for explaining an estimation process performed by the estimation apparatus according to the first embodiment.
  • FIG. 10 is a flowchart for explaining an estimation process performed by the estimation apparatus according to the second embodiment.
  • the estimation apparatus 100 according to the embodiment of the present invention is connected to the Internet 300 as shown in FIG.
  • a plurality of terminals 200 are connected to the Internet 300.
  • the estimation apparatus 100 receives from the terminal 200 a time when a predetermined operation is performed on the terminal 200 and a report that the predetermined operation has been performed, and estimates whether or not the user of the terminal 200 has experienced a predetermined event. It is a device to do.
  • the terminal 200 is a device that accepts various operations by the user. When the user performs a predetermined operation on the terminal 200, the terminal 200 notifies the estimation device 100 of the time when the predetermined operation is performed, or performs a predetermined operation. To notify you.
  • the terminal 200 is a device such as a digital broadcast receiving device or a smartphone, and the estimation device 100 will be described as a server that receives information from these devices.
  • the user is required to perform a predetermined operation while a baseball game is being relayed on television, and the estimation device 100 allows the user to play a game based on the predetermined operation by the user. It shall be estimated whether it was watching or not.
  • the present invention is not limited to the case where the user is experiencing an event or content through television or the Internet, but the user can directly experience sports games, plays, movies, etc. on the spot ( (Watching, watching theater, watching, etc.)
  • the information processing apparatus 600 includes a CPU (Central Processing Unit) 601, a ROM (Read Only Memory) 602, a RAM 603, a storage device 604, a NIC (Network Interface Card) 605, an image A processing unit 606, an audio processing unit 607, a display 608, a speaker 609, and a controller 610 are provided.
  • a CPU Central Processing Unit
  • ROM Read Only Memory
  • RAM Random Access Memory
  • NIC Network Interface Card
  • the CPU 601 controls the operation of the information processing apparatus 600 as a whole, is connected to each component, and exchanges control signals and data.
  • the ROM 602 records an operating system program and various data necessary for operation control of the entire information processing apparatus 600.
  • the RAM 603 is for temporarily storing data and programs, and holds programs and data read from the storage device 604 and other data necessary for communication.
  • the storage device 604 includes a hard disk, a flash memory, and the like, and stores data to be processed by the information processing device 600. Further, the storage device 604 may be configured to include a device that reads data from a non-transitory computer-readable information recording medium such as a CD (Compact Disc).
  • a CD Compact Disc
  • the NIC 605 is used to connect the information processing apparatus 600 to a computer communication network such as the Internet, and communicates with other information processing apparatuses and the like via the NIC 605.
  • the image processing unit 606 processes the data read from the storage device 604 or the like or the data taken by the camera by the image arithmetic processor included in the CPU 601 or the image processing unit 606, and stores it in the frame memory included in the image processing unit 606. Record.
  • the image information recorded in the frame memory is converted into a video signal at a predetermined synchronization timing and output to the display 608.
  • the audio processing unit 607 converts the data read from the storage device 604 or the like into an analog audio signal and outputs it from the speaker 609.
  • the controller 610 receives an instruction input from the user.
  • the estimation apparatus 100 realized in the information processing apparatus 600 will be described with reference to FIGS. 1 to 12.
  • a program that functions as the estimation apparatus 100 is executed, and the estimation apparatus 100 according to the embodiment is realized.
  • the estimation device 100 includes a reception unit 101, an acquisition unit 102, a calculation unit 103, and an estimation unit 104.
  • the CPU 601 and the NIC 605 cooperate to function as the reception unit 101, and the CPU 601 functions as the acquisition unit 102, the calculation unit 103, and the estimation unit 104.
  • the accepting unit 101 accepts from each terminal 200 the time when the user performed a predetermined operation on the terminal 200 used by each of the plurality of users.
  • the predetermined operation is an operation performed on the terminal 200 by a user using the terminal 200.
  • a user who is watching a baseball game on a television is required to perform a predetermined operation when a predetermined event occurs (such as a cue end of a game, a strikeout, a start, or a home team attack start).
  • the predetermined operation is performed by pressing a predetermined button on the remote controller of the digital broadcast receiving apparatus or accessing a designated page on the Internet.
  • a user is required to press a predetermined button on the remote control of the digital broadcast receiving device when a signal from the ball umpire is given to the end of the game in a baseball game where team P and team Q play.
  • a predetermined button on the remote controller at the timing when the game end is signaled by the ball umpire
  • the time when the predetermined button is pressed is transmitted from the digital broadcast receiving device to the estimation apparatus 100.
  • the accepting unit 101 accepts the time transmitted from the digital broadcast receiving device of the user a-1.
  • the digital broadcast receiving apparatus may transmit that a predetermined button has been pressed, and the reception unit 101 may determine that the time when the digital broadcast receiving apparatus has pressed is a predetermined operation.
  • the accepting unit 101 When the accepting unit 101 accepts the time from the user's terminal 200, for example, the accepting unit 101 registers the time in the operation history table 100a of FIG.
  • the operation history table 100a a user ID 100a1 for identifying a user who performed a predetermined operation at the received time and an operation time 100a2 indicating the time when the predetermined operation was performed are registered in association with each other.
  • the first line of the operation history table 100a in FIG. 4 indicates that the user a-1 whose user ID 100a1 is “a-1” has pressed a predetermined button on the remote control at “18:00:05”. Show.
  • the acquisition unit 102 acquires a first time distribution of a predetermined operation from the received time.
  • the first time distribution is a time distribution of a predetermined operation obtained from the entire time received by the receiving unit 101.
  • the acquisition unit 102 refers to the operation history table 100a in FIG. 4 and calculates the first time distribution of predetermined operations (FIG. 5) from the operation times of the users a-1 to a-na (na: any natural number). ) To get.
  • the horizontal axis indicates the time of a predetermined operation
  • the vertical axis indicates the number of times of the predetermined operation received from each terminal 200.
  • the calculating unit 103 calculates the degree of coincidence between the acquired first time distribution and the time received from each terminal 200.
  • the degree of coincidence is an index indicating in which position of the first time distribution the time received from the terminal used by each user is included.
  • the calculation unit 103 determines the operation time of the user to be estimated.
  • the degree of coincidence is calculated by determining to which position of the distribution belongs.
  • the estimation unit 104 estimates whether each of the plurality of users has experienced a predetermined event associated with a predetermined operation in advance based on the degree of coincidence.
  • the predetermined event is an event associated with a predetermined operation in advance, and is an event in which the predetermined operation is performed due to the event.
  • experience includes all experiences that the user can learn through the five senses, such as seeing, listening, touching, appreciating, and moving by themselves.
  • a predetermined button is pressed in response to a signal from the end of the game of the ball umpire.
  • the predetermined event is a signal to end the game of the ball umpire, Viewing is an experience.
  • a scene is a television program, if there is a phenomenon in which the server is accessed all at once, this “certain scene” becomes a predetermined event.
  • the degree of coincidence is represented by a value indicating how many times the standard deviation of the first time distribution. For example, when the operation time of a certain user falls within the range of ⁇ 2 ( ⁇ 2SD) of the standard deviation in the first time distribution, the estimation unit 104 determines that the certain user is associated with a predetermined operation in advance. It is estimated that the event was experienced.
  • the range of ⁇ 2 of the standard deviation is a range where about 95% of users who have performed a predetermined operation perform a predetermined operation at a time included in the range, assuming that the distribution follows a normal distribution.
  • a user performs a predetermined operation during a time period when many users have performed the predetermined operation, the user reacts to the same cause as the cause of the other user performing the predetermined operation. It can be considered that the operation was performed. Therefore, since the predetermined operation is an operation performed in response to the predetermined event, it is estimated that the user has experienced the predetermined event.
  • the estimation unit 104 estimates that the user a-1 has experienced a predetermined event.
  • the degree of coincidence is calculated as + 100SD, and is included in the range of ⁇ 2 of the standard deviation of the time distribution of FIG. I can't. Therefore, the estimation unit 104 estimates that the user a-2 has not experienced the predetermined event.
  • the experience object is, for example, various events such as content including video or audio, sports games, plays, performances, movies, or battles (for example, Go / Chess / game battles) Performance, performance, performance, etc., which is the object of the user's experience regardless of whether it is provided through a medium such as television or the Internet.
  • the experience target is a baseball relay program, and in the following, a case where it is desired to estimate whether or not a baseball relay program has been viewed will be described.
  • the accepting unit 101 accepts the time of a predetermined operation performed by each of a plurality of users from each terminal 200.
  • the accepting unit 101 accepts from the terminal 200 the time when the predetermined button is pushed every time the team P takes a strike.
  • the acquisition unit 102 acquires a second time distribution of a predetermined operation performed by the user for each of the plurality of users.
  • the second time distribution is a time distribution of a predetermined operation obtained for each user from the time received by the receiving unit 101.
  • the reception unit 101 receives each time of a predetermined operation performed a plurality of times from the user, and as shown in the operation history table 100b of FIG. 6, operation times for a plurality of predetermined operations are registered for each user. If so, the acquisition unit 102 obtains an operation time distribution for each user.
  • FIG. 7 shows the time distribution (first time distribution) of the time when the predetermined button is pressed and the time when the predetermined button is pressed by the user a-1 for all users whose time has been received by the receiving unit 101.
  • the example of a relationship with time distribution (2nd time distribution) is shown.
  • FIG. 7 shows that a predetermined event occurs a plurality of times (events 1 to x (x: an arbitrary natural number. In this embodiment, the number of strikeouts taken by the team P in this embodiment)) ... after x has occurred, the predetermined button is pressed at a timing included in the time zone when another user pressed the predetermined button, and after event 2, the predetermined button has not been pressed. It shows that.
  • the calculating unit 103 calculates the similarity between the acquired first time distribution and the acquired second time distribution.
  • u i is a T-dimensional vector, and the second time distribution can be represented by u i .
  • the calculation unit 103 obtains the first time distribution w t of the predetermined operation as follows.
  • w is a T-dimensional vector.
  • w t ⁇ i u i, t
  • the similarity c i between the second time distribution of the operation by the user i and the first time distribution of the predetermined operation is represented by the inner product of the direction vector of the vector u i and the direction vector of the vector w.
  • the inner product itself of u i and w may be used as the similarity.
  • the similarity increases as the number of coincidence between the time interval in which other users press the predetermined button and the time interval in which the user a-1 presses the predetermined button increases.
  • the estimation unit 104 estimates, based on the similarity, whether or not the user who has acquired the second time distribution related to the similarity has experienced an experience target in which a predetermined event occurs.
  • the estimation unit 104 has a predetermined degree of similarity between the time distribution acquired for the user a-1 and the time distribution acquired for all users notified of the time of the predetermined operation. If it is equal to or greater than the threshold value, it is estimated that the user a-1 has experienced content (baseball game relay) including predetermined events 1 to x.
  • the present embodiment if a certain user is also performing a predetermined operation during a time period when many users have performed the predetermined operation, the certain user is the same cause as another user performing the predetermined operation. In response to this, it can be considered that a predetermined operation has been performed, and it can be easily estimated that the cause (predetermined event) was experienced.
  • the time when the event occurs (for example, in the example of watching a baseball game in this embodiment, the team P Information such as the time when the strikeout was taken) must be prepared as history information.
  • the administrator it is not necessary for the administrator to prepare history information such as that an event has occurred at a certain time, and whether or not the predetermined event was experienced in real time based only on the user's operation Can be estimated.
  • the estimation apparatus 100 may notify each user's terminal 200 to perform a predetermined operation when a predetermined event occurs.
  • the estimation apparatus 100 designates the type of event for which an operation is requested (game end signal, strikeout, start, or start of home team attack, etc.) and notifies the terminal 200 before the game starts.
  • the time at which the predetermined operation is performed is immediately transmitted from the terminal 200, and when the estimation apparatus 100 accepts the time at which the predetermined operation is performed, the estimation apparatus 100 immediately counts and calculates the time distribution of the predetermined operation or the most recent predetermined time. You may make it display the number of time (namely, predetermined operation) received within the number of seconds on the terminal 200.
  • the estimating apparatus 100 may detect that the number of predetermined operations has suddenly increased and notify the user's terminal 200 to that effect. For example, when a predetermined operation is received from a smartphone application and the number of predetermined operations by other users suddenly increases, the estimation apparatus 100 applies a predetermined operation to a smartphone of a user who has not activated the smartphone application. You may make it perform the push notification accompanied with the still image of the television near the time when operation increased suddenly. According to such a structure, an application can be started and it can be induced to watch TV.
  • the accepting unit 101 determines whether or not the time when the user performed a predetermined operation on the terminal 200 used by each of the plurality of users has been accepted from each terminal 200 (step S101). If the reception unit 101 determines that the time when the predetermined operation is performed is received (step S101; Yes), the reception time is registered (step S102). On the other hand, if the reception unit 101 determines that the time when the predetermined operation is performed is not received (step S101; No), the reception unit 101 waits as it is.
  • the reception unit 101 receives the time when the user a-1 performed a predetermined operation from the terminal 200 of the user a-1, the time received is registered in the operation history table 100a of FIG. On the other hand, when the reception unit 101 does not receive the time from any of the terminals 200, it waits as it is.
  • the estimating apparatus 100 determines whether or not an instruction to execute an estimation as to whether or not the user has experienced an event previously associated with a predetermined operation has been received (step S103).
  • the acquisition unit 102 acquires a first time distribution of a predetermined operation from the received time (step S104).
  • the acquisition unit 102 may acquire the second time distribution of the predetermined operation performed by the user for each of the plurality of users.
  • the acquisition unit 102 may display the operation history table in FIG. Referring to 100a, the first time distribution of a predetermined operation is acquired from the operation times of users a-1 to a-na.
  • the process returns to step S101.
  • the acquisition unit 102 acquires the operation time for each user. A time distribution (second time distribution) may be obtained.
  • the calculating unit 103 matches the degree of coincidence between the acquired first time distribution and the time received from each terminal 200, or the degree of similarity between the acquired first time distribution and the acquired second time distribution. Is calculated (step S105).
  • the calculation unit 103 calculates the degree of coincidence by determining to which position of the first time distribution acquired from the entire time received by the receiving unit 101 the operation time of the user a-1 belongs.
  • the calculation unit 103 calculates the time distribution of the predetermined operation by the user a-1 and the time of the predetermined operation for all the users for which the reception unit 101 has received the time. Distribution and similarity are obtained by (Equation 1).
  • the estimation unit 104 determines whether a user who has performed a predetermined operation at the received time has experienced a predetermined event associated with the predetermined operation in advance, or based on the similarity Thus, it is estimated whether or not the user who has acquired the time distribution related to the degree of similarity has experienced the experience object in which the predetermined event occurs (step S106).
  • the estimation unit 104 estimates that the user a-1 has experienced a predetermined event. .
  • the estimation unit 104 determines that the user a -1 is estimated to have experienced the experience object in which the predetermined event occurs.
  • the estimation device 100 includes a reception unit 101, an acquisition unit 102, a calculation unit 103, an estimation unit 104, and an allocation unit 105.
  • the calculation unit 103 and the estimation unit 104 have the same functions as those in the first embodiment.
  • functions different from or added to the first embodiment of the reception unit 101 and the acquisition unit 102 and functions of the allocation unit 105 will be described.
  • the CPU 601 and the NIC 605 cooperate to function as the allocation unit 105.
  • the assigning unit 105 randomly assigns to each terminal 200 a margin time until each terminal 200 reports that the predetermined operation has been performed to the estimation apparatus 100 from the time when the predetermined operation was performed.
  • the margin time is the time from when the predetermined operation is performed at the terminal 200 until the time when the predetermined operation is reported to the estimation apparatus 100.
  • the assigning unit 105 randomly assigns a margin time of 0 to 120 seconds to the terminals 200 of the users a-1 to a-na.
  • the accepting unit 101 accepts from each terminal 200 a report that a predetermined operation reported after the allowance time has elapsed.
  • the margin time allocated to the user a-1 is 5 seconds, from the time when the user a-1 performed a predetermined operation (18:00:05) from the terminal 200 of the user a-1. After 5 seconds (18:00:10), a report indicating that a predetermined operation has been performed is transmitted, and the receiving unit 101 receives this report from the terminal 200 of the user a-1. In addition, the reception unit 101 receives the time at which the user a-1 performed a predetermined operation from the terminal 200 of the user a-1.
  • the reception unit 101 When the reception unit 101 receives a report and a predetermined operation time from the user's terminal 200, for example, the reception unit 101 registers the time when the report arrived and the operation time in the operation history table 100c of FIG. Moreover, when the allocation unit 105 allocates a margin time to each user, the allocation unit 105 registers the margin time in the operation history table 100c of FIG.
  • the operation history table 100c corresponds to the user ID 100c1, the allocated margin time 100c2, the report arrival time 100c3 indicating the time when the report is received, and the operation time 100c4 indicating the time when the predetermined operation is performed. It is registered with it.
  • the acquisition unit 102 obtains the third time distribution of the report indicating that the predetermined operation has been performed and the concentration level of access to the estimation apparatus 100 from the time when the report indicating that the predetermined operation has been received is received. get.
  • the first time distribution is a time distribution of a predetermined operation time by all the users who have received the time
  • the second time distribution is determined by a user who is an object for estimating whether or not the experience object is experienced. It is a time distribution of the time of a predetermined operation
  • the third time distribution is a time distribution of the time at which the report acquired for all users who have received a report indicating that the predetermined operation has been received.
  • the acquisition unit 102 refers to the operation history table 100c in FIG. 10, and the first time distribution (time distribution 401 in FIG. 11) of the operation times of the users a-1 to a-na and the third of the report arrival times. A time distribution (time distribution 402 in FIG. 11) is obtained. Then, the acquisition unit 102 obtains the degree of concentration of access (report) to the estimation apparatus 100 from the time distribution of report arrival times.
  • the degree of access concentration is represented by, for example, how many reports are received per minute.
  • the allocating unit 105 adjusts the margin time so that the deviation between the first time distribution and the third time distribution becomes small while keeping the access concentration level below the limit threshold.
  • the limit threshold is a value that is the upper limit of access concentration, and is a value that requires the access concentration to be less than or equal to this value. For example, it is specified by the administrator of the estimation apparatus 100 in consideration of the system access tolerance and the like.
  • the allocating unit 105 determines the peak of the time distribution 402 (FIG. 11) of the report arrival times of the users a-1 to a-na within a predetermined threshold by the users a-1 to a-na.
  • the margin time is set so that the deviation 500 (FIG. 11) between the time distribution 401 (FIG. 11) of the operation time and the time distribution 402 (FIG. 11) of the report arrival times from the users a-1 to a-na becomes small. Adjust.
  • the estimation apparatus 100 it is possible to control the degree of concentration of access to the estimation apparatus 100 and to make the time for receiving reports closer to the actual operation time. Thereby, it is possible to estimate whether or not the user has experienced a predetermined event or experience object based on the user's operation while preventing excessive access to the estimation device 100.
  • the operation time is before the margin time before the time when the report arrives at estimation apparatus 100 (report arrival time). It is conceivable that. Therefore, time adjustment at the terminal 200 can be omitted. In addition, when the time before the report arrival time is regarded as the operation time, the operation time may not be transmitted from the terminal 200.
  • the terminal 200 autonomously increases the margin time. You may do it. Then, when the report arrives at the estimation apparatus 100, the estimation apparatus 100 may reset the margin time for the terminal 200 in consideration of the degree of access concentration.
  • the estimation device 100 may be accessed when the application is activated, and the estimation device 100 may allocate a spare time to the accessed terminal 200.
  • the estimating apparatus 100 can grasp the total number that may receive a report of a predetermined operation, and can predict the degree of access concentration.
  • the margin time may be set longer on the terminal 200 side so as not to increase the concentration of access.
  • the time when the predetermined operation received from each terminal 200 is performed is the time measured by the clock of each terminal 200, and the calculation unit 103 determines the time of the predetermined operation measured by each terminal 200 and the predetermined time. You may make it obtain
  • the operation time 100c4 of the operation history table 100c is a time measured by the clock of each terminal 200. It is assumed that the estimation device 100 and the terminal 200 are set in time with Japan Standard Time or the like.
  • the calculation unit 103 obtains the difference between the report arrival time 100c3 and the operation time 100c4 in the operation history table 100c (FIG. 10). If the difference is larger than the allocated margin time, it is considered that a communication delay has occurred. Further, the obtained difference may be classified, for example, for each ISP (Internet Services ⁇ Provider) or each base station.
  • ISP Internet Services ⁇ Provider
  • a delay test can be performed.
  • Each terminal 200 randomly allocates a surplus time from the time when the predetermined operation is performed until it reports to the estimation apparatus 100 that the predetermined operation has been performed (step S201).
  • the assigning unit 105 randomly assigns a margin time of 0 to 120 seconds to the terminals 200 of the users a-1 to a-na. Moreover, when the allocation unit 105 allocates a margin time to each user, the allocation unit 105 registers the margin time in the operation history table 100c of FIG.
  • the receiving unit 101 determines from each terminal 200 whether a report indicating that a predetermined operation reported after the allowance time has elapsed and a time when the user performed the predetermined operation has been received (step S202). ).
  • the reception unit 101 determines that the report indicating that the predetermined operation has been performed and the time when the predetermined operation has been received (step S202; Yes)
  • the arrival time of the report indicating that the predetermined operation has been performed (report) Arrival time) and time (operation time) at which a predetermined operation is performed are registered (step S203).
  • the reception unit 101 determines that it has not received a report that a predetermined operation has been performed and the time at which the predetermined operation has been performed (step S202; No)
  • the reception unit 101 waits as it is.
  • the reception unit 101 receives a report indicating that a predetermined operation has been performed from the terminal 200 of the user a-1 and a time when the user a-1 has performed the predetermined operation (operation time), the operation illustrated in FIG. Report arrival time and operation time when the report arrived are registered in the history table 100c.
  • the reception unit 101 waits as it is.
  • the acquisition unit 102 acquires the first time distribution from the time of the received predetermined operation, and the predetermined operation is performed.
  • the third time distribution is acquired from the time when the report to the effect is received (step S205).
  • the acquisition unit 102 refers to the operation history table 100c in FIG. 10, and the first time distribution (time distribution 401 in FIG. 11) of the operation times of the users a-1 to a-na and the third of the report arrival times.
  • a time distribution (time distribution 402 in FIG. 11) is obtained.
  • the acquisition unit 102 acquires the degree of concentration of access to the estimation device 100 from the third time distribution of the report arrival time (step S208).
  • the acquisition unit 102 obtains the degree of concentration of access to the estimation apparatus 100 from the third time distribution (time distribution 402 in FIG. 11) of the report arrival time.
  • the allocating unit 105 adjusts the margin time so that the difference between the predetermined first time distribution and the third time distribution is reduced while suppressing the access concentration level to a threshold value or less (step S209).
  • the assigning unit 105 operates the users a-1 to a-na while keeping the peak of the time distribution 402 (FIG. 11) of the report arrival times of the users a-1 to a-na within the limit threshold.
  • the margin time is adjusted so that the difference 500 (FIG. 11) between the time distribution 401 (FIG. 11) of the time and the time distribution 402 (FIG. 11) of the report arrival times from the users a-1 to a-na becomes small. To do.

Abstract

A reception unit (101) receives, from a terminal used by each user of a plurality of users, a time at which the user performed a predetermined operation on the terminal. From these received times, an acquisition unit (102) obtains a first time distribution of events where the predetermined operation was performed. A calculation unit (103) calculates a degree of coincidence between the obtained first time distribution and the time received from each terminal. An estimation unit (104) estimates whether or not each user of the plurality of users experienced a predetermined event pre-associated with the predetermined operation, on the basis of the calculated degree of coincidence for the user.

Description

推定装置、推定方法、プログラム、及び、非一時的なコンピュータ読取可能な情報記録媒体Estimation apparatus, estimation method, program, and non-transitory computer-readable information recording medium
　本発明は、推定装置、推定方法、プログラム、及び、非一時的なコンピュータ読取可能な情報記録媒体に関し、特に、イベントの体験状態についての推定に関するものである。 The present invention relates to an estimation device, an estimation method, a program, and a non-transitory computer-readable information recording medium, and particularly relates to estimation of an event experience state.
　テレビ等の既存のインフラにおいて、ユーザが視聴しているか否か等のユーザの行動を確認したいという要望は、従来から存在する。このような要望に応えるため、例えば、特許文献１には、放送広告を、リアルタイム視聴、録画視聴又はオンデマンド視聴のいずれかにかかわらず、放送広告が視聴されたことを確認する技術が開示されている。 In the existing infrastructure such as television, there has been a demand for confirming user behavior such as whether or not the user is watching. In order to meet such a demand, for example, Patent Document 1 discloses a technology for confirming that a broadcast advertisement is viewed regardless of whether the broadcast advertisement is viewed in real time, recorded or viewed on demand. ing.
特開２００９－２９６３８８号公報JP 2009-296388 A
　上記の技術では、放送広告に予め広告の開始から終了までの放送秒数を埋め込み、放送広告を再生した利用者側の端末において、放送広告が再生された秒数を計測し、最初に埋め込まれた放送秒数と、再生された秒数を比較することにより、広告が視聴されたか否かを判断する。しかし、このように、予め全てのコンテンツについて放送秒数等の情報を用意し、埋め込みを行い、さらに端末において再生時間を計測することは、手間がかかるので、より簡易な技術が求められている。 In the above technology, the broadcast seconds from the start to the end of the advertisement are embedded in the broadcast advertisement in advance, and the number of seconds that the broadcast advertisement is played is measured at the user terminal that has played the broadcast advertisement. It is determined whether or not the advertisement has been viewed by comparing the broadcast seconds and the reproduced seconds. However, it takes time and effort to prepare information such as the number of broadcast seconds for all the contents in advance, embed them, and measure the playback time on the terminal. Therefore, a simpler technique is required. .
　近年では、コンテンツの観賞中にデジタル放送やＳＮＳ（Social Networking Service）等を介してユーザの操作を求めることができる。このようなユーザが行う操作を利用して、コンテンツやコンテンツ中のイベントを観賞等の体験をしているか否かを判断できれば、予め情報を用意する等の手間をかけることなく、ユーザの行動を確認することができる。 In recent years, user operations can be requested through digital broadcasting, SNS (Social Networking Service), etc. while viewing content. If it is possible to determine whether or not the user has experienced viewing the content and the event in the content by using the operation performed by such a user, the user's action can be performed without taking the trouble of preparing information in advance. Can be confirmed.
　本発明は、上記のような課題を解決するもので、ユーザの操作から当該ユーザが所定のイベントを体験していたか否かを推定するのに好適な推定装置、推定方法、プログラム、及び、非一時的なコンピュータ読取可能な情報記録媒体を提供することを目的とする。 The present invention solves the above-described problems, and is an estimation device, an estimation method, a program, and a non-optimum suitable for estimating whether or not the user has experienced a predetermined event from a user's operation. It is an object to provide a temporary computer-readable information recording medium.
　本発明の第１の観点に係る推定装置は、
　複数のユーザのそれぞれが使用する端末において前記ユーザが所定の操作を行った時刻を、前記各端末から受け付ける受付部と、
　前記受け付けた時刻から、前記所定の操作の第１時間分布を取得する取得部と、
　前記取得された第１時間分布と、前記各端末から受け付けた時刻と、の一致度を算定する算定部と、
　前記一致度に基づいて、前記複数のユーザのそれぞれが、前記所定の操作に予め対応付けられた所定のイベントを体験していたか否かを推定する推定部と、
　を備えることを特徴とする。 An estimation apparatus according to a first aspect of the present invention is:
A reception unit that receives the time at which the user performs a predetermined operation on the terminal used by each of the plurality of users from each of the terminals;
An acquisition unit for acquiring a first time distribution of the predetermined operation from the received time;
A calculating unit that calculates the degree of coincidence between the acquired first time distribution and the time received from each terminal;
An estimation unit that estimates whether each of the plurality of users has experienced a predetermined event associated with the predetermined operation based on the degree of coincidence;
It is characterized by providing.
　また、上記観点に係る推定装置において、
　前記所定のイベントは、複数回生じるものであって、
　前記受付部は、前記複数のユーザのそれぞれが行った前記所定の操作の時刻を、前記各端末から受け付け、
　前記取得部は、前記複数のユーザのそれぞれについて、前記ユーザが行った前記所定の操作の第２時間分布を取得し、
　前記算定部は、前記取得された第１時間分布と、前記取得された第２時間分布と、の類似度を算定し、
　前記推定部は、前記類似度に基づいて、前記類似度にかかる前記第２時間分布が取得されたユーザが、前記所定のイベントが生じる体験対象を体験していたか否かを推定する
　ことを特徴とする。 In the estimation device according to the above aspect,
The predetermined event occurs a plurality of times,
The reception unit receives time of the predetermined operation performed by each of the plurality of users from each terminal,
The acquisition unit acquires a second time distribution of the predetermined operation performed by the user for each of the plurality of users.
The calculating unit calculates a similarity between the acquired first time distribution and the acquired second time distribution;
The estimation unit estimates, based on the similarity, whether or not the user who has acquired the second time distribution related to the similarity has experienced the experience target in which the predetermined event occurs. And
　また、上記観点に係る推定装置において、
　前記各端末が、前記所定の操作が行われた時刻から前記推定装置へ前記所定の操作が行われた旨を報告するまでの余裕時間を、前記各端末にランダムに割り当てる割当部
　をさらに備え、
　前記受付部は、前記余裕時間経過後に報告される前記所定の操作が行われた旨の報告を、前記各端末から受け付け、
　前記取得部は、前記所定の操作が行われた旨の報告を受け付けた時刻から、前記所定の操作が行われた旨の報告の第３時間分布と、前記推定装置へのアクセスの集中度と、を取得し、
　前記割当部は、前記アクセスの集中度を限界閾値以下に抑えつつ、前記第１時間分布と、前記第３時間分布とのずれが小さくなるように、前記余裕時間を調節する
　ことを特徴とする。 In the estimation device according to the above aspect,
An allocation unit that randomly allocates each terminal with a margin time from the time when the predetermined operation is performed until the terminal reports the fact that the predetermined operation has been performed to the estimation device;
The reception unit receives a report that the predetermined operation reported after the allowance time has elapsed from each terminal,
The acquisition unit, from the time when the report indicating that the predetermined operation has been received is received, a third time distribution of the report indicating that the predetermined operation has been performed, and the degree of concentration of access to the estimation device, Get the
The allocating unit adjusts the margin time so as to reduce a difference between the first time distribution and the third time distribution while suppressing the access concentration to a threshold value or less. .
　また、上記観点に係る推定装置において、
　前記各端末から受け付けた前記所定の操作が行われた時刻は、前記各端末の時計で計測された時刻であり、
　前記算定部は、前記各端末で計測された前記所定の操作の時刻と、前記所定の操作が行われた旨の報告を受け付けた時刻と、の差を求める
　ことを特徴とする。 In the estimation device according to the above aspect,
The time when the predetermined operation received from each terminal is performed is the time measured by the clock of each terminal,
The calculating unit obtains a difference between the time of the predetermined operation measured at each terminal and the time when a report indicating that the predetermined operation has been received is received.
　本発明の第２の観点に係る推定方法は、
　推定装置が実行する推定方法であって、
　前記推定装置が、複数のユーザのそれぞれが使用する端末において前記ユーザが所定の操作を行った時刻を、前記各端末から受け付ける受付工程と、
　前記推定装置が、前記受け付けた時刻から、前記所定の操作の第１時間分布を取得する取得工程と、
　前記推定装置が、前記取得された第１時間分布と、前記各端末から受け付けた時刻と、の一致度を算定する算定工程と、
　前記推定装置が、前記一致度に基づいて、前記複数のユーザのそれぞれが、前記所定の操作に予め対応付けられた所定のイベントを体験していたか否かを推定する推定工程と、
　を備えることを特徴とする。 The estimation method according to the second aspect of the present invention is:
An estimation method executed by an estimation device,
An accepting step for accepting, from each of the terminals, the time when the user performed a predetermined operation on the terminal used by each of the plurality of users by the estimation device;
An obtaining step in which the estimation device obtains a first time distribution of the predetermined operation from the accepted time;
A calculation step in which the estimation device calculates a degree of coincidence between the acquired first time distribution and the time received from each terminal;
An estimation step in which the estimation device estimates whether each of the plurality of users has experienced a predetermined event previously associated with the predetermined operation based on the degree of coincidence;
It is characterized by providing.
　本発明の第３の観点に係るプログラムは、
　コンピュータを、
　複数のユーザのそれぞれが使用する端末において前記ユーザが所定の操作を行った時刻を、前記各端末から受け付ける受付部、
　前記受け付けた時刻から、前記所定の操作の第１時間分布を取得する取得部、
　前記取得された第１時間分布と、前記各端末から受け付けた時刻と、の一致度を算定する算定部、
　前記一致度に基づいて、前記複数のユーザのそれぞれが、前記所定の操作に予め対応付けられた所定のイベントを体験していたか否かを推定する推定部、
　として機能させることを特徴とする。 The program according to the third aspect of the present invention is:
Computer
A receiving unit that receives, from each terminal, a time at which the user performs a predetermined operation in a terminal used by each of a plurality of users;
An acquisition unit for acquiring a first time distribution of the predetermined operation from the received time;
A calculation unit that calculates the degree of coincidence between the acquired first time distribution and the time received from each terminal;
An estimation unit that estimates whether each of the plurality of users has experienced a predetermined event previously associated with the predetermined operation based on the degree of coincidence,
It is made to function as.
　本発明の第４の観点に係る非一時的なコンピュータ読取可能な情報記録媒体は、
　コンピュータを、
　複数のユーザのそれぞれが使用する端末において前記ユーザが所定の操作を行った時刻を、前記各端末から受け付ける受付部、
　前記受け付けた時刻から、前記所定の操作の第１時間分布を取得する取得部、
　前記取得された第１時間分布と、前記各端末から受け付けた時刻と、の一致度を算定する算定部、
　前記一致度に基づいて、前記複数のユーザのそれぞれが、前記所定の操作に予め対応付けられた所定のイベントを体験していたか否かを推定する推定部、
　として機能させることを特徴とするプログラムを記録する。 A non-transitory computer-readable information recording medium according to the fourth aspect of the present invention is provided.
Computer
A receiving unit that receives, from each terminal, a time at which the user performs a predetermined operation in a terminal used by each of a plurality of users;
An acquisition unit for acquiring a first time distribution of the predetermined operation from the received time;
A calculation unit that calculates the degree of coincidence between the acquired first time distribution and the time received from each terminal;
An estimation unit that estimates whether each of the plurality of users has experienced a predetermined event previously associated with the predetermined operation based on the degree of coincidence,
A program characterized by functioning as a program is recorded.
　上記非一時的なコンピュータ読取可能な情報記録媒体は、コンピュータとは独立して配布・販売することができる。ここで、非一時的な（non-transitory）情報記録媒体とは、有形な（tangible）情報記録媒体をいう。非一時的な情報記録媒体は、例えば、コンパクトディスク、フレキシブルディスク、ハードディスク、光磁気ディスク、ディジタルビデオディスク、磁気テープ、半導体メモリ等である。また、一時的な（transitory）情報記録媒体とは、伝送媒体（伝搬信号）それ自体を示す。一時的な情報記録媒体は、例えば、電気信号、光信号、電磁波等である。なお、一時的な（temporary）記憶領域とは、データやプログラムを一時的に記憶するための領域であり、例えば、ＲＡＭ（Random Access Memory）等の揮発性メモリである。 The non-transitory computer-readable information recording medium can be distributed and sold independently of the computer. Here, the non-transitory information recording medium refers to a tangible information recording medium. Non-temporary information recording media are, for example, compact disks, flexible disks, hard disks, magneto-optical disks, digital video disks, magnetic tapes, semiconductor memories, and the like. The transitory information recording medium refers to the transmission medium (propagation signal) itself. The temporary information recording medium is, for example, an electric signal, an optical signal, an electromagnetic wave, or the like. The temporary storage area is an area for temporarily storing data and programs, and is, for example, a volatile memory such as a RAM (Random Access Memory).
　本発明によれば、ユーザの操作から当該ユーザが所定のイベントを体験していたか否かを推定するのに好適な推定装置、推定方法、プログラム、及び、非一時的なコンピュータ読取可能な情報記録媒体を提供することができる。 According to the present invention, an estimation device, an estimation method, a program, and a non-transitory computer-readable information record suitable for estimating whether or not the user has experienced a predetermined event from the user's operation A medium can be provided.
本発明の実施形態に係る推定装置及び端末の関係を示す図である。It is a figure which shows the relationship between the estimation apparatus which concerns on embodiment of this invention, and a terminal. 本発明の実施形態に係る推定装置が実現される典型的な情報処理装置の概要構成を示す図である。It is a figure which shows schematic structure of the typical information processing apparatus with which the estimation apparatus which concerns on embodiment of this invention is implement | achieved. 実施形態１に係る推定装置の概要構成を示す図である。It is a figure which shows schematic structure of the estimation apparatus which concerns on Embodiment 1. FIG. 操作履歴テーブルを説明するための図である。It is a figure for demonstrating the operation history table. 第１時間分布の例を示す図である。It is a figure which shows the example of 1st time distribution. 操作履歴テーブルを説明するための図である。It is a figure for demonstrating the operation history table. 複数のイベントについて取得された第１時間分布と、ユーザａ－１について取得された第２時間分布との関係を説明するための図である。It is a figure for demonstrating the relationship between the 1st time distribution acquired about the some event, and the 2nd time distribution acquired about the user a-1. 実施形態１に係る推定装置が行う推定処理を説明するためのフローチャートである。6 is a flowchart for explaining an estimation process performed by the estimation apparatus according to the first embodiment. 実施形態２に係る推定装置の概要構成を示す図である。It is a figure which shows schematic structure of the estimation apparatus which concerns on Embodiment 2. FIG. 操作履歴テーブルを説明するための図である。It is a figure for demonstrating the operation history table. 操作時刻の第１時間分布と報告到着時刻の第３時間分布との関係を説明するための図である。It is a figure for demonstrating the relationship between the 1st time distribution of operation time, and the 3rd time distribution of report arrival time. 実施形態２に係る推定装置が行う推定処理を説明するためのフローチャートである。10 is a flowchart for explaining an estimation process performed by the estimation apparatus according to the second embodiment.
（１．全体構成）
　本発明の実施形態に係る推定装置１００は、図１に示すように、インターネット３００に接続される。この他、インターネット３００には、複数の端末２００が接続される。 (1. Overall configuration)
The estimation apparatus 100 according to the embodiment of the present invention is connected to the Internet 300 as shown in FIG. In addition, a plurality of terminals 200 are connected to the Internet 300.
　推定装置１００は、端末２００から、端末２００において所定の操作が行われた時刻や所定の操作が行われた旨の報告を受け付け、端末２００のユーザが所定のイベントを体験していたか否か推定する装置である。 The estimation apparatus 100 receives from the terminal 200 a time when a predetermined operation is performed on the terminal 200 and a report that the predetermined operation has been performed, and estimates whether or not the user of the terminal 200 has experienced a predetermined event. It is a device to do.
　端末２００は、ユーザによる様々な操作を受け付ける装置であり、ユーザが端末２００にて所定の操作を行うと、所定の操作を行った時刻を推定装置１００に通知したり、所定の操作を行った旨を通知したりする。 The terminal 200 is a device that accepts various operations by the user. When the user performs a predetermined operation on the terminal 200, the terminal 200 notifies the estimation device 100 of the time when the predetermined operation is performed, or performs a predetermined operation. To notify you.
　以下の実施形態では、テレビを観賞しているユーザが、デジタル放送受信機器において所定の操作を行う場合や、スマートフォン等の機器で所定の操作を行う場合を例に説明する。したがって、以下の実施形態では、端末２００は、デジタル放送受信機器やスマートフォン等の機器であり、推定装置１００は、これらから情報を受け付けるサーバとして説明する。 In the following embodiment, a case where a user watching a television performs a predetermined operation on a digital broadcast receiving device or a case where a user performs a predetermined operation on a device such as a smartphone will be described as an example. Therefore, in the following embodiments, the terminal 200 is a device such as a digital broadcast receiving device or a smartphone, and the estimation device 100 will be described as a server that receives information from these devices.
　また、以下の実施形態では、テレビで野球の試合が中継されている間に、ユーザが所定の操作を求められることとし、推定装置１００は、ユーザによる所定の操作に基づいて、ユーザが試合を見ていたか否かを推定するものとする。 Further, in the following embodiment, the user is required to perform a predetermined operation while a baseball game is being relayed on television, and the estimation device 100 allows the user to play a game based on the predetermined operation by the user. It shall be estimated whether it was watching or not.
　なお、本願発明は、ユーザが、テレビやインターネット等を通してある事象やコンテンツを視聴等の体験をしている場合に限らず、ユーザが、スポーツの試合、演劇、映画等を直接その場で体験（観戦、観劇、観賞等）している場合にも適用可能である。 Note that the present invention is not limited to the case where the user is experiencing an event or content through television or the Internet, but the user can directly experience sports games, plays, movies, etc. on the spot ( (Watching, watching theater, watching, etc.)
（２．情報処理装置の概要構成）
　本発明の実施形態に係る推定装置１００が実現される典型的な情報処理装置６００の概要構成について説明する。 (2. Outline configuration of information processing apparatus)
A schematic configuration of a typical information processing apparatus 600 that realizes the estimation apparatus 100 according to the embodiment of the present invention will be described.
　情報処理装置６００は、図２に示すように、ＣＰＵ（Central Processing Unit）６０１と、ＲＯＭ（Read Only Memory）６０２と、ＲＡＭ　６０３と、記憶装置６０４と、ＮＩＣ（Network Interface Card）６０５と、画像処理部６０６と、音声処理部６０７と、ディスプレイ６０８と、スピーカ６０９と、コントローラ６１０と、を備える。 As shown in FIG. 2, the information processing apparatus 600 includes a CPU (Central Processing Unit) 601, a ROM (Read Only Memory) 602, a RAM 603, a storage device 604, a NIC (Network Interface Card) 605, an image A processing unit 606, an audio processing unit 607, a display 608, a speaker 609, and a controller 610 are provided.
　ＣＰＵ　６０１は、情報処理装置６００全体の動作を制御し、各構成要素と接続され、制御信号やデータをやりとりする。 The CPU 601 controls the operation of the information processing apparatus 600 as a whole, is connected to each component, and exchanges control signals and data.
　ＲＯＭ　６０２には、情報処理装置６００全体の動作制御に必要なオペレーティングシステムのプログラムや各種のデータが記録される。 The ROM 602 records an operating system program and various data necessary for operation control of the entire information processing apparatus 600.
　ＲＡＭ　６０３は、データやプログラムを一時的に記憶するためのもので、記憶装置６０４から読み出したプログラムやデータ、その他、通信に必要なデータ等が保持される。 The RAM 603 is for temporarily storing data and programs, and holds programs and data read from the storage device 604 and other data necessary for communication.
　記憶装置６０４は、ハードディスクやフラッシュメモリ等から構成され、情報処理装置６００で処理するデータを記憶する。また、記憶装置６０４は、ＣＤ（Compact Disc）等の非一時的なコンピュータ読取可能な情報記録媒体からデータを読み出すデバイス等を備えるように構成されてもよい。 The storage device 604 includes a hard disk, a flash memory, and the like, and stores data to be processed by the information processing device 600. Further, the storage device 604 may be configured to include a device that reads data from a non-transitory computer-readable information recording medium such as a CD (Compact Disc).
　ＮＩＣ　６０５は、情報処理装置６００をインターネット等のコンピュータ通信網に接続するためのものであり、ＮＩＣ　６０５を介して他の情報処理装置等とやりとりをする。 The NIC 605 is used to connect the information processing apparatus 600 to a computer communication network such as the Internet, and communicates with other information processing apparatuses and the like via the NIC 605.
　画像処理部６０６は、記憶装置６０４等から読み出されたデータやカメラで撮影されたデータをＣＰＵ　６０１や画像処理部６０６が備える画像演算プロセッサによって加工処理し、画像処理部６０６が備えるフレームメモリに記録する。フレームメモリに記録された画像情報は、所定の同期タイミングでビデオ信号に変換され、ディスプレイ６０８に出力される。 The image processing unit 606 processes the data read from the storage device 604 or the like or the data taken by the camera by the image arithmetic processor included in the CPU 601 or the image processing unit 606, and stores it in the frame memory included in the image processing unit 606. Record. The image information recorded in the frame memory is converted into a video signal at a predetermined synchronization timing and output to the display 608.
　音声処理部６０７は、記憶装置６０４等から読み出されたデータをアナログ音声信号に変換し、スピーカ６０９から出力させる。 The audio processing unit 607 converts the data read from the storage device 604 or the like into an analog audio signal and outputs it from the speaker 609.
　コントローラ６１０は、ユーザからの指示入力を受け付ける。 The controller 610 receives an instruction input from the user.
　以下、上記情報処理装置６００において実現される推定装置１００について、図１乃至図１２を参照して説明する。情報処理装置６００に電源が投入されると、推定装置１００として機能させるプログラムが実行され、実施形態に係る推定装置１００が実現される。 Hereinafter, the estimation apparatus 100 realized in the information processing apparatus 600 will be described with reference to FIGS. 1 to 12. When the information processing apparatus 600 is powered on, a program that functions as the estimation apparatus 100 is executed, and the estimation apparatus 100 according to the embodiment is realized.
（３．実施形態１に係る推定装置の概要構成）
　推定装置１００は、図３に示すように、受付部１０１と、取得部１０２と、算定部１０３と、推定部１０４と、から構成される。 (3. Outline configuration of estimation apparatus according to Embodiment 1)
As illustrated in FIG. 3, the estimation device 100 includes a reception unit 101, an acquisition unit 102, a calculation unit 103, and an estimation unit 104.
　本実施形態において、ＣＰＵ　６０１及びＮＩＣ　６０５が協働して、受付部１０１として機能し、ＣＰＵ　６０１が、取得部１０２、算定部１０３及び推定部１０４として機能する。 In this embodiment, the CPU 601 and the NIC 605 cooperate to function as the reception unit 101, and the CPU 601 functions as the acquisition unit 102, the calculation unit 103, and the estimation unit 104.
　受付部１０１は、複数のユーザのそれぞれが使用する端末２００においてユーザが所定の操作を行った時刻を、各端末２００から受け付ける。 The accepting unit 101 accepts from each terminal 200 the time when the user performed a predetermined operation on the terminal 200 used by each of the plurality of users.
　所定の操作とは、端末２００を使用するユーザが、端末２００において行う操作である。本実施形態では、テレビで野球観戦をしているユーザは、所定のイベント（試合終了の合図、三振、出塁、又は、ホームチームの攻撃回開始等）が起きたら所定の操作を行うことが求められるとし、所定の操作は、デジタル放送受信機器のリモコンで所定のボタンを押す、或いは、インターネットの指定されたページにアクセスする等とする。 The predetermined operation is an operation performed on the terminal 200 by a user using the terminal 200. In this embodiment, a user who is watching a baseball game on a television is required to perform a predetermined operation when a predetermined event occurs (such as a cue end of a game, a strikeout, a start, or a home team attack start). The predetermined operation is performed by pressing a predetermined button on the remote controller of the digital broadcast receiving apparatus or accessing a designated page on the Internet.
　例えば、ユーザは、チームＰとチームＱとが対戦する野球の試合において、球審より試合終了の合図がされると、デジタル放送受信機器のリモコンの所定のボタンを押すことが求められるとする。例えば、球審より試合終了の合図がされたタイミングで、ユーザａ－１がリモコンで所定のボタンを押すと、デジタル放送受信機器から、所定のボタンが押された時刻が推定装置１００宛に送信される。受付部１０１は、ユーザａ－１のデジタル放送受信機器から送信された時刻を受け付ける。なお、デジタル放送受信機器が、所定のボタンが押圧された旨を送信し、受付部１０１は、押圧された旨を受け付けた時刻を、所定の操作を行った時刻としてもよい。 For example, suppose that a user is required to press a predetermined button on the remote control of the digital broadcast receiving device when a signal from the ball umpire is given to the end of the game in a baseball game where team P and team Q play. For example, when the user a-1 presses a predetermined button on the remote controller at the timing when the game end is signaled by the ball umpire, the time when the predetermined button is pressed is transmitted from the digital broadcast receiving device to the estimation apparatus 100. The The accepting unit 101 accepts the time transmitted from the digital broadcast receiving device of the user a-1. Note that the digital broadcast receiving apparatus may transmit that a predetermined button has been pressed, and the reception unit 101 may determine that the time when the digital broadcast receiving apparatus has pressed is a predetermined operation.
　受付部１０１は、ユーザの端末２００から時刻を受け付けると、例えば、図４の操作履歴テーブル１００ａに時刻等を登録する。操作履歴テーブル１００ａは、受け付けた時刻に所定の操作を行ったユーザを識別するためのユーザＩＤ　１００ａ１と、所定の操作が行われた時刻を示す操作時刻１００ａ２と、が対応付けて登録されている。例えば、図４の操作履歴テーブル１００ａの１行目は、ユーザＩＤ　１００ａ１が“ａ－１”のユーザａ－１が、“１８時００分０５秒”にリモコンで所定のボタンを押したことを示す。 When the accepting unit 101 accepts the time from the user's terminal 200, for example, the accepting unit 101 registers the time in the operation history table 100a of FIG. In the operation history table 100a, a user ID 100a1 for identifying a user who performed a predetermined operation at the received time and an operation time 100a2 indicating the time when the predetermined operation was performed are registered in association with each other. . For example, the first line of the operation history table 100a in FIG. 4 indicates that the user a-1 whose user ID 100a1 is “a-1” has pressed a predetermined button on the remote control at “18:00:05”. Show.
　取得部１０２は、受け付けた時刻から、所定の操作の第１時間分布を取得する。 The acquisition unit 102 acquires a first time distribution of a predetermined operation from the received time.
　第１時間分布とは、受付部１０１が受け付けた時刻全体から求めた、所定の操作の時間分布である。 The first time distribution is a time distribution of a predetermined operation obtained from the entire time received by the receiving unit 101.
　例えば、取得部１０２は、図４の操作履歴テーブル１００ａを参照して、ユーザａ－１～ａ－ｎａ（ｎａ：任意の自然数）の操作時刻から、所定の操作の第１時間分布（図５）を取得する。図５では、横軸は、所定の操作の時刻、縦軸は、各端末２００から受け付けた所定の操作の時刻の件数を示している。 For example, the acquisition unit 102 refers to the operation history table 100a in FIG. 4 and calculates the first time distribution of predetermined operations (FIG. 5) from the operation times of the users a-1 to a-na (na: any natural number). ) To get. In FIG. 5, the horizontal axis indicates the time of a predetermined operation, and the vertical axis indicates the number of times of the predetermined operation received from each terminal 200.
　算定部１０３は、取得された第１時間分布と、各端末２００から受け付けた時刻と、の一致度を算定する。 The calculating unit 103 calculates the degree of coincidence between the acquired first time distribution and the time received from each terminal 200.
　一致度とは、それぞれのユーザが使用する端末から受けた時刻が、第１時間分布のどの位置に含まれるかを表す指標である。 The degree of coincidence is an index indicating in which position of the first time distribution the time received from the terminal used by each user is included.
　例えば、図５に示すような時間分布が得られたとすると（平均時刻：１８時００時００分、標準偏差（ＳＤ）：３０秒）、算定部１０３は、推定の対象となるユーザの操作時刻がこの分布のどの位置に属するかを判断することにより一致度を算定する。 For example, when a time distribution as shown in FIG. 5 is obtained (average time: 18:00, standard deviation (SD): 30 seconds), the calculation unit 103 determines the operation time of the user to be estimated. The degree of coincidence is calculated by determining to which position of the distribution belongs.
　推定部１０４は、一致度に基づいて、複数のユーザのそれぞれが、所定の操作に予め対応付けられた所定のイベントを体験していたか否かを推定する。 The estimation unit 104 estimates whether each of the plurality of users has experienced a predetermined event associated with a predetermined operation in advance based on the degree of coincidence.
　所定のイベントとは、所定の操作に予め対応付けられたイベントであり、所定の操作がイベントに起因して行われるようなイベントである。 The predetermined event is an event associated with a predetermined operation in advance, and is an event in which the predetermined operation is performed due to the event.
　また、「体験」には、見る、聞く、触る、観賞する、自ら動く等、ユーザが五感等を介して知得できるすべての経験が含まれる。 In addition, “experience” includes all experiences that the user can learn through the five senses, such as seeing, listening, touching, appreciating, and moving by themselves.
　本実施形態では、球審の試合終了の合図を受けて、所定のボタンが押圧されることを求められており、この場合、所定のイベントとは、球審の試合終了の合図であり、当該合図の視聴が体験に該当する。なお、この他、テレビ番組である場面になると、一斉にサーバにアクセスされる様な現象がある場合には、この「ある場面」が所定のイベントとなる。 In this embodiment, it is requested that a predetermined button is pressed in response to a signal from the end of the game of the ball umpire. In this case, the predetermined event is a signal to end the game of the ball umpire, Viewing is an experience. In addition to this, when a scene is a television program, if there is a phenomenon in which the server is accessed all at once, this “certain scene” becomes a predetermined event.
　以下の例では、一致度は、第１時間分布の標準偏差の何倍かを示す値で表す。例えば、推定部１０４は、あるユーザの操作時刻が、第１時間分布において標準偏差の±２（±２ＳＤ）の範囲に収まる場合は、当該あるユーザは、所定の操作に予め対応付けられた所定のイベントを体験していたと推定する。標準偏差の±２の範囲とは、分布が正規分布に従うとすると、所定の操作を行ったユーザの約９５％がその範囲に含まれる時刻に所定の操作を行った範囲である。多くのユーザが所定の操作を行った時間帯に、あるユーザが所定の操作を行ったとすると、当該ユーザは、他のユーザが所定の操作を行った原因と同じ原因に反応して、所定の操作を行ったと考えることができる。よって、所定の操作は、所定のイベントに対応して行われる操作なので、当該ユーザは所定のイベントを体験していたと推定される。 In the following example, the degree of coincidence is represented by a value indicating how many times the standard deviation of the first time distribution. For example, when the operation time of a certain user falls within the range of ± 2 (± 2SD) of the standard deviation in the first time distribution, the estimation unit 104 determines that the certain user is associated with a predetermined operation in advance. It is estimated that the event was experienced. The range of ± 2 of the standard deviation is a range where about 95% of users who have performed a predetermined operation perform a predetermined operation at a time included in the range, assuming that the distribution follows a normal distribution. If a user performs a predetermined operation during a time period when many users have performed the predetermined operation, the user reacts to the same cause as the cause of the other user performing the predetermined operation. It can be considered that the operation was performed. Therefore, since the predetermined operation is an operation performed in response to the predetermined event, it is estimated that the user has experienced the predetermined event.
　例えば、ユーザａ－１は、“１８時００分０５秒”に所定の操作を行っているので、一致度は、＋０．１７ＳＤと求められ、図５の時間分布の標準偏差の±２の範囲に含まれる。よって、推定部１０４は、ユーザａ－１は所定のイベントを体験していたと推定する。一方、ユーザａ－２は、“１８時５０分００秒”に所定の操作を行っているので、一致度は、＋１００ＳＤと求められ、図５の時間分布の標準偏差の±２の範囲に含まれない。よって、推定部１０４は、ユーザａ－２は所定のイベントを体験していなかったと推定する。 For example, since the user a-1 performs a predetermined operation at “18:00:05”, the coincidence degree is calculated as + 0.17SD, and the range of ± 2 of the standard deviation of the time distribution in FIG. include. Therefore, the estimation unit 104 estimates that the user a-1 has experienced a predetermined event. On the other hand, since the user a-2 performs a predetermined operation at “18:50:00”, the degree of coincidence is calculated as + 100SD, and is included in the range of ± 2 of the standard deviation of the time distribution of FIG. I can't. Therefore, the estimation unit 104 estimates that the user a-2 has not experienced the predetermined event.
　なお、所定のイベントが複数回生じる場合は、所定のイベントが生じる体験対象を体験していたか否かを推定することができる。 In addition, when a predetermined event occurs a plurality of times, it can be estimated whether or not the experience object in which the predetermined event occurs has been experienced.
　ここで、体験対象とは、例えば、映像又は音声を含むコンテンツや、その場で行われるスポーツの試合、演劇、演奏、映画又は対戦（例えば、囲碁・チェス・ゲームの対戦）等の各種の催し、パフォーマンス、興行又は演目等であって、テレビやインターネット等の媒体を通して提供されるか否かに関わらず、ユーザによる体験の対象となるものである。本実施形態では、体験対象は、野球の中継番組であり、以下では、野球の中継番組を視聴していたか否かを推定したい場合を例に説明する。 Here, the experience object is, for example, various events such as content including video or audio, sports games, plays, performances, movies, or battles (for example, Go / Chess / game battles) Performance, performance, performance, etc., which is the object of the user's experience regardless of whether it is provided through a medium such as television or the Internet. In this embodiment, the experience target is a baseball relay program, and in the following, a case where it is desired to estimate whether or not a baseball relay program has been viewed will be described.
　受付部１０１は、複数のユーザのそれぞれが行った所定の操作の時刻を、各端末２００から受け付ける。 The accepting unit 101 accepts the time of a predetermined operation performed by each of a plurality of users from each terminal 200.
　例えば、ユーザは、チームＰ対チームＱの野球の試合で、チームＰが三振を奪った場合、リモコンの所定のボタンを押すことが求められるとする。各ユーザが、チームＰが三振を奪った度に所定のボタンを押すと、受付部１０１は、端末２００から、チームＰが三振を奪った度に所定のボタンが押された時刻を受け付ける。 For example, it is assumed that the user is required to press a predetermined button on the remote control when the team P takes a strikeout in a team P vs. team Q baseball game. When each user presses a predetermined button every time the team P takes a strike, the accepting unit 101 accepts from the terminal 200 the time when the predetermined button is pushed every time the team P takes a strike.
　取得部１０２は、複数のユーザのそれぞれについて、ユーザが行った所定の操作の第２時間分布を取得する。 The acquisition unit 102 acquires a second time distribution of a predetermined operation performed by the user for each of the plurality of users.
　第２時間分布とは、受付部１０１が受け付けた時刻からユーザ毎に求めた所定の操作の時間分布である。 The second time distribution is a time distribution of a predetermined operation obtained for each user from the time received by the receiving unit 101.
　例えば、受付部１０１が、ユーザから複数回行われた所定の操作の各時刻を受け付け、図６の操作履歴テーブル１００ｂに示すように、各ユーザについて複数の所定の操作についての操作時刻が登録されているとすると、取得部１０２は、ユーザ毎に操作の時間分布を求める。 For example, the reception unit 101 receives each time of a predetermined operation performed a plurality of times from the user, and as shown in the operation history table 100b of FIG. 6, operation times for a plurality of predetermined operations are registered for each user. If so, the acquisition unit 102 obtains an operation time distribution for each user.
　図７に、受付部１０１が時刻を受け付けた全ユーザについての、所定のボタンが押圧された時刻の時間分布（第１時間分布）と、ユーザａ－１により所定のボタンが押圧された時刻の時間分布（第２時間分布）との関係の例を示す。図７は、所定のイベントが複数回生じ（イベント１～ｘ（ｘ：任意の自然数。本実施形態では、チームＰが奪った三振の数））、ユーザａ－１は、イベント１、３、・・・、ｘが起きた後、他のユーザが所定のボタンを押圧した時間帯に含まれるタイミングで所定のボタンを押圧し、イベント２が起きた後は、所定のボタンを押圧していないことを示す。 FIG. 7 shows the time distribution (first time distribution) of the time when the predetermined button is pressed and the time when the predetermined button is pressed by the user a-1 for all users whose time has been received by the receiving unit 101. The example of a relationship with time distribution (2nd time distribution) is shown. FIG. 7 shows that a predetermined event occurs a plurality of times (events 1 to x (x: an arbitrary natural number. In this embodiment, the number of strikeouts taken by the team P in this embodiment)) ... after x has occurred, the predetermined button is pressed at a timing included in the time zone when another user pressed the predetermined button, and after event 2, the predetermined button has not been pressed. It shows that.
　算定部１０３は、取得された第１時間分布と、取得された第２時間分布と、の類似度を算定する。 The calculating unit 103 calculates the similarity between the acquired first time distribution and the acquired second time distribution.
　例えば、類似度は以下のように求める。 For example, the similarity is obtained as follows.
　ユーザが視聴している野球の試合時間を１５秒毎の時間区間に区切り、先頭から順に各時間区間に番号０～Ｔ－１を割り当てる。そして、あるユーザｉがある時間区間ｔにて所定の操作を行ったとすると、
　ui,t = 1
とし、あるユーザｉがある時間区間ｔにて所定の操作を行っていなければ、
　ui,t = 0
とする。ここで、uiはＴ次元のベクトルであり、第２時間分布は、uiで表すことができる。 The baseball game time being viewed by the user is divided into time intervals of 15 seconds, and numbers 0 to T-1 are assigned to the time intervals in order from the top. And if a certain user i performs a predetermined operation in a certain time interval t,
u i, t = 1
If a certain user i is not performing a predetermined operation in a certain time interval t,
u i, t = 0
And Here, u i is a T-dimensional vector, and the second time distribution can be represented by u i .
　次に、算定部１０３は、所定の操作の第１時間分布wtを以下のように求める。wはＴ次元のベクトルである。
　wt = Σi ui,t  Next, the calculation unit 103 obtains the first time distribution w t of the predetermined operation as follows. w is a T-dimensional vector.
w t = Σ i u i, t
　ユーザｉによる操作の第２時間分布と、所定の操作の第１時間分布との類似度ciを、ベクトルuiの方向ベクトルとベクトルwの方向ベクトルとの内積で表す。ベクトルuiの長さUiは、
　Ui = (Σt ui,t 2)1/2 
　ベクトルwの長さWは、
　W = (Σt wt 2)1/2 
である。これらから、類似度ciを以下のように求める。
　類似度ci = Σt ui,t×wt / (Ui×W)　・・・（式１） The similarity c i between the second time distribution of the operation by the user i and the first time distribution of the predetermined operation is represented by the inner product of the direction vector of the vector u i and the direction vector of the vector w. The length U i of the vector u i is
U i = (Σ t u i, t 2 ) 1/2
The length W of the vector w is
W = (Σ t w t 2 ) 1/2
It is. From these, the similarity c i is obtained as follows.
Similarity c i = Σ t u i, t × w t / (U i × W) ··· ( Equation 1)
　なお、uiとwの内積そのものを類似度としても良い。 The inner product itself of u i and w may be used as the similarity.
　すなわち、例えば、図７において、他のユーザ達が所定のボタンを押圧した時間区間とユーザａ－１が所定のボタンを押圧した時間区間とが一致する数が大きいほど類似度が高くなる。 That is, for example, in FIG. 7, the similarity increases as the number of coincidence between the time interval in which other users press the predetermined button and the time interval in which the user a-1 presses the predetermined button increases.
　推定部１０４は、類似度に基づいて、類似度にかかる第２時間分布が取得されたユーザが、所定のイベントが生じる体験対象を体験していたか否かを推定する。 The estimation unit 104 estimates, based on the similarity, whether or not the user who has acquired the second time distribution related to the similarity has experienced an experience target in which a predetermined event occurs.
　例えば、推定部１０４は、上記のように求めた、ユーザａ－１について取得された時間分布と、所定の操作の時刻が通知された全ユーザについて取得された時間分布との類似度が所定の閾値以上の場合は、ユーザａ－１が所定のイベント１～ｘが含まれるコンテンツ（野球の試合中継）を体験していたと推定する。 For example, the estimation unit 104 has a predetermined degree of similarity between the time distribution acquired for the user a-1 and the time distribution acquired for all users notified of the time of the predetermined operation. If it is equal to or greater than the threshold value, it is estimated that the user a-1 has experienced content (baseball game relay) including predetermined events 1 to x.
　本実施形態によれば、多くのユーザが所定の操作をした時間帯に、あるユーザも所定の操作をしていれば、あるユーザは、他のユーザが所定の操作を行った原因と同じ原因に反応して、所定の操作を行ったと考えることができ、その原因（所定のイベント）を体験していたと簡易に推定することができる。 According to the present embodiment, if a certain user is also performing a predetermined operation during a time period when many users have performed the predetermined operation, the certain user is the same cause as another user performing the predetermined operation. In response to this, it can be considered that a predetermined operation has been performed, and it can be easily estimated that the cause (predetermined event) was experienced.
　また、一般的に、あるユーザが、所定のイベントをリアルタイムで体験していたか否かを判断するためには、当該イベントが起きた時刻（例えば、本実施形態の野球観戦の例ではチームＰが三振を奪った時刻）等の情報を履歴情報として用意しなければならない。しかし、本実施形態によれば、ある時刻においてあるイベントが起きた等の履歴情報を管理者が用意する必要がなく、ユーザの操作のみに基づいて、所定のイベントをリアルタイムで体験していたか否かを推定することができる。 In general, in order to determine whether or not a user has experienced a predetermined event in real time, the time when the event occurs (for example, in the example of watching a baseball game in this embodiment, the team P Information such as the time when the strikeout was taken) must be prepared as history information. However, according to the present embodiment, it is not necessary for the administrator to prepare history information such as that an event has occurred at a certain time, and whether or not the predetermined event was experienced in real time based only on the user's operation Can be estimated.
　なお、推定装置１００は、各ユーザの端末２００に、所定のイベントが生じた時に所定の操作を行うよう、通知するようにしてもよい。例えば、推定装置１００は、操作を求めるイベントの種類（試合終了の合図、三振、出塁、又は、ホームチームの攻撃回開始等）を指定して、試合開始前に、端末２００に通知する。 Note that the estimation apparatus 100 may notify each user's terminal 200 to perform a predetermined operation when a predetermined event occurs. For example, the estimation apparatus 100 designates the type of event for which an operation is requested (game end signal, strikeout, start, or start of home team attack, etc.) and notifies the terminal 200 before the game starts.
　また、端末２００から、所定の操作を行った時刻が直ちに送信され、推定装置１００は、所定の操作を行った時刻を受け付けると、直ちに集計して、所定の操作の時間分布や、最近の所定秒数内に受け付けた時刻（すなわち、所定の操作）の数を端末２００に表示させるようにしてもよい。 In addition, the time at which the predetermined operation is performed is immediately transmitted from the terminal 200, and when the estimation apparatus 100 accepts the time at which the predetermined operation is performed, the estimation apparatus 100 immediately counts and calculates the time distribution of the predetermined operation or the most recent predetermined time. You may make it display the number of time (namely, predetermined operation) received within the number of seconds on the terminal 200.
　また、推定装置１００は、所定の操作の数が急に増加したことを検知して、ユーザの端末２００に、その旨を通知するようにしてもよい。例えば、スマートフォンのアプリから所定の操作を受け付けている場合、他のユーザによる所定の操作の数が急に多くなると、推定装置１００は、スマートフォンのアプリを起動していないユーザのスマートフォンに、所定の操作が急に増加した時刻付近のテレビの静止画像を伴うプッシュ通知を行うようにしてもよい。このような構成によれば、アプリを起動し、テレビの視聴に誘導することができる。 Further, the estimating apparatus 100 may detect that the number of predetermined operations has suddenly increased and notify the user's terminal 200 to that effect. For example, when a predetermined operation is received from a smartphone application and the number of predetermined operations by other users suddenly increases, the estimation apparatus 100 applies a predetermined operation to a smartphone of a user who has not activated the smartphone application. You may make it perform the push notification accompanied with the still image of the television near the time when operation increased suddenly. According to such a structure, an application can be started and it can be induced to watch TV.
（４．実施形態１の推定装置の動作）
　本実施形態の推定装置１００の動作について説明する。推定装置１００は、例えば、電源が投入されると、図８に示す推定処理を開始する。 (4. Operation of estimation apparatus of embodiment 1)
Operation | movement of the estimation apparatus 100 of this embodiment is demonstrated. For example, when the power is turned on, the estimation apparatus 100 starts the estimation process illustrated in FIG.
　受付部１０１は、複数のユーザのそれぞれが使用する端末２００においてユーザが所定の操作を行った時刻を、各端末２００から受け付けたか否かを判断する（ステップＳ１０１）。受付部１０１は、所定の操作を行った時刻を受け付けたと判断すると（ステップＳ１０１；Ｙｅｓ）、受け付けた時刻を登録する（ステップＳ１０２）。一方、受付部１０１は、所定の操作を行った時刻を受け付けていないと判断すると（ステップＳ１０１；Ｎｏ）、そのまま待機する。 The accepting unit 101 determines whether or not the time when the user performed a predetermined operation on the terminal 200 used by each of the plurality of users has been accepted from each terminal 200 (step S101). If the reception unit 101 determines that the time when the predetermined operation is performed is received (step S101; Yes), the reception time is registered (step S102). On the other hand, if the reception unit 101 determines that the time when the predetermined operation is performed is not received (step S101; No), the reception unit 101 waits as it is.
　例えば、受付部１０１が、ユーザａ－１の端末２００から、ユーザａ－１が所定の操作を行った時刻を受け付けると、図４の操作履歴テーブル１００ａに受け付けた時刻を登録する。一方、受付部１０１が、いずれの端末２００からも時刻を受け付けない場合は、そのまま待機する。 For example, when the reception unit 101 receives the time when the user a-1 performed a predetermined operation from the terminal 200 of the user a-1, the time received is registered in the operation history table 100a of FIG. On the other hand, when the reception unit 101 does not receive the time from any of the terminals 200, it waits as it is.
　推定装置１００は、ユーザが所定の操作に予め対応付けられたイベントを体験していたか否かの推定を実行する指示を受け付けたか否かを判断する（ステップＳ１０３）。推定装置１００が、推定を実行するよう指示を受け付けたと判断すると（ステップＳ１０３；Ｙｅｓ）、取得部１０２は、受け付けた時刻から、所定の操作の第１時間分布を取得する（ステップＳ１０４）。一方、推定装置１００が、推定を実行するよう指示を受け付けていないと判断すると（ステップＳ１０３；Ｎｏ）、ステップＳ１０１に戻る。なお、所定のイベントが複数回生じる場合は、ステップＳ１０４において、取得部１０２は、複数のユーザのそれぞれについて、ユーザが行った所定の操作の第２時間分布を取得するようにしてもよい。 The estimating apparatus 100 determines whether or not an instruction to execute an estimation as to whether or not the user has experienced an event previously associated with a predetermined operation has been received (step S103). When the estimation apparatus 100 determines that an instruction to perform estimation is received (step S103; Yes), the acquisition unit 102 acquires a first time distribution of a predetermined operation from the received time (step S104). On the other hand, if the estimation apparatus 100 determines that it has not received an instruction to perform estimation (step S103; No), the process returns to step S101. If the predetermined event occurs a plurality of times, in step S104, the acquisition unit 102 may acquire the second time distribution of the predetermined operation performed by the user for each of the plurality of users.
　例えば、推定装置１００の管理者が、ユーザａ－１が所定のイベントを体験していたか否かを推定するよう、推定装置１００に指示したとすると、取得部１０２は、図４の操作履歴テーブル１００ａを参照して、ユーザａ－１～ａ－ｎａの操作時刻から、所定の操作の第１時間分布を取得する。一方、管理者から指示を受け付けない場合は、ステップＳ１０１に戻る。なお、取得部１０２は、図６の操作履歴テーブル１００ｂに示すように、各ユーザについて複数の所定の操作についての操作時刻が登録されている場合は、取得部１０２は、ユーザ毎に操作時刻の時間分布（第２時間分布）を求めるようにしてもよい。 For example, if the administrator of the estimation apparatus 100 instructs the estimation apparatus 100 to estimate whether or not the user a-1 has experienced a predetermined event, the acquisition unit 102 may display the operation history table in FIG. Referring to 100a, the first time distribution of a predetermined operation is acquired from the operation times of users a-1 to a-na. On the other hand, when the instruction is not received from the administrator, the process returns to step S101. As shown in the operation history table 100b of FIG. 6, when the operation time for a plurality of predetermined operations is registered for each user, the acquisition unit 102 acquires the operation time for each user. A time distribution (second time distribution) may be obtained.
　算定部１０３は、取得された第１時間分布と、各端末２００から受け付けた時刻と、の一致度、或いは、取得された第１時間分布と、取得された第２時間分布と、の類似度を算定する（ステップＳ１０５）。 The calculating unit 103 matches the degree of coincidence between the acquired first time distribution and the time received from each terminal 200, or the degree of similarity between the acquired first time distribution and the acquired second time distribution. Is calculated (step S105).
　例えば、算定部１０３は、ユーザａ－１の操作時刻が、受付部１０１が受け付けた時刻全体から取得した第１時間分布のどの位置に属するか否かを判断することにより一致度を算定する。ユーザ毎に操作時刻の時間分布が求められた場合は、算定部１０３は、ユーザａ－１による所定の操作の時間分布と、受付部１０１が時刻を受け付けた全ユーザについての所定の操作の時間分布と類似度を、（式１）により求める。 For example, the calculation unit 103 calculates the degree of coincidence by determining to which position of the first time distribution acquired from the entire time received by the receiving unit 101 the operation time of the user a-1 belongs. When the time distribution of the operation time is obtained for each user, the calculation unit 103 calculates the time distribution of the predetermined operation by the user a-1 and the time of the predetermined operation for all the users for which the reception unit 101 has received the time. Distribution and similarity are obtained by (Equation 1).
　推定部１０４は、一致度に基づいて、受け付けた時刻に所定の操作を行ったユーザが、所定の操作に予め対応付けられた所定のイベントを体験していたか否か、或いは、類似度に基づいて、類似度にかかる時間分布が取得されたユーザが、所定のイベントが生じる体験対象を体験していたか否かを推定する（ステップＳ１０６）。 Based on the degree of coincidence, the estimation unit 104 determines whether a user who has performed a predetermined operation at the received time has experienced a predetermined event associated with the predetermined operation in advance, or based on the similarity Thus, it is estimated whether or not the user who has acquired the time distribution related to the degree of similarity has experienced the experience object in which the predetermined event occurs (step S106).
　例えば、推定部１０４は、ユーザａ－１の操作時刻が、取得された第１時間分布において標準偏差の±２の範囲に収まる場合、ユーザａ－１は所定のイベントを体験していたと推定する。或いは、推定部１０４は、ユーザａ－１について取得された時間分布と、受付部１０１が時刻を受け付けた全ユーザについて取得された時間分布との類似度が所定の閾値以上の場合は、ユーザａ－１が所定のイベントが生じる体験対象を体験していたと推定する。 For example, when the operation time of the user a-1 falls within the range of ± 2 of the standard deviation in the acquired first time distribution, the estimation unit 104 estimates that the user a-1 has experienced a predetermined event. . Alternatively, when the similarity between the time distribution acquired for the user a-1 and the time distribution acquired for all users whose reception unit 101 has received time is equal to or greater than a predetermined threshold, the estimation unit 104 determines that the user a -1 is estimated to have experienced the experience object in which the predetermined event occurs.
（５．実施形態２に係る推定装置の概要構成）
　推定装置１００は、図９に示すように、受付部１０１と、取得部１０２と、算定部１０３と、推定部１０４と、割当部１０５と、から構成される。 (5. Outline configuration of estimation apparatus according to Embodiment 2)
As illustrated in FIG. 9, the estimation device 100 includes a reception unit 101, an acquisition unit 102, a calculation unit 103, an estimation unit 104, and an allocation unit 105.
　実施形態２において、算定部１０３及び推定部１０４は実施形態１と同様の機能を有する。以下、受付部１０１及び取得部１０２の実施形態１と異なる機能又は追加される機能、並びに、割当部１０５の機能について説明する。 In the second embodiment, the calculation unit 103 and the estimation unit 104 have the same functions as those in the first embodiment. Hereinafter, functions different from or added to the first embodiment of the reception unit 101 and the acquisition unit 102 and functions of the allocation unit 105 will be described.
　本実施形態において、ＣＰＵ　６０１及びＮＩＣ　６０５が協働して、割当部１０５として機能する。 In the present embodiment, the CPU 601 and the NIC 605 cooperate to function as the allocation unit 105.
　割当部１０５は、各端末２００が、所定の操作が行われた時刻から推定装置１００へ所定の操作が行われた旨を報告するまでの余裕時間を、各端末２００にランダムに割り当てる。 The assigning unit 105 randomly assigns to each terminal 200 a margin time until each terminal 200 reports that the predetermined operation has been performed to the estimation apparatus 100 from the time when the predetermined operation was performed.
　余裕時間とは、端末２００において所定の操作が行われた旨を、所定の操作が行われた時刻から、推定装置１００へ報告するまでの時間である。 The margin time is the time from when the predetermined operation is performed at the terminal 200 until the time when the predetermined operation is reported to the estimation apparatus 100.
　例えば、割当部１０５は、ユーザａ－１～ａ－ｎａの端末２００に、０秒～１２０秒の余裕時間をランダムに割り当てる。 For example, the assigning unit 105 randomly assigns a margin time of 0 to 120 seconds to the terminals 200 of the users a-1 to a-na.
　受付部１０１は、余裕時間経過後に報告される所定の操作が行われた旨の報告を、各端末２００から受け付ける。 The accepting unit 101 accepts from each terminal 200 a report that a predetermined operation reported after the allowance time has elapsed.
　例えば、ユーザａ－１に割り当てられた余裕時間が５秒であるとすると、ユーザａ－１の端末２００から、ユーザａ－１が所定の操作を行った時刻（１８時００時０５秒）から５秒後（１８時００時１０秒）に所定の操作が行われた旨の報告が送信され、受付部１０１は、ユーザａ－１の端末２００から、この報告を受け付ける。また、受付部１０１は、ユーザａ－１の端末２００から、ユーザａ－１が所定の操作が行った時刻を受け付ける。 For example, if the margin time allocated to the user a-1 is 5 seconds, from the time when the user a-1 performed a predetermined operation (18:00:05) from the terminal 200 of the user a-1. After 5 seconds (18:00:10), a report indicating that a predetermined operation has been performed is transmitted, and the receiving unit 101 receives this report from the terminal 200 of the user a-1. In addition, the reception unit 101 receives the time at which the user a-1 performed a predetermined operation from the terminal 200 of the user a-1.
　受付部１０１は、ユーザの端末２００から報告及び所定の操作の時刻を受け付けると、例えば、図１０の操作履歴テーブル１００ｃに、報告が到着した時刻及び操作時刻を登録する。また、割当部１０５は、各ユーザに余裕時間を割り当てると、図１０の操作履歴テーブル１００ｃに余裕時間を登録する。操作履歴テーブル１００ｃには、ユーザＩＤ　１００ｃ１と、割り当てられた余裕時間１００ｃ２と、報告を受け付けた時刻を示す報告到着時刻１００ｃ３と、所定の操作が行われた時刻を示す操作時刻１００ｃ４と、が対応付けて登録されている。 When the reception unit 101 receives a report and a predetermined operation time from the user's terminal 200, for example, the reception unit 101 registers the time when the report arrived and the operation time in the operation history table 100c of FIG. Moreover, when the allocation unit 105 allocates a margin time to each user, the allocation unit 105 registers the margin time in the operation history table 100c of FIG. The operation history table 100c corresponds to the user ID 100c1, the allocated margin time 100c2, the report arrival time 100c3 indicating the time when the report is received, and the operation time 100c4 indicating the time when the predetermined operation is performed. It is registered with it.
　取得部１０２は、所定の操作が行われた旨の報告を受け付けた時刻から、所定の操作が行われた旨の報告の第３時間分布と、推定装置１００へのアクセスの集中度と、を取得する。 The acquisition unit 102 obtains the third time distribution of the report indicating that the predetermined operation has been performed and the concentration level of access to the estimation apparatus 100 from the time when the report indicating that the predetermined operation has been received is received. get.
　すなわち、第１時間分布は、時刻を受け付けた全ユーザによる所定の操作の時刻の時間分布であり、第２時間分布は、体験対象を体験していたか否かの推定を行う対象となるユーザによる所定の操作の時刻の時間分布であり、第３時間分布は、所定の操作が行われた旨の報告を受け付けた全ユーザについて取得した当該報告を受け付けた時刻の時間分布である。 That is, the first time distribution is a time distribution of a predetermined operation time by all the users who have received the time, and the second time distribution is determined by a user who is an object for estimating whether or not the experience object is experienced. It is a time distribution of the time of a predetermined operation, and the third time distribution is a time distribution of the time at which the report acquired for all users who have received a report indicating that the predetermined operation has been received.
　例えば、取得部１０２は、図１０の操作履歴テーブル１００ｃを参照して、ユーザａ－１～ａ－ｎａの操作時刻の第１時間分布（図１１の時間分布４０１）及び報告到着時刻の第３時間分布（図１１の時間分布４０２）を求める。そして、取得部１０２は、報告到着時刻の時間分布から推定装置１００へのアクセス（報告）の集中度を求める。アクセスの集中度は、例えば、１分間に何件の報告を受け付けたかによって表す。 For example, the acquisition unit 102 refers to the operation history table 100c in FIG. 10, and the first time distribution (time distribution 401 in FIG. 11) of the operation times of the users a-1 to a-na and the third of the report arrival times. A time distribution (time distribution 402 in FIG. 11) is obtained. Then, the acquisition unit 102 obtains the degree of concentration of access (report) to the estimation apparatus 100 from the time distribution of report arrival times. The degree of access concentration is represented by, for example, how many reports are received per minute.
　割当部１０５は、アクセスの集中度を限界閾値以下に抑えつつ、第１時間分布と、第３時間分布とのずれが小さくなるように、余裕時間を調節する。 The allocating unit 105 adjusts the margin time so that the deviation between the first time distribution and the third time distribution becomes small while keeping the access concentration level below the limit threshold.
　限界閾値とは、アクセスの集中度の上限となる値であり、アクセスの集中度をこの値以下にすることが求められる値である。例えば、推定装置１００の管理者により、システムのアクセス許容度等を考慮して指定される。 The limit threshold is a value that is the upper limit of access concentration, and is a value that requires the access concentration to be less than or equal to this value. For example, it is specified by the administrator of the estimation apparatus 100 in consideration of the system access tolerance and the like.
　例えば、割当部１０５は、ユーザａ－１～ａ－ｎａの報告到着時刻の時間分布４０２（図１１）のピークを、限界閾値以下に収まるようにしつつ、ユーザａ－１～ａ－ｎａによる所定の操作時刻の時間分布４０１（図１１）と、ユーザａ－１～ａ－ｎａからの報告到着時刻の時間分布４０２（図１１）とのずれ５００（図１１）が小さくなるように、余裕時間を調節する。 For example, the allocating unit 105 determines the peak of the time distribution 402 (FIG. 11) of the report arrival times of the users a-1 to a-na within a predetermined threshold by the users a-1 to a-na. The margin time is set so that the deviation 500 (FIG. 11) between the time distribution 401 (FIG. 11) of the operation time and the time distribution 402 (FIG. 11) of the report arrival times from the users a-1 to a-na becomes small. Adjust.
　本実施形態によれば、推定装置１００へのアクセスの集中度を制御し、かつ、報告を受ける時刻を実際の操作時刻に近づけることができる。これにより、推定装置１００への過剰なアクセスを防ぎつつ、ユーザの操作に基づき、ユーザが所定のイベント又は体験対象を体験していたか否かの推定を行うことができる。 According to the present embodiment, it is possible to control the degree of concentration of access to the estimation apparatus 100 and to make the time for receiving reports closer to the actual operation time. Thereby, it is possible to estimate whether or not the user has experienced a predetermined event or experience object based on the user's operation while preventing excessive access to the estimation device 100.
　なお、端末２００は、所定の操作の時刻（操作時刻）から余裕時間後に推定装置１００に報告を行うので、操作時刻は、推定装置１００に報告が到着した時刻（報告到着時刻）より余裕時間前と考えられる。したがって、端末２００における時刻合わせを省くことができる。また、報告到着時刻より余裕時間前の時刻を操作時刻とみなす場合は、端末２００から操作時刻が送信されない構成としてもよい。 Since terminal 200 reports to estimation apparatus 100 after a margin time from a predetermined operation time (operation time), the operation time is before the margin time before the time when the report arrives at estimation apparatus 100 (report arrival time). it is conceivable that. Therefore, time adjustment at the terminal 200 can be omitted. In addition, when the time before the report arrival time is regarded as the operation time, the operation time may not be transmitted from the terminal 200.
　また、ユーザが端末２００の時計の時刻をずらして、操作時刻に不正を加えたとしても、報告到着時刻から余裕時間前を操作時刻として用いることにより、このような不正行為を無効化することができ、安易なチート行為を防止することもできる。 Further, even if the user shifts the time of the clock of the terminal 200 and adds fraud to the operation time, it is possible to invalidate such fraud by using the time before the report arrival time as the operation time. It can also prevent easy cheating.
　また、推定装置１００へのアクセスが集中して、推定装置１００に報告が到着した旨を端末２００に連絡する応答パケットが、端末２００に到着しない場合、端末２００が自律的に余裕時間を大きくするようにしてもよい。そして、推定装置１００に報告が到着した時点で、推定装置１００は、アクセスの集中度を勘案して、当該端末２００に対する余裕時間を再設定するようにしてもよい。 Further, when the access to the estimation apparatus 100 is concentrated and the response packet for notifying the terminal 200 that the report has arrived at the estimation apparatus 100 does not arrive at the terminal 200, the terminal 200 autonomously increases the margin time. You may do it. Then, when the report arrives at the estimation apparatus 100, the estimation apparatus 100 may reset the margin time for the terminal 200 in consideration of the degree of access concentration.
　また、スマートフォンにおいて所定の操作が行われる場合は、アプリ起動時に推定装置１００にアクセスし、推定装置１００はアクセスした端末２００に対し余裕時間を割り当てるようにしてもよい。 In addition, when a predetermined operation is performed on the smartphone, the estimation device 100 may be accessed when the application is activated, and the estimation device 100 may allocate a spare time to the accessed terminal 200.
　このような構成によれば、推定装置１００は、所定の操作の報告を受ける可能性のある総数を把握することができ、アクセスの集中度合いを予測することが可能となる。 According to such a configuration, the estimating apparatus 100 can grasp the total number that may receive a report of a predetermined operation, and can predict the degree of access concentration.
　また、アプリ起動時に推定装置１００との通信ができない場合には、端末２００側で、アクセスの集中度を高めないように、余裕時間を大きめに設定するようにしてもよい。 In addition, when communication with the estimation apparatus 100 is not possible when the application is activated, the margin time may be set longer on the terminal 200 side so as not to increase the concentration of access.
　また、各端末２００から受け付けた所定の操作が行われた時刻は、各端末２００の時計で計測された時刻とし、算定部１０３は、各端末２００で計測された所定の操作の時刻と、所定の操作が行われた旨の報告を受け付けた時刻と、の差を求めるようにしてもよい。 In addition, the time when the predetermined operation received from each terminal 200 is performed is the time measured by the clock of each terminal 200, and the calculation unit 103 determines the time of the predetermined operation measured by each terminal 200 and the predetermined time. You may make it obtain | require the difference with the time which received the report to the effect of having been performed.
　例えば、操作履歴テーブル１００ｃ（図１０）の操作時刻１００ｃ４は、各端末２００の時計で計測された時刻である。なお、推定装置１００及び端末２００は、日本標準時等と時刻合わせがされていることとする。 For example, the operation time 100c4 of the operation history table 100c (FIG. 10) is a time measured by the clock of each terminal 200. It is assumed that the estimation device 100 and the terminal 200 are set in time with Japan Standard Time or the like.
　例えば、算定部１０３は、操作履歴テーブル１００ｃ（図１０）の報告到着時刻１００ｃ３と、操作時刻１００ｃ４と、の差を求める。差が、割り当てた余裕時間より大きい場合は、通信遅延が生じていると考えられる。また、求められた差を、例えば、ＩＳＰ（Internet Services Provider）毎や基地局毎に分類してもよい。 For example, the calculation unit 103 obtains the difference between the report arrival time 100c3 and the operation time 100c4 in the operation history table 100c (FIG. 10). If the difference is larger than the allocated margin time, it is considered that a communication delay has occurred. Further, the obtained difference may be classified, for example, for each ISP (Internet Services 基地 Provider) or each base station.
　このような構成によれば、遅延テストを行うことができる。 According to such a configuration, a delay test can be performed.
（６．実施形態２の推定装置の動作）
　実施形態２の推定装置１００の動作について説明する。推定装置１００は、例えば、電源が投入されると、図１２に示す推定処理を開始する。なお、図１２のフローチャートのステップＳ２０４、Ｓ２０６、Ｓ２０７の処理は、図８のフローチャートのステップＳ１０３、Ｓ１０５、Ｓ１０６の処理と同様である。したがって、これらの処理については省略する。 (6. Operation of estimation apparatus of embodiment 2)
Operation | movement of the estimation apparatus 100 of Embodiment 2 is demonstrated. For example, when the power is turned on, the estimation apparatus 100 starts the estimation process illustrated in FIG. Note that the processing in steps S204, S206, and S207 in the flowchart in FIG. 12 is the same as the processing in steps S103, S105, and S106 in the flowchart in FIG. Therefore, these processes are omitted.
　各端末２００が、所定の操作が行われた時刻から推定装置１００へ所定の操作が行われた旨を報告するまでの余裕時間を、各端末のそれぞれにランダムに割り当てる（ステップＳ２０１）。 Each terminal 200 randomly allocates a surplus time from the time when the predetermined operation is performed until it reports to the estimation apparatus 100 that the predetermined operation has been performed (step S201).
　例えば、割当部１０５は、ユーザａ－１～ａ－ｎａの端末２００に、０秒～１２０秒の余裕時間をランダムに割り当てる。また、割当部１０５は、各ユーザに余裕時間を割り当てると、図１０の操作履歴テーブル１００ｃに余裕時間を登録する。 For example, the assigning unit 105 randomly assigns a margin time of 0 to 120 seconds to the terminals 200 of the users a-1 to a-na. Moreover, when the allocation unit 105 allocates a margin time to each user, the allocation unit 105 registers the margin time in the operation history table 100c of FIG.
　受付部１０１は、各端末２００から、余裕時間経過後に報告される所定の操作が行われた旨の報告、及び、ユーザが所定の操作を行った時刻を受け付けたか否かを判断する（ステップＳ２０２）。受付部１０１は、所定の操作が行われた旨の報告及び所定の操作を行った時刻を受け付けたと判断すると（ステップＳ２０２；Ｙｅｓ）、所定の操作が行われた旨の報告の到着時刻（報告到着時刻）及び所定の操作を行った時刻（操作時刻）を登録する（ステップＳ２０３）。一方、受付部１０１は、所定の操作が行われた旨の報告及び所定の操作を行った時刻を受け付けていないと判断すると（ステップＳ２０２；Ｎｏ）、そのまま待機する。 The receiving unit 101 determines from each terminal 200 whether a report indicating that a predetermined operation reported after the allowance time has elapsed and a time when the user performed the predetermined operation has been received (step S202). ). When the reception unit 101 determines that the report indicating that the predetermined operation has been performed and the time when the predetermined operation has been received (step S202; Yes), the arrival time of the report indicating that the predetermined operation has been performed (report) Arrival time) and time (operation time) at which a predetermined operation is performed are registered (step S203). On the other hand, if the reception unit 101 determines that it has not received a report that a predetermined operation has been performed and the time at which the predetermined operation has been performed (step S202; No), the reception unit 101 waits as it is.
　例えば、受付部１０１が、ユーザａ－１の端末２００から、所定の操作を行った旨の報告及びユーザａ－１が所定の操作を行った時刻（操作時刻）を受け付けると、図１０の操作履歴テーブル１００ｃに、当該報告が到着した報告到着時刻と操作時刻とを登録する。一方、受付部１０１が、いずれの端末２００からも報告及び時刻を受け付けない場合は、そのまま待機する。 For example, when the reception unit 101 receives a report indicating that a predetermined operation has been performed from the terminal 200 of the user a-1 and a time when the user a-1 has performed the predetermined operation (operation time), the operation illustrated in FIG. Report arrival time and operation time when the report arrived are registered in the history table 100c. On the other hand, when the reception unit 101 does not receive a report and time from any terminal 200, the reception unit 101 waits as it is.
　推定装置１００が、推定を実行するよう指示を受け付けたと判断すると（ステップＳ２０４；Ｙｅｓ）、取得部１０２は、受け付けた所定の操作の時刻から第１時間分布を取得し、所定の操作が行われた旨の報告を受け付けた時刻から、第３時間分布を取得する（ステップＳ２０５）。 When the estimation apparatus 100 determines that an instruction to execute estimation has been received (step S204; Yes), the acquisition unit 102 acquires the first time distribution from the time of the received predetermined operation, and the predetermined operation is performed. The third time distribution is acquired from the time when the report to the effect is received (step S205).
　例えば、取得部１０２は、図１０の操作履歴テーブル１００ｃを参照して、ユーザａ－１～ａ－ｎａの操作時刻の第１時間分布（図１１の時間分布４０１）及び報告到着時刻の第３時間分布（図１１の時間分布４０２）を求める。 For example, the acquisition unit 102 refers to the operation history table 100c in FIG. 10, and the first time distribution (time distribution 401 in FIG. 11) of the operation times of the users a-1 to a-na and the third of the report arrival times. A time distribution (time distribution 402 in FIG. 11) is obtained.
　ステップＳ２０７において推定が行われたあと、取得部１０２は、報告到着時刻の第３時間分布から推定装置１００へのアクセスの集中度を取得する（ステップＳ２０８）。 After the estimation is performed in step S207, the acquisition unit 102 acquires the degree of concentration of access to the estimation device 100 from the third time distribution of the report arrival time (step S208).
　例えば、取得部１０２は、報告到着時刻の第３時間分布（図１１の時間分布４０２）から推定装置１００へのアクセスの集中度を求める。 For example, the acquisition unit 102 obtains the degree of concentration of access to the estimation apparatus 100 from the third time distribution (time distribution 402 in FIG. 11) of the report arrival time.
　割当部１０５は、アクセスの集中度を限界閾値以下に抑えつつ、所定の第１時間分布と、第３時間分布とのずれが小さくなるように、余裕時間を調節する（ステップＳ２０９）。 The allocating unit 105 adjusts the margin time so that the difference between the predetermined first time distribution and the third time distribution is reduced while suppressing the access concentration level to a threshold value or less (step S209).
　例えば、割当部１０５は、ユーザａ－１～ａ－ｎａの報告到着時刻の時間分布４０２（図１１）のピークを、限界閾値以下に収まるようにしつつ、ユーザａ－１～ａ－ｎａの操作時刻の時間分布４０１（図１１）と、ユーザａ－１～ａ－ｎａからの報告到着時刻の時間分布４０２（図１１）とのずれ５００（図１１）が小さくなるように、余裕時間を調節する。 For example, the assigning unit 105 operates the users a-1 to a-na while keeping the peak of the time distribution 402 (FIG. 11) of the report arrival times of the users a-1 to a-na within the limit threshold. The margin time is adjusted so that the difference 500 (FIG. 11) between the time distribution 401 (FIG. 11) of the time and the time distribution 402 (FIG. 11) of the report arrival times from the users a-1 to a-na becomes small. To do.
　本発明は、本発明の広義の精神と範囲を逸脱することなく、様々な実施の形態及び変形が可能とされるものである。また、上述した実施の形態は、この発明を説明するためのものであり、本発明の範囲を限定するものではない。すなわち、本発明の範囲は、実施の形態ではなく、特許請求の範囲によって示される。そして、特許請求の範囲内及びそれと同等の発明の意義の範囲内で施される様々な変形が、この発明の範囲内とみなされる。 The present invention is capable of various embodiments and modifications without departing from the broad spirit and scope of the present invention. The above-described embodiments are for explaining the present invention and do not limit the scope of the present invention. In other words, the scope of the present invention is shown not by the embodiments but by the claims. Various modifications within the scope of the claims and within the scope of the equivalent invention are considered to be within the scope of the present invention.
１００　推定装置
１０１　受付部
１０２　取得部
１０３　算定部
１０４　推定部
１０５　割当部
２００　端末
３００　インターネット
４０１、４０２　時間分布
５００　ずれ
６００　情報処理装置
６０１　ＣＰＵ
６０２　ＲＯＭ
６０３　ＲＡＭ
６０４　記憶装置
６０５　ＮＩＣ
６０６　画像処理部
６０７　音声処理部
６０８　ディスプレイ
６０９　スピーカ
６１０　コントローラ DESCRIPTION OF SYMBOLS 100 Estimation apparatus 101 Reception part 102 Acquisition part 103 Calculation part 104 Estimation part 105 Allocation part 200 Terminal 300 Internet 401, 402 Time distribution 500 Deviation 600 Information processing apparatus 601 CPU
602 ROM
603 RAM
604 Storage device 605 NIC
606 Image processing unit 607 Audio processing unit 608 Display 609 Speaker 610 Controller

Claims (7)

  1. 　複数のユーザのそれぞれが使用する端末において前記ユーザが所定の操作を行った時刻を、前記各端末から受け付ける受付部と、
    　前記受け付けた時刻から、前記所定の操作の第１時間分布を取得する取得部と、
    　前記取得された第１時間分布と、前記各端末から受け付けた時刻と、の一致度を算定する算定部と、
    　前記一致度に基づいて、前記複数のユーザのそれぞれが、前記所定の操作に予め対応付けられた所定のイベントを体験していたか否かを推定する推定部と、
    　を備えることを特徴とする推定装置。     A reception unit that receives the time at which the user performs a predetermined operation on the terminal used by each of the plurality of users from each of the terminals;
    An acquisition unit for acquiring a first time distribution of the predetermined operation from the received time;
    A calculating unit that calculates the degree of coincidence between the acquired first time distribution and the time received from each terminal;
    An estimation unit that estimates whether each of the plurality of users has experienced a predetermined event associated with the predetermined operation based on the degree of coincidence;
    An estimation apparatus comprising:
  2. 　前記所定のイベントは、複数回生じるものであって、
    　前記受付部は、前記複数のユーザのそれぞれが行った前記所定の操作の時刻を、前記各端末から受け付け、
    　前記取得部は、前記複数のユーザのそれぞれについて、前記ユーザが行った前記所定の操作の第２時間分布を取得し、
    　前記算定部は、前記取得された第１時間分布と、前記取得された第２時間分布と、の類似度を算定し、
    　前記推定部は、前記類似度に基づいて、前記類似度にかかる前記第２時間分布が取得されたユーザが、前記所定のイベントが生じる体験対象を体験していたか否かを推定する
    　ことを特徴とする請求項１に記載の推定装置。     The predetermined event occurs a plurality of times,
    The reception unit receives time of the predetermined operation performed by each of the plurality of users from each terminal,
    The acquisition unit acquires a second time distribution of the predetermined operation performed by the user for each of the plurality of users.
    The calculating unit calculates a similarity between the acquired first time distribution and the acquired second time distribution;
    The estimation unit estimates, based on the similarity, whether or not the user who has acquired the second time distribution related to the similarity has experienced the experience target in which the predetermined event occurs. The estimation apparatus according to claim 1.
  3. 　前記各端末が、前記所定の操作が行われた時刻から前記推定装置へ前記所定の操作が行われた旨を報告するまでの余裕時間を、前記各端末にランダムに割り当てる割当部
    　をさらに備え、
    　前記受付部は、前記余裕時間経過後に報告される前記所定の操作が行われた旨の報告を、前記各端末から受け付け、
    　前記取得部は、前記所定の操作が行われた旨の報告を受け付けた時刻から、前記所定の操作が行われた旨の報告の第３時間分布と、前記推定装置へのアクセスの集中度と、を取得し、
    　前記割当部は、前記アクセスの集中度を限界閾値以下に抑えつつ、前記第１時間分布と、前記第３時間分布とのずれが小さくなるように、前記余裕時間を調節する
    　ことを特徴とする請求項１に記載の推定装置。     An allocation unit that randomly allocates each terminal with a margin time from the time when the predetermined operation is performed until the terminal reports the fact that the predetermined operation has been performed to the estimation device;
    The reception unit receives a report that the predetermined operation reported after the allowance time has elapsed from each terminal,
    The acquisition unit, from the time when the report indicating that the predetermined operation has been received is received, a third time distribution of the report indicating that the predetermined operation has been performed, and the degree of concentration of access to the estimation device, Get the
    The allocating unit adjusts the margin time so as to reduce a difference between the first time distribution and the third time distribution while suppressing the access concentration to a threshold value or less. The estimation apparatus according to claim 1.
  4. 　前記各端末から受け付けた前記所定の操作が行われた時刻は、前記各端末の時計で計測された時刻であり、
    　前記算定部は、前記各端末で計測された前記所定の操作の時刻と、前記所定の操作が行われた旨の報告を受け付けた時刻と、の差を求める
    　ことを特徴とする請求項３に記載の推定装置。     The time when the predetermined operation received from each terminal is performed is the time measured by the clock of each terminal,
    The said calculation part calculates | requires the difference of the time of the said predetermined operation measured in each said terminal, and the time which received the report that the said predetermined operation was performed. The estimation device described.
  5. 　推定装置が実行する推定方法であって、
    　前記推定装置が、複数のユーザのそれぞれが使用する端末において前記ユーザが所定の操作を行った時刻を、前記各端末から受け付ける受付工程と、
    　前記推定装置が、前記受け付けた時刻から、前記所定の操作の第１時間分布を取得する取得工程と、
    　前記推定装置が、前記取得された第１時間分布と、前記各端末から受け付けた時刻と、の一致度を算定する算定工程と、
    　前記推定装置が、前記一致度に基づいて、前記複数のユーザのそれぞれが、前記所定の操作に予め対応付けられた所定のイベントを体験していたか否かを推定する推定工程と、
    　を備えることを特徴とする推定方法。     An estimation method executed by an estimation device,
    An accepting step for accepting, from each of the terminals, the time when the user performed a predetermined operation on the terminal used by each of the plurality of users by the estimation device;
    An obtaining step in which the estimation device obtains a first time distribution of the predetermined operation from the accepted time;
    A calculation step in which the estimation device calculates a degree of coincidence between the acquired first time distribution and the time received from each terminal;
    An estimation step in which the estimation device estimates whether each of the plurality of users has experienced a predetermined event previously associated with the predetermined operation based on the degree of coincidence;
    An estimation method comprising:
  6. 　コンピュータを、
    　複数のユーザのそれぞれが使用する端末において前記ユーザが所定の操作を行った時刻を、前記各端末から受け付ける受付部、
    　前記受け付けた時刻から、前記所定の操作の第１時間分布を取得する取得部、
    　前記取得された第１時間分布と、前記各端末から受け付けた時刻と、の一致度を算定する算定部、
    　前記一致度に基づいて、前記複数のユーザのそれぞれが、前記所定の操作に予め対応付けられた所定のイベントを体験していたか否かを推定する推定部、
    　として機能させることを特徴とするプログラム。     Computer
    A receiving unit that receives, from each terminal, a time at which the user performs a predetermined operation in a terminal used by each of a plurality of users;
    An acquisition unit for acquiring a first time distribution of the predetermined operation from the received time;
    A calculation unit that calculates the degree of coincidence between the acquired first time distribution and the time received from each terminal;
    An estimation unit that estimates whether each of the plurality of users has experienced a predetermined event previously associated with the predetermined operation based on the degree of coincidence,
    A program characterized by functioning as
  7. 　コンピュータを、
    　複数のユーザのそれぞれが使用する端末において前記ユーザが所定の操作を行った時刻を、前記各端末から受け付ける受付部、
    　前記受け付けた時刻から、前記所定の操作の第１時間分布を取得する取得部、
    　前記取得された第１時間分布と、前記各端末から受け付けた時刻と、の一致度を算定する算定部、
    　前記一致度に基づいて、前記複数のユーザのそれぞれが、前記所定の操作に予め対応付けられた所定のイベントを体験していたか否かを推定する推定部、
    　として機能させることを特徴とするプログラムを記録する非一時的なコンピュータ読取可能な情報記録媒体。     Computer
    A receiving unit that receives, from each terminal, a time at which the user performs a predetermined operation in a terminal used by each of a plurality of users;
    An acquisition unit for acquiring a first time distribution of the predetermined operation from the received time;
    A calculation unit that calculates the degree of coincidence between the acquired first time distribution and the time received from each terminal;
    An estimation unit that estimates whether each of the plurality of users has experienced a predetermined event previously associated with the predetermined operation based on the degree of coincidence,
    A non-transitory computer-readable information recording medium for recording a program characterized by functioning as a computer program.
PCT/JP2016/088306 2016-12-22 2016-12-22 Estimation device, estimation method, program, and non-transitory computer-readable information recording medium WO2018116434A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2016/088306 WO2018116434A1 (en) 2016-12-22 2016-12-22 Estimation device, estimation method, program, and non-transitory computer-readable information recording medium
JP2017516789A JP6139814B1 (en) 2016-12-22 2016-12-22 Estimation apparatus, estimation method, program, and non-transitory computer-readable information recording medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2016/088306 WO2018116434A1 (en) 2016-12-22 2016-12-22 Estimation device, estimation method, program, and non-transitory computer-readable information recording medium

Publications (1)

Publication Number Publication Date
WO2018116434A1 true WO2018116434A1 (en) 2018-06-28

Family

ID=58794440

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2016/088306 WO2018116434A1 (en) 2016-12-22 2016-12-22 Estimation device, estimation method, program, and non-transitory computer-readable information recording medium

Country Status (2)

Country Link
JP (1) JP6139814B1 (en)
WO (1) WO2018116434A1 (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0970035A (en) * 1995-08-31 1997-03-11 Toshiba Corp Two-way character broadcast receiver
WO2006077728A1 (en) * 2004-12-28 2006-07-27 Softbank Bb Corp. Television broadcast viewing system and television broadcast viewing method
WO2011081207A1 (en) * 2010-01-04 2011-07-07 日本電気株式会社 Communication support system, communication support method, and recording medium

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6168459B2 (en) * 2012-04-19 2017-07-26 パナソニックＩｐマネジメント株式会社 Living behavior estimation device, program, computer-readable recording medium
DE102015113941A1 (en) * 2014-08-21 2016-02-25 Affectomatics Ltd. Rating of restaurants based on affective response

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0970035A (en) * 1995-08-31 1997-03-11 Toshiba Corp Two-way character broadcast receiver
WO2006077728A1 (en) * 2004-12-28 2006-07-27 Softbank Bb Corp. Television broadcast viewing system and television broadcast viewing method
WO2011081207A1 (en) * 2010-01-04 2011-07-07 日本電気株式会社 Communication support system, communication support method, and recording medium

Also Published As

Publication number Publication date
JPWO2018116434A1 (en) 2018-12-20
JP6139814B1 (en) 2017-05-31

Similar Documents

Publication Publication Date Title
US11438394B2 (en) Systems, methods, and media for controlling delivery of content
US9278288B2 (en) Automatic generation of a game replay video
JP5086189B2 (en) Server, method and program for generating digest video of video content
KR101411739B1 (en) Method for capturing contents on tv and connecting with social service using second device and system thereof
CN109257631A (en) Video carousel playback method, device, computer equipment and storage medium
CN106534879A (en) Live broadcasting switching method and system based on attention
JP2013192062A (en) Video distribution system, video distribution apparatus, video distribution method and program
EP3310048B1 (en) Video bit rate identification method and device
US20150358378A1 (en) Method and apparatus for adjusting streaming media data transmission
CN108419103B (en) Video transmission method and device
JP6139814B1 (en) Estimation apparatus, estimation method, program, and non-transitory computer-readable information recording medium
US8972597B2 (en) Method and system for enabling generation of a summary of a data stream
JP2013222390A (en) Reply acceptance device, reply acceptance program and reply acceptance method
EP2820815A1 (en) An improved method and apparatus for video content distribution
US10257549B2 (en) Enhancing TV with wireless broadcast messages
CN109618239A (en) A kind of resource transmission method based on internet interactive application
JP3966343B2 (en) Distribution management method, distribution management apparatus, and distribution management system
JP7188718B1 (en) Notification method and backend server
KR102551307B1 (en) Method and system for providing game skill
EP3300376A1 (en) Method and apparatus for processing iptv program, and iptv system
WO2016041328A1 (en) Method for allocating recording tasks to set-top box, and related device
JP2014204228A (en) Program display device and program display method
JP2014049985A (en) Information collection device and information collection method
CN110248250A (en) A kind of method and device of video playback
JP2012049605A (en) Access frequency estimation device, method, and program

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2017516789

Country of ref document: JP

Kind code of ref document: A

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

Ref document number: 16924657

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16924657

Country of ref document: EP

Kind code of ref document: A1